Spaces:
Sleeping
Sleeping
Commit
·
1f6629c
1
Parent(s):
a860811
traning and test changes
Browse files- app/app2.py +106 -0
- features/__pycache__/calendar.cpython-311.pyc +0 -0
- features/__pycache__/electricity_prices.cpython-311.pyc +0 -0
- features/__pycache__/weater_measures.cpython-311.pyc +0 -0
- features/__pycache__/weather_measures.cpython-311.pyc +0 -0
- features/calendar.py +34 -0
- features/electricity_prices.py +15 -10
- features/weather_measures.py +15 -7
- {Old → hide/Old}/1_feature_backfill_OLD.ipynb +0 -0
- {Old → hide/Old}/2_feature_pipeline_OLD.ipynb +0 -0
- hide/Old/3_training_pipeline copy.ipynb +0 -0
- {Old → hide/Old}/3_training_pipeline_OLD.ipynb +0 -0
- {Old → hide/Old}/4_batch_inference_OLD.ipynb +0 -0
- {notebooks → hide/Old}/predict_example.py +0 -0
- {notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_prophet.ipynb +0 -0
- {notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_pytorch.ipynb +0 -0
- {notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_tensorflow.ipynb +0 -0
- {notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_windowtensor.ipynb +0 -0
- notebooks/1_feature_backfill.ipynb +608 -614
- notebooks/2_feature_pipeline.ipynb +547 -729
- notebooks/3_training_pipeline.ipynb +0 -0
- notebooks/4_batch_inference copy.ipynb +448 -0
- notebooks/4_batch_inference.ipynb +96 -963
- notebooks/model/dk_electricity_model.pkl +0 -0
- notebooks/test.ipynb +0 -0
app/app2.py
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import datetime
|
2 |
+
import joblib
|
3 |
+
from math import radians
|
4 |
+
|
5 |
+
import pandas as pd
|
6 |
+
import numpy as np
|
7 |
+
import plotly.express as px
|
8 |
+
from matplotlib import pyplot
|
9 |
+
import warnings
|
10 |
+
|
11 |
+
import hopsworks
|
12 |
+
|
13 |
+
import streamlit as st
|
14 |
+
|
15 |
+
import folium
|
16 |
+
from streamlit_folium import st_folium
|
17 |
+
import json
|
18 |
+
|
19 |
+
start_date = (datetime.datetime.now() - datetime.timedelta(hours=200))
|
20 |
+
end_date = (datetime.datetime.now())
|
21 |
+
|
22 |
+
synthetic_data.set_random_seed(12345)
|
23 |
+
credit_cards = [cc["cc_num"] for cc in synthetic_data.generate_list_credit_card_numbers()]
|
24 |
+
lat = 0
|
25 |
+
long = 0
|
26 |
+
|
27 |
+
warnings.filterwarnings("ignore")
|
28 |
+
|
29 |
+
project = hopsworks.login()
|
30 |
+
fs = project.get_feature_store()
|
31 |
+
|
32 |
+
@st.cache(allow_output_mutation=True, suppress_st_warning=True)
|
33 |
+
def retrieve_dataset(fv, start_date, end_date):
|
34 |
+
st.write(36 * "-")
|
35 |
+
print_fancy_header('\n💾 Dataset Retrieving...')
|
36 |
+
batch_data = fv.get_batch_data(start_time = start_date, end_time = end_date)
|
37 |
+
batch_data.drop(["tid", "cc_num", "datetime"], axis = 1, inplace=True)
|
38 |
+
return batch_data
|
39 |
+
|
40 |
+
|
41