changes to project

.github/workflows/features-and-predictions.yml

@@ -0,0 +1,35 @@
+name: electricity-feature-and-prediction-pipelines
+
+on:
+
+  # To run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+  # Schedule the workflow to run at 23:50 everyday
+  schedule:
+   - cron: '50 23 * * *'
+
+jobs:
+  test_schedule:
+    runs-on: ubuntu-latest
+    steps:
+      - name: checkout repo content
+        uses: actions/checkout@v2
+
+      - name: setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.11.5'
+          
+      - name: install python packages
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      
+      - name: execute python workflows from bash script
+        env: 
+          HOPSWORKS_API_KEY: ${{ secrets.HOPSWORKS_API_KEY }}
+        run: ./scripts/run_feature_and_prediction_pipelines.sh
+
+      
+

.github/workflows/sync_to_hf.yml

@@ -1,13 +1,17 @@
 name: Sync to Hugging Face hub
 on:
+
+  # To run this workflow manually from the Actions tab
+  workflow_dispatch:
+
+  # Schedule the workflow to run at 23:59 everyday
   schedule:
-    - cron: '0 0 * * *' # At 00:00 everyday
+    - cron: '59 23 * * *' 
+  
+  # Push events to the main branch
   push:
     branches: [main]
 
-  # to run this workflow manually from the Actions tab
-  workflow_dispatch:
-
 jobs:
   sync-to-hub:
     runs-on: ubuntu-latest

app.py

@@ -19,8 +19,12 @@ from streamlit_folium import st_folium
 # This is the functions we have created to generate features for electricity prices and weather measures
 from features import electricity_prices, weather_measures, calendar 
 
-def print_fancy_header(text, font_size=22, color="#ff5f27"):
-    res = f'<span style="color:{color}; font-size: {font_size}px;">{text}</span>'
+def print_fancy_header(text, font_width="bold", font_size=22, color="#2656a3"):
+    res = f'<span style="font-width:{font_width}; color:{color}; font-size:{font_size}px;">{text}</span>'
+    st.markdown(res, unsafe_allow_html=True)  
+
+def print_fancy_subheader(text, font_width="bold", font_size=22, color="#333"):
+    res = f'<span style="font-width:{font_width}; color:{color}; font-size:{font_size}px;">{text}</span>'
     st.markdown(res, unsafe_allow_html=True)  
 
 # I want to cache this so streamlit would run much faster after restart (it restarts a lot)
@@ -47,67 +51,102 @@ def download_model(name="electricity_price_prediction_model",
     saved_model_dir = retrieved_model.download()
     return saved_model_dir
 
+# with open('data/calendar_incl_holiday.csv') as csv_file:
+#     target_days = csv.reader(csv_file)
+
+# Function to load the dataset
+@st.cache_data  # Cache the function to enhance performance
+def load_data():
+    # Fetching weather forecast measures for the next 5 days
+    weather_forecast_df = weather_measures.forecast_weather_measures(
+        forecast_length=5
+    )
+
+    # Fetching danish calendar
+    calendar_df = calendar.get_calendar()
+
+    # Merging the weather forecast and calendar dataframes
+    new_data = pd.merge(weather_forecast_df, calendar_df, how='inner', left_on='date', right_on='date')
+
+    st.write("New data:")
+    st.write(new_data.sample(5))            
+
+    # Drop columns 'date', 'datetime', 'timestamp' from the DataFrame 'new_data'
+    data = new_data.drop(columns=['date', 'datetime', 'timestamp'])
 
+    predictions = retrieved_xgboost_model.predict(data)
 
-def plot_price(df):
-    # create figure with plotly express
-    fig = px.line(df, x='date', y='dk1_spotpricedkk_kwh', color='type')
-
-    # customize line colors and styles
-    fig.update_traces(mode='lines+markers')
-    fig.update_layout({
-        'plot_bgcolor': 'rgba(0, 0, 0, 0)',
-        'paper_bgcolor': 'rgba(0, 0, 0, 0)',
-        'legend_title': 'type',
-        'legend_font': {'size': 12},
-        'legend_bgcolor': 'rgba(0, 0, 0, 0)',
-        'xaxis': {'title': 'Date'},
-        'yaxis': {'title': 'dk1_spotpricedkk_kwh'},
-        'shapes': [{
-            'type': 'line',
-            'x0': datetime.datetime.now().strftime('%Y-%m-%d'),
-            'y0': 0,
-            'x1': datetime.datetime.now().strftime('%Y-%m-%d'),
-            'y1': df['dk1_spotpricedkk_kwh'].max(),
-            'line': {'color': 'red', 'width': 2, 'dash': 'dashdot'}
-        }]
-    })
-
-    # show plot
-    st.plotly_chart(fig, use_container_width=True)
-
-with open('data/calendar_incl_holiday.csv') as csv_file:
-    target_days = csv.reader(csv_file)
+    predictions_data = {
+        'prediction': predictions,
+        'time': new_data["datetime"],
+    }
+
+    predictions_df = pd.DataFrame(predictions_data).sort_values(by='time')
+
+    return predictions_df
 
 #########################
-st.title('🌫 Electricity Price Prediction 🌦')
+
+progress_bar = st.sidebar.header('⚙️ Working Progress')
+progress_bar = st.sidebar.progress(0)
+
+# Title for the streamlit app
+st.title('Electricity Price Prediction 🌦')
+
+# Subtitle
+st.markdown("""
+            Welcome to the electricity price predicter for DK1.
+""")
 
 st.write(3 * "-")
-print_fancy_header('\n📡 Connecting to Hopsworks Feature Store...')
-
-st.write("Logging... ")
-# (Attention! If the app has stopped at this step,
-# please enter your Hopsworks API Key in the commmand prompt.)
-project = hopsworks.login(project = "camillah", api_key_value=os.environ['HOPSWORKS_API_KEY'])
-fs = project.get_feature_store()
-st.write("✅ Logged in successfully!")
-
-# Retrieve the model registry
-mr = project.get_model_registry()
-
-# Retrieving the model from the Model Registry
-retrieved_model = mr.get_model(
-    name="electricity_price_prediction_model", 
-    version=1,
+
+with st.expander("📊 **Data Engineering and Machine Learning Operations in Business**"):
+                 st.markdown("""
+LEARNING OBJECTIVES
+- Using our skills for designing, implementing, and managing data pipelines and ML systems.
+- Focus on practical applications within a business context.
+- Cover topics such as data ingestion, preprocessing, model deployment, monitoring, and maintenance.
+- Emphasize industry best practices for effective operation of ML systems.
+"""
 )
+                 
+with st.expander("📊 **This assigment**"):
+                 st.markdown("""
+The objective of this assignment is to build a prediction system that predicts the electricity prices in Denmark (area DK1) based on weather conditions, previous prices, and the Danish holidays.
+"""
+)
+                 
+with st.sidebar:
+    # st.write("This code will be printed to the sidebar.")
+
+    print_fancy_header('\n📡 Connecting to Hopsworks Feature Store...')
 
-# Downloading the saved model to a local directory
-saved_model_dir = retrieved_model.download()
+    st.write("Logging... ")
+    # please enter your Hopsworks API Key in the commmand prompt.)
+    # project = hopsworks.login(project = "camillah", api_key_value=os.environ['HOPSWORKS_API_KEY'])
+    project = hopsworks.login()
+    fs = project.get_feature_store()
+    progress_bar.progress(40)
+    st.write("✅ Logged in successfully!")
 
-# Loading the saved XGB model
-retrieved_xgboost_model = joblib.load(saved_model_dir + "/dk_electricity_model.pkl")
+    # Retrieve the model registry
+    mr = project.get_model_registry()
+
+    # Retrieving the model from the Model Registry
+    retrieved_model = mr.get_model(
+        name="electricity_price_prediction_model", 
+        version=1,
+    )
+
+    # Downloading the saved model to a local directory
+    saved_model_dir = retrieved_model.download()
+
+    # Loading the saved XGB model
+    retrieved_xgboost_model = joblib.load(saved_model_dir + "/dk_electricity_model.pkl")
+
+    st.write("✅ Model successfully loaded!")
 
-st.write("✅ Model successfully loaded!")
+    progress_bar.progress(80)
 
 # I am going to load data for of last 60 days (for feature engineering)
 today = datetime.date.today()
@@ -115,70 +154,61 @@ date_threshold = today - datetime.timedelta(days=60)
 
 st.write(3 * "-")
 print_fancy_header('\n☁️ Retriving batch data from Feature Store...')
-# Fetching weather forecast measures for the next 5 days
-weather_forecast_df = weather_measures.forecast_weather_measures(
-    forecast_length=5
-)
-
-# Fetching danish calendar
-calendar_df = calendar.get_calendar()
 
-# Merging the weather forecast and calendar dataframes
-new_data = pd.merge(weather_forecast_df, calendar_df, how='inner', left_on='date', right_on='date')
+predictions_df = load_data()
 
-st.write("New data:")
-st.write(new_data.sample(5))            
+progress_bar.progress(100)
 
-# Drop columns 'date', 'datetime', 'timestamp' from the DataFrame 'new_data'
-data = new_data.drop(columns=['date', 'datetime', 'timestamp'])
+# Sidebar filter: Date range
+min_value = 1
+max_value = int(len(predictions_df['time'].unique()) / 24)
+default = int(48 / 24)
+date_range = st.sidebar.slider("Select Date Range", min_value=min_value, max_value=max_value, value=default)
+filtered_predictions_df = predictions_df.head(date_range * 24)
 
-predictions = retrieved_xgboost_model.predict(data)
-
-predictions_data = {
-    'prediction': predictions,
-    'time': new_data["datetime"],
-}
+visualization_option = st.selectbox(
+    "Select Visualization 🎨", 
+    ["Matrix", 
+    "Linechart"]
+)
 
-# Create a DataFrame from the predictions data
-predictions_df = pd.DataFrame(predictions_data)
-predictions_df = predictions_df.sort_values(by='time')
+# Visualizations based on user selection
+if visualization_option == "Matrix":
+    data = filtered_predictions_df
+    data['date'] = data['time'].dt.strftime('%Y-%m-%d')
+    data['time_of_day'] = data['time'].dt.strftime('%H:%M')
+    data.drop(columns=['time'], inplace=True)
+
+    # Pivot the DataFrame
+    pivot_df = data.pivot(index='time_of_day', columns='date', values='prediction')
+
+    st.write(pivot_df)  
+
+elif visualization_option == "Linechart":
+    # Create Altair chart with line and dots
+    chart = alt.Chart(filtered_predictions_df).mark_line(point=True).encode(
+        x='time:T',
+        y='prediction:Q',
+        tooltip=[alt.Tooltip('time:T', title='Date', format='%d-%m-%Y'), 
+                 alt.Tooltip('time:T', title='Time', format='%H:%M'), 
+                 alt.Tooltip('prediction:Q', title='Spot Price (DKK)', format='.2f')
+                ]
+    )
 
-st.write("predictions_df:")
-st.write(predictions_df.sample(5))       
+    # Display the chart
+    st.altair_chart(chart, use_container_width=True)
 
+# #########################
+# st.write(3 * '-')
+# st.write("\n")
 
-#########################
-st.write(3 * '-')
-st.write("\n")
+# print_fancy_header('\n📈 Predictions Table for today and 4 days ahead')
 
-print_fancy_header('\n📈 Predictions Table for today and 4 days ahead')
+# #########################
+# st.write(3 * '-')
+# st.write("\n")
 
-# Reshape the predictions data to a Table format, where each row represents a hour and each column a day
-table_df = predictions_df['prediction'].values.reshape(-1, 24)
-table_df = pd.DataFrame(table_df, columns=[f'{i}:00' for i in range(24)], index = [f'Day {i}' for i in range(table_df.shape[0])])
 
-st.write(table_df.T.style.set_properties(**{'width': '100%', 'max-width': 'none'}))
 
-#########################
-st.write(3 * '-')
-st.write("\n")
-
-# Create a slider for selecting the number of days to display
-num_hours = st.slider("Select number of hours to display", min_value=1, max_value=120, value=48)
-
-# Filter the predictions dataframe based on the selected number of days
-filtered_predictions_df = predictions_df.head(num_hours)
-
-# Create Altair chart with line and dots
-chart = alt.Chart(filtered_predictions_df).mark_line(point=True).encode(
-    x='time:T',
-    y='prediction:Q',
-    tooltip=[alt.Tooltip('time:T', title='Date', format='%d-%m-%Y'), 
-             alt.Tooltip('time:T', title='Time', format='%H:%M'), 
-             alt.Tooltip('prediction:Q', title='Spot Price (DKK)', format='.2f')
-            ]
-)
 
-# Display the chart
-st.altair_chart(chart, use_container_width=True)
 

features/calendar.py

@@ -3,7 +3,7 @@ import numpy as np
 import pandas as pd
 
 
-def get_calendar() -> pd.DataFrame:
+def dk_calendar() -> pd.DataFrame:
     """
     Fetches calendar for Denmark.
 
@@ -25,7 +25,7 @@ def get_calendar() -> pd.DataFrame:
     df['day'] = df['date_'].dt.day
     df['month'] = df['date_'].dt.month
     df['year'] = df['date_'].dt.year
-    df['holiday'] = np.where(df['type'] == 'Not a Workday', 1, 0)
+    df['workday'] = np.where(df['type'] == 'Not a Workday', 0, 1)
 
     # Drop the columns 'type' and 'date_' to finalize the calender dataframe
     calendar = df.drop(['type','date_'], axis=1)

features/plots.py

@@ -1,208 +0,0 @@
-import pandas as pd
-import numpy as np
-from datetime import date, timedelta
-import datetime
-from tqdm import tqdm 
-import plotly.express as px
-import plotly.graph_objects as go
-import plotly.colors as pc
-from typing import List, Union, Optional, Tuple, Dict
-
-
-def plot_historical_id(ids_to_show: List[int], data: pd.DataFrame) -> go.Figure:
-    """
-    Plots time series data for a specified list of IDs.
-
-    Parameters:
-    - ids_to_show (list): A list of IDs for which time series data should be plotted.
-    - data (pd.DataFrame): The DataFrame containing the data to be plotted, with columns ['date', 'id', 'price'].
-
-    Returns:
-    - Figure
-    """
-    # Filter the DataFrame to include only the specified IDs
-    filtered_df = data[data['id'].isin(ids_to_show)]
-
-    # Convert the 'date' column to datetime type
-    filtered_df['date'] = pd.to_datetime(filtered_df['date'], format='%Y-%m-%d')
-    filtered_df.sort_values('date', inplace=True)
-
-    # Generate a colormap with distinct colors based on the number of unique IDs
-    unique_ids = filtered_df['id'].unique()
-    num_ids = len(unique_ids)
-    colors = pc.qualitative.Set1 * (num_ids // len(pc.qualitative.Set1) + 1)
-
-    # Create a dictionary to map IDs to colors
-    color_map = dict(zip(unique_ids, colors[:num_ids]))
-
-    # Create a time series plot using Plotly Express
-    fig = px.line(
-        filtered_df, 
-        x='date', 
-        y='price', 
-        color='id',
-        title=f'Historical Prices for {ids_to_show} IDs',
-        labels={'date': 'Date', 'price': 'Price'},
-        line_group='id',
-        color_discrete_map=color_map,
-    )
-
-    return fig
-
-
-def plot_prediction_test(
-    id_to_show: int, 
-    X_train: pd.DataFrame, 
-    X_test: pd.DataFrame, 
-    y_train: Union[pd.Series, pd.DataFrame], 
-    y_test: Union[pd.Series, pd.DataFrame], 
-    train_date: pd.Series, 
-    test_date: pd.Series,
-    predictions: Optional[pd.Series] = None
-) -> go.Figure:
-    """
-    Plots a time series for a specific ID, showing training and test data on the same plot.
-
-    Parameters:
-    - id_to_show (int): The ID to be displayed in the plot.
-    - X_train (pd.DataFrame): The feature data for the training set.
-    - X_test (pd.DataFrame): The feature data for the test set.
-    - y_train (pd.Series or pd.DataFrame): The target data for the training set.
-    - y_test (pd.Series or pd.DataFrame): The target data for the test set.
-    - train_date (pd.Series): The date column for the training data.
-    - test_date (pd.Series): The date column for the test data.
-    - predictions (pd.Series or None): Predicted values for the test data. Default is None.
-
-    Returns:
-    - Figure
-    """
-    # Combine features and target data for training and test sets
-    train = pd.concat([train_date, X_train, y_train], axis=1)
-    test = pd.concat([test_date, X_test, y_test], axis=1)
-    
-    # Filter and sort data for the specified ID
-    train_sorted = train[train.id == id_to_show].sort_values('date')
-    test_sorted = test[test.id == id_to_show].sort_values('date')
-
-    # Create a Plotly figure
-    fig = go.Figure()
-    
-    # Add a trace for training data (blue)
-    fig.add_trace(go.Scatter(
-        x=train_sorted['date'], 
-        y=train_sorted['price'],
-        mode='lines',
-        name='Training Data',  
-        line=dict(color='blue')
-    ))
-    
-    # Add a trace for test data (red)
-    fig.add_trace(go.Scatter(
-        x=test_sorted['date'], 
-        y=test_sorted['price'],
-        mode='lines',
-        name='Test Data', 
-        line=dict(color='green')
-    ))
-    
-    if predictions is not None:
-        pred_df = pd.DataFrame()
-        pred_df['date'] = test_sorted['date']
-        pred_df['price'] = predictions
-        fig.add_trace(go.Scatter(
-            x=pred_df['date'], 
-            y=pred_df['price'],
-            mode='lines',
-            name='Prediction', 
-            line=dict(color='red')
-        ))
-        
-    
-    # Set X-axis range to span the entire date range from both training and test data
-    fig.update_xaxes(range=[train_sorted['date'].min(), test_sorted['date'].max()])
-    
-    # Customize plot layout
-    fig.update_layout(
-        title=f'Time Series for the {id_to_show} ID',
-        xaxis_title='Date',
-        yaxis_title='Price',
-        legend_title='Data Type'
-    )
-
-    return fig
-
-
-def plot_prediction(
-    id_to_show: int, 
-    data: pd.DataFrame,
-    week_ago: str,
-    predictions: Optional[pd.Series] = None,
-) -> go.Figure:
-    """
-    Display a time series plot for a specific ID, showcasing historical data, real prices, and predicted prices.
-
-    Parameters:
-    - id_to_show (int): The unique identifier for the data series to be displayed.
-    - data (pd.DataFrame): A DataFrame containing time series data.
-    - week_ago (str): A string representing a date one week ago (in 'YYYY-MM-DD' format).
-    - predictions (pd.Series or None, optional): Predicted price values for the test data. Default is None.
-
-    Returns:
-    - fig (plotly.graph_objs.Figure): A Plotly figure object containing the generated time series plot.
-    """
-    data_sorted = data[data.id == id_to_show].sort_values('date')
-    data_sorted['date'] = pd.to_datetime(data_sorted['date'])
-
-    time_ago = (datetime.datetime.strptime(week_ago, '%Y-%m-%d') - timedelta(days=210)).strftime("%Y-%m-%d")
-    data_historical = data_sorted.loc[
-        (data_sorted['date'] <= datetime.datetime.strptime(week_ago, "%Y-%m-%d")) &
-        (data_sorted['date'] >= datetime.datetime.strptime(time_ago, "%Y-%m-%d"))
-    ]
-    data_last_week = data_sorted[data_sorted.date > week_ago]
-
-    # Create a Plotly figure
-    fig = go.Figure()
-    
-    # Add a trace for training data (blue)
-    fig.add_trace(go.Scatter(
-        x=data_historical['date'], 
-        y=data_historical['price'],
-        mode='lines',
-        name='Historical Data',  
-        line=dict(color='blue')
-    ))
-    
-    # Add a trace for test data (red)
-    fig.add_trace(go.Scatter(
-        x=data_last_week['date'], 
-        y=data_last_week['price'],
-        mode='lines',
-        name='Real Price', 
-        line=dict(color='green')
-    ))
-    
-    if predictions is not None:
-        pred_df = pd.DataFrame()
-        pred_df['date'] = data_last_week['date']
-        pred_df['price'] = predictions
-        fig.add_trace(go.Scatter(
-            x=pred_df['date'], 
-            y=pred_df['price'],
-            mode='lines',
-            name='Predicted Price', 
-            line=dict(color='red')
-        ))
-        
-    
-    # Set X-axis range to span the entire date range from both training and test data
-    fig.update_xaxes(range=[data_historical['date'].min(), data_last_week['date'].max()])
-    
-    # Customize plot layout
-    fig.update_layout(
-        title=f'Predicted price for the {id_to_show} ID',
-        xaxis_title='Date',
-        yaxis_title='Price',
-        legend_title='Data Type'
-    )
-
-    return fig

hide/Old/1_feature_backfill_OLD.ipynb

@@ -1,1404 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 01: Feature Backfill</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Load the data and process features\n",
-    "2. Connect to the Hopsworks feature store\n",
-    "3. Create feature groups and upload them to the feature store"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages\n",
-    "\n",
-    "First, we'll install the Python packages required for this notebook. We'll use the --quiet command after specifying the names of the libraries to ensure a silent installation process. Then, we'll proceed to import all the necessary libraries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install of the packages for hopsworks\n",
-    "# !pip install -U hopsworks --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Importing of the packages for the needed libraries for the Jupyter notebook\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "# Ignore warnings\n",
-    "import warnings \n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 💽 Load the historical data\n",
-    "\n",
-    "The data you will use comes from three different sources:\n",
-    "\n",
-    "- Electricity prices in Denmark per day from [Energinet](https://www.energidataservice.dk).\n",
-    "- Different meteorological observations from [Open meteo](https://www.open-meteo.com).\n",
-    "- Danish Calendar with the type if the date is a national holiday or not. This files is made manually by the group and is located in the \"*data*\" folder inside this repository."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\">💸 Electricity prices per day from Energinet\n",
-    "*Hvis vi skal have tariffer med i modellen, anbefales det at vi sætter en faktor på 0.2 i tidsrummet 22 - 16 og en faktor på 0.6 eller 0.7 i tidsrummet 17 - 21.*\n",
-    "\n",
-    "This first dataset is Electricity prices per day from Energinet/Dataservice. Here we use "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining the URL for the API call to the electricity price data\n",
-    "electricity_api_url = ('https://api.energidataservice.dk/dataset/Elspotprices?offset=0&start=2022-01-01T00:00&end=2023-12-31T23:59&filter=%7B%22PriceArea%22:[%22DK1%22]%7D&sort=HourUTC%20DESC')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<Response [200]>\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Fetch data from the API and make the output to a pandas dataframe\n",
-    "electricity_data_response = requests.get(electricity_api_url)\n",
-    "electricity_data = electricity_data_response.json()\n",
-    "electricity_df = pd.DataFrame(electricity_data['records'])\n",
-    "\n",
-    "# Checking the result of the API call. If the response if 200 then the API call was successfull\n",
-    "print(electricity_data_response)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>HourUTC</th>\n",
-       "      <th>HourDK</th>\n",
-       "      <th>PriceArea</th>\n",
-       "      <th>SpotPriceDKK</th>\n",
-       "      <th>SpotPriceEUR</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2023-12-31T22:00:00</td>\n",
-       "      <td>2023-12-31T23:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>200.309998</td>\n",
-       "      <td>26.870001</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2023-12-31T21:00:00</td>\n",
-       "      <td>2023-12-31T22:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>213.729996</td>\n",
-       "      <td>28.670000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2023-12-31T20:00:00</td>\n",
-       "      <td>2023-12-31T21:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>220.660004</td>\n",
-       "      <td>29.600000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2023-12-31T19:00:00</td>\n",
-       "      <td>2023-12-31T20:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>260.100006</td>\n",
-       "      <td>34.889999</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2023-12-31T18:00:00</td>\n",
-       "      <td>2023-12-31T19:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>295.510010</td>\n",
-       "      <td>39.639999</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "               HourUTC               HourDK PriceArea  SpotPriceDKK  \\\n",
-       "0  2023-12-31T22:00:00  2023-12-31T23:00:00       DK1    200.309998   \n",
-       "1  2023-12-31T21:00:00  2023-12-31T22:00:00       DK1    213.729996   \n",
-       "2  2023-12-31T20:00:00  2023-12-31T21:00:00       DK1    220.660004   \n",
-       "3  2023-12-31T19:00:00  2023-12-31T20:00:00       DK1    260.100006   \n",
-       "4  2023-12-31T18:00:00  2023-12-31T19:00:00       DK1    295.510010   \n",
-       "\n",
-       "   SpotPriceEUR  \n",
-       "0     26.870001  \n",
-       "1     28.670000  \n",
-       "2     29.600000  \n",
-       "3     34.889999  \n",
-       "4     39.639999  "
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "electricity_df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Datapreprocessing by making the spotprice per kwh instead of mwh\n",
-    "electricity_df['SpotPriceDKK_KWH'] = electricity_df['SpotPriceDKK'] / 1000"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Datacleaning by removing the columns that are not needed\n",
-    "electricity_df.drop('SpotPriceDKK', axis=1, inplace=True)\n",
-    "electricity_df.drop('SpotPriceEUR', axis=1, inplace=True)\n",
-    "electricity_df.drop('HourUTC', axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Renaming the columns and reformating the time column\n",
-    "electricity_df.rename(columns={'HourDK': 'time'}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Formatting the date column\n",
-    "electricity_df['time'] = electricity_df['time'].astype(str).str[:-3]\n",
-    "electricity_df['date'] = electricity_df['time'].str[:10]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a new column for the date called electricity_temporary_date_column and insert it as the first column in the dataframe\n",
-    "electricity_temporary_date_column = electricity_df.pop('date')\n",
-    "electricity_df.insert(0, 'date', electricity_temporary_date_column)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert string 'date' column to date type and 'time' column to datetime format\n",
-    "electricity_df['date'] = pd.to_datetime(electricity_df['date'], format='%Y-%m-%d').dt.date\n",
-    "electricity_df['time'] = pd.to_datetime(electricity_df['time'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>PriceArea</th>\n",
-       "      <th>SpotPriceDKK_KWH</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 23:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.20031</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 22:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.21373</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 21:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.22066</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 20:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.26010</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 19:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.29551</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time PriceArea  SpotPriceDKK_KWH\n",
-       "0  2023-12-31 2023-12-31 23:00:00       DK1           0.20031\n",
-       "1  2023-12-31 2023-12-31 22:00:00       DK1           0.21373\n",
-       "2  2023-12-31 2023-12-31 21:00:00       DK1           0.22066\n",
-       "3  2023-12-31 2023-12-31 20:00:00       DK1           0.26010\n",
-       "4  2023-12-31 2023-12-31 19:00:00       DK1           0.29551"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "electricity_df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 17520 entries, 0 to 17519\n",
-      "Data columns (total 4 columns):\n",
-      " #   Column            Non-Null Count  Dtype         \n",
-      "---  ------            --------------  -----         \n",
-      " 0   date              17520 non-null  object        \n",
-      " 1   time              17520 non-null  datetime64[ns]\n",
-      " 2   PriceArea         17520 non-null  object        \n",
-      " 3   SpotPriceDKK_KWH  17520 non-null  float64       \n",
-      "dtypes: datetime64[ns](1), float64(1), object(2)\n",
-      "memory usage: 547.6+ KB\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Showing the information for the electricity dataframe\n",
-    "electricity_df.info()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>PriceArea</th>\n",
-       "      <th>SpotPriceDKK_KWH</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 23:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.20031</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 22:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.21373</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 21:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.22066</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 20:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.26010</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>2023-12-31</td>\n",
-       "      <td>2023-12-31 19:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.29551</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time PriceArea  SpotPriceDKK_KWH\n",
-       "0  2023-12-31 2023-12-31 23:00:00       DK1           0.20031\n",
-       "2  2023-12-31 2023-12-31 22:00:00       DK1           0.21373\n",
-       "4  2023-12-31 2023-12-31 21:00:00       DK1           0.22066\n",
-       "6  2023-12-31 2023-12-31 20:00:00       DK1           0.26010\n",
-       "8  2023-12-31 2023-12-31 19:00:00       DK1           0.29551"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Fetching historical electricity prices data\n",
-    "electricity = electricity_prices.fetch_electricity_prices(historical=True, start='2022-01-01', end='2023-12-31')\n",
-    "electricity = electricity[(electricity['PriceArea'] == \"DK1\")]\n",
-    "electricity.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🌤 Weather measurements from Open Meteo\n",
-    "\n",
-    "Burde have enddate 2023-12-31. url = (\"https://archive-api.open-meteo.com/v1/archive?latitude=57.048&longitude=9.9187&start_date=2022-01-01&end_date=2023-12-31&hourly=temperature_2m,relative_humidity_2m,precipitation,rain,snowfall,weather_code,cloud_cover,wind_speed_10m,wind_gusts_10m\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining the URL for the API call to the weather data   \n",
-    "weather_api_url = (\"https://archive-api.open-meteo.com/v1/archive?latitude=57.048&longitude=9.9187&start_date=2022-01-01&end_date=2023-12-31&hourly=temperature_2m,relative_humidity_2m,precipitation,rain,snowfall,weather_code,cloud_cover,wind_speed_10m,wind_gusts_10m\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<Response [200]>\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Fetch data from the API and make the output to a pandas dataframe\n",
-    "weather_data_response = requests.get(weather_api_url)\n",
-    "weather_data = weather_data_response.json()\n",
-    "weather_df = pd.DataFrame(weather_data['hourly'])\n",
-    "\n",
-    "# Checking the result of the API call. If the response if 200 then the API call was successfull\n",
-    "print(weather_data_response)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Formatting the date column\n",
-    "weather_df['date'] = weather_df['time'].str[:10]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a new column for the date called weather_temporary_date_column and insert it as the first column in the dataframe\n",
-    "weather_temporary_date_column = weather_df.pop('date')\n",
-    "weather_df.insert(0, 'date', weather_temporary_date_column)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert string 'date' column to date type and 'time' column to datetime format\n",
-    "weather_df['date'] = pd.to_datetime(weather_df['date'], format='%Y-%m-%d').dt.date\n",
-    "weather_df['time'] = pd.to_datetime(weather_df['time'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 00:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>16.2</td>\n",
-       "      <td>36.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 01:00:00</td>\n",
-       "      <td>6.6</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>16.2</td>\n",
-       "      <td>30.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 02:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>99</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>15.5</td>\n",
-       "      <td>30.6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 03:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>12.7</td>\n",
-       "      <td>28.8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 04:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>99</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>10.6</td>\n",
-       "      <td>23.8</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time  temperature_2m  relative_humidity_2m  \\\n",
-       "0  2022-01-01 2022-01-01 00:00:00             6.7                   100   \n",
-       "1  2022-01-01 2022-01-01 01:00:00             6.6                   100   \n",
-       "2  2022-01-01 2022-01-01 02:00:00             6.7                    99   \n",
-       "3  2022-01-01 2022-01-01 03:00:00             6.7                   100   \n",
-       "4  2022-01-01 2022-01-01 04:00:00             6.7                    99   \n",
-       "\n",
-       "   precipitation  rain  snowfall  weather_code  cloud_cover  wind_speed_10m  \\\n",
-       "0            0.0   0.0       0.0             3          100            16.2   \n",
-       "1            0.0   0.0       0.0             3          100            16.2   \n",
-       "2            0.0   0.0       0.0             3          100            15.5   \n",
-       "3            0.0   0.0       0.0             3          100            12.7   \n",
-       "4            0.0   0.0       0.0             3          100            10.6   \n",
-       "\n",
-       "   wind_gusts_10m  \n",
-       "0            36.0  \n",
-       "1            30.2  \n",
-       "2            30.6  \n",
-       "3            28.8  \n",
-       "4            23.8  "
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "weather_df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 17520 entries, 0 to 17519\n",
-      "Data columns (total 11 columns):\n",
-      " #   Column                Non-Null Count  Dtype         \n",
-      "---  ------                --------------  -----         \n",
-      " 0   date                  17520 non-null  object        \n",
-      " 1   time                  17520 non-null  datetime64[ns]\n",
-      " 2   temperature_2m        17520 non-null  float64       \n",
-      " 3   relative_humidity_2m  17520 non-null  int64         \n",
-      " 4   precipitation         17520 non-null  float64       \n",
-      " 5   rain                  17520 non-null  float64       \n",
-      " 6   snowfall              17520 non-null  float64       \n",
-      " 7   weather_code          17520 non-null  int64         \n",
-      " 8   cloud_cover           17520 non-null  int64         \n",
-      " 9   wind_speed_10m        17520 non-null  float64       \n",
-      " 10  wind_gusts_10m        17520 non-null  float64       \n",
-      "dtypes: datetime64[ns](1), float64(6), int64(3), object(1)\n",
-      "memory usage: 1.5+ MB\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Showing the information for the weather dataframe\n",
-    "weather_df.info()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 00:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>16.2</td>\n",
-       "      <td>36.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 01:00:00</td>\n",
-       "      <td>6.6</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>16.2</td>\n",
-       "      <td>30.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 02:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>99</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>15.5</td>\n",
-       "      <td>30.6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 03:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>12.7</td>\n",
-       "      <td>28.8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>2022-01-01 04:00:00</td>\n",
-       "      <td>6.7</td>\n",
-       "      <td>99</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>3</td>\n",
-       "      <td>100</td>\n",
-       "      <td>10.6</td>\n",
-       "      <td>23.8</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time  temperature_2m  relative_humidity_2m  \\\n",
-       "0  2022-01-01 2022-01-01 00:00:00             6.7                   100   \n",
-       "1  2022-01-01 2022-01-01 01:00:00             6.6                   100   \n",
-       "2  2022-01-01 2022-01-01 02:00:00             6.7                    99   \n",
-       "3  2022-01-01 2022-01-01 03:00:00             6.7                   100   \n",
-       "4  2022-01-01 2022-01-01 04:00:00             6.7                    99   \n",
-       "\n",
-       "   precipitation  rain  snowfall  weather_code  cloud_cover  wind_speed_10m  \\\n",
-       "0            0.0   0.0       0.0             3          100            16.2   \n",
-       "1            0.0   0.0       0.0             3          100            16.2   \n",
-       "2            0.0   0.0       0.0             3          100            15.5   \n",
-       "3            0.0   0.0       0.0             3          100            12.7   \n",
-       "4            0.0   0.0       0.0             3          100            10.6   \n",
-       "\n",
-       "   wind_gusts_10m  \n",
-       "0            36.0  \n",
-       "1            30.2  \n",
-       "2            30.6  \n",
-       "3            28.8  \n",
-       "4            23.8  "
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Fetching historical electricity prices data\n",
-    "weater = weater_measures.fetch_weater_measures()\n",
-    "weater.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🗓️ Calendar of Danish workdays and holidays "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>type</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>01/01/2022</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>02/01/2022</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>03/01/2022</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>04/01/2022</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>05/01/2022</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1091</th>\n",
-       "      <td>27/12/2024</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1092</th>\n",
-       "      <td>28/12/2024</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1093</th>\n",
-       "      <td>29/12/2024</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1094</th>\n",
-       "      <td>30/12/2024</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1095</th>\n",
-       "      <td>31/12/2024</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>1096 rows × 2 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "            date           type\n",
-       "0     01/01/2022  Not a Workday\n",
-       "1     02/01/2022  Not a Workday\n",
-       "2     03/01/2022        Workday\n",
-       "3     04/01/2022        Workday\n",
-       "4     05/01/2022        Workday\n",
-       "...          ...            ...\n",
-       "1091  27/12/2024        Workday\n",
-       "1092  28/12/2024  Not a Workday\n",
-       "1093  29/12/2024  Not a Workday\n",
-       "1094  30/12/2024        Workday\n",
-       "1095  31/12/2024        Workday\n",
-       "\n",
-       "[1096 rows x 2 columns]"
-      ]
-     },
-     "execution_count": 24,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Read csv file with calender\n",
-    "calender_df = pd.read_csv('https://raw.githubusercontent.com/Camillahannesbo/MLOPs-Assignment-/main/data/calendar_incl_holiday.csv', delimiter=';', usecols=['date', 'type'])\n",
-    " \n",
-    "# Display the DataFrame\n",
-    "calender_df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Formatting the date column by replacing the / with -\n",
-    "calender_df['date'] = calender_df['date'].str.replace('/', '-')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining the function for flipping the date to the left\n",
-    "\n",
-    "# Flip the date to the left\n",
-    "def flip_date_left(date):\n",
-    "    parts = date.split(\"-\")  # Assuming the date format is \"YYYY-MM-DD\"\n",
-    "    flipped_date = \"-\".join(parts[::-1])\n",
-    "    return flipped_date\n",
-    "\n",
-    "# Flip the date to the left for the date column\n",
-    "def flip_dates_left_in_column(column):\n",
-    "    flipped_column = [flip_date_left(date) for date in column]\n",
-    "    return flipped_column"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Make the new flipped_dates_column based on the function above and insert it as the 'date' column in the dataframe\n",
-    "flipped_dates_column = flip_dates_left_in_column(calender_df['date'])\n",
-    "calender_df['date'] = flipped_dates_column"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert string 'date' column to date type\n",
-    "calender_df['date'] = pd.to_datetime(calender_df['date'], format='%Y-%m-%d').dt.date"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>type</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2022-01-02</td>\n",
-       "      <td>Not a Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2022-01-03</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2022-01-04</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2022-01-05</td>\n",
-       "      <td>Workday</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date           type\n",
-       "0  2022-01-01  Not a Workday\n",
-       "1  2022-01-02  Not a Workday\n",
-       "2  2022-01-03        Workday\n",
-       "3  2022-01-04        Workday\n",
-       "4  2022-01-05        Workday"
-      ]
-     },
-     "execution_count": 29,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "calender_df.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 1096 entries, 0 to 1095\n",
-      "Data columns (total 2 columns):\n",
-      " #   Column  Non-Null Count  Dtype \n",
-      "---  ------  --------------  ----- \n",
-      " 0   date    1096 non-null   object\n",
-      " 1   type    1096 non-null   object\n",
-      "dtypes: object(2)\n",
-      "memory usage: 17.3+ KB\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Showing the information for the calender dataframe\n",
-    "calender_df.info()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store\n",
-    "\n",
-    "First we will connect to Hopsworks Feature Store so we can access and create Feature Groups.\n",
-    "Feature groups can also be used to define a namespace for features. For instance, in a real-life setting you would likely want to experiment with different window lengths. In that case, you can create feature groups with identical schema for each window length. \n",
-    "\n",
-    "Before you can create a feature group you need to connect to our feature store."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import hopsworks\n",
-    "\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "fs = project.get_feature_store()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🪄 Creating Feature Groups\n",
-    "\n",
-    "When creating a feature group, you must name it and designate a primary key. Additionally, it's helpful to include a description of the feature group's contents and a version number; if not defined, it will default to `1`. \n",
-    "\n",
-    "We've configured `online_enabled` as `True` to enable the feature group to be read via the Online API for a Feature View."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating the feature group for the weater data\n",
-    "weather_fg = fs.get_or_create_feature_group(\n",
-    "    name=\"weather_measurements\",\n",
-    "    version=1,\n",
-    "    description=\"Weather measurements from Open Meteo API\",\n",
-    "    primary_key=[\"date\"],\n",
-    "    event_time=\"time\",\n",
-    "    online_enabled=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "By now, you've only outlined metadata for the feature group. There's no data stored, nor is there a defined schema for it. To establish persistence for the feature group, you'll need to populate it with its associated data using the `insert` function"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Inserting the weather_df into the feature group named weather_fg\n",
-    "weather_fg.insert(weather_df)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We make a descriptions for each feature we put into the feature group. In this way we are adding more information and documentation to the user"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "weather_feature_descriptions = [\n",
-    "    {\"name\": \"date\", \"description\": \"Date of the weather measurement\"},\n",
-    "    {\"name\": \"time\", \"description\": \"Time of the weather measurement\"},\n",
-    "    {\"name\": \"temperature_2m\", \"description\": \"Temperature at 2m above ground\"},\n",
-    "    {\"name\": \"relative_humidity_2m\", \"description\": \"Relative humidity at 2m above ground\"},\n",
-    "    {\"name\": \"precipitation\", \"description\": \"Precipitation\"},\n",
-    "    {\"name\": \"rain\", \"description\": \"Rain\"},\n",
-    "    {\"name\": \"snowfall\", \"description\": \"Snowfall\"},   \n",
-    "    {\"name\": \"weather_code\", \"description\": \"Weather code\"},   \n",
-    "    {\"name\": \"cloud_cover\", \"description\": \"Cloud cover\"},   \n",
-    "    {\"name\": \"wind_speed_10m\", \"description\": \"Wind speed at 10m above ground\"},   \n",
-    "    {\"name\": \"wind_gusts_10m\", \"description\": \"Wind gusts at 10m above ground\"},   \n",
-    "]\n",
-    "\n",
-    "for desc in weather_feature_descriptions: \n",
-    "    weather_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "We replicate the process for both the `electricity_fg` and `danish_holidays_fg` by establishing feature groups and inserting the dataframes into their respective feature groups."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating the feature group for the electricity prices\n",
-    "electricity_fg = fs.get_or_create_feature_group(\n",
-    "    name=\"electricity_prices\",\n",
-    "    version=1,\n",
-    "    description=\"Electricity prices from Energidata API\",\n",
-    "    primary_key=[\"date\"],\n",
-    "    online_enabled=True,\n",
-    "    event_time=\"time\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Inserting the electricity_df into the feature group named electricity_fg\n",
-    "electricity_fg.insert(electricity_df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "electricity_feature_descriptions = [\n",
-    "    {\"name\": \"date\", \"description\": \"Date of the electricity measurement\"},\n",
-    "    {\"name\": \"time\", \"description\": \"Time of the electricity measurement\"},\n",
-    "    {\"name\": \"PriceArea\", \"description\": \"Price area for the electricity measurement\"},\n",
-    "    {\"name\": \"SpotPriceDKK_KWH\", \"description\": \"Spot price in DKK per KWH\"}, \n",
-    "]\n",
-    "\n",
-    "for desc in electricity_feature_descriptions: \n",
-    "    electricity_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating the feature group for the danish holidays\n",
-    "danish_holidays_fg = fs.get_or_create_feature_group(\n",
-    "    name=\"danish_holidays\",\n",
-    "    version=1,\n",
-    "    description=\"Danish holidays calendar.\",\n",
-    "    online_enabled=True,\n",
-    "    primary_key=[\"date\"],\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Inserting the calender_df into the feature group named danish_holidays_fg\n",
-    "danish_holidays_fg.insert(calender_df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "danish_holidays_feature_descriptions = [\n",
-    "    {\"name\": \"date\", \"description\": \"Date in the calendar\"},\n",
-    "    {\"name\": \"type\", \"description\": \"Holyday or not holyday\"},\n",
-    "]\n",
-    "\n",
-    "for desc in danish_holidays_feature_descriptions: \n",
-    "    danish_holidays_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 02: Feature Pipeline </span>\n",
-    "\n",
-    "In the next notebook, you will be generating new data for the Feature Groups."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-streamlit",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/Old/2_feature_pipeline_OLD.ipynb

@@ -1,561 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 02: Feature Pipeline</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Parse new aata.\n",
-    "2. Insert new data into the Feature Store."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Importing of the packages for the needed libraries for the Jupyter notebook\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "# Ignore warnings\n",
-    "import warnings \n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> 🪄 Parsing new data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\">💸 Electricity prices per day from Energinet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining the URL for the API call to the electricity price data\n",
-    "electricity_api_url = ('https://api.energidataservice.dk/dataset/Elspotprices?offset=0&start=2024-01-01T00:00&end=2024-04-08T00:00&filter=%7B%22PriceArea%22:[%22DK1%22]%7D&sort=HourUTC%20DESC')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<Response [200]>\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Fetch data from the API and make the output to a pandas dataframe\n",
-    "electricity_data_response = requests.get(electricity_api_url)\n",
-    "electricity_data = electricity_data_response.json()\n",
-    "electricity_df = pd.DataFrame(electricity_data['records'])\n",
-    "\n",
-    "# Checking the result of the API call. If the response if 200 then the API call was successfull\n",
-    "print(electricity_data_response)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Datapreprocessing by making the spotprice per kwh instead of mwh\n",
-    "electricity_df['SpotPriceDKK_KWH'] = electricity_df['SpotPriceDKK'] / 1000"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Datacleaning by removing the columns that are not needed\n",
-    "electricity_df.drop('SpotPriceDKK', axis=1, inplace=True)\n",
-    "electricity_df.drop('SpotPriceEUR', axis=1, inplace=True)\n",
-    "electricity_df.drop('HourUTC', axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Renaming the columns and reformating the time column\n",
-    "electricity_df.rename(columns={'HourDK': 'time'}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Formatting the date column\n",
-    "electricity_df['time'] = electricity_df['time'].astype(str).str[:-3]\n",
-    "electricity_df['date'] = electricity_df['time'].str[:10]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a new column for the date called electricity_temporary_date_column and insert it as the first column in the dataframe\n",
-    "electricity_temporary_date_column = electricity_df.pop('date')\n",
-    "electricity_df.insert(0, 'date', electricity_temporary_date_column)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert string 'date' column to date type and 'time' column to datetime format\n",
-    "electricity_df['date'] = pd.to_datetime(electricity_df['date'], format='%Y-%m-%d').dt.date\n",
-    "electricity_df['time'] = pd.to_datetime(electricity_df['time'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>PriceArea</th>\n",
-       "      <th>SpotPriceDKK_KWH</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2024-04-07</td>\n",
-       "      <td>2024-04-07 23:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.31886</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2024-04-07</td>\n",
-       "      <td>2024-04-07 22:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.34078</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2024-04-07</td>\n",
-       "      <td>2024-04-07 21:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.35958</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2024-04-07</td>\n",
-       "      <td>2024-04-07 20:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.35645</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2024-04-07</td>\n",
-       "      <td>2024-04-07 19:00:00</td>\n",
-       "      <td>DK1</td>\n",
-       "      <td>0.34399</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time PriceArea  SpotPriceDKK_KWH\n",
-       "0  2024-04-07 2024-04-07 23:00:00       DK1           0.31886\n",
-       "1  2024-04-07 2024-04-07 22:00:00       DK1           0.34078\n",
-       "2  2024-04-07 2024-04-07 21:00:00       DK1           0.35958\n",
-       "3  2024-04-07 2024-04-07 20:00:00       DK1           0.35645\n",
-       "4  2024-04-07 2024-04-07 19:00:00       DK1           0.34399"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "electricity_df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🌤 Weather measurements from Open Meteo"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining the URL for the API call to the electricity price data\n",
-    "weather_api_url = ('https://archive-api.open-meteo.com/v1/archive?latitude=57.048&longitude=9.9187&start_date=2024-01-01&end_date=2024-04-08&hourly=temperature_2m,relative_humidity_2m,precipitation,rain,snowfall,weather_code,cloud_cover,wind_speed_10m,wind_gusts_10m&timezone=auto')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<Response [200]>\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Fetch data from the API and make the output to a pandas dataframe\n",
-    "weather_data_response = requests.get(weather_api_url)\n",
-    "weather_data = weather_data_response.json()\n",
-    "weather_df = pd.DataFrame(weather_data['hourly'])\n",
-    "\n",
-    "# Checking the result of the API call\n",
-    "print(weather_data_response)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Formatting the date column\n",
-    "weather_df['date'] = weather_df['time'].str[:10]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a new column for the date called weather_temporary_date_column and insert it as the first column in the dataframe\n",
-    "weather_temporary_date_column = weather_df.pop('date')\n",
-    "weather_df.insert(0, 'date', weather_temporary_date_column)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert string 'date' column to date type\n",
-    "weather_df['date'] = pd.to_datetime(weather_df['date'], format='%Y-%m-%d').dt.date\n",
-    "weather_df['time'] = pd.to_datetime(weather_df['time'])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>time</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>2024-01-01</td>\n",
-       "      <td>2024-01-01 00:00:00</td>\n",
-       "      <td>4.8</td>\n",
-       "      <td>95</td>\n",
-       "      <td>1.8</td>\n",
-       "      <td>1.8</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>61</td>\n",
-       "      <td>100</td>\n",
-       "      <td>23.6</td>\n",
-       "      <td>49.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>2024-01-01</td>\n",
-       "      <td>2024-01-01 01:00:00</td>\n",
-       "      <td>4.9</td>\n",
-       "      <td>95</td>\n",
-       "      <td>1.2</td>\n",
-       "      <td>1.2</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>55</td>\n",
-       "      <td>100</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>43.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>2024-01-01</td>\n",
-       "      <td>2024-01-01 02:00:00</td>\n",
-       "      <td>4.8</td>\n",
-       "      <td>96</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>53</td>\n",
-       "      <td>100</td>\n",
-       "      <td>18.4</td>\n",
-       "      <td>39.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>2024-01-01</td>\n",
-       "      <td>2024-01-01 03:00:00</td>\n",
-       "      <td>4.3</td>\n",
-       "      <td>96</td>\n",
-       "      <td>0.8</td>\n",
-       "      <td>0.8</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>53</td>\n",
-       "      <td>100</td>\n",
-       "      <td>16.7</td>\n",
-       "      <td>33.8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>2024-01-01</td>\n",
-       "      <td>2024-01-01 04:00:00</td>\n",
-       "      <td>4.4</td>\n",
-       "      <td>97</td>\n",
-       "      <td>0.3</td>\n",
-       "      <td>0.3</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>51</td>\n",
-       "      <td>100</td>\n",
-       "      <td>15.4</td>\n",
-       "      <td>30.2</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         date                time  temperature_2m  relative_humidity_2m  \\\n",
-       "0  2024-01-01 2024-01-01 00:00:00             4.8                    95   \n",
-       "1  2024-01-01 2024-01-01 01:00:00             4.9                    95   \n",
-       "2  2024-01-01 2024-01-01 02:00:00             4.8                    96   \n",
-       "3  2024-01-01 2024-01-01 03:00:00             4.3                    96   \n",
-       "4  2024-01-01 2024-01-01 04:00:00             4.4                    97   \n",
-       "\n",
-       "   precipitation  rain  snowfall  weather_code  cloud_cover  wind_speed_10m  \\\n",
-       "0            1.8   1.8       0.0            61          100            23.6   \n",
-       "1            1.2   1.2       0.0            55          100            21.6   \n",
-       "2            0.6   0.6       0.0            53          100            18.4   \n",
-       "3            0.8   0.8       0.0            53          100            16.7   \n",
-       "4            0.3   0.3       0.0            51          100            15.4   \n",
-       "\n",
-       "   wind_gusts_10m  \n",
-       "0            49.0  \n",
-       "1            43.2  \n",
-       "2            39.2  \n",
-       "3            33.8  \n",
-       "4            30.2  "
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "weather_df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import hopsworks\n",
-    "\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "fs = project.get_feature_store()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve feature groups\n",
-    "weather_fg = fs.get_feature_group(\n",
-    "    name=\"weather_measurements\",\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "electricity_fg = fs.get_feature_group(\n",
-    "    name=\"electricity_prices\",\n",
-    "    version=1,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> ⬆️ Uploading new data to the Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Inserting the weather_df into the feature group named weather_fg\n",
-    "weather_fg.insert(weather_df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Inserting the electricity_df into the feature group named electricity_fg\n",
-    "electricity_fg.insert(electricity_df)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 03: Traning </span>\n",
-    "\n",
-    "In the next notebook, you will be generating new data for the Feature Groups."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-mlops",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.8"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/Old/3_training_pipeline_OLD.ipynb

@@ -1,349 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 03: Training Pipeline</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Feature selection.\n",
-    "2. Feature transformations.\n",
-    "3. Training datasets creation.\n",
-    "4. Loading the training data.\n",
-    "5. Train the model.\n",
-    "6. Register model to Hopsworks model registry."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install tensorflow --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-04-16 16:06:19.917866: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "import inspect \n",
-    "import datetime\n",
-    "\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import tensorflow as tf\n",
-    "\n",
-    "#ignore warnings\n",
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n",
-      "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/550040\n",
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    }
-   ],
-   "source": [
-    "import hopsworks\n",
-    "\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "fs = project.get_feature_store() "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve feature groups\n",
-    "electricity_fg = fs.get_feature_group(\n",
-    "    name='electricity_prices',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "weather_fg = fs.get_feature_group(\n",
-    "    name='weather_measurements',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "danish_holidays_fg = fs.get_feature_group(\n",
-    "    name='danish_holidays',\n",
-    "    version=1,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🖍 Feature View Creation and Retrieving </span>\n",
-    "\n",
-    "Let's start by selecting all the features you want to include for model training/inference."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Select features for training data\n",
-    "selected_features = electricity_fg.select_all()\\\n",
-    "    .join(\n",
-    "    weather_fg\\\n",
-    "        .select_except([\"timestamp\"])\n",
-    "    )\\\n",
-    "    .join(\n",
-    "        danish_holidays_fg.select_all()\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🤖 Transformation Functions</span>\n",
-    "\n",
-    "Hopsworks Feature Store provides functionality to attach transformation functions to feature views and comes with built-in transformation functions such as `min_max_scaler`, `standard_scaler`, `robust_scaler` and `label_encoder`.\n",
-    "\n",
-    "You will preprocess your data using *min-max scaling* on numerical features and *label encoding* on categorical features. To do this you simply define a mapping between our features and transformation functions. This ensures that transformation functions such as *min-max scaling* are fitted only on the training data (and not the validation/test data), which ensures that there is no data leakage."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "transformation_functions = {\n",
-    "        \"SpotPriceDKK_KWH\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"temperature_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"relative_humidity_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"precipitation\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"rain\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"snowfall\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"weather_code\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"cloud_cover\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"wind_speed_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"wind_gusts_10m\": fs.get_transformation_function(name=\"min_max_scaler\")\n",
-    "    }"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` stands between **Feature Groups** and **Training Dataset**. Сombining **Feature Groups** we can create **Feature Views** which store a metadata of our data. Having **Feature Views** we can create **Training Dataset**.\n",
-    "\n",
-    "The Feature Views allows schema in form of a query with filters, define a model target feature/label and additional transformation functions.\n",
-    "\n",
-    "In order to create Feature View we can use `FeatureStore.get_or_create_feature_view()` method.\n",
-    "\n",
-    "We can specify next parameters:\n",
-    "\n",
-    "- `name` - name of a feature group.\n",
-    "\n",
-    "- `version` - version of a feature group.\n",
-    "\n",
-    "- `labels`- our target variable.\n",
-    "\n",
-    "- `transformation_functions` - functions to transform our features.\n",
-    "\n",
-    "- `query` - query object with data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "feature_view = fs.get_or_create_feature_view(\n",
-    "    name='electricity_feature_view',\n",
-    "    version=1,\n",
-    "    labels=[], # you will define our 'y' later manualy\n",
-    "    transformation_functions=transformation_functions,\n",
-    "    query=selected_features,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🏋️ Training Dataset Creation</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> ⛳️ Dataset with train, test and validation splits</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# since you didn't specify 'labels' in feature view creation, it will return None for Y.\n",
-    "X_train, X_val, X_test, _, _, _ = feature_view.train_validation_test_split(\n",
-    "    train_start=\"2021-01-01\",\n",
-    "    train_end=\"2022-02-28\",\n",
-    "    validation_start=\"2022-03-01\",\n",
-    "    validation_end=\"2022-05-31\",\n",
-    "    test_start=\"2022-06-01\",\n",
-    "    test_end=\"2022-09-09\",\n",
-    "    description='Electricity price prediction dataset',\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Sorting the training, validation, and test datasets based on the 'time' column\n",
-    "X_train.sort_values([\"time\"], inplace=True)\n",
-    "X_val.sort_values([\"time\"], inplace=True)\n",
-    "X_test.sort_values([\"time\"], inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define 'y_train', 'y_val' and 'y_test'\n",
-    "y_train = X_train[[\"SpotPriceDKK_KWH\"]]\n",
-    "y_val = X_val[[\"SpotPriceDKK_KWH\"]]\n",
-    "y_test = X_test[[\"SpotPriceDKK_KWH\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Dropping the 'day' and 'timestamp' columns from the training, validation, and test datasets\n",
-    "X_train.drop([\"date\", \"time\"], axis=1, inplace=True)\n",
-    "X_val.drop([\"date\", \"time\"], axis=1, inplace=True)\n",
-    "X_test.drop([\"date\", \"time\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Displaying the first 5 rows of the test dataset (X_test)\n",
-    "X_test.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🗃 Window timeseries dataset </span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'>🗄 Model Registry</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 04: Batch Inference </span>\n",
-    "\n",
-    "In the next notebook you will use your registered model to predict batch data."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-mlops",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.8"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/Old/4_batch_inference_OLD.ipynb

@@ -1,80 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 04: Batch Inference</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "\n",
-    "1. Load batch data.\n",
-    "2. Predict using model from Model Registry."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages\n",
-    "\n",
-    "First, we'll install the Python packages required for this notebook. We'll use the --quiet command after specifying the names of the libraries to ensure a silent installation process. Then, we'll proceed to import all the necessary libraries."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Feature View Retrieval"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> 🗄 Model Registry"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> 📮 Retrieving model from Model Registry"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ✨ Load Batch Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> 🤖 Making the predictions"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/Old/predict_example.py

@@ -1,33 +0,0 @@
-import os
-import numpy as np
-import pandas as pd
-import hsfs
-import joblib
-
-
-class Predict(object):
-
-    def __init__(self):
-        """ Initializes the serving state, reads a trained model"""        
-        # get feature store handle
-        fs_conn = hsfs.connection()
-        self.fs = fs_conn.get_feature_store()
-        
-        # get feature view
-        self.fv = self.fs.get_feature_view("electricity_feature_view", 1)
-        
-        # initialize serving
-        self.fv.init_serving(1)
-
-        # load the trained model
-        self.model = joblib.load(os.environ["ARTIFACT_FILES_PATH"] + "/dk_electricity_model.pkl")
-        print("Initialization Complete")
-
-    
-    def predict(self, timestamp_value, date_value):
-        """ Serves a prediction request usign a trained model"""
-        # Retrieve feature vectors
-        feature_vector = self.fv.get_feature_vector(
-            entry = {['timestamp','date']: [timestamp_value[0], date_value[0]]}
-        )
-        return self.model.predict(np.asarray(feature_vector[1:]).reshape(1, -1)).tolist()

hide/notebooks_dev/3_training_pipeline_dev_prophet.ipynb

@@ -1,943 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 03: Training Pipeline</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Feature selection.\n",
-    "2. Feature transformations.\n",
-    "3. Training datasets creation.\n",
-    "4. Loading the training data.\n",
-    "5. Train the model.\n",
-    "6. Register model to Hopsworks model registry."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install tensorflow --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Importing the packages for the needed libraries for the Jupyter notebook\n",
-    "import inspect \n",
-    "import datetime\n",
-    "\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import tensorflow as tf\n",
-    "\n",
-    "#ignore warnings\n",
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n",
-      "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/556180\n",
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Importing the hopsworks module\n",
-    "import hopsworks\n",
-    "\n",
-    "# Logging in to the Hopsworks project\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "# Getting the feature store from the project\n",
-    "fs = project.get_feature_store() "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve the feature groups\n",
-    "electricity_fg = fs.get_feature_group(\n",
-    "    name='electricity_prices',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "weather_fg = fs.get_feature_group(\n",
-    "    name='weather_measurements',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "danish_holidays_fg = fs.get_feature_group(\n",
-    "    name='danish_holidayss',\n",
-    "    version=1,\n",
-    ")\n",
-    "forecast_renewable_energy_fg = fs.get_feature_group(\n",
-    "    name='forecast_renewable_energy',\n",
-    "    version=1\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🖍 Feature View Creation and Retrieving </span>\n",
-    "\n",
-    "We first select the features that we want to include for model training.\n",
-    "\n",
-    "Since we specified `primary_key`as `date` and `event_time` as `timestamp` in part 01 we can now join them together for the `electricity_fg`, `weather_fg` and `forecast_renewable_energy_fg`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "hmmm skal 'time' egentlig være 'date'???"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Select features for training data\n",
-    "selected_features = electricity_fg.select_all()\\\n",
-    "    .join(weather_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(forecast_renewable_energy_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(danish_holidays_fg.select_all())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Uncomment this if you would like to view your selected features\n",
-    "# selected_features.show(5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🤖 Transformation Functions</span>\n",
-    "\n",
-    "We preprocess our data using *min-max scaling* on the numerical features and *label encoding* on the one categorical feature we have.\n",
-    "To achieve this, we create a mapping between our features and transformation functions. This ensures that transformation functions like min-max scaling are applied exclusively on the training data, preventing any data leakage into the validation or test sets.\n",
-    "\n",
-    "To achieve this, we create a mapping between our features and transformation functions - ved ikke om man kan sige det her?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining transformation functions for feature scaling and encoding\n",
-    "transformation_functions = {\n",
-    "        \"dk1_spotpricedkk_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_offshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_onshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_solar_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"temperature_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"relative_humidity_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"precipitation\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"rain\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"snowfall\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"weather_code\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"cloud_cover\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"wind_speed_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"wind_gusts_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"type\": fs.get_transformation_function(name=\"label_encoder\"),\n",
-    "    }"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` stands between **Feature Groups** and **Training Dataset**. Сombining **Feature Groups** we can create **Feature Views** which store a metadata of our data. Having **Feature Views** we can create **Training Dataset**.\n",
-    "\n",
-    "The Feature Views allows schema in form of a query with filters, define a model target feature/label and additional transformation functions.\n",
-    "\n",
-    "In order to create Feature View we can use `FeatureStore.get_or_create_feature_view()` method.\n",
-    "\n",
-    "We can specify next parameters:\n",
-    "\n",
-    "- `name` - name of a feature group.\n",
-    "\n",
-    "- `version` - version of a feature group.\n",
-    "\n",
-    "- `labels`- our target variable.\n",
-    "\n",
-    "- `transformation_functions` - functions to transform our features.\n",
-    "\n",
-    "- `query` - query object with data."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "ved ikke om den her omformulering af botten går an?"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` serve as an intermediary between **Feature Groups** and the **Training Dataset**. By combining various **Feature Groups**, we can construct **Feature Views**, which retain metadata about our data. Utilizing **Feature Views**, we can subsequently generate a **Training Dataset**.\n",
-    "\n",
-    "Feature Views facilitate the definition of schema through queries with filters, identification of the model's target feature or label, and application of additional transformation functions.\n",
-    "\n",
-    "To create a Feature View, we employ the `FeatureStore.get_or_create_feature_view()` method, where we specify the following parameters:\n",
-    "\n",
-    "- `name`: The name of the feature group.\n",
-    "\n",
-    "- `version`: The version of the feature group.\n",
-    "\n",
-    "- `labels`: Our target variable.\n",
-    "\n",
-    "- `transformation_functions`: Functions to transform our features.\n",
-    "\n",
-    "- `query`: A query object containing the relevant data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Getting or creating a feature view named 'electricity_feature_view'\n",
-    "version = 1 # Defining the version for the feature view\n",
-    "feature_view = fs.get_or_create_feature_view(\n",
-    "    name='electricity_feature_view',\n",
-    "    version=version,\n",
-    "    labels=[], # Labels will be defined manually later for our 'y'\n",
-    "    transformation_functions=transformation_functions,\n",
-    "    query=selected_features,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🏋️ Training Dataset Creation</span>\n",
-    "\n",
-    "In Hopsworks training data is a query where the projection (set of features) is determined by the parent FeatureView with an optional snapshot on disk of the data returned by the query.\n",
-    "\n",
-    "**Training Dataset  may contain splits such as:** \n",
-    "* Training set - the subset of training data used to train a model.\n",
-    "* Validation set - the subset of training data used to evaluate hparams when training a model\n",
-    "* Test set - the holdout subset of training data used to evaluate a mode\n",
-    "\n",
-    "Training dataset is created using `fs.create_training_dataset()` method.\n",
-    "\n",
-    "**From feature view APIs you can also create training datasts based on even time filters specifing `start_time` and `end_time`** "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> ⛳️ Dataset with train, test and validation splits</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Finished: Reading data from Hopsworks, using ArrowFlight (199.29s) \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "VersionWarning: Incremented version to `19`.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Splitting the feature view data into train, validation, and test sets\n",
-    "# We didn't specify 'labels' in feature view creation, it will therefore return 'None' for Y\n",
-    "X_train, X_val, X_test, _, _, _ = feature_view.train_validation_test_split(\n",
-    "    train_start=\"2022-01-01\",\n",
-    "    train_end=\"2023-06-30\",\n",
-    "    validation_start=\"2023-07-01\",\n",
-    "    validation_end=\"2023-09-30\",\n",
-    "    test_start=\"2023-10-01\",\n",
-    "    test_end=\"2023-12-31\",\n",
-    "    description='Electricity price prediction dataset',\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Sorting the training, validation, and test datasets based on the 'timestamp' column\n",
-    "X_train.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_val.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_test.sort_values([\"timestamp\"], inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Extracting the target variable 'dk1_spotpricedkk_kwh' and defineing 'y_train', 'y_val' and 'y_test' \n",
-    "y_train = X_train[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_val = X_val[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_test = X_test[[\"dk1_spotpricedkk_kwh\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Dropping the 'date', 'time' and 'timestamp' columns from the training, validation, and test datasets\n",
-    "# X_train.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "# X_val.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "# X_test.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Dropping the 'dare', 'time' and 'timestamp' and dependent variable (y) columns from the training, validation, and test datasets\n",
-    "# X_train.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "# X_val.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "# X_test.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>timestamp</th>\n",
-       "      <th>time</th>\n",
-       "      <th>date</th>\n",
-       "      <th>dk1_spotpricedkk_kwh</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "      <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_solar_forecastintraday_kwh</th>\n",
-       "      <th>type</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>1640995200000</td>\n",
-       "      <td>2022-01-01 00:00:00+00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.945277</td>\n",
-       "      <td>0.481878</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>1640995200000</td>\n",
-       "      <td>2022-01-01 00:00:00+00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.934795</td>\n",
-       "      <td>0.446702</td>\n",
-       "      <td>0.000008</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>1640995200000</td>\n",
-       "      <td>2022-01-01 00:00:00+00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.773045</td>\n",
-       "      <td>0.264375</td>\n",
-       "      <td>0.000018</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>1640995200000</td>\n",
-       "      <td>2022-01-01 00:00:00+00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "      <td>0.426339</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.195960</td>\n",
-       "      <td>0.187305</td>\n",
-       "      <td>0.913059</td>\n",
-       "      <td>0.358547</td>\n",
-       "      <td>0.000012</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>1640995200000</td>\n",
-       "      <td>2022-01-01 00:00:00+00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.493641</td>\n",
-       "      <td>0.133456</td>\n",
-       "      <td>0.005406</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "             timestamp                       time        date  \\\n",
-       "5905751  1640995200000  2022-01-01 00:00:00+00:00  2022-01-01   \n",
-       "19398    1640995200000  2022-01-01 00:00:00+00:00  2022-01-01   \n",
-       "5919627  1640995200000  2022-01-01 00:00:00+00:00  2022-01-01   \n",
-       "4719247  1640995200000  2022-01-01 00:00:00+00:00  2022-01-01   \n",
-       "4743896  1640995200000  2022-01-01 00:00:00+00:00  2022-01-01   \n",
-       "\n",
-       "         dk1_spotpricedkk_kwh  temperature_2m  relative_humidity_2m  \\\n",
-       "5905751              0.179988        0.435268              0.986667   \n",
-       "19398                0.179988        0.435268              0.986667   \n",
-       "5919627              0.179988        0.417411              0.933333   \n",
-       "4719247              0.179988        0.426339              0.933333   \n",
-       "4743896              0.179988        0.417411              0.933333   \n",
-       "\n",
-       "         precipitation      rain  snowfall  weather_code  cloud_cover  \\\n",
-       "5905751       0.011364  0.011364       0.0          0.68          1.0   \n",
-       "19398         0.011364  0.011364       0.0          0.68          1.0   \n",
-       "5919627       0.000000  0.000000       0.0          0.04          1.0   \n",
-       "4719247       0.000000  0.000000       0.0          0.04          1.0   \n",
-       "4743896       0.000000  0.000000       0.0          0.04          1.0   \n",
-       "\n",
-       "         wind_speed_10m  wind_gusts_10m  \\\n",
-       "5905751        0.315152        0.272633   \n",
-       "19398          0.315152        0.272633   \n",
-       "5919627        0.082828        0.074922   \n",
-       "4719247        0.195960        0.187305   \n",
-       "4743896        0.082828        0.074922   \n",
-       "\n",
-       "         dk1_offshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                                0.945277   \n",
-       "19398                                  0.934795   \n",
-       "5919627                                0.773045   \n",
-       "4719247                                0.913059   \n",
-       "4743896                                0.493641   \n",
-       "\n",
-       "         dk1_onshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                               0.481878   \n",
-       "19398                                 0.446702   \n",
-       "5919627                               0.264375   \n",
-       "4719247                               0.358547   \n",
-       "4743896                               0.133456   \n",
-       "\n",
-       "         dk1_solar_forecastintraday_kwh  type  \n",
-       "5905751                        0.000000     1  \n",
-       "19398                          0.000008     1  \n",
-       "5919627                        0.000018     1  \n",
-       "4719247                        0.000012     1  \n",
-       "4743896                        0.005406     1  "
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Displaying the first 5 rows of the train dataset (X_train)\n",
-    "X_train.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>dk1_spotpricedkk_kwh</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "               date  dk1_spotpricedkk_kwh\n",
-       "5905751  2022-01-01              0.179988\n",
-       "19398    2022-01-01              0.179988\n",
-       "5919627  2022-01-01              0.179988\n",
-       "4719247  2022-01-01              0.179988\n",
-       "4743896  2022-01-01              0.179988"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df = X_train[[\"date\", \"dk1_spotpricedkk_kwh\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>ds</th>\n",
-       "      <th>y</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                 ds         y\n",
-       "5905751  2022-01-01  0.179988\n",
-       "19398    2022-01-01  0.179988\n",
-       "5919627  2022-01-01  0.179988\n",
-       "4719247  2022-01-01  0.179988\n",
-       "4743896  2022-01-01  0.179988"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.columns = [\"ds\", \"y\"]\n",
-    "df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🗃 Window timeseries dataset </span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling Testing</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from prophet import Prophet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "14:24:30 - cmdstanpy - INFO - Chain [1] start processing\n"
-     ]
-    }
-   ],
-   "source": [
-    "m = Prophet(interval_width=0.95, daily_seasonality=True)\n",
-    "model = m.fit(df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "future = m.make_future_dataframe(periods=100,freq='D')\n",
-    "forecast = m.predict(future)\n",
-    "forecast.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "plot1 = m.plot(forecast)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# import pandas as pd\n",
-    "# import numpy as np\n",
-    "# import xgboost as xgb\n",
-    "# from sklearn.metrics import mean_squared_error\n",
-    "# import os"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Initialize the XGBoost regressor\n",
-    "# model = xgb.XGBRegressor()\n",
-    "# model_val = xgb.XGBRegressor()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Train the model on the training data\n",
-    "# model.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Make predictions on the validation set\n",
-    "# y_test_pred = model.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Calculate RMSE on the validation set\n",
-    "# mse = mean_squared_error(y_test, y_test_pred, squared=False)\n",
-    "# print(f\"Mean Squared Error (MSE): {mse}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'>🗄 Model Registry</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Exporting the trained model to a directory\n",
-    "model_dir = \"electricity_price_model\"\n",
-    "print('Exporting trained model to: {}'.format(model_dir))\n",
-    "\n",
-    "# Saving the model using TensorFlow's saved_model.save function\n",
-    "tf.saved_model.save(model, model_dir)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieving the Model Registry\n",
-    "mr = project.get_model_registry()\n",
-    "\n",
-    "# Extracting loss value from the training history\n",
-    "metrics = {'loss': history_dict['val_loss'][0]} \n",
-    "\n",
-    "# Creating a TensorFlow model in the Model Registry\n",
-    "tf_model = mr.tensorflow.create_model(\n",
-    "    name=\"DK_electricity_price_prediction_model\",\n",
-    "    metrics=metrics,\n",
-    "    description=\"Hourly electricity price prediction model.\",\n",
-    "    input_example=n_step_window.example[0].numpy(),\n",
-    ")\n",
-    "\n",
-    "# Saving the model to the specified directory\n",
-    "tf_model.save(model_dir)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 04: Batch Inference </span>\n",
-    "\n",
-    "In the next notebook you will use your registered model to predict batch data."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-mlops",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/notebooks_dev/3_training_pipeline_dev_pytorch.ipynb

@@ -1,874 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 03: Training Pipeline</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Feature selection.\n",
-    "2. Feature transformations.\n",
-    "3. Training datasets creation.\n",
-    "4. Loading the training data.\n",
-    "5. Train the model.\n",
-    "6. Register model to Hopsworks model registry."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install tensorflow --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Importing the packages for the needed libraries for the Jupyter notebook\n",
-    "import inspect \n",
-    "import datetime\n",
-    "\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
-    "#ignore warnings\n",
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'cuda:0'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "device = 'cuda:0' if torch.cuda.is_available() else 'cpu'\n",
-    "device"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n",
-      "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/556180\n",
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Importing the hopsworks module\n",
-    "import hopsworks\n",
-    "\n",
-    "# Logging in to the Hopsworks project\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "# Getting the feature store from the project\n",
-    "fs = project.get_feature_store() "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve the feature groups\n",
-    "electricity_fg = fs.get_feature_group(\n",
-    "    name='electricity_prices',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "weather_fg = fs.get_feature_group(\n",
-    "    name='weather_measurements',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "danish_holidays_fg = fs.get_feature_group(\n",
-    "    name='danish_holidayss',\n",
-    "    version=1,\n",
-    ")\n",
-    "forecast_renewable_energy_fg = fs.get_feature_group(\n",
-    "    name='forecast_renewable_energy',\n",
-    "    version=1\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🖍 Feature View Creation and Retrieving </span>\n",
-    "\n",
-    "We first select the features that we want to include for model training.\n",
-    "\n",
-    "Since we specified `primary_key`as `date` and `event_time` as `timestamp` in part 01 we can now join them together for the `electricity_fg`, `weather_fg` and `forecast_renewable_energy_fg`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "hmmm skal 'time' egentlig være 'date'???"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Select features for training data\n",
-    "selected_features = electricity_fg.select_all()\\\n",
-    "    .join(weather_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(forecast_renewable_energy_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(danish_holidays_fg.select_all())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Uncomment this if you would like to view your selected features\n",
-    "# selected_features.show(5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🤖 Transformation Functions</span>\n",
-    "\n",
-    "We preprocess our data using *min-max scaling* on the numerical features and *label encoding* on the one categorical feature we have.\n",
-    "To achieve this, we create a mapping between our features and transformation functions. This ensures that transformation functions like min-max scaling are applied exclusively on the training data, preventing any data leakage into the validation or test sets.\n",
-    "\n",
-    "To achieve this, we create a mapping between our features and transformation functions - ved ikke om man kan sige det her?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining transformation functions for feature scaling and encoding\n",
-    "transformation_functions = {\n",
-    "        \"dk1_spotpricedkk_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_offshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_onshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_solar_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"temperature_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"relative_humidity_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"precipitation\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"rain\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"snowfall\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"weather_code\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"cloud_cover\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"wind_speed_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"wind_gusts_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"type\": fs.get_transformation_function(name=\"label_encoder\"),\n",
-    "    }"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` stands between **Feature Groups** and **Training Dataset**. Сombining **Feature Groups** we can create **Feature Views** which store a metadata of our data. Having **Feature Views** we can create **Training Dataset**.\n",
-    "\n",
-    "The Feature Views allows schema in form of a query with filters, define a model target feature/label and additional transformation functions.\n",
-    "\n",
-    "In order to create Feature View we can use `FeatureStore.get_or_create_feature_view()` method.\n",
-    "\n",
-    "We can specify next parameters:\n",
-    "\n",
-    "- `name` - name of a feature group.\n",
-    "\n",
-    "- `version` - version of a feature group.\n",
-    "\n",
-    "- `labels`- our target variable.\n",
-    "\n",
-    "- `transformation_functions` - functions to transform our features.\n",
-    "\n",
-    "- `query` - query object with data."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "ved ikke om den her omformulering af botten går an?"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` serve as an intermediary between **Feature Groups** and the **Training Dataset**. By combining various **Feature Groups**, we can construct **Feature Views**, which retain metadata about our data. Utilizing **Feature Views**, we can subsequently generate a **Training Dataset**.\n",
-    "\n",
-    "Feature Views facilitate the definition of schema through queries with filters, identification of the model's target feature or label, and application of additional transformation functions.\n",
-    "\n",
-    "To create a Feature View, we employ the `FeatureStore.get_or_create_feature_view()` method, where we specify the following parameters:\n",
-    "\n",
-    "- `name`: The name of the feature group.\n",
-    "\n",
-    "- `version`: The version of the feature group.\n",
-    "\n",
-    "- `labels`: Our target variable.\n",
-    "\n",
-    "- `transformation_functions`: Functions to transform our features.\n",
-    "\n",
-    "- `query`: A query object containing the relevant data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Getting or creating a feature view named 'electricity_feature_view'\n",
-    "version = 1 # Defining the version for the feature view\n",
-    "feature_view = fs.get_or_create_feature_view(\n",
-    "    name='electricity_feature_view',\n",
-    "    version=version,\n",
-    "    labels=[], # Labels will be defined manually later for our 'y'\n",
-    "    transformation_functions=transformation_functions,\n",
-    "    query=selected_features,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🏋️ Training Dataset Creation</span>\n",
-    "\n",
-    "In Hopsworks training data is a query where the projection (set of features) is determined by the parent FeatureView with an optional snapshot on disk of the data returned by the query.\n",
-    "\n",
-    "**Training Dataset  may contain splits such as:** \n",
-    "* Training set - the subset of training data used to train a model.\n",
-    "* Validation set - the subset of training data used to evaluate hparams when training a model\n",
-    "* Test set - the holdout subset of training data used to evaluate a mode\n",
-    "\n",
-    "Training dataset is created using `fs.create_training_dataset()` method.\n",
-    "\n",
-    "**From feature view APIs you can also create training datasts based on even time filters specifing `start_time` and `end_time`** "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> ⛳️ Dataset with train, test and validation splits</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Finished: Reading data from Hopsworks, using ArrowFlight (211.16s) \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "VersionWarning: Incremented version to `21`.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Splitting the feature view data into train, validation, and test sets\n",
-    "# We didn't specify 'labels' in feature view creation, it will therefore return 'None' for Y\n",
-    "X_train, X_val, X_test, _, _, _ = feature_view.train_validation_test_split(\n",
-    "    train_start=\"2022-01-01\",\n",
-    "    train_end=\"2023-06-30\",\n",
-    "    validation_start=\"2023-07-01\",\n",
-    "    validation_end=\"2023-09-30\",\n",
-    "    test_start=\"2023-10-01\",\n",
-    "    test_end=\"2023-12-31\",\n",
-    "    description='Electricity price prediction dataset',\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Sorting the training, validation, and test datasets based on the 'timestamp' column\n",
-    "X_train.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_val.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_test.sort_values([\"timestamp\"], inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Extracting the target variable 'dk1_spotpricedkk_kwh' and defineing 'y_train', 'y_val' and 'y_test' \n",
-    "y_train = X_train[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_val = X_val[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_test = X_test[[\"dk1_spotpricedkk_kwh\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Dropping the 'date', 'time' and 'timestamp' columns from the training, validation, and test datasets\n",
-    "X_train.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "X_val.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "X_test.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Dropping the 'dare', 'time' and 'timestamp' and dependent variable (y) columns from the training, validation, and test datasets\n",
-    "X_train.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "X_val.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "X_test.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "      <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_solar_forecastintraday_kwh</th>\n",
-       "      <th>type</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.945277</td>\n",
-       "      <td>0.481878</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.934795</td>\n",
-       "      <td>0.446702</td>\n",
-       "      <td>0.000008</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.773045</td>\n",
-       "      <td>0.264375</td>\n",
-       "      <td>0.000018</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>0.426339</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.195960</td>\n",
-       "      <td>0.187305</td>\n",
-       "      <td>0.913059</td>\n",
-       "      <td>0.358547</td>\n",
-       "      <td>0.000012</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.493641</td>\n",
-       "      <td>0.133456</td>\n",
-       "      <td>0.005406</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         temperature_2m  relative_humidity_2m  precipitation      rain  \\\n",
-       "5905751        0.435268              0.986667       0.011364  0.011364   \n",
-       "19398          0.435268              0.986667       0.011364  0.011364   \n",
-       "5919627        0.417411              0.933333       0.000000  0.000000   \n",
-       "4719247        0.426339              0.933333       0.000000  0.000000   \n",
-       "4743896        0.417411              0.933333       0.000000  0.000000   \n",
-       "\n",
-       "         snowfall  weather_code  cloud_cover  wind_speed_10m  wind_gusts_10m  \\\n",
-       "5905751       0.0          0.68          1.0        0.315152        0.272633   \n",
-       "19398         0.0          0.68          1.0        0.315152        0.272633   \n",
-       "5919627       0.0          0.04          1.0        0.082828        0.074922   \n",
-       "4719247       0.0          0.04          1.0        0.195960        0.187305   \n",
-       "4743896       0.0          0.04          1.0        0.082828        0.074922   \n",
-       "\n",
-       "         dk1_offshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                                0.945277   \n",
-       "19398                                  0.934795   \n",
-       "5919627                                0.773045   \n",
-       "4719247                                0.913059   \n",
-       "4743896                                0.493641   \n",
-       "\n",
-       "         dk1_onshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                               0.481878   \n",
-       "19398                                 0.446702   \n",
-       "5919627                               0.264375   \n",
-       "4719247                               0.358547   \n",
-       "4743896                               0.133456   \n",
-       "\n",
-       "         dk1_solar_forecastintraday_kwh  type  \n",
-       "5905751                        0.000000     1  \n",
-       "19398                          0.000008     1  \n",
-       "5919627                        0.000018     1  \n",
-       "4719247                        0.000012     1  \n",
-       "4743896                        0.005406     1  "
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Displaying the first 5 rows of the train dataset (X_train)\n",
-    "X_train.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🗃 Window timeseries dataset </span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(5012736, 13)"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "X_train.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling Testing</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "AttributeError",
-     "evalue": "'DataFrame' object has no attribute 'reshape'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_15496\\1411499862.py\u001b[0m in \u001b[0;36m?\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mX_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m13\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\cudatest\\Lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m?\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m   6200\u001b[0m             \u001b[1;32mand\u001b[0m \u001b[0mname\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_accessors\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   6201\u001b[0m             \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   6202\u001b[0m         ):\n\u001b[0;32m   6203\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 6204\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[1;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'reshape'"
-     ]
-    }
-   ],
-   "source": [
-    "X_train = X_train.reshape((-1, 1, 13))\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "AttributeError",
-     "evalue": "'DataFrame' object has no attribute 'reshape'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
-      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_15496\\1311144430.py\u001b[0m in \u001b[0;36m?\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mX_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m13\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[0mX_test\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mX_test\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m13\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0my_train\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0my_train\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
-      "\u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\cudatest\\Lib\\site-packages\\pandas\\core\\generic.py\u001b[0m in \u001b[0;36m?\u001b[1;34m(self, name)\u001b[0m\n\u001b[0;32m   6200\u001b[0m             \u001b[1;32mand\u001b[0m \u001b[0mname\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_accessors\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   6201\u001b[0m             \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_info_axis\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_can_hold_identifiers_and_holds_name\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   6202\u001b[0m         ):\n\u001b[0;32m   6203\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 6204\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[1;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'reshape'"
-     ]
-    }
-   ],
-   "source": [
-    "X_train = X_train.reshape((-1, 13, 1))\n",
-    "X_test = X_test.reshape((-1, 13, 1))\n",
-    "\n",
-    "y_train = y_train.reshape((-1, 1))\n",
-    "y_test = y_test.reshape((-1, 1))\n",
-    "\n",
-    "X_train.shape, X_test.shape, y_train.shape, y_test.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "ValueError",
-     "evalue": "could not determine the shape of object type 'DataFrame'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[17], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m X_train \u001b[38;5;241m=\u001b[39m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtensor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mastype\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mfloat\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mfloat()\n\u001b[0;32m      2\u001b[0m y_train \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mtensor(y_train)\u001b[38;5;241m.\u001b[39mfloat()\n\u001b[0;32m      3\u001b[0m X_test \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mtensor(X_test\u001b[38;5;241m.\u001b[39mastype(\u001b[38;5;28mfloat\u001b[39m))\u001b[38;5;241m.\u001b[39mfloat()\n",
-      "\u001b[1;31mValueError\u001b[0m: could not determine the shape of object type 'DataFrame'"
-     ]
-    }
-   ],
-   "source": [
-    "X_train = torch.tensor(X_train.astype(float)).float()\n",
-    "y_train = torch.tensor(y_train).float()\n",
-    "X_test = torch.tensor(X_test.astype(float)).float()\n",
-    "y_test = torch.tensor(y_test).float()\n",
-    "\n",
-    "X_train.shape, X_test.shape, y_train.shape, y_test.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# import pandas as pd\n",
-    "# import numpy as np\n",
-    "# import xgboost as xgb\n",
-    "# from sklearn.metrics import mean_squared_error\n",
-    "# import os"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Initialize the XGBoost regressor\n",
-    "# model = xgb.XGBRegressor()\n",
-    "# model_val = xgb.XGBRegressor()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Train the model on the training data\n",
-    "# model.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Make predictions on the validation set\n",
-    "# y_test_pred = model.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Calculate RMSE on the validation set\n",
-    "# mse = mean_squared_error(y_test, y_test_pred, squared=False)\n",
-    "# print(f\"Mean Squared Error (MSE): {mse}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'>🗄 Model Registry</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Exporting trained model to: electricity_price_model\n",
-      "INFO:tensorflow:Assets written to: electricity_price_model\\assets\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Exporting the trained model to a directory\n",
-    "model_dir = \"electricity_price_model\"\n",
-    "print('Exporting trained model to: {}'.format(model_dir))\n",
-    "\n",
-    "# Saving the model using TensorFlow's saved_model.save function\n",
-    "tf.saved_model.save(model, model_dir)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 44,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading: 100.000%|██████████| 59/59 elapsed<00:01 remaining<00:001<00:01,  3.38it/s]\n",
-      "Uploading: 100.000%|██████████| 397272/397272 elapsed<00:02 remaining<00:00  3.38it/s]\n",
-      "Uploading: 0.000%|          | 0/112411 elapsed<00:01 remaining<?0:04<00:01,  3.38it/s]\n",
-      "Uploading model files (2 dirs, 2 files):  17%|█▋        | 1/6 [00:07<00:35,  7.08s/it]\n"
-     ]
-    },
-    {
-     "ename": "RestAPIError",
-     "evalue": "Metadata operation error: (url: https://c.app.hopsworks.ai/hopsworks-api/api/project/556180/dataset/upload/%2FProjects%2Fbenjami3%2FModels%2FDK_electricity_price_prediction_model%2F1%5Cvariables). Server response: \nHTTP code: 400, HTTP reason: Invalid URI, body: b''",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mRestAPIError\u001b[0m                              Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[44], line 16\u001b[0m\n\u001b[0;32m      8\u001b[0m tf_model \u001b[38;5;241m=\u001b[39m mr\u001b[38;5;241m.\u001b[39mtensorflow\u001b[38;5;241m.\u001b[39mcreate_model(\n\u001b[0;32m      9\u001b[0m     name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDK_electricity_price_prediction_model\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     10\u001b[0m     metrics\u001b[38;5;241m=\u001b[39mmetrics,\n\u001b[0;32m     11\u001b[0m     description\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHourly electricity price prediction model.\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     12\u001b[0m     input_example\u001b[38;5;241m=\u001b[39mn_step_window\u001b[38;5;241m.\u001b[39mexample[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mnumpy(),\n\u001b[0;32m     13\u001b[0m )\n\u001b[0;32m     15\u001b[0m \u001b[38;5;66;03m# Saving the model to the specified directory\u001b[39;00m\n\u001b[1;32m---> 16\u001b[0m \u001b[43mtf_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_dir\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\model.py:101\u001b[0m, in \u001b[0;36mModel.save\u001b[1;34m(self, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m     90\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msave\u001b[39m(\u001b[38;5;28mself\u001b[39m, model_path, await_registration\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m480\u001b[39m, keep_original_files\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m     91\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Persist this model including model files and metadata to the model registry.\u001b[39;00m\n\u001b[0;32m     92\u001b[0m \n\u001b[0;32m     93\u001b[0m \u001b[38;5;124;03m    # Arguments\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     99\u001b[0m \u001b[38;5;124;03m        `Model`: The model metadata object.\u001b[39;00m\n\u001b[0;32m    100\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 101\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_model_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    102\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    103\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    104\u001b[0m \u001b[43m        \u001b[49m\u001b[43mawait_registration\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mawait_registration\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    105\u001b[0m \u001b[43m        \u001b[49m\u001b[43mkeep_original_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_original_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    106\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:421\u001b[0m, in \u001b[0;36mModelEngine.save\u001b[1;34m(self, model_instance, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m    419\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m be:\n\u001b[0;32m    420\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_api\u001b[38;5;241m.\u001b[39mrm(model_instance\u001b[38;5;241m.\u001b[39mversion_path)\n\u001b[1;32m--> 421\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m be\n\u001b[0;32m    423\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel created, explore it at \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m model_instance\u001b[38;5;241m.\u001b[39mget_url())\n\u001b[0;32m    425\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model_instance\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:385\u001b[0m, in \u001b[0;36mModelEngine.save\u001b[1;34m(self, model_instance, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m    381\u001b[0m \u001b[38;5;66;03m# check local relative\u001b[39;00m\n\u001b[0;32m    382\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(\n\u001b[0;32m    383\u001b[0m     os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(os\u001b[38;5;241m.\u001b[39mgetcwd(), model_path)\n\u001b[0;32m    384\u001b[0m ):  \u001b[38;5;66;03m# check local relative\u001b[39;00m\n\u001b[1;32m--> 385\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_save_model_from_local_or_hopsfs_mount\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    386\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_instance\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_instance\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    387\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgetcwd\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    388\u001b[0m \u001b[43m        \u001b[49m\u001b[43mkeep_original_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_original_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    389\u001b[0m \u001b[43m        \u001b[49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    391\u001b[0m \u001b[38;5;66;03m# check project relative\u001b[39;00m\n\u001b[0;32m    392\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_api\u001b[38;5;241m.\u001b[39mpath_exists(\n\u001b[0;32m    393\u001b[0m     model_path\n\u001b[0;32m    394\u001b[0m ):  \u001b[38;5;66;03m# check hdfs relative and absolute\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:249\u001b[0m, in \u001b[0;36mModelEngine._save_model_from_local_or_hopsfs_mount\u001b[1;34m(self, model_instance, model_path, keep_original_files, update_upload_progress)\u001b[0m\n\u001b[0;32m    240\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_copy_or_move_hopsfs_model(\n\u001b[0;32m    241\u001b[0m         from_hdfs_model_path\u001b[38;5;241m=\u001b[39mmodel_path\u001b[38;5;241m.\u001b[39mreplace(\n\u001b[0;32m    242\u001b[0m             constants\u001b[38;5;241m.\u001b[39mMODEL_REGISTRY\u001b[38;5;241m.\u001b[39mHOPSFS_MOUNT_PREFIX, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    246\u001b[0m         update_upload_progress\u001b[38;5;241m=\u001b[39mupdate_upload_progress,\n\u001b[0;32m    247\u001b[0m     )\n\u001b[0;32m    248\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 249\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_upload_local_model\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    250\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfrom_local_model_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    251\u001b[0m \u001b[43m        \u001b[49m\u001b[43mto_model_version_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_instance\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mversion_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    252\u001b[0m \u001b[43m        \u001b[49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    253\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:225\u001b[0m, in \u001b[0;36mModelEngine._upload_local_model\u001b[1;34m(self, from_local_model_path, to_model_version_path, update_upload_progress)\u001b[0m\n\u001b[0;32m    223\u001b[0m     update_upload_progress(n_dirs, n_files)\n\u001b[0;32m    224\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m f_name \u001b[38;5;129;01min\u001b[39;00m files:\n\u001b[1;32m--> 225\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mroot\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mf_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mremote_base_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    226\u001b[0m     n_files \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m    227\u001b[0m     update_upload_progress(n_dirs, n_files)\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\local_engine.py:38\u001b[0m, in \u001b[0;36mLocalEngine.upload\u001b[1;34m(self, local_path, remote_path)\u001b[0m\n\u001b[0;32m     36\u001b[0m local_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_abs_path(local_path)\n\u001b[0;32m     37\u001b[0m remote_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepend_project_path(remote_path)\n\u001b[1;32m---> 38\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dataset_api\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlocal_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mremote_path\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:152\u001b[0m, in \u001b[0;36mDatasetApi.upload\u001b[1;34m(self, local_path, upload_path, overwrite, chunk_size, simultaneous_uploads, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    150\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    151\u001b[0m                 pbar\u001b[38;5;241m.\u001b[39mclose()\n\u001b[1;32m--> 152\u001b[0m             \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[0;32m    154\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    155\u001b[0m     pbar\u001b[38;5;241m.\u001b[39mclose()\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:148\u001b[0m, in \u001b[0;36mDatasetApi.upload\u001b[1;34m(self, local_path, upload_path, overwrite, chunk_size, simultaneous_uploads, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    146\u001b[0m _, _ \u001b[38;5;241m=\u001b[39m wait(futures)\n\u001b[0;32m    147\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 148\u001b[0m     _ \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfuture\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfutures\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    150\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:148\u001b[0m, in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m    146\u001b[0m _, _ \u001b[38;5;241m=\u001b[39m wait(futures)\n\u001b[0;32m    147\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 148\u001b[0m     _ \u001b[38;5;241m=\u001b[39m [\u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m future \u001b[38;5;129;01min\u001b[39;00m futures]\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    150\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\_base.py:449\u001b[0m, in \u001b[0;36mFuture.result\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m    447\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m CancelledError()\n\u001b[0;32m    448\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;241m==\u001b[39m FINISHED:\n\u001b[1;32m--> 449\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__get_result\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    451\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_condition\u001b[38;5;241m.\u001b[39mwait(timeout)\n\u001b[0;32m    453\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;129;01min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\_base.py:401\u001b[0m, in \u001b[0;36mFuture.__get_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    399\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception:\n\u001b[0;32m    400\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 401\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception\n\u001b[0;32m    402\u001b[0m     \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m    403\u001b[0m         \u001b[38;5;66;03m# Break a reference cycle with the exception in self._exception\u001b[39;00m\n\u001b[0;32m    404\u001b[0m         \u001b[38;5;28mself\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\thread.py:58\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     55\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m     57\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m---> 58\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     59\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m     60\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfuture\u001b[38;5;241m.\u001b[39mset_exception(exc)\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:189\u001b[0m, in \u001b[0;36mDatasetApi._upload_chunk\u001b[1;34m(self, base_params, upload_path, file_name, chunk, pbar, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    184\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[0;32m    185\u001b[0m     re\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;129;01min\u001b[39;00m DatasetApi\u001b[38;5;241m.\u001b[39mFLOW_PERMANENT_ERRORS\n\u001b[0;32m    186\u001b[0m     \u001b[38;5;129;01mor\u001b[39;00m chunk\u001b[38;5;241m.\u001b[39mretries \u001b[38;5;241m>\u001b[39m max_chunk_retries\n\u001b[0;32m    187\u001b[0m ):\n\u001b[0;32m    188\u001b[0m     chunk\u001b[38;5;241m.\u001b[39mstatus \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfailed\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 189\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m re\n\u001b[0;32m    190\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(chunk_retry_interval)\n\u001b[0;32m    191\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:178\u001b[0m, in \u001b[0;36mDatasetApi._upload_chunk\u001b[1;34m(self, base_params, upload_path, file_name, chunk, pbar, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    176\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m    177\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 178\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_upload_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    179\u001b[0m \u001b[43m            \u001b[49m\u001b[43mquery_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mupload_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfile_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcontent\u001b[49m\n\u001b[0;32m    180\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    181\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[0;32m    182\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m RestAPIError \u001b[38;5;28;01mas\u001b[39;00m re:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:214\u001b[0m, in \u001b[0;36mDatasetApi._upload_request\u001b[1;34m(self, params, path, file_name, chunk)\u001b[0m\n\u001b[0;32m    211\u001b[0m path_params \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mproject\u001b[39m\u001b[38;5;124m\"\u001b[39m, _client\u001b[38;5;241m.\u001b[39m_project_id, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdataset\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mupload\u001b[39m\u001b[38;5;124m\"\u001b[39m, path]\n\u001b[0;32m    213\u001b[0m \u001b[38;5;66;03m# Flow configuration params are sent as form data\u001b[39;00m\n\u001b[1;32m--> 214\u001b[0m \u001b[43m_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_send_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    215\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mPOST\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfiles\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfile\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\n\u001b[0;32m    216\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\decorators.py:35\u001b[0m, in \u001b[0;36mconnected.<locals>.if_connected\u001b[1;34m(inst, *args, **kwargs)\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m inst\u001b[38;5;241m.\u001b[39m_connected:\n\u001b[0;32m     34\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m NoHopsworksConnectionError\n\u001b[1;32m---> 35\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43minst\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\client\\base.py:108\u001b[0m, in \u001b[0;36mClient._send_request\u001b[1;34m(self, method, path_params, query_params, headers, data, stream, files)\u001b[0m\n\u001b[0;32m    105\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_session\u001b[38;5;241m.\u001b[39msend(prepped, verify\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_verify, stream\u001b[38;5;241m=\u001b[39mstream)\n\u001b[0;32m    107\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m/\u001b[39m\u001b[38;5;241m/\u001b[39m \u001b[38;5;241m100\u001b[39m \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m--> 108\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m exceptions\u001b[38;5;241m.\u001b[39mRestAPIError(url, response)\n\u001b[0;32m    110\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n\u001b[0;32m    111\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
-      "\u001b[1;31mRestAPIError\u001b[0m: Metadata operation error: (url: https://c.app.hopsworks.ai/hopsworks-api/api/project/556180/dataset/upload/%2FProjects%2Fbenjami3%2FModels%2FDK_electricity_price_prediction_model%2F1%5Cvariables). Server response: \nHTTP code: 400, HTTP reason: Invalid URI, body: b''"
-     ]
-    }
-   ],
-   "source": [
-    "# Retrieving the Model Registry\n",
-    "mr = project.get_model_registry()\n",
-    "\n",
-    "# Extracting loss value from the training history\n",
-    "metrics = {'loss': history_dict['val_loss'][0]} \n",
-    "\n",
-    "# Creating a TensorFlow model in the Model Registry\n",
-    "tf_model = mr.tensorflow.create_model(\n",
-    "    name=\"DK_electricity_price_prediction_model\",\n",
-    "    metrics=metrics,\n",
-    "    description=\"Hourly electricity price prediction model.\",\n",
-    "    input_example=n_step_window.example[0].numpy(),\n",
-    ")\n",
-    "\n",
-    "# Saving the model to the specified directory\n",
-    "tf_model.save(model_dir)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 04: Batch Inference </span>\n",
-    "\n",
-    "In the next notebook you will use your registered model to predict batch data."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-mlops",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.16"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

hide/notebooks_dev/3_training_pipeline_dev_tensorflow.ipynb

@@ -1,818 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Data Engineering and Machine Learning Operations in Business** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 03: Training Pipeline</span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## 🗒️ This notebook is divided into the following sections:\n",
-    "1. Feature selection.\n",
-    "2. Feature transformations.\n",
-    "3. Training datasets creation.\n",
-    "4. Loading the training data.\n",
-    "5. Train the model.\n",
-    "6. Register model to Hopsworks model registry."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install tensorflow --quiet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Importing the packages for the needed libraries for the Jupyter notebook\n",
-    "import inspect \n",
-    "import datetime\n",
-    "\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import tensorflow as tf\n",
-    "\n",
-    "#ignore warnings\n",
-    "import warnings\n",
-    "warnings.filterwarnings('ignore')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "c:\\Users\\Benj3\\anaconda3\\envs\\tensor\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n",
-      "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/556180\n",
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Importing the hopsworks module\n",
-    "import hopsworks\n",
-    "\n",
-    "# Logging in to the Hopsworks project\n",
-    "project = hopsworks.login()\n",
-    "\n",
-    "# Getting the feature store from the project\n",
-    "fs = project.get_feature_store() "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Retrieve the feature groups\n",
-    "electricity_fg = fs.get_feature_group(\n",
-    "    name='electricity_prices',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "weather_fg = fs.get_feature_group(\n",
-    "    name='weather_measurements',\n",
-    "    version=1,\n",
-    ")\n",
-    "\n",
-    "danish_holidays_fg = fs.get_feature_group(\n",
-    "    name='danish_holidayss',\n",
-    "    version=1,\n",
-    ")\n",
-    "forecast_renewable_energy_fg = fs.get_feature_group(\n",
-    "    name='forecast_renewable_energy',\n",
-    "    version=1\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🖍 Feature View Creation and Retrieving </span>\n",
-    "\n",
-    "We first select the features that we want to include for model training.\n",
-    "\n",
-    "Since we specified `primary_key`as `date` and `event_time` as `timestamp` in part 01 we can now join them together for the `electricity_fg`, `weather_fg` and `forecast_renewable_energy_fg`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "hmmm skal 'time' egentlig være 'date'???"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Select features for training data\n",
-    "selected_features = electricity_fg.select_all()\\\n",
-    "    .join(weather_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(forecast_renewable_energy_fg.select_except([\"timestamp\", \"time\"]))\\\n",
-    "    .join(danish_holidays_fg.select_all())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Uncomment this if you would like to view your selected features\n",
-    "# selected_features.show(5)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> 🤖 Transformation Functions</span>\n",
-    "\n",
-    "We preprocess our data using *min-max scaling* on the numerical features and *label encoding* on the one categorical feature we have.\n",
-    "To achieve this, we create a mapping between our features and transformation functions. This ensures that transformation functions like min-max scaling are applied exclusively on the training data, preventing any data leakage into the validation or test sets.\n",
-    "\n",
-    "To achieve this, we create a mapping between our features and transformation functions - ved ikke om man kan sige det her?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Defining transformation functions for feature scaling and encoding\n",
-    "transformation_functions = {\n",
-    "        \"dk1_spotpricedkk_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_offshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_onshore_wind_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"dk1_solar_forecastintraday_kwh\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"temperature_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"relative_humidity_2m\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"precipitation\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"rain\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"snowfall\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"weather_code\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"cloud_cover\": fs.get_transformation_function(name=\"min_max_scaler\"), \n",
-    "        \"wind_speed_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"wind_gusts_10m\": fs.get_transformation_function(name=\"min_max_scaler\"),\n",
-    "        \"type\": fs.get_transformation_function(name=\"label_encoder\"),\n",
-    "    }"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` stands between **Feature Groups** and **Training Dataset**. Сombining **Feature Groups** we can create **Feature Views** which store a metadata of our data. Having **Feature Views** we can create **Training Dataset**.\n",
-    "\n",
-    "The Feature Views allows schema in form of a query with filters, define a model target feature/label and additional transformation functions.\n",
-    "\n",
-    "In order to create Feature View we can use `FeatureStore.get_or_create_feature_view()` method.\n",
-    "\n",
-    "We can specify next parameters:\n",
-    "\n",
-    "- `name` - name of a feature group.\n",
-    "\n",
-    "- `version` - version of a feature group.\n",
-    "\n",
-    "- `labels`- our target variable.\n",
-    "\n",
-    "- `transformation_functions` - functions to transform our features.\n",
-    "\n",
-    "- `query` - query object with data."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "ved ikke om den her omformulering af botten går an?"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Feature Views` serve as an intermediary between **Feature Groups** and the **Training Dataset**. By combining various **Feature Groups**, we can construct **Feature Views**, which retain metadata about our data. Utilizing **Feature Views**, we can subsequently generate a **Training Dataset**.\n",
-    "\n",
-    "Feature Views facilitate the definition of schema through queries with filters, identification of the model's target feature or label, and application of additional transformation functions.\n",
-    "\n",
-    "To create a Feature View, we employ the `FeatureStore.get_or_create_feature_view()` method, where we specify the following parameters:\n",
-    "\n",
-    "- `name`: The name of the feature group.\n",
-    "\n",
-    "- `version`: The version of the feature group.\n",
-    "\n",
-    "- `labels`: Our target variable.\n",
-    "\n",
-    "- `transformation_functions`: Functions to transform our features.\n",
-    "\n",
-    "- `query`: A query object containing the relevant data."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Getting or creating a feature view named 'electricity_feature_view'\n",
-    "version = 1 # Defining the version for the feature view\n",
-    "feature_view = fs.get_or_create_feature_view(\n",
-    "    name='electricity_feature_view',\n",
-    "    version=version,\n",
-    "    labels=[], # Labels will be defined manually later for our 'y'\n",
-    "    transformation_functions=transformation_functions,\n",
-    "    query=selected_features,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\"> 🏋️ Training Dataset Creation</span>\n",
-    "\n",
-    "In Hopsworks training data is a query where the projection (set of features) is determined by the parent FeatureView with an optional snapshot on disk of the data returned by the query.\n",
-    "\n",
-    "**Training Dataset  may contain splits such as:** \n",
-    "* Training set - the subset of training data used to train a model.\n",
-    "* Validation set - the subset of training data used to evaluate hparams when training a model\n",
-    "* Test set - the holdout subset of training data used to evaluate a mode\n",
-    "\n",
-    "Training dataset is created using `fs.create_training_dataset()` method.\n",
-    "\n",
-    "**From feature view APIs you can also create training datasts based on even time filters specifing `start_time` and `end_time`** "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\"> ⛳️ Dataset with train, test and validation splits</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Finished: Reading data from Hopsworks, using ArrowFlight (198.29s) \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "VersionWarning: Incremented version to `15`.\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Splitting the feature view data into train, validation, and test sets\n",
-    "# We didn't specify 'labels' in feature view creation, it will therefore return 'None' for Y\n",
-    "X_train, X_val, X_test, _, _, _ = feature_view.train_validation_test_split(\n",
-    "    train_start=\"2022-01-01\",\n",
-    "    train_end=\"2023-06-30\",\n",
-    "    validation_start=\"2023-07-01\",\n",
-    "    validation_end=\"2023-09-30\",\n",
-    "    test_start=\"2023-10-01\",\n",
-    "    test_end=\"2023-12-31\",\n",
-    "    description='Electricity price prediction dataset',\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Sorting the training, validation, and test datasets based on the 'timestamp' column\n",
-    "X_train.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_val.sort_values([\"timestamp\"], inplace=True)\n",
-    "X_test.sort_values([\"timestamp\"], inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Extracting the target variable 'dk1_spotpricedkk_kwh' and defineing 'y_train', 'y_val' and 'y_test' \n",
-    "y_train = X_train[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_val = X_val[[\"dk1_spotpricedkk_kwh\"]]\n",
-    "y_test = X_test[[\"dk1_spotpricedkk_kwh\"]]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Dropping the 'date', 'time' and 'timestamp' columns from the training, validation, and test datasets\n",
-    "X_train.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "X_val.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)\n",
-    "X_test.drop([\"date\", \"time\", \"timestamp\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Dropping the 'dare', 'time' and 'timestamp' and dependent variable (y) columns from the training, validation, and test datasets\n",
-    "X_train.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "X_val.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)\n",
-    "X_test.drop([\"dk1_spotpricedkk_kwh\"], axis=1, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "      <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_solar_forecastintraday_kwh</th>\n",
-       "      <th>type</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.945277</td>\n",
-       "      <td>0.481878</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>0.435268</td>\n",
-       "      <td>0.986667</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.011364</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.68</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.315152</td>\n",
-       "      <td>0.272633</td>\n",
-       "      <td>0.934795</td>\n",
-       "      <td>0.446702</td>\n",
-       "      <td>0.000008</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.773045</td>\n",
-       "      <td>0.264375</td>\n",
-       "      <td>0.000018</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>0.426339</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.195960</td>\n",
-       "      <td>0.187305</td>\n",
-       "      <td>0.913059</td>\n",
-       "      <td>0.358547</td>\n",
-       "      <td>0.000012</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>0.417411</td>\n",
-       "      <td>0.933333</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.000000</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.04</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.082828</td>\n",
-       "      <td>0.074922</td>\n",
-       "      <td>0.493641</td>\n",
-       "      <td>0.133456</td>\n",
-       "      <td>0.005406</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         temperature_2m  relative_humidity_2m  precipitation      rain  \\\n",
-       "5905751        0.435268              0.986667       0.011364  0.011364   \n",
-       "19398          0.435268              0.986667       0.011364  0.011364   \n",
-       "5919627        0.417411              0.933333       0.000000  0.000000   \n",
-       "4719247        0.426339              0.933333       0.000000  0.000000   \n",
-       "4743896        0.417411              0.933333       0.000000  0.000000   \n",
-       "\n",
-       "         snowfall  weather_code  cloud_cover  wind_speed_10m  wind_gusts_10m  \\\n",
-       "5905751       0.0          0.68          1.0        0.315152        0.272633   \n",
-       "19398         0.0          0.68          1.0        0.315152        0.272633   \n",
-       "5919627       0.0          0.04          1.0        0.082828        0.074922   \n",
-       "4719247       0.0          0.04          1.0        0.195960        0.187305   \n",
-       "4743896       0.0          0.04          1.0        0.082828        0.074922   \n",
-       "\n",
-       "         dk1_offshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                                0.945277   \n",
-       "19398                                  0.934795   \n",
-       "5919627                                0.773045   \n",
-       "4719247                                0.913059   \n",
-       "4743896                                0.493641   \n",
-       "\n",
-       "         dk1_onshore_wind_forecastintraday_kwh  \\\n",
-       "5905751                               0.481878   \n",
-       "19398                                 0.446702   \n",
-       "5919627                               0.264375   \n",
-       "4719247                               0.358547   \n",
-       "4743896                               0.133456   \n",
-       "\n",
-       "         dk1_solar_forecastintraday_kwh  type  \n",
-       "5905751                        0.000000     1  \n",
-       "19398                          0.000008     1  \n",
-       "5919627                        0.000018     1  \n",
-       "4719247                        0.000012     1  \n",
-       "4743896                        0.005406     1  "
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Displaying the first 5 rows of the train dataset (X_train)\n",
-    "X_train.head()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>dk1_spotpricedkk_kwh</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>5905751</th>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19398</th>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5919627</th>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4719247</th>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4743896</th>\n",
-       "      <td>0.179988</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         dk1_spotpricedkk_kwh\n",
-       "5905751              0.179988\n",
-       "19398                0.179988\n",
-       "5919627              0.179988\n",
-       "4719247              0.179988\n",
-       "4743896              0.179988"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "\n",
-    "# Displaying the first 5 rows of the train dataset (y_train)\n",
-    "y_train.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🗃 Window timeseries dataset </span>"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style=\"color:#2656a3;\">🧬 Modeling</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 43,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from keras.preprocessing.sequence import TimeseriesGenerator\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# define generator\n",
-    "n_input = 12\n",
-    "n_features = 13\n",
-    "generator = TimeseriesGenerator(X_train, X_train, length=n_input, batch_size=32)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "ename": "",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31mThe kernel failed to start as 'TypeAliasType' could not be imported from 'c:\\Users\\Benj3\\anaconda3\\envs\\tensor\\Lib\\site-packages\\typing_extensions.py'.\n",
-      "\u001b[1;31mClick <a href='https://aka.ms/kernelFailuresModuleImportErrFromFile'>here</a> for more info."
-     ]
-    }
-   ],
-   "source": [
-    "X, y = generator[1]\n",
-    "print(f'Given the Array: \\n{X.flatten()}')\n",
-    "print(f'Predict this y: \\n {y}')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## <span style='color:#2656a3'>🗄 Model Registry</span>"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Exporting trained model to: electricity_price_model\n",
-      "INFO:tensorflow:Assets written to: electricity_price_model\\assets\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Exporting the trained model to a directory\n",
-    "model_dir = \"electricity_price_model\"\n",
-    "print('Exporting trained model to: {}'.format(model_dir))\n",
-    "\n",
-    "# Saving the model using TensorFlow's saved_model.save function\n",
-    "tf.saved_model.save(model, model_dir)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 44,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connected. Call `.close()` to terminate connection gracefully.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading: 100.000%|██████████| 59/59 elapsed<00:01 remaining<00:001<00:01,  3.38it/s]\n",
-      "Uploading: 100.000%|██████████| 397272/397272 elapsed<00:02 remaining<00:00  3.38it/s]\n",
-      "Uploading: 0.000%|          | 0/112411 elapsed<00:01 remaining<?0:04<00:01,  3.38it/s]\n",
-      "Uploading model files (2 dirs, 2 files):  17%|█▋        | 1/6 [00:07<00:35,  7.08s/it]\n"
-     ]
-    },
-    {
-     "ename": "RestAPIError",
-     "evalue": "Metadata operation error: (url: https://c.app.hopsworks.ai/hopsworks-api/api/project/556180/dataset/upload/%2FProjects%2Fbenjami3%2FModels%2FDK_electricity_price_prediction_model%2F1%5Cvariables). Server response: \nHTTP code: 400, HTTP reason: Invalid URI, body: b''",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[1;31mRestAPIError\u001b[0m                              Traceback (most recent call last)",
-      "Cell \u001b[1;32mIn[44], line 16\u001b[0m\n\u001b[0;32m      8\u001b[0m tf_model \u001b[38;5;241m=\u001b[39m mr\u001b[38;5;241m.\u001b[39mtensorflow\u001b[38;5;241m.\u001b[39mcreate_model(\n\u001b[0;32m      9\u001b[0m     name\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mDK_electricity_price_prediction_model\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     10\u001b[0m     metrics\u001b[38;5;241m=\u001b[39mmetrics,\n\u001b[0;32m     11\u001b[0m     description\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHourly electricity price prediction model.\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m     12\u001b[0m     input_example\u001b[38;5;241m=\u001b[39mn_step_window\u001b[38;5;241m.\u001b[39mexample[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mnumpy(),\n\u001b[0;32m     13\u001b[0m )\n\u001b[0;32m     15\u001b[0m \u001b[38;5;66;03m# Saving the model to the specified directory\u001b[39;00m\n\u001b[1;32m---> 16\u001b[0m \u001b[43mtf_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_dir\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\model.py:101\u001b[0m, in \u001b[0;36mModel.save\u001b[1;34m(self, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m     90\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21msave\u001b[39m(\u001b[38;5;28mself\u001b[39m, model_path, await_registration\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m480\u001b[39m, keep_original_files\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m     91\u001b[0m \u001b[38;5;250m    \u001b[39m\u001b[38;5;124;03m\"\"\"Persist this model including model files and metadata to the model registry.\u001b[39;00m\n\u001b[0;32m     92\u001b[0m \n\u001b[0;32m     93\u001b[0m \u001b[38;5;124;03m    # Arguments\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     99\u001b[0m \u001b[38;5;124;03m        `Model`: The model metadata object.\u001b[39;00m\n\u001b[0;32m    100\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> 101\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_model_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msave\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    102\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[0;32m    103\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    104\u001b[0m \u001b[43m        \u001b[49m\u001b[43mawait_registration\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mawait_registration\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    105\u001b[0m \u001b[43m        \u001b[49m\u001b[43mkeep_original_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_original_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    106\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:421\u001b[0m, in \u001b[0;36mModelEngine.save\u001b[1;34m(self, model_instance, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m    419\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m be:\n\u001b[0;32m    420\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_api\u001b[38;5;241m.\u001b[39mrm(model_instance\u001b[38;5;241m.\u001b[39mversion_path)\n\u001b[1;32m--> 421\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m be\n\u001b[0;32m    423\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel created, explore it at \u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;241m+\u001b[39m model_instance\u001b[38;5;241m.\u001b[39mget_url())\n\u001b[0;32m    425\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m model_instance\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:385\u001b[0m, in \u001b[0;36mModelEngine.save\u001b[1;34m(self, model_instance, model_path, await_registration, keep_original_files)\u001b[0m\n\u001b[0;32m    381\u001b[0m \u001b[38;5;66;03m# check local relative\u001b[39;00m\n\u001b[0;32m    382\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mexists(\n\u001b[0;32m    383\u001b[0m     os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(os\u001b[38;5;241m.\u001b[39mgetcwd(), model_path)\n\u001b[0;32m    384\u001b[0m ):  \u001b[38;5;66;03m# check local relative\u001b[39;00m\n\u001b[1;32m--> 385\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_save_model_from_local_or_hopsfs_mount\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    386\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_instance\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_instance\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    387\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m(\u001b[49m\u001b[43mos\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgetcwd\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmodel_path\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    388\u001b[0m \u001b[43m        \u001b[49m\u001b[43mkeep_original_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_original_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    389\u001b[0m \u001b[43m        \u001b[49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    391\u001b[0m \u001b[38;5;66;03m# check project relative\u001b[39;00m\n\u001b[0;32m    392\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_dataset_api\u001b[38;5;241m.\u001b[39mpath_exists(\n\u001b[0;32m    393\u001b[0m     model_path\n\u001b[0;32m    394\u001b[0m ):  \u001b[38;5;66;03m# check hdfs relative and absolute\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:249\u001b[0m, in \u001b[0;36mModelEngine._save_model_from_local_or_hopsfs_mount\u001b[1;34m(self, model_instance, model_path, keep_original_files, update_upload_progress)\u001b[0m\n\u001b[0;32m    240\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_copy_or_move_hopsfs_model(\n\u001b[0;32m    241\u001b[0m         from_hdfs_model_path\u001b[38;5;241m=\u001b[39mmodel_path\u001b[38;5;241m.\u001b[39mreplace(\n\u001b[0;32m    242\u001b[0m             constants\u001b[38;5;241m.\u001b[39mMODEL_REGISTRY\u001b[38;5;241m.\u001b[39mHOPSFS_MOUNT_PREFIX, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    246\u001b[0m         update_upload_progress\u001b[38;5;241m=\u001b[39mupdate_upload_progress,\n\u001b[0;32m    247\u001b[0m     )\n\u001b[0;32m    248\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 249\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_upload_local_model\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    250\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfrom_local_model_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    251\u001b[0m \u001b[43m        \u001b[49m\u001b[43mto_model_version_path\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmodel_instance\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mversion_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    252\u001b[0m \u001b[43m        \u001b[49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mupdate_upload_progress\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    253\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\model_engine.py:225\u001b[0m, in \u001b[0;36mModelEngine._upload_local_model\u001b[1;34m(self, from_local_model_path, to_model_version_path, update_upload_progress)\u001b[0m\n\u001b[0;32m    223\u001b[0m     update_upload_progress(n_dirs, n_files)\n\u001b[0;32m    224\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m f_name \u001b[38;5;129;01min\u001b[39;00m files:\n\u001b[1;32m--> 225\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mroot\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43mf_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mremote_base_path\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    226\u001b[0m     n_files \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m1\u001b[39m\n\u001b[0;32m    227\u001b[0m     update_upload_progress(n_dirs, n_files)\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\engine\\local_engine.py:38\u001b[0m, in \u001b[0;36mLocalEngine.upload\u001b[1;34m(self, local_path, remote_path)\u001b[0m\n\u001b[0;32m     36\u001b[0m local_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_abs_path(local_path)\n\u001b[0;32m     37\u001b[0m remote_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_prepend_project_path(remote_path)\n\u001b[1;32m---> 38\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dataset_api\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupload\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlocal_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mremote_path\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:152\u001b[0m, in \u001b[0;36mDatasetApi.upload\u001b[1;34m(self, local_path, upload_path, overwrite, chunk_size, simultaneous_uploads, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    150\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    151\u001b[0m                 pbar\u001b[38;5;241m.\u001b[39mclose()\n\u001b[1;32m--> 152\u001b[0m             \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[0;32m    154\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    155\u001b[0m     pbar\u001b[38;5;241m.\u001b[39mclose()\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:148\u001b[0m, in \u001b[0;36mDatasetApi.upload\u001b[1;34m(self, local_path, upload_path, overwrite, chunk_size, simultaneous_uploads, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    146\u001b[0m _, _ \u001b[38;5;241m=\u001b[39m wait(futures)\n\u001b[0;32m    147\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 148\u001b[0m     _ \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfuture\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mfutures\u001b[49m\u001b[43m]\u001b[49m\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    150\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:148\u001b[0m, in \u001b[0;36m<listcomp>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m    146\u001b[0m _, _ \u001b[38;5;241m=\u001b[39m wait(futures)\n\u001b[0;32m    147\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 148\u001b[0m     _ \u001b[38;5;241m=\u001b[39m [\u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m future \u001b[38;5;129;01min\u001b[39;00m futures]\n\u001b[0;32m    149\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m    150\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m pbar \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\_base.py:449\u001b[0m, in \u001b[0;36mFuture.result\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m    447\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m CancelledError()\n\u001b[0;32m    448\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;241m==\u001b[39m FINISHED:\n\u001b[1;32m--> 449\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m__get_result\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    451\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_condition\u001b[38;5;241m.\u001b[39mwait(timeout)\n\u001b[0;32m    453\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;129;01min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\_base.py:401\u001b[0m, in \u001b[0;36mFuture.__get_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    399\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception:\n\u001b[0;32m    400\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 401\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception\n\u001b[0;32m    402\u001b[0m     \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[0;32m    403\u001b[0m         \u001b[38;5;66;03m# Break a reference cycle with the exception in self._exception\u001b[39;00m\n\u001b[0;32m    404\u001b[0m         \u001b[38;5;28mself\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\concurrent\\futures\\thread.py:58\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     55\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m\n\u001b[0;32m     57\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m---> 58\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     59\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mBaseException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m exc:\n\u001b[0;32m     60\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfuture\u001b[38;5;241m.\u001b[39mset_exception(exc)\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:189\u001b[0m, in \u001b[0;36mDatasetApi._upload_chunk\u001b[1;34m(self, base_params, upload_path, file_name, chunk, pbar, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    184\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[0;32m    185\u001b[0m     re\u001b[38;5;241m.\u001b[39mresponse\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;129;01min\u001b[39;00m DatasetApi\u001b[38;5;241m.\u001b[39mFLOW_PERMANENT_ERRORS\n\u001b[0;32m    186\u001b[0m     \u001b[38;5;129;01mor\u001b[39;00m chunk\u001b[38;5;241m.\u001b[39mretries \u001b[38;5;241m>\u001b[39m max_chunk_retries\n\u001b[0;32m    187\u001b[0m ):\n\u001b[0;32m    188\u001b[0m     chunk\u001b[38;5;241m.\u001b[39mstatus \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfailed\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m--> 189\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m re\n\u001b[0;32m    190\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(chunk_retry_interval)\n\u001b[0;32m    191\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:178\u001b[0m, in \u001b[0;36mDatasetApi._upload_chunk\u001b[1;34m(self, base_params, upload_path, file_name, chunk, pbar, max_chunk_retries, chunk_retry_interval)\u001b[0m\n\u001b[0;32m    176\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[0;32m    177\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 178\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_upload_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    179\u001b[0m \u001b[43m            \u001b[49m\u001b[43mquery_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mupload_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfile_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcontent\u001b[49m\n\u001b[0;32m    180\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    181\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[0;32m    182\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m RestAPIError \u001b[38;5;28;01mas\u001b[39;00m re:\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\core\\dataset_api.py:214\u001b[0m, in \u001b[0;36mDatasetApi._upload_request\u001b[1;34m(self, params, path, file_name, chunk)\u001b[0m\n\u001b[0;32m    211\u001b[0m path_params \u001b[38;5;241m=\u001b[39m [\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mproject\u001b[39m\u001b[38;5;124m\"\u001b[39m, _client\u001b[38;5;241m.\u001b[39m_project_id, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdataset\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mupload\u001b[39m\u001b[38;5;124m\"\u001b[39m, path]\n\u001b[0;32m    213\u001b[0m \u001b[38;5;66;03m# Flow configuration params are sent as form data\u001b[39;00m\n\u001b[1;32m--> 214\u001b[0m \u001b[43m_client\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_send_request\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    215\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mPOST\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mpath_params\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfiles\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mfile\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mchunk\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\n\u001b[0;32m    216\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\decorators.py:35\u001b[0m, in \u001b[0;36mconnected.<locals>.if_connected\u001b[1;34m(inst, *args, **kwargs)\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m inst\u001b[38;5;241m.\u001b[39m_connected:\n\u001b[0;32m     34\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m NoHopsworksConnectionError\n\u001b[1;32m---> 35\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[43minst\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[1;32mc:\\Users\\Benj3\\anaconda3\\envs\\energy\\Lib\\site-packages\\hsml\\client\\base.py:108\u001b[0m, in \u001b[0;36mClient._send_request\u001b[1;34m(self, method, path_params, query_params, headers, data, stream, files)\u001b[0m\n\u001b[0;32m    105\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_session\u001b[38;5;241m.\u001b[39msend(prepped, verify\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_verify, stream\u001b[38;5;241m=\u001b[39mstream)\n\u001b[0;32m    107\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m/\u001b[39m\u001b[38;5;241m/\u001b[39m \u001b[38;5;241m100\u001b[39m \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m2\u001b[39m:\n\u001b[1;32m--> 108\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m exceptions\u001b[38;5;241m.\u001b[39mRestAPIError(url, response)\n\u001b[0;32m    110\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m stream:\n\u001b[0;32m    111\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
-      "\u001b[1;31mRestAPIError\u001b[0m: Metadata operation error: (url: https://c.app.hopsworks.ai/hopsworks-api/api/project/556180/dataset/upload/%2FProjects%2Fbenjami3%2FModels%2FDK_electricity_price_prediction_model%2F1%5Cvariables). Server response: \nHTTP code: 400, HTTP reason: Invalid URI, body: b''"
-     ]
-    }
-   ],
-   "source": [
-    "# Retrieving the Model Registry\n",
-    "mr = project.get_model_registry()\n",
-    "\n",
-    "# Extracting loss value from the training history\n",
-    "metrics = {'loss': history_dict['val_loss'][0]} \n",
-    "\n",
-    "# Creating a TensorFlow model in the Model Registry\n",
-    "tf_model = mr.tensorflow.create_model(\n",
-    "    name=\"DK_electricity_price_prediction_model\",\n",
-    "    metrics=metrics,\n",
-    "    description=\"Hourly electricity price prediction model.\",\n",
-    "    input_example=n_step_window.example[0].numpy(),\n",
-    ")\n",
-    "\n",
-    "# Saving the model to the specified directory\n",
-    "tf_model.save(model_dir)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "\n",
-    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 04: Batch Inference </span>\n",
-    "\n",
-    "In the next notebook you will use your registered model to predict batch data."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "bds-mlops",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.9"
-  },
-  "orig_nbformat": 4
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

notebooks/1_feature_backfill.ipynb

@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,15 +38,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "c:\\Users\\Benj3\\OneDrive\\Dokumenter\\VSCode\\MLOPs-Assignment-\n",
-      "c:\\Users\\Benj3\\OneDrive\\Dokumenter\\VSCode\\MLOPs-Assignment-\\notebooks\n"
+      "/Users/tobiasmjensen/Documents/aau_bds/m5_data-engineering-and-mlops/exam_assigment/MLOPs-Assignment-\n",
+      "/Users/tobiasmjensen/Documents/aau_bds/m5_data-engineering-and-mlops/exam_assigment/MLOPs-Assignment-/notebooks\n"
      ]
     }
    ],
@@ -64,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -80,6 +80,18 @@
     "warnings.filterwarnings('ignore', category=DeprecationWarning)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# <span style=\"color:#2656a3;\"> 🤖 Transformation Functions</span>\n",
+    "\n",
+    "We preprocess our data using *min-max scaling* on the numerical features and *label encoding* on the one categorical feature we have.\n",
+    "To achieve this, we create a mapping between our features and transformation functions. This ensures that transformation functions like min-max scaling are applied exclusively on the training data, preventing any data leakage into the validation or test sets.\n",
+    "\n",
+    "To achieve this, we create a mapping between our features and transformation functions - ved ikke om man kan sige det her?"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -91,7 +103,6 @@
     "- Electricity prices in Denmark on hourly basis per day from [Energinet](https://www.energidataservice.dk). Loacated in the *featuresfolder* under electricity_prices.\n",
     "- Different meteorological observations based on Aalborg Denmark from [Open Meteo](https://www.open-meteo.com). Loacated in the *featuresfolder* under weather_measures.\n",
     "- Danish calendar that categorizes dates into types based on whether it is a weekday or not. This files is made manually by the group and is located in the *datafolder* inside this repository.\n",
-    "- Forecast Renewable Energy next day from [Energinet](https://www.energidataservice.dk). Loacated in the *featuresfolder* under electricity_prices.\n",
     "- Weather Forecast based on Aalborg Denmark from [Open Meteo](https://www.open-meteo.com). Loacated in the *featuresfolder* under weather_measures. (This data is used later to parse in new real-time weather data)\n"
    ]
   },
@@ -105,7 +116,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -122,7 +133,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -207,7 +218,7 @@
        "4  1641009600000 2022-01-01 04:00:00  2022-01-01     4               0.28013"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -219,7 +230,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -252,44 +263,44 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>20440</th>\n",
-       "      <td>1714590000000</td>\n",
-       "      <td>2024-05-01 19:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
+       "      <th>20464</th>\n",
+       "      <td>1714676400000</td>\n",
+       "      <td>2024-05-02 19:00:00</td>\n",
+       "      <td>2024-05-02</td>\n",
        "      <td>19</td>\n",
-       "      <td>0.37590</td>\n",
+       "      <td>0.31266</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20441</th>\n",
-       "      <td>1714593600000</td>\n",
-       "      <td>2024-05-01 20:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
+       "      <th>20465</th>\n",
+       "      <td>1714680000000</td>\n",
+       "      <td>2024-05-02 20:00:00</td>\n",
+       "      <td>2024-05-02</td>\n",
        "      <td>20</td>\n",
-       "      <td>0.37292</td>\n",
+       "      <td>0.31318</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20442</th>\n",
-       "      <td>1714597200000</td>\n",
-       "      <td>2024-05-01 21:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
+       "      <th>20466</th>\n",
+       "      <td>1714683600000</td>\n",
+       "      <td>2024-05-02 21:00:00</td>\n",
+       "      <td>2024-05-02</td>\n",
        "      <td>21</td>\n",
-       "      <td>0.25366</td>\n",
+       "      <td>0.31266</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20443</th>\n",
-       "      <td>1714600800000</td>\n",
-       "      <td>2024-05-01 22:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
+       "      <th>20467</th>\n",
+       "      <td>1714687200000</td>\n",
+       "      <td>2024-05-02 22:00:00</td>\n",
+       "      <td>2024-05-02</td>\n",
        "      <td>22</td>\n",
-       "      <td>0.22315</td>\n",
+       "      <td>0.28245</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20444</th>\n",
-       "      <td>1714604400000</td>\n",
-       "      <td>2024-05-01 23:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
+       "      <th>20468</th>\n",
+       "      <td>1714690800000</td>\n",
+       "      <td>2024-05-02 23:00:00</td>\n",
+       "      <td>2024-05-02</td>\n",
        "      <td>23</td>\n",
-       "      <td>0.16408</td>\n",
+       "      <td>0.25306</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -297,21 +308,21 @@
       ],
       "text/plain": [
        "           timestamp            datetime        date  hour  \\\n",
-       "20440  1714590000000 2024-05-01 19:00:00  2024-05-01    19   \n",
-       "20441  1714593600000 2024-05-01 20:00:00  2024-05-01    20   \n",
-       "20442  1714597200000 2024-05-01 21:00:00  2024-05-01    21   \n",
-       "20443  1714600800000 2024-05-01 22:00:00  2024-05-01    22   \n",
-       "20444  1714604400000 2024-05-01 23:00:00  2024-05-01    23   \n",
+       "20464  1714676400000 2024-05-02 19:00:00  2024-05-02    19   \n",
+       "20465  1714680000000 2024-05-02 20:00:00  2024-05-02    20   \n",
+       "20466  1714683600000 2024-05-02 21:00:00  2024-05-02    21   \n",
+       "20467  1714687200000 2024-05-02 22:00:00  2024-05-02    22   \n",
+       "20468  1714690800000 2024-05-02 23:00:00  2024-05-02    23   \n",
        "\n",
        "       dk1_spotpricedkk_kwh  \n",
-       "20440               0.37590  \n",
-       "20441               0.37292  \n",
-       "20442               0.25366  \n",
-       "20443               0.22315  \n",
-       "20444               0.16408  "
+       "20464               0.31266  \n",
+       "20465               0.31318  \n",
+       "20466               0.31266  \n",
+       "20467               0.28245  \n",
+       "20468               0.25306  "
       ]
      },
-     "execution_count": 43,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -323,7 +334,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -331,17 +342,17 @@
      "output_type": "stream",
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 20445 entries, 0 to 20444\n",
+      "RangeIndex: 20469 entries, 0 to 20468\n",
       "Data columns (total 5 columns):\n",
       " #   Column                Non-Null Count  Dtype         \n",
       "---  ------                --------------  -----         \n",
-      " 0   timestamp             20445 non-null  int64         \n",
-      " 1   datetime              20445 non-null  datetime64[ns]\n",
-      " 2   date                  20445 non-null  object        \n",
-      " 3   hour                  20445 non-null  int32         \n",
-      " 4   dk1_spotpricedkk_kwh  20445 non-null  float64       \n",
-      "dtypes: datetime64[ns](1), float64(1), int32(1), int64(1), object(1)\n",
-      "memory usage: 718.9+ KB\n"
+      " 0   timestamp             20469 non-null  int64         \n",
+      " 1   datetime              20469 non-null  datetime64[ns]\n",
+      " 2   date                  20469 non-null  object        \n",
+      " 3   hour                  20469 non-null  int64         \n",
+      " 4   dk1_spotpricedkk_kwh  20469 non-null  float64       \n",
+      "dtypes: datetime64[ns](1), float64(1), int64(2), object(1)\n",
+      "memory usage: 799.7+ KB\n"
      ]
     }
    ],
@@ -350,308 +361,6 @@
     "electricity_df.info()"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\">☀️💨 Forecast Renewable Energy next day from Energinet\n",
-    "Second dataset is Forecast Renewable Energy next day also on hourly basis from Energinet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Fetching historical forecast of renewable energy data for area DK1 from January 1, 2022\n",
-    "# Note: The end date is currently left out to retrieve data up to the present date of yesterday \n",
-    "# Today is not included in the data as it is not historical data\n",
-    "forecast_renewable_energy_df = electricity_prices.forecast_renewable_energy(\n",
-    "    historical=True, \n",
-    "    area = [\"DK1\"],\n",
-    "    start= '2022-01-01', \n",
-    "    #end='2023-12-31'\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>timestamp</th>\n",
-       "      <th>datetime</th>\n",
-       "      <th>date</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_solar_forecastintraday_kwh</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1641024000000</td>\n",
-       "      <td>2022-01-01 08:00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>8</td>\n",
-       "      <td>611708.313</td>\n",
-       "      <td>236791.672</td>\n",
-       "      <td>49.583</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1641027600000</td>\n",
-       "      <td>2022-01-01 09:00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>9</td>\n",
-       "      <td>459708.344</td>\n",
-       "      <td>196666.672</td>\n",
-       "      <td>4841.250</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1641031200000</td>\n",
-       "      <td>2022-01-01 10:00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>10</td>\n",
-       "      <td>310375.000</td>\n",
-       "      <td>178500.000</td>\n",
-       "      <td>20352.501</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1641034800000</td>\n",
-       "      <td>2022-01-01 11:00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>11</td>\n",
-       "      <td>320750.000</td>\n",
-       "      <td>201125.000</td>\n",
-       "      <td>35718.750</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1641038400000</td>\n",
-       "      <td>2022-01-01 12:00:00</td>\n",
-       "      <td>2022-01-01</td>\n",
-       "      <td>12</td>\n",
-       "      <td>355666.656</td>\n",
-       "      <td>277666.656</td>\n",
-       "      <td>38026.669</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "       timestamp            datetime        date  hour  \\\n",
-       "0  1641024000000 2022-01-01 08:00:00  2022-01-01     8   \n",
-       "1  1641027600000 2022-01-01 09:00:00  2022-01-01     9   \n",
-       "2  1641031200000 2022-01-01 10:00:00  2022-01-01    10   \n",
-       "3  1641034800000 2022-01-01 11:00:00  2022-01-01    11   \n",
-       "4  1641038400000 2022-01-01 12:00:00  2022-01-01    12   \n",
-       "\n",
-       "   dk1_offshore_wind_forecastintraday_kwh  \\\n",
-       "0                              611708.313   \n",
-       "1                              459708.344   \n",
-       "2                              310375.000   \n",
-       "3                              320750.000   \n",
-       "4                              355666.656   \n",
-       "\n",
-       "   dk1_onshore_wind_forecastintraday_kwh  dk1_solar_forecastintraday_kwh  \n",
-       "0                             236791.672                          49.583  \n",
-       "1                             196666.672                        4841.250  \n",
-       "2                             178500.000                       20352.501  \n",
-       "3                             201125.000                       35718.750  \n",
-       "4                             277666.656                       38026.669  "
-      ]
-     },
-     "execution_count": 46,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the forecast_renewable_energy dataframe\n",
-    "forecast_renewable_energy_df.head(5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>timestamp</th>\n",
-       "      <th>datetime</th>\n",
-       "      <th>date</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
-       "      <th>dk1_solar_forecastintraday_kwh</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>14426</th>\n",
-       "      <td>1714590000000</td>\n",
-       "      <td>2024-05-01 19:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
-       "      <td>19</td>\n",
-       "      <td>816250.000</td>\n",
-       "      <td>1382208.374</td>\n",
-       "      <td>272910.828</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14427</th>\n",
-       "      <td>1714593600000</td>\n",
-       "      <td>2024-05-01 20:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
-       "      <td>20</td>\n",
-       "      <td>848500.000</td>\n",
-       "      <td>1388583.374</td>\n",
-       "      <td>46086.666</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14428</th>\n",
-       "      <td>1714597200000</td>\n",
-       "      <td>2024-05-01 21:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
-       "      <td>21</td>\n",
-       "      <td>886041.687</td>\n",
-       "      <td>1554791.626</td>\n",
-       "      <td>1338.750</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14429</th>\n",
-       "      <td>1714600800000</td>\n",
-       "      <td>2024-05-01 22:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
-       "      <td>22</td>\n",
-       "      <td>919416.687</td>\n",
-       "      <td>1698875.000</td>\n",
-       "      <td>0.000</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14430</th>\n",
-       "      <td>1714604400000</td>\n",
-       "      <td>2024-05-01 23:00:00</td>\n",
-       "      <td>2024-05-01</td>\n",
-       "      <td>23</td>\n",
-       "      <td>934708.313</td>\n",
-       "      <td>1739375.000</td>\n",
-       "      <td>0.000</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "           timestamp            datetime        date  hour  \\\n",
-       "14426  1714590000000 2024-05-01 19:00:00  2024-05-01    19   \n",
-       "14427  1714593600000 2024-05-01 20:00:00  2024-05-01    20   \n",
-       "14428  1714597200000 2024-05-01 21:00:00  2024-05-01    21   \n",
-       "14429  1714600800000 2024-05-01 22:00:00  2024-05-01    22   \n",
-       "14430  1714604400000 2024-05-01 23:00:00  2024-05-01    23   \n",
-       "\n",
-       "       dk1_offshore_wind_forecastintraday_kwh  \\\n",
-       "14426                              816250.000   \n",
-       "14427                              848500.000   \n",
-       "14428                              886041.687   \n",
-       "14429                              919416.687   \n",
-       "14430                              934708.313   \n",
-       "\n",
-       "       dk1_onshore_wind_forecastintraday_kwh  dk1_solar_forecastintraday_kwh  \n",
-       "14426                            1382208.374                      272910.828  \n",
-       "14427                            1388583.374                       46086.666  \n",
-       "14428                            1554791.626                        1338.750  \n",
-       "14429                            1698875.000                           0.000  \n",
-       "14430                            1739375.000                           0.000  "
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the last 5 rows of the forecast_renewable_energy dataframe\n",
-    "forecast_renewable_energy_df.tail(5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 14431 entries, 0 to 14430\n",
-      "Data columns (total 7 columns):\n",
-      " #   Column                                  Non-Null Count  Dtype         \n",
-      "---  ------                                  --------------  -----         \n",
-      " 0   timestamp                               14431 non-null  int64         \n",
-      " 1   datetime                                14431 non-null  datetime64[ns]\n",
-      " 2   date                                    14431 non-null  object        \n",
-      " 3   hour                                    14431 non-null  int32         \n",
-      " 4   dk1_offshore_wind_forecastintraday_kwh  14415 non-null  float64       \n",
-      " 5   dk1_onshore_wind_forecastintraday_kwh   14415 non-null  float64       \n",
-      " 6   dk1_solar_forecastintraday_kwh          14415 non-null  float64       \n",
-      "dtypes: datetime64[ns](1), float64(3), int32(1), int64(1), object(1)\n",
-      "memory usage: 733.0+ KB\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Showing the information for the forecast_renewable_energy dataframe\n",
-    "forecast_renewable_energy_df.info()"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -669,7 +378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -685,7 +394,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -832,7 +541,7 @@
        "4        100.0            10.6            23.8  "
       ]
      },
-     "execution_count": 50,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -844,7 +553,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -885,84 +594,84 @@
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>20419</th>\n",
-       "      <td>1714503600000</td>\n",
-       "      <td>2024-04-30 19:00:00</td>\n",
-       "      <td>2024-04-30</td>\n",
+       "      <th>20443</th>\n",
+       "      <td>1714590000000</td>\n",
+       "      <td>2024-05-01 19:00:00</td>\n",
+       "      <td>2024-05-01</td>\n",
        "      <td>19</td>\n",
-       "      <td>13.8</td>\n",
-       "      <td>64.0</td>\n",
+       "      <td>15.4</td>\n",
+       "      <td>71.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>6.0</td>\n",
-       "      <td>15.3</td>\n",
-       "      <td>26.3</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>14.8</td>\n",
+       "      <td>25.9</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20420</th>\n",
-       "      <td>1714507200000</td>\n",
-       "      <td>2024-04-30 20:00:00</td>\n",
-       "      <td>2024-04-30</td>\n",
+       "      <th>20444</th>\n",
+       "      <td>1714593600000</td>\n",
+       "      <td>2024-05-01 20:00:00</td>\n",
+       "      <td>2024-05-01</td>\n",
        "      <td>20</td>\n",
-       "      <td>13.5</td>\n",
-       "      <td>66.0</td>\n",
+       "      <td>14.7</td>\n",
+       "      <td>69.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>18.7</td>\n",
-       "      <td>32.8</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>19.2</td>\n",
+       "      <td>33.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20421</th>\n",
-       "      <td>1714510800000</td>\n",
-       "      <td>2024-04-30 21:00:00</td>\n",
-       "      <td>2024-04-30</td>\n",
+       "      <th>20445</th>\n",
+       "      <td>1714597200000</td>\n",
+       "      <td>2024-05-01 21:00:00</td>\n",
+       "      <td>2024-05-01</td>\n",
        "      <td>21</td>\n",
-       "      <td>13.4</td>\n",
+       "      <td>14.3</td>\n",
        "      <td>67.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>13.0</td>\n",
-       "      <td>21.1</td>\n",
-       "      <td>38.2</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>20.5</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20422</th>\n",
-       "      <td>1714514400000</td>\n",
-       "      <td>2024-04-30 22:00:00</td>\n",
-       "      <td>2024-04-30</td>\n",
+       "      <th>20446</th>\n",
+       "      <td>1714600800000</td>\n",
+       "      <td>2024-05-01 22:00:00</td>\n",
+       "      <td>2024-05-01</td>\n",
        "      <td>22</td>\n",
-       "      <td>12.8</td>\n",
-       "      <td>67.0</td>\n",
+       "      <td>13.4</td>\n",
+       "      <td>68.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>9.0</td>\n",
-       "      <td>21.0</td>\n",
-       "      <td>38.5</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>20.2</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>20423</th>\n",
-       "      <td>1714518000000</td>\n",
-       "      <td>2024-04-30 23:00:00</td>\n",
-       "      <td>2024-04-30</td>\n",
+       "      <th>20447</th>\n",
+       "      <td>1714604400000</td>\n",
+       "      <td>2024-05-01 23:00:00</td>\n",
+       "      <td>2024-05-01</td>\n",
        "      <td>23</td>\n",
-       "      <td>12.0</td>\n",
+       "      <td>12.4</td>\n",
        "      <td>70.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>18.0</td>\n",
-       "      <td>20.7</td>\n",
-       "      <td>38.5</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>18.8</td>\n",
+       "      <td>36.4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -970,28 +679,28 @@
       ],
       "text/plain": [
        "           timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "20419  1714503600000 2024-04-30 19:00:00  2024-04-30    19            13.8   \n",
-       "20420  1714507200000 2024-04-30 20:00:00  2024-04-30    20            13.5   \n",
-       "20421  1714510800000 2024-04-30 21:00:00  2024-04-30    21            13.4   \n",
-       "20422  1714514400000 2024-04-30 22:00:00  2024-04-30    22            12.8   \n",
-       "20423  1714518000000 2024-04-30 23:00:00  2024-04-30    23            12.0   \n",
+       "20443  1714590000000 2024-05-01 19:00:00  2024-05-01    19            15.4   \n",
+       "20444  1714593600000 2024-05-01 20:00:00  2024-05-01    20            14.7   \n",
+       "20445  1714597200000 2024-05-01 21:00:00  2024-05-01    21            14.3   \n",
+       "20446  1714600800000 2024-05-01 22:00:00  2024-05-01    22            13.4   \n",
+       "20447  1714604400000 2024-05-01 23:00:00  2024-05-01    23            12.4   \n",
        "\n",
        "       relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "20419                  64.0            0.0   0.0       0.0           0.0   \n",
-       "20420                  66.0            0.0   0.0       0.0           0.0   \n",
-       "20421                  67.0            0.0   0.0       0.0           0.0   \n",
-       "20422                  67.0            0.0   0.0       0.0           0.0   \n",
-       "20423                  70.0            0.0   0.0       0.0           0.0   \n",
+       "20443                  71.0            0.0   0.0       0.0           0.0   \n",
+       "20444                  69.0            0.0   0.0       0.0           0.0   \n",
+       "20445                  67.0            0.0   0.0       0.0           0.0   \n",
+       "20446                  68.0            0.0   0.0       0.0           0.0   \n",
+       "20447                  70.0            0.0   0.0       0.0           0.0   \n",
        "\n",
        "       cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "20419          6.0            15.3            26.3  \n",
-       "20420          2.0            18.7            32.8  \n",
-       "20421         13.0            21.1            38.2  \n",
-       "20422          9.0            21.0            38.5  \n",
-       "20423         18.0            20.7            38.5  "
+       "20443         13.0            14.8            25.9  \n",
+       "20444          7.0            19.2            33.8  \n",
+       "20445          2.0            20.5            37.4  \n",
+       "20446          7.0            20.2            37.4  \n",
+       "20447         17.0            18.8            36.4  "
       ]
      },
-     "execution_count": 51,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1003,7 +712,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -1011,25 +720,25 @@
      "output_type": "stream",
      "text": [
       "<class 'pandas.core.frame.DataFrame'>\n",
-      "Index: 20424 entries, 0 to 20423\n",
+      "Int64Index: 20448 entries, 0 to 20447\n",
       "Data columns (total 13 columns):\n",
       " #   Column                Non-Null Count  Dtype         \n",
       "---  ------                --------------  -----         \n",
-      " 0   timestamp             20424 non-null  int64         \n",
-      " 1   datetime              20424 non-null  datetime64[ns]\n",
-      " 2   date                  20424 non-null  object        \n",
-      " 3   hour                  20424 non-null  int32         \n",
-      " 4   temperature_2m        20424 non-null  float64       \n",
-      " 5   relative_humidity_2m  20424 non-null  float64       \n",
-      " 6   precipitation         20424 non-null  float64       \n",
-      " 7   rain                  20424 non-null  float64       \n",
-      " 8   snowfall              20424 non-null  float64       \n",
-      " 9   weather_code          20424 non-null  float64       \n",
-      " 10  cloud_cover           20424 non-null  float64       \n",
-      " 11  wind_speed_10m        20424 non-null  float64       \n",
-      " 12  wind_gusts_10m        20424 non-null  float64       \n",
-      "dtypes: datetime64[ns](1), float64(9), int32(1), int64(1), object(1)\n",
-      "memory usage: 2.1+ MB\n"
+      " 0   timestamp             20448 non-null  int64         \n",
+      " 1   datetime              20448 non-null  datetime64[ns]\n",
+      " 2   date                  20448 non-null  object        \n",
+      " 3   hour                  20448 non-null  int64         \n",
+      " 4   temperature_2m        20448 non-null  float64       \n",
+      " 5   relative_humidity_2m  20448 non-null  float64       \n",
+      " 6   precipitation         20448 non-null  float64       \n",
+      " 7   rain                  20448 non-null  float64       \n",
+      " 8   snowfall              20448 non-null  float64       \n",
+      " 9   weather_code          20448 non-null  float64       \n",
+      " 10  cloud_cover           20448 non-null  float64       \n",
+      " 11  wind_speed_10m        20448 non-null  float64       \n",
+      " 12  wind_gusts_10m        20448 non-null  float64       \n",
+      "dtypes: datetime64[ns](1), float64(9), int64(2), object(1)\n",
+      "memory usage: 2.2+ MB\n"
      ]
     }
    ],
@@ -1042,13 +751,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### <span style=\"color:#2656a3;\"> 🌈 Weather Forecast\n",
+    "#### <span style=\"color:#2656a3;\"> 🌈  Forecast Weather Measures\n",
     "Weather Forecast from Open Meteo is now being fetched. This data is used in part 02 the feature_pipeline to parse in new real-time weather data."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1060,7 +769,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -1102,83 +811,83 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1714608000000</td>\n",
-       "      <td>2024-05-02 00:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714694400000</td>\n",
+       "      <td>2024-05-03 00:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>0</td>\n",
-       "      <td>14.9</td>\n",
-       "      <td>66.0</td>\n",
-       "      <td>0.0</td>\n",
+       "      <td>14.3</td>\n",
+       "      <td>65.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>13.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>41.4</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>20.5</td>\n",
+       "      <td>36.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>1714611600000</td>\n",
-       "      <td>2024-05-02 01:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714698000000</td>\n",
+       "      <td>2024-05-03 01:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>1</td>\n",
-       "      <td>14.2</td>\n",
-       "      <td>71.0</td>\n",
+       "      <td>13.6</td>\n",
+       "      <td>69.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>20.5</td>\n",
-       "      <td>37.1</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>21.6</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>1714615200000</td>\n",
-       "      <td>2024-05-02 02:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714701600000</td>\n",
+       "      <td>2024-05-03 02:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>2</td>\n",
-       "      <td>13.4</td>\n",
-       "      <td>73.0</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>72.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>70.0</td>\n",
-       "      <td>21.2</td>\n",
-       "      <td>36.7</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>20.9</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>1714618800000</td>\n",
-       "      <td>2024-05-02 03:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714705200000</td>\n",
+       "      <td>2024-05-03 03:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>3</td>\n",
-       "      <td>13.2</td>\n",
-       "      <td>72.0</td>\n",
-       "      <td>0.1</td>\n",
-       "      <td>0.1</td>\n",
+       "      <td>12.7</td>\n",
+       "      <td>73.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>22.3</td>\n",
-       "      <td>39.2</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>19.8</td>\n",
+       "      <td>34.6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>1714622400000</td>\n",
-       "      <td>2024-05-02 04:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714708800000</td>\n",
+       "      <td>2024-05-03 04:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>4</td>\n",
-       "      <td>12.7</td>\n",
+       "      <td>12.4</td>\n",
        "      <td>73.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>2.0</td>\n",
-       "      <td>78.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>38.9</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>18.7</td>\n",
+       "      <td>33.8</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1186,28 +895,28 @@
       ],
       "text/plain": [
        "       timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "0  1714608000000 2024-05-02 00:00:00  2024-05-02     0            14.9   \n",
-       "1  1714611600000 2024-05-02 01:00:00  2024-05-02     1            14.2   \n",
-       "2  1714615200000 2024-05-02 02:00:00  2024-05-02     2            13.4   \n",
-       "3  1714618800000 2024-05-02 03:00:00  2024-05-02     3            13.2   \n",
-       "4  1714622400000 2024-05-02 04:00:00  2024-05-02     4            12.7   \n",
+       "0  1714694400000 2024-05-03 00:00:00  2024-05-03     0            14.3   \n",
+       "1  1714698000000 2024-05-03 01:00:00  2024-05-03     1            13.6   \n",
+       "2  1714701600000 2024-05-03 02:00:00  2024-05-03     2            13.0   \n",
+       "3  1714705200000 2024-05-03 03:00:00  2024-05-03     3            12.7   \n",
+       "4  1714708800000 2024-05-03 04:00:00  2024-05-03     4            12.4   \n",
        "\n",
        "   relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "0                  66.0            0.0   0.0       0.0           0.0   \n",
-       "1                  71.0            0.0   0.0       0.0           0.0   \n",
-       "2                  73.0            0.0   0.0       0.0           2.0   \n",
-       "3                  72.0            0.1   0.1       0.0          51.0   \n",
+       "0                  65.0            0.0   0.0       0.0           1.0   \n",
+       "1                  69.0            0.0   0.0       0.0           0.0   \n",
+       "2                  72.0            0.0   0.0       0.0           0.0   \n",
+       "3                  73.0            0.0   0.0       0.0           1.0   \n",
        "4                  73.0            0.0   0.0       0.0           2.0   \n",
        "\n",
        "   cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "0         13.0            21.6            41.4  \n",
-       "1          4.0            20.5            37.1  \n",
-       "2         70.0            21.2            36.7  \n",
-       "3         51.0            22.3            39.2  \n",
-       "4         78.0            21.6            38.9  "
+       "0         25.0            20.5            36.0  \n",
+       "1         12.0            21.6            37.4  \n",
+       "2          7.0            20.9            37.4  \n",
+       "3         26.0            19.8            34.6  \n",
+       "4         54.0            18.7            33.8  "
       ]
      },
-     "execution_count": 54,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1219,7 +928,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -1261,83 +970,83 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>115</th>\n",
-       "      <td>1715022000000</td>\n",
-       "      <td>2024-05-06 19:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715108400000</td>\n",
+       "      <td>2024-05-07 19:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>19</td>\n",
-       "      <td>10.7</td>\n",
-       "      <td>91.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>41.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>16.6</td>\n",
-       "      <td>32.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>10.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>116</th>\n",
-       "      <td>1715025600000</td>\n",
-       "      <td>2024-05-06 20:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715112000000</td>\n",
+       "      <td>2024-05-07 20:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>20</td>\n",
-       "      <td>10.1</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
+       "      <td>10.7</td>\n",
+       "      <td>49.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>19.5</td>\n",
-       "      <td>37.1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.6</td>\n",
+       "      <td>8.3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>117</th>\n",
-       "      <td>1715029200000</td>\n",
-       "      <td>2024-05-06 21:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715115600000</td>\n",
+       "      <td>2024-05-07 21:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>21</td>\n",
-       "      <td>9.5</td>\n",
-       "      <td>88.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
+       "      <td>9.6</td>\n",
+       "      <td>56.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>42.1</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.2</td>\n",
+       "      <td>5.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>118</th>\n",
-       "      <td>1715032800000</td>\n",
-       "      <td>2024-05-06 22:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715119200000</td>\n",
+       "      <td>2024-05-07 22:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>22</td>\n",
-       "      <td>9.3</td>\n",
-       "      <td>86.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
+       "      <td>8.7</td>\n",
+       "      <td>58.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>22.0</td>\n",
-       "      <td>41.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.3</td>\n",
+       "      <td>5.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>119</th>\n",
-       "      <td>1715036400000</td>\n",
-       "      <td>2024-05-06 23:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715122800000</td>\n",
+       "      <td>2024-05-07 23:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>23</td>\n",
-       "      <td>9.1</td>\n",
-       "      <td>84.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
+       "      <td>7.9</td>\n",
+       "      <td>57.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.3</td>\n",
-       "      <td>40.3</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.8</td>\n",
+       "      <td>6.5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -1345,28 +1054,28 @@
       ],
       "text/plain": [
        "         timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "115  1715022000000 2024-05-06 19:00:00  2024-05-06    19            10.7   \n",
-       "116  1715025600000 2024-05-06 20:00:00  2024-05-06    20            10.1   \n",
-       "117  1715029200000 2024-05-06 21:00:00  2024-05-06    21             9.5   \n",
-       "118  1715032800000 2024-05-06 22:00:00  2024-05-06    22             9.3   \n",
-       "119  1715036400000 2024-05-06 23:00:00  2024-05-06    23             9.1   \n",
+       "115  1715108400000 2024-05-07 19:00:00  2024-05-07    19            12.0   \n",
+       "116  1715112000000 2024-05-07 20:00:00  2024-05-07    20            10.7   \n",
+       "117  1715115600000 2024-05-07 21:00:00  2024-05-07    21             9.6   \n",
+       "118  1715119200000 2024-05-07 22:00:00  2024-05-07    22             8.7   \n",
+       "119  1715122800000 2024-05-07 23:00:00  2024-05-07    23             7.9   \n",
        "\n",
        "     relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "115                  91.0            1.4   1.4       0.0          61.0   \n",
-       "116                  90.0            1.4   1.4       0.0          61.0   \n",
-       "117                  88.0            1.4   1.4       0.0          61.0   \n",
-       "118                  86.0            0.6   0.6       0.0           3.0   \n",
-       "119                  84.0            0.6   0.6       0.0           3.0   \n",
+       "115                  41.0            0.0   0.0       0.0           0.0   \n",
+       "116                  49.0            0.0   0.0       0.0           0.0   \n",
+       "117                  56.0            0.0   0.0       0.0           0.0   \n",
+       "118                  58.0            0.0   0.0       0.0           0.0   \n",
+       "119                  57.0            0.0   0.0       0.0           0.0   \n",
        "\n",
        "     cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "115        100.0            16.6            32.0  \n",
-       "116        100.0            19.5            37.1  \n",
-       "117        100.0            21.6            42.1  \n",
-       "118        100.0            22.0            41.0  \n",
-       "119        100.0            21.3            40.3  "
+       "115          0.0             4.2            10.8  \n",
+       "116          0.0             3.6             8.3  \n",
+       "117          0.0             3.2             5.4  \n",
+       "118          0.0             3.3             5.8  \n",
+       "119          0.0             3.8             6.5  "
       ]
      },
-     "execution_count": 55,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1378,7 +1087,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -1393,7 +1102,7 @@
       " 0   timestamp             120 non-null    int64         \n",
       " 1   datetime              120 non-null    datetime64[ns]\n",
       " 2   date                  120 non-null    object        \n",
-      " 3   hour                  120 non-null    int32         \n",
+      " 3   hour                  120 non-null    int64         \n",
       " 4   temperature_2m        120 non-null    float64       \n",
       " 5   relative_humidity_2m  120 non-null    float64       \n",
       " 6   precipitation         120 non-null    float64       \n",
@@ -1403,8 +1112,8 @@
       " 10  cloud_cover           120 non-null    float64       \n",
       " 11  wind_speed_10m        120 non-null    float64       \n",
       " 12  wind_gusts_10m        120 non-null    float64       \n",
-      "dtypes: datetime64[ns](1), float64(9), int32(1), int64(1), object(1)\n",
-      "memory usage: 11.8+ KB\n"
+      "dtypes: datetime64[ns](1), float64(9), int64(2), object(1)\n",
+      "memory usage: 12.3+ KB\n"
      ]
     }
    ],
@@ -1423,16 +1132,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 69,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
-    "calender_df = calendar.get_calendar()"
+    "calender_df = calendar.dk_calendar()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 66,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -1461,7 +1170,7 @@
        "      <th>day</th>\n",
        "      <th>month</th>\n",
        "      <th>year</th>\n",
-       "      <th>holiday</th>\n",
+       "      <th>workday</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -1472,7 +1181,7 @@
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>2022</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -1481,7 +1190,7 @@
        "      <td>2</td>\n",
        "      <td>1</td>\n",
        "      <td>2022</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
@@ -1490,7 +1199,7 @@
        "      <td>3</td>\n",
        "      <td>1</td>\n",
        "      <td>2022</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
@@ -1499,7 +1208,7 @@
        "      <td>4</td>\n",
        "      <td>1</td>\n",
        "      <td>2022</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
@@ -1508,22 +1217,22 @@
        "      <td>5</td>\n",
        "      <td>1</td>\n",
        "      <td>2022</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "         date  dayofweek  day  month  year  holiday\n",
-       "0  2022-01-01          5    1      1  2022        1\n",
-       "1  2022-01-02          6    2      1  2022        1\n",
-       "2  2022-01-03          0    3      1  2022        0\n",
-       "3  2022-01-04          1    4      1  2022        0\n",
-       "4  2022-01-05          2    5      1  2022        0"
+       "         date  dayofweek  day  month  year  workday\n",
+       "0  2022-01-01          5    1      1  2022        0\n",
+       "1  2022-01-02          6    2      1  2022        0\n",
+       "2  2022-01-03          0    3      1  2022        1\n",
+       "3  2022-01-04          1    4      1  2022        1\n",
+       "4  2022-01-05          2    5      1  2022        1"
       ]
      },
-     "execution_count": 66,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1535,7 +1244,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 70,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -1564,7 +1273,7 @@
        "      <th>day</th>\n",
        "      <th>month</th>\n",
        "      <th>year</th>\n",
-       "      <th>holiday</th>\n",
+       "      <th>workday</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
@@ -1575,7 +1284,7 @@
        "      <td>27</td>\n",
        "      <td>12</td>\n",
        "      <td>2024</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1092</th>\n",
@@ -1584,7 +1293,7 @@
        "      <td>28</td>\n",
        "      <td>12</td>\n",
        "      <td>2024</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1093</th>\n",
@@ -1593,7 +1302,7 @@
        "      <td>29</td>\n",
        "      <td>12</td>\n",
        "      <td>2024</td>\n",
-       "      <td>1</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1094</th>\n",
@@ -1602,7 +1311,7 @@
        "      <td>30</td>\n",
        "      <td>12</td>\n",
        "      <td>2024</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1095</th>\n",
@@ -1611,22 +1320,22 @@
        "      <td>31</td>\n",
        "      <td>12</td>\n",
        "      <td>2024</td>\n",
-       "      <td>0</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "            date  dayofweek  day  month  year  holiday\n",
-       "1091  2024-12-27          4   27     12  2024        0\n",
-       "1092  2024-12-28          5   28     12  2024        1\n",
-       "1093  2024-12-29          6   29     12  2024        1\n",
-       "1094  2024-12-30          0   30     12  2024        0\n",
-       "1095  2024-12-31          1   31     12  2024        0"
+       "            date  dayofweek  day  month  year  workday\n",
+       "1091  2024-12-27          4   27     12  2024        1\n",
+       "1092  2024-12-28          5   28     12  2024        0\n",
+       "1093  2024-12-29          6   29     12  2024        0\n",
+       "1094  2024-12-30          0   30     12  2024        1\n",
+       "1095  2024-12-31          1   31     12  2024        1"
       ]
      },
-     "execution_count": 70,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1638,7 +1347,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -1651,13 +1360,13 @@
       " #   Column     Non-Null Count  Dtype \n",
       "---  ------     --------------  ----- \n",
       " 0   date       1096 non-null   object\n",
-      " 1   dayofweek  1096 non-null   int32 \n",
-      " 2   day        1096 non-null   int32 \n",
-      " 3   month      1096 non-null   int32 \n",
-      " 4   year       1096 non-null   int32 \n",
-      " 5   holiday    1096 non-null   int32 \n",
-      "dtypes: int32(5), object(1)\n",
-      "memory usage: 30.1+ KB\n"
+      " 1   dayofweek  1096 non-null   int64 \n",
+      " 2   day        1096 non-null   int64 \n",
+      " 3   month      1096 non-null   int64 \n",
+      " 4   year       1096 non-null   int64 \n",
+      " 5   workday    1096 non-null   int64 \n",
+      "dtypes: int64(5), object(1)\n",
+      "memory usage: 51.5+ KB\n"
      ]
     }
    ],
@@ -1668,7 +1377,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -1681,13 +1390,13 @@
       " #   Column     Non-Null Count  Dtype \n",
       "---  ------     --------------  ----- \n",
       " 0   date       1096 non-null   object\n",
-      " 1   dayofweek  1096 non-null   int32 \n",
-      " 2   day        1096 non-null   int32 \n",
-      " 3   month      1096 non-null   int32 \n",
-      " 4   year       1096 non-null   int32 \n",
-      " 5   holiday    1096 non-null   int32 \n",
-      "dtypes: int32(5), object(1)\n",
-      "memory usage: 30.1+ KB\n"
+      " 1   dayofweek  1096 non-null   int64 \n",
+      " 2   day        1096 non-null   int64 \n",
+      " 3   month      1096 non-null   int64 \n",
+      " 4   year       1096 non-null   int64 \n",
+      " 5   workday    1096 non-null   int64 \n",
+      "dtypes: int64(5), object(1)\n",
+      "memory usage: 51.5+ KB\n"
      ]
     }
    ],
@@ -1707,17 +1416,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Connection closed.\n",
       "Connected. Call `.close()` to terminate connection gracefully.\n",
       "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/556180\n",
+      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/554133\n",
       "Connected. Call `.close()` to terminate connection gracefully.\n"
      ]
     }
@@ -1754,7 +1462,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1778,7 +1486,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -1786,15 +1494,22 @@
      "output_type": "stream",
      "text": [
       "Feature Group created successfully, explore it at \n",
-      "https://c.app.hopsworks.ai:443/p/556180/fs/552003/fg/775531\n"
+      "https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/778586\n"
      ]
     },
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading Dataframe: 100.00% |██████████| Rows 20445/20445 | Elapsed Time: 00:06 | Remaining Time: 00:00\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8d08f0f4717746c1b7c3b16c7490cf51",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Uploading Dataframe: 0.00% |          | Rows 0/20469 | Elapsed Time: 00:00 | Remaining Time: ?"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stdout",
@@ -1802,16 +1517,16 @@
      "text": [
       "Launching job: electricity_prices_1_offline_fg_materialization\n",
       "Job started successfully, you can follow the progress at \n",
-      "https://c.app.hopsworks.ai/p/556180/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
+      "https://c.app.hopsworks.ai/p/554133/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "(<hsfs.core.job.Job at 0x1ce32519310>, None)"
+       "(<hsfs.core.job.Job at 0x17f2dc950>, None)"
       ]
      },
-     "execution_count": 75,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1830,7 +1545,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1852,59 +1567,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We replicate the process for both the `forecast_renewable_energy_fg`, `weather_fg` and `danish_holidays_fg` by establishing feature groups and inserting the dataframes into their respective feature groups."
+    "We replicate the process for both the `weather_fg` and `danish_holidays_fg` by establishing feature groups and inserting the dataframes into their respective feature groups."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Creating the feature group for the electricity prices\n",
-    "# forecast_renewable_energy_fg = fs.get_or_create_feature_group(\n",
-    "#     name=\"forecast_renewable_energy\",\n",
-    "#     version=1,\n",
-    "#     description=\"Forecast on Renewable Energy on ForecastType from Energidata API\",\n",
-    "#     primary_key=[\"date\",\"timestamp\"], \n",
-    "#     online_enabled=True,\n",
-    "#     event_time=\"timestamp\",\n",
-    "# )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Inserting the electricity_df into the feature group named electricity_fg\n",
-    "# forecast_renewable_energy_fg.insert(forecast_renewable_energy_df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # List of descriptions for forecast_renewable_energy features\n",
-    "# forecast_renewable_energy_feature_descriptions = [\n",
-    "#     {\"name\": \"timestamp\", \"description\": \"Timestamp for the event_time\"},\n",
-    "#     {\"name\": \"date\", \"description\": \"Date of the forecast\"},\n",
-    "#     {\"name\": \"datetime\", \"description\": \"Date and time for the forecast\"},\n",
-    "#     {\"name\": \"hour\", \"description\": \"Hour of day\"},\n",
-    "#     {\"name\": \"dk1_offshore_wind_forecastintraday_kwh\", \"description\": \"The forecast for the coming day at 6am Danish time zone\"},\n",
-    "# ]\n",
-    "\n",
-    "# # Updating feature descriptions\n",
-    "# for desc in forecast_renewable_energy_feature_descriptions: \n",
-    "#     forecast_renewable_energy_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 77,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1921,7 +1589,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 78,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [
     {
@@ -1929,15 +1597,22 @@
      "output_type": "stream",
      "text": [
       "Feature Group created successfully, explore it at \n",
-      "https://c.app.hopsworks.ai:443/p/556180/fs/552003/fg/774518\n"
+      "https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/777575\n"
      ]
     },
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading Dataframe: 100.00% |██████████| Rows 20424/20424 | Elapsed Time: 00:08 | Remaining Time: 00:00\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5978d081e84c49999233b2b00aa46be7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Uploading Dataframe: 0.00% |          | Rows 0/20448 | Elapsed Time: 00:00 | Remaining Time: ?"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stdout",
@@ -1945,16 +1620,16 @@
      "text": [
       "Launching job: weather_measurements_1_offline_fg_materialization\n",
       "Job started successfully, you can follow the progress at \n",
-      "https://c.app.hopsworks.ai/p/556180/jobs/named/weather_measurements_1_offline_fg_materialization/executions\n"
+      "https://c.app.hopsworks.ai/p/554133/jobs/named/weather_measurements_1_offline_fg_materialization/executions\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "(<hsfs.core.job.Job at 0x1ce326d4a50>, None)"
+       "(<hsfs.core.job.Job at 0x308979690>, None)"
       ]
      },
-     "execution_count": 78,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1966,7 +1641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 79,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1994,7 +1669,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2010,7 +1685,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
@@ -2018,15 +1693,22 @@
      "output_type": "stream",
      "text": [
       "Feature Group created successfully, explore it at \n",
-      "https://c.app.hopsworks.ai:443/p/556180/fs/552003/fg/776524\n"
+      "https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/777576\n"
      ]
     },
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading Dataframe: 100.00% |██████████| Rows 1096/1096 | Elapsed Time: 00:06 | Remaining Time: 00:00\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "376ce1b46ca6473b830e6ad9af28276a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Uploading Dataframe: 0.00% |          | Rows 0/1096 | Elapsed Time: 00:00 | Remaining Time: ?"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stdout",
@@ -2034,16 +1716,16 @@
      "text": [
       "Launching job: dk_calendar_1_offline_fg_materialization\n",
       "Job started successfully, you can follow the progress at \n",
-      "https://c.app.hopsworks.ai/p/556180/jobs/named/dk_calendar_1_offline_fg_materialization/executions\n"
+      "https://c.app.hopsworks.ai/p/554133/jobs/named/dk_calendar_1_offline_fg_materialization/executions\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "(<hsfs.core.job.Job at 0x1ce326c2010>, None)"
+       "(<hsfs.core.job.Job at 0x3088ef590>, None)"
       ]
      },
-     "execution_count": 81,
+     "execution_count": 29,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -2055,7 +1737,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2064,7 +1746,7 @@
     "    {\"name\": \"date\", \"description\": \"Date in the calendar\"},\n",
     "    {\"name\": \"day\", \"description\": \"Day number of the week. Monday is 0 and Sunday is 6\"},\n",
     "    {\"name\": \"month\", \"description\": \"Month number of the year\"},\n",
-    "    {\"name\": \"holiday\", \"description\": \"Holiday or not holiday\"},\n",
+    "    {\"name\": \"workday\", \"description\": \"Workday or not a workday\"},\n",
     "]\n",
     "\n",
     "# Updating feature descriptions\n",

notebooks/2_feature_pipeline.ipynb

@@ -27,15 +27,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "c:\\Users\\Benj3\\OneDrive\\Dokumenter\\VSCode\\MLOPs-Assignment-\n",
-      "c:\\Users\\Benj3\\OneDrive\\Dokumenter\\VSCode\\MLOPs-Assignment-\\notebooks\n"
+      "/Users/tobiasmjensen/Documents/aau_bds/m5_data-engineering-and-mlops/exam_assigment/MLOPs-Assignment-\n",
+      "/Users/tobiasmjensen/Documents/aau_bds/m5_data-engineering-and-mlops/exam_assigment/MLOPs-Assignment-/notebooks\n"
      ]
     }
    ],
@@ -53,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -88,7 +88,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -135,195 +135,195 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1714608000000</td>\n",
-       "      <td>2024-05-02 00:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714694400000</td>\n",
+       "      <td>2024-05-03 00:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>0</td>\n",
-       "      <td>0.10859</td>\n",
+       "      <td>0.22214</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>1714611600000</td>\n",
-       "      <td>2024-05-02 01:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714698000000</td>\n",
+       "      <td>2024-05-03 01:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>1</td>\n",
-       "      <td>0.08160</td>\n",
+       "      <td>0.21893</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>1714615200000</td>\n",
-       "      <td>2024-05-02 02:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714701600000</td>\n",
+       "      <td>2024-05-03 02:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>2</td>\n",
-       "      <td>0.07458</td>\n",
+       "      <td>0.22348</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>1714618800000</td>\n",
-       "      <td>2024-05-02 03:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714705200000</td>\n",
+       "      <td>2024-05-03 03:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>3</td>\n",
-       "      <td>0.05818</td>\n",
+       "      <td>0.22385</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>1714622400000</td>\n",
-       "      <td>2024-05-02 04:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714708800000</td>\n",
+       "      <td>2024-05-03 04:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>4</td>\n",
-       "      <td>0.07928</td>\n",
+       "      <td>0.22706</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>5</th>\n",
-       "      <td>1714626000000</td>\n",
-       "      <td>2024-05-02 05:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714712400000</td>\n",
+       "      <td>2024-05-03 05:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>5</td>\n",
-       "      <td>0.22920</td>\n",
+       "      <td>0.23825</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>6</th>\n",
-       "      <td>1714629600000</td>\n",
-       "      <td>2024-05-02 06:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714716000000</td>\n",
+       "      <td>2024-05-03 06:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>6</td>\n",
-       "      <td>0.29699</td>\n",
+       "      <td>0.26167</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>7</th>\n",
-       "      <td>1714633200000</td>\n",
-       "      <td>2024-05-02 07:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714719600000</td>\n",
+       "      <td>2024-05-03 07:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>7</td>\n",
-       "      <td>0.38605</td>\n",
+       "      <td>0.32045</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>8</th>\n",
-       "      <td>1714636800000</td>\n",
-       "      <td>2024-05-02 08:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714723200000</td>\n",
+       "      <td>2024-05-03 08:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>8</td>\n",
-       "      <td>0.43729</td>\n",
+       "      <td>0.31881</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>9</th>\n",
-       "      <td>1714640400000</td>\n",
-       "      <td>2024-05-02 09:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714726800000</td>\n",
+       "      <td>2024-05-03 09:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>9</td>\n",
-       "      <td>0.23457</td>\n",
+       "      <td>0.28860</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>10</th>\n",
-       "      <td>1714644000000</td>\n",
-       "      <td>2024-05-02 10:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714730400000</td>\n",
+       "      <td>2024-05-03 10:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>10</td>\n",
-       "      <td>0.03804</td>\n",
+       "      <td>0.28413</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>11</th>\n",
-       "      <td>1714647600000</td>\n",
-       "      <td>2024-05-02 11:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714734000000</td>\n",
+       "      <td>2024-05-03 11:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>11</td>\n",
-       "      <td>-0.00060</td>\n",
+       "      <td>0.25339</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>12</th>\n",
-       "      <td>1714651200000</td>\n",
-       "      <td>2024-05-02 12:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714737600000</td>\n",
+       "      <td>2024-05-03 12:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>12</td>\n",
-       "      <td>-0.01290</td>\n",
+       "      <td>0.25324</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>13</th>\n",
-       "      <td>1714654800000</td>\n",
-       "      <td>2024-05-02 13:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714741200000</td>\n",
+       "      <td>2024-05-03 13:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>13</td>\n",
-       "      <td>-0.02014</td>\n",
+       "      <td>0.24325</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>14</th>\n",
-       "      <td>1714658400000</td>\n",
-       "      <td>2024-05-02 14:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714744800000</td>\n",
+       "      <td>2024-05-03 14:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>14</td>\n",
-       "      <td>-0.00037</td>\n",
+       "      <td>0.23698</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>15</th>\n",
-       "      <td>1714662000000</td>\n",
-       "      <td>2024-05-02 15:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714748400000</td>\n",
+       "      <td>2024-05-03 15:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>15</td>\n",
-       "      <td>-0.01037</td>\n",
+       "      <td>0.22751</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>16</th>\n",
-       "      <td>1714665600000</td>\n",
-       "      <td>2024-05-02 16:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714752000000</td>\n",
+       "      <td>2024-05-03 16:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>16</td>\n",
-       "      <td>0.03013</td>\n",
+       "      <td>0.22676</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>17</th>\n",
-       "      <td>1714669200000</td>\n",
-       "      <td>2024-05-02 17:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714755600000</td>\n",
+       "      <td>2024-05-03 17:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>17</td>\n",
-       "      <td>0.26045</td>\n",
+       "      <td>0.34283</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>18</th>\n",
-       "      <td>1714672800000</td>\n",
-       "      <td>2024-05-02 18:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714759200000</td>\n",
+       "      <td>2024-05-03 18:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>18</td>\n",
-       "      <td>0.29125</td>\n",
+       "      <td>0.60010</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>19</th>\n",
-       "      <td>1714676400000</td>\n",
-       "      <td>2024-05-02 19:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714762800000</td>\n",
+       "      <td>2024-05-03 19:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>19</td>\n",
-       "      <td>0.31266</td>\n",
+       "      <td>0.72356</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>20</th>\n",
-       "      <td>1714680000000</td>\n",
-       "      <td>2024-05-02 20:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714766400000</td>\n",
+       "      <td>2024-05-03 20:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>20</td>\n",
-       "      <td>0.31318</td>\n",
+       "      <td>0.82068</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>21</th>\n",
-       "      <td>1714683600000</td>\n",
-       "      <td>2024-05-02 21:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714770000000</td>\n",
+       "      <td>2024-05-03 21:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>21</td>\n",
-       "      <td>0.31266</td>\n",
+       "      <td>0.78524</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>22</th>\n",
-       "      <td>1714687200000</td>\n",
-       "      <td>2024-05-02 22:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714773600000</td>\n",
+       "      <td>2024-05-03 22:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>22</td>\n",
-       "      <td>0.28245</td>\n",
+       "      <td>0.68119</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>23</th>\n",
-       "      <td>1714690800000</td>\n",
-       "      <td>2024-05-02 23:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714777200000</td>\n",
+       "      <td>2024-05-03 23:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>23</td>\n",
-       "      <td>0.25306</td>\n",
+       "      <td>0.63822</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
@@ -331,33 +331,33 @@
       ],
       "text/plain": [
        "        timestamp            datetime        date  hour  dk1_spotpricedkk_kwh\n",
-       "0   1714608000000 2024-05-02 00:00:00  2024-05-02     0               0.10859\n",
-       "1   1714611600000 2024-05-02 01:00:00  2024-05-02     1               0.08160\n",
-       "2   1714615200000 2024-05-02 02:00:00  2024-05-02     2               0.07458\n",
-       "3   1714618800000 2024-05-02 03:00:00  2024-05-02     3               0.05818\n",
-       "4   1714622400000 2024-05-02 04:00:00  2024-05-02     4               0.07928\n",
-       "5   1714626000000 2024-05-02 05:00:00  2024-05-02     5               0.22920\n",
-       "6   1714629600000 2024-05-02 06:00:00  2024-05-02     6               0.29699\n",
-       "7   1714633200000 2024-05-02 07:00:00  2024-05-02     7               0.38605\n",
-       "8   1714636800000 2024-05-02 08:00:00  2024-05-02     8               0.43729\n",
-       "9   1714640400000 2024-05-02 09:00:00  2024-05-02     9               0.23457\n",
-       "10  1714644000000 2024-05-02 10:00:00  2024-05-02    10               0.03804\n",
-       "11  1714647600000 2024-05-02 11:00:00  2024-05-02    11              -0.00060\n",
-       "12  1714651200000 2024-05-02 12:00:00  2024-05-02    12              -0.01290\n",
-       "13  1714654800000 2024-05-02 13:00:00  2024-05-02    13              -0.02014\n",
-       "14  1714658400000 2024-05-02 14:00:00  2024-05-02    14              -0.00037\n",
-       "15  1714662000000 2024-05-02 15:00:00  2024-05-02    15              -0.01037\n",
-       "16  1714665600000 2024-05-02 16:00:00  2024-05-02    16               0.03013\n",
-       "17  1714669200000 2024-05-02 17:00:00  2024-05-02    17               0.26045\n",
-       "18  1714672800000 2024-05-02 18:00:00  2024-05-02    18               0.29125\n",
-       "19  1714676400000 2024-05-02 19:00:00  2024-05-02    19               0.31266\n",
-       "20  1714680000000 2024-05-02 20:00:00  2024-05-02    20               0.31318\n",
-       "21  1714683600000 2024-05-02 21:00:00  2024-05-02    21               0.31266\n",
-       "22  1714687200000 2024-05-02 22:00:00  2024-05-02    22               0.28245\n",
-       "23  1714690800000 2024-05-02 23:00:00  2024-05-02    23               0.25306"
+       "0   1714694400000 2024-05-03 00:00:00  2024-05-03     0               0.22214\n",
+       "1   1714698000000 2024-05-03 01:00:00  2024-05-03     1               0.21893\n",
+       "2   1714701600000 2024-05-03 02:00:00  2024-05-03     2               0.22348\n",
+       "3   1714705200000 2024-05-03 03:00:00  2024-05-03     3               0.22385\n",
+       "4   1714708800000 2024-05-03 04:00:00  2024-05-03     4               0.22706\n",
+       "5   1714712400000 2024-05-03 05:00:00  2024-05-03     5               0.23825\n",
+       "6   1714716000000 2024-05-03 06:00:00  2024-05-03     6               0.26167\n",
+       "7   1714719600000 2024-05-03 07:00:00  2024-05-03     7               0.32045\n",
+       "8   1714723200000 2024-05-03 08:00:00  2024-05-03     8               0.31881\n",
+       "9   1714726800000 2024-05-03 09:00:00  2024-05-03     9               0.28860\n",
+       "10  1714730400000 2024-05-03 10:00:00  2024-05-03    10               0.28413\n",
+       "11  1714734000000 2024-05-03 11:00:00  2024-05-03    11               0.25339\n",
+       "12  1714737600000 2024-05-03 12:00:00  2024-05-03    12               0.25324\n",
+       "13  1714741200000 2024-05-03 13:00:00  2024-05-03    13               0.24325\n",
+       "14  1714744800000 2024-05-03 14:00:00  2024-05-03    14               0.23698\n",
+       "15  1714748400000 2024-05-03 15:00:00  2024-05-03    15               0.22751\n",
+       "16  1714752000000 2024-05-03 16:00:00  2024-05-03    16               0.22676\n",
+       "17  1714755600000 2024-05-03 17:00:00  2024-05-03    17               0.34283\n",
+       "18  1714759200000 2024-05-03 18:00:00  2024-05-03    18               0.60010\n",
+       "19  1714762800000 2024-05-03 19:00:00  2024-05-03    19               0.72356\n",
+       "20  1714766400000 2024-05-03 20:00:00  2024-05-03    20               0.82068\n",
+       "21  1714770000000 2024-05-03 21:00:00  2024-05-03    21               0.78524\n",
+       "22  1714773600000 2024-05-03 22:00:00  2024-05-03    22               0.68119\n",
+       "23  1714777200000 2024-05-03 23:00:00  2024-05-03    23               0.63822"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -367,36 +367,6 @@
     "electricity_df"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### <span style=\"color:#2656a3;\">☀️💨 Forecast Renewable Energy next day from Energinet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Fetching non-historical forecast of renewable energy data for area DK1\n",
-    "# forecast_renewable_energy_df = electricity_prices.forecast_renewable_energy(\n",
-    "#     historical=False,\n",
-    "#     area=[\"DK1\"]\n",
-    "# )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Display the forecast_renewable_energy dataframe\n",
-    "# forecast_renewable_energy_df"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -408,41 +378,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### <span style=\"color:#2656a3;\"> 🕰️ Historical Weather Measures"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Fetching non-historical weather data for area DK1\n",
-    "#historical_weather_df = weather_measures.historical_weather_measures(\n",
-    "#    historical=False\n",
-    "#)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Display the first 5 rows of the dataframe\n",
-    "#historical_weather_df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### <span style=\"color:#2656a3;\"> 🌈 Weather Forecast"
+    "#### <span style=\"color:#2656a3;\"> 🌈 Forecast Weather Measures"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -454,7 +395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -496,83 +437,83 @@
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
-       "      <td>1714608000000</td>\n",
-       "      <td>2024-05-02 00:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714694400000</td>\n",
+       "      <td>2024-05-03 00:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>0</td>\n",
-       "      <td>14.9</td>\n",
-       "      <td>66.0</td>\n",
+       "      <td>14.3</td>\n",
+       "      <td>65.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>13.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>41.4</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>25.0</td>\n",
+       "      <td>20.5</td>\n",
+       "      <td>36.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
-       "      <td>1714611600000</td>\n",
-       "      <td>2024-05-02 01:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714698000000</td>\n",
+       "      <td>2024-05-03 01:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>1</td>\n",
-       "      <td>14.2</td>\n",
-       "      <td>71.0</td>\n",
+       "      <td>13.6</td>\n",
+       "      <td>69.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>20.5</td>\n",
-       "      <td>37.1</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>21.6</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
-       "      <td>1714615200000</td>\n",
-       "      <td>2024-05-02 02:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714701600000</td>\n",
+       "      <td>2024-05-03 02:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>2</td>\n",
-       "      <td>13.4</td>\n",
-       "      <td>73.0</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>72.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>70.0</td>\n",
-       "      <td>21.2</td>\n",
-       "      <td>36.7</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>20.9</td>\n",
+       "      <td>37.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
-       "      <td>1714618800000</td>\n",
-       "      <td>2024-05-02 03:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714705200000</td>\n",
+       "      <td>2024-05-03 03:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>3</td>\n",
-       "      <td>13.2</td>\n",
-       "      <td>72.0</td>\n",
-       "      <td>0.1</td>\n",
-       "      <td>0.1</td>\n",
+       "      <td>12.7</td>\n",
+       "      <td>73.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>22.3</td>\n",
-       "      <td>39.2</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>19.8</td>\n",
+       "      <td>34.6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
-       "      <td>1714622400000</td>\n",
-       "      <td>2024-05-02 04:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
+       "      <td>1714708800000</td>\n",
+       "      <td>2024-05-03 04:00:00</td>\n",
+       "      <td>2024-05-03</td>\n",
        "      <td>4</td>\n",
-       "      <td>12.7</td>\n",
+       "      <td>12.4</td>\n",
        "      <td>73.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>2.0</td>\n",
-       "      <td>78.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>38.9</td>\n",
+       "      <td>54.0</td>\n",
+       "      <td>18.7</td>\n",
+       "      <td>33.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
@@ -592,457 +533,140 @@
        "    </tr>\n",
        "    <tr>\n",
        "      <th>115</th>\n",
-       "      <td>1715022000000</td>\n",
-       "      <td>2024-05-06 19:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
+       "      <td>1715108400000</td>\n",
+       "      <td>2024-05-07 19:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
        "      <td>19</td>\n",
-       "      <td>10.7</td>\n",
-       "      <td>91.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>41.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>16.6</td>\n",
-       "      <td>32.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>116</th>\n",
-       "      <td>1715025600000</td>\n",
-       "      <td>2024-05-06 20:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>20</td>\n",
-       "      <td>10.1</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>19.5</td>\n",
-       "      <td>37.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>117</th>\n",
-       "      <td>1715029200000</td>\n",
-       "      <td>2024-05-06 21:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>21</td>\n",
-       "      <td>9.5</td>\n",
-       "      <td>88.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>42.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>118</th>\n",
-       "      <td>1715032800000</td>\n",
-       "      <td>2024-05-06 22:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>22</td>\n",
-       "      <td>9.3</td>\n",
-       "      <td>86.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>22.0</td>\n",
-       "      <td>41.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>119</th>\n",
-       "      <td>1715036400000</td>\n",
-       "      <td>2024-05-06 23:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>23</td>\n",
-       "      <td>9.1</td>\n",
-       "      <td>84.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.3</td>\n",
-       "      <td>40.3</td>\n",
+       "      <td>4.2</td>\n",
+       "      <td>10.8</td>\n",
        "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>120 rows × 13 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "         timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "0    1714608000000 2024-05-02 00:00:00  2024-05-02     0            14.9   \n",
-       "1    1714611600000 2024-05-02 01:00:00  2024-05-02     1            14.2   \n",
-       "2    1714615200000 2024-05-02 02:00:00  2024-05-02     2            13.4   \n",
-       "3    1714618800000 2024-05-02 03:00:00  2024-05-02     3            13.2   \n",
-       "4    1714622400000 2024-05-02 04:00:00  2024-05-02     4            12.7   \n",
-       "..             ...                 ...         ...   ...             ...   \n",
-       "115  1715022000000 2024-05-06 19:00:00  2024-05-06    19            10.7   \n",
-       "116  1715025600000 2024-05-06 20:00:00  2024-05-06    20            10.1   \n",
-       "117  1715029200000 2024-05-06 21:00:00  2024-05-06    21             9.5   \n",
-       "118  1715032800000 2024-05-06 22:00:00  2024-05-06    22             9.3   \n",
-       "119  1715036400000 2024-05-06 23:00:00  2024-05-06    23             9.1   \n",
-       "\n",
-       "     relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "0                    66.0            0.0   0.0       0.0           0.0   \n",
-       "1                    71.0            0.0   0.0       0.0           0.0   \n",
-       "2                    73.0            0.0   0.0       0.0           2.0   \n",
-       "3                    72.0            0.1   0.1       0.0          51.0   \n",
-       "4                    73.0            0.0   0.0       0.0           2.0   \n",
-       "..                    ...            ...   ...       ...           ...   \n",
-       "115                  91.0            1.4   1.4       0.0          61.0   \n",
-       "116                  90.0            1.4   1.4       0.0          61.0   \n",
-       "117                  88.0            1.4   1.4       0.0          61.0   \n",
-       "118                  86.0            0.6   0.6       0.0           3.0   \n",
-       "119                  84.0            0.6   0.6       0.0           3.0   \n",
-       "\n",
-       "     cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "0           13.0            21.6            41.4  \n",
-       "1            4.0            20.5            37.1  \n",
-       "2           70.0            21.2            36.7  \n",
-       "3           51.0            22.3            39.2  \n",
-       "4           78.0            21.6            38.9  \n",
-       "..           ...             ...             ...  \n",
-       "115        100.0            16.6            32.0  \n",
-       "116        100.0            19.5            37.1  \n",
-       "117        100.0            21.6            42.1  \n",
-       "118        100.0            22.0            41.0  \n",
-       "119        100.0            21.3            40.3  \n",
-       "\n",
-       "[120 rows x 13 columns]"
-      ]
-     },
-     "execution_count": 27,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the weather_forecast_df dataframe\n",
-    "weather_forecast_df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>timestamp</th>\n",
-       "      <th>datetime</th>\n",
-       "      <th>date</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
        "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>1714608000000</td>\n",
-       "      <td>2024-05-02 00:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
-       "      <td>0</td>\n",
-       "      <td>14.9</td>\n",
-       "      <td>66.0</td>\n",
+       "      <th>116</th>\n",
+       "      <td>1715112000000</td>\n",
+       "      <td>2024-05-07 20:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
+       "      <td>20</td>\n",
+       "      <td>10.7</td>\n",
+       "      <td>49.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>13.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>41.4</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.6</td>\n",
+       "      <td>8.3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>1714611600000</td>\n",
-       "      <td>2024-05-02 01:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
-       "      <td>1</td>\n",
-       "      <td>14.2</td>\n",
-       "      <td>71.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
+       "      <th>117</th>\n",
+       "      <td>1715115600000</td>\n",
+       "      <td>2024-05-07 21:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
+       "      <td>21</td>\n",
+       "      <td>9.6</td>\n",
+       "      <td>56.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>4.0</td>\n",
-       "      <td>20.5</td>\n",
-       "      <td>37.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>1714615200000</td>\n",
-       "      <td>2024-05-02 02:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
-       "      <td>2</td>\n",
-       "      <td>13.4</td>\n",
-       "      <td>73.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>70.0</td>\n",
-       "      <td>21.2</td>\n",
-       "      <td>36.7</td>\n",
+       "      <td>3.2</td>\n",
+       "      <td>5.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>1714618800000</td>\n",
-       "      <td>2024-05-02 03:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
-       "      <td>3</td>\n",
-       "      <td>13.2</td>\n",
-       "      <td>72.0</td>\n",
-       "      <td>0.1</td>\n",
-       "      <td>0.1</td>\n",
+       "      <th>118</th>\n",
+       "      <td>1715119200000</td>\n",
+       "      <td>2024-05-07 22:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
+       "      <td>22</td>\n",
+       "      <td>8.7</td>\n",
+       "      <td>58.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>51.0</td>\n",
-       "      <td>22.3</td>\n",
-       "      <td>39.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>1714622400000</td>\n",
-       "      <td>2024-05-02 04:00:00</td>\n",
-       "      <td>2024-05-02</td>\n",
-       "      <td>4</td>\n",
-       "      <td>12.7</td>\n",
-       "      <td>73.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>78.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>38.9</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "       timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "0  1714608000000 2024-05-02 00:00:00  2024-05-02     0            14.9   \n",
-       "1  1714611600000 2024-05-02 01:00:00  2024-05-02     1            14.2   \n",
-       "2  1714615200000 2024-05-02 02:00:00  2024-05-02     2            13.4   \n",
-       "3  1714618800000 2024-05-02 03:00:00  2024-05-02     3            13.2   \n",
-       "4  1714622400000 2024-05-02 04:00:00  2024-05-02     4            12.7   \n",
-       "\n",
-       "   relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "0                  66.0            0.0   0.0       0.0           0.0   \n",
-       "1                  71.0            0.0   0.0       0.0           0.0   \n",
-       "2                  73.0            0.0   0.0       0.0           2.0   \n",
-       "3                  72.0            0.1   0.1       0.0          51.0   \n",
-       "4                  73.0            0.0   0.0       0.0           2.0   \n",
-       "\n",
-       "   cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "0         13.0            21.6            41.4  \n",
-       "1          4.0            20.5            37.1  \n",
-       "2         70.0            21.2            36.7  \n",
-       "3         51.0            22.3            39.2  \n",
-       "4         78.0            21.6            38.9  "
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Display the first 5 rows of the weather_forecast dataframe\n",
-    "weather_forecast_df.head(5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>timestamp</th>\n",
-       "      <th>datetime</th>\n",
-       "      <th>date</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>temperature_2m</th>\n",
-       "      <th>relative_humidity_2m</th>\n",
-       "      <th>precipitation</th>\n",
-       "      <th>rain</th>\n",
-       "      <th>snowfall</th>\n",
-       "      <th>weather_code</th>\n",
-       "      <th>cloud_cover</th>\n",
-       "      <th>wind_speed_10m</th>\n",
-       "      <th>wind_gusts_10m</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>115</th>\n",
-       "      <td>1715022000000</td>\n",
-       "      <td>2024-05-06 19:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>19</td>\n",
-       "      <td>10.7</td>\n",
-       "      <td>91.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>16.6</td>\n",
-       "      <td>32.0</td>\n",
+       "      <td>3.3</td>\n",
+       "      <td>5.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>116</th>\n",
-       "      <td>1715025600000</td>\n",
-       "      <td>2024-05-06 20:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>20</td>\n",
-       "      <td>10.1</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
+       "      <th>119</th>\n",
+       "      <td>1715122800000</td>\n",
+       "      <td>2024-05-07 23:00:00</td>\n",
+       "      <td>2024-05-07</td>\n",
+       "      <td>23</td>\n",
+       "      <td>7.9</td>\n",
+       "      <td>57.0</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>19.5</td>\n",
-       "      <td>37.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>117</th>\n",
-       "      <td>1715029200000</td>\n",
-       "      <td>2024-05-06 21:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>21</td>\n",
-       "      <td>9.5</td>\n",
-       "      <td>88.0</td>\n",
-       "      <td>1.4</td>\n",
-       "      <td>1.4</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>61.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.6</td>\n",
-       "      <td>42.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>118</th>\n",
-       "      <td>1715032800000</td>\n",
-       "      <td>2024-05-06 22:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>22</td>\n",
-       "      <td>9.3</td>\n",
-       "      <td>86.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>22.0</td>\n",
-       "      <td>41.0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>119</th>\n",
-       "      <td>1715036400000</td>\n",
-       "      <td>2024-05-06 23:00:00</td>\n",
-       "      <td>2024-05-06</td>\n",
-       "      <td>23</td>\n",
-       "      <td>9.1</td>\n",
-       "      <td>84.0</td>\n",
-       "      <td>0.6</td>\n",
-       "      <td>0.6</td>\n",
        "      <td>0.0</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>100.0</td>\n",
-       "      <td>21.3</td>\n",
-       "      <td>40.3</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>3.8</td>\n",
+       "      <td>6.5</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
+       "<p>120 rows × 13 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
        "         timestamp            datetime        date  hour  temperature_2m  \\\n",
-       "115  1715022000000 2024-05-06 19:00:00  2024-05-06    19            10.7   \n",
-       "116  1715025600000 2024-05-06 20:00:00  2024-05-06    20            10.1   \n",
-       "117  1715029200000 2024-05-06 21:00:00  2024-05-06    21             9.5   \n",
-       "118  1715032800000 2024-05-06 22:00:00  2024-05-06    22             9.3   \n",
-       "119  1715036400000 2024-05-06 23:00:00  2024-05-06    23             9.1   \n",
+       "0    1714694400000 2024-05-03 00:00:00  2024-05-03     0            14.3   \n",
+       "1    1714698000000 2024-05-03 01:00:00  2024-05-03     1            13.6   \n",
+       "2    1714701600000 2024-05-03 02:00:00  2024-05-03     2            13.0   \n",
+       "3    1714705200000 2024-05-03 03:00:00  2024-05-03     3            12.7   \n",
+       "4    1714708800000 2024-05-03 04:00:00  2024-05-03     4            12.4   \n",
+       "..             ...                 ...         ...   ...             ...   \n",
+       "115  1715108400000 2024-05-07 19:00:00  2024-05-07    19            12.0   \n",
+       "116  1715112000000 2024-05-07 20:00:00  2024-05-07    20            10.7   \n",
+       "117  1715115600000 2024-05-07 21:00:00  2024-05-07    21             9.6   \n",
+       "118  1715119200000 2024-05-07 22:00:00  2024-05-07    22             8.7   \n",
+       "119  1715122800000 2024-05-07 23:00:00  2024-05-07    23             7.9   \n",
        "\n",
        "     relative_humidity_2m  precipitation  rain  snowfall  weather_code  \\\n",
-       "115                  91.0            1.4   1.4       0.0          61.0   \n",
-       "116                  90.0            1.4   1.4       0.0          61.0   \n",
-       "117                  88.0            1.4   1.4       0.0          61.0   \n",
-       "118                  86.0            0.6   0.6       0.0           3.0   \n",
-       "119                  84.0            0.6   0.6       0.0           3.0   \n",
+       "0                    65.0            0.0   0.0       0.0           1.0   \n",
+       "1                    69.0            0.0   0.0       0.0           0.0   \n",
+       "2                    72.0            0.0   0.0       0.0           0.0   \n",
+       "3                    73.0            0.0   0.0       0.0           1.0   \n",
+       "4                    73.0            0.0   0.0       0.0           2.0   \n",
+       "..                    ...            ...   ...       ...           ...   \n",
+       "115                  41.0            0.0   0.0       0.0           0.0   \n",
+       "116                  49.0            0.0   0.0       0.0           0.0   \n",
+       "117                  56.0            0.0   0.0       0.0           0.0   \n",
+       "118                  58.0            0.0   0.0       0.0           0.0   \n",
+       "119                  57.0            0.0   0.0       0.0           0.0   \n",
        "\n",
        "     cloud_cover  wind_speed_10m  wind_gusts_10m  \n",
-       "115        100.0            16.6            32.0  \n",
-       "116        100.0            19.5            37.1  \n",
-       "117        100.0            21.6            42.1  \n",
-       "118        100.0            22.0            41.0  \n",
-       "119        100.0            21.3            40.3  "
+       "0           25.0            20.5            36.0  \n",
+       "1           12.0            21.6            37.4  \n",
+       "2            7.0            20.9            37.4  \n",
+       "3           26.0            19.8            34.6  \n",
+       "4           54.0            18.7            33.8  \n",
+       "..           ...             ...             ...  \n",
+       "115          0.0             4.2            10.8  \n",
+       "116          0.0             3.6             8.3  \n",
+       "117          0.0             3.2             5.4  \n",
+       "118          0.0             3.3             5.8  \n",
+       "119          0.0             3.8             6.5  \n",
+       "\n",
+       "[120 rows x 13 columns]"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "weather_forecast_df.tail(5)"
+    "# Display the weather forecast dataframe\n",
+    "weather_forecast_df"
    ]
   },
   {
@@ -1056,17 +680,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Connection closed.\n",
       "Connected. Call `.close()` to terminate connection gracefully.\n",
       "\n",
-      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/556180\n",
+      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/554133\n",
       "Connected. Call `.close()` to terminate connection gracefully.\n"
      ]
     }
@@ -1084,7 +707,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1094,11 +717,6 @@
     "    version=1,\n",
     ")\n",
     "\n",
-    "# forecast_renewable_energy_fg = fs.get_feature_group(\n",
-    "#     name=\"forecast_renewable_energy\",\n",
-    "#     version=1,\n",
-    "# )\n",
-    "\n",
     "weather_fg = fs.get_feature_group(\n",
     "    name=\"weather_measurements\",\n",
     "    version=1,\n",
@@ -1115,15 +733,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading Dataframe: 100.00% |███��██████| Rows 24/24 | Elapsed Time: 00:06 | Remaining Time: 00:00\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "14af0030d68542cdae43f516e0e0f7a7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Uploading Dataframe: 0.00% |          | Rows 0/24 | Elapsed Time: 00:00 | Remaining Time: ?"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stdout",
@@ -1131,16 +756,16 @@
      "text": [
       "Launching job: electricity_prices_1_offline_fg_materialization\n",
       "Job started successfully, you can follow the progress at \n",
-      "https://c.app.hopsworks.ai/p/556180/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
+      "https://c.app.hopsworks.ai/p/554133/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "(<hsfs.core.job.Job at 0x29ebfbd7190>, None)"
+       "(<hsfs.core.job.Job at 0x3058ab890>, None)"
       ]
      },
-     "execution_count": 32,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1153,26 +778,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# # Inserting the forecast_renewable_energy_df into the feature group named forecast_renewable_energy_fg\n",
-    "# forecast_renewable_energy_fg.insert(forecast_renewable_energy_df, \n",
-    "#                                     write_options={\"wait_for_job\" : False})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Uploading Dataframe: 100.00% |██████████| Rows 120/120 | Elapsed Time: 00:06 | Remaining Time: 00:00\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "81dfae8d4c1942aaba0d1b0ff7917720",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Uploading Dataframe: 0.00% |          | Rows 0/120 | Elapsed Time: 00:00 | Remaining Time: ?"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stdout",
@@ -1180,16 +801,16 @@
      "text": [
       "Launching job: weather_measurements_1_offline_fg_materialization\n",
       "Job started successfully, you can follow the progress at \n",
-      "https://c.app.hopsworks.ai/p/556180/jobs/named/weather_measurements_1_offline_fg_materialization/executions\n"
+      "https://c.app.hopsworks.ai/p/554133/jobs/named/weather_measurements_1_offline_fg_materialization/executions\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "(<hsfs.core.job.Job at 0x29ebfad6550>, None)"
+       "(<hsfs.core.job.Job at 0x3058f5d10>, None)"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }

scripts/run_feature_and_prediction_pipelines.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+set -e
+
+cd notebooks
+
+# Run the feature pipeline
+jupyter nbconvert --to notebook --execute 2_feature_pipeline.ipynb
+
+# Run the batch inference pipeline
+jupyter nbconvert --to notebook --execute 4_batch_inference.ipynb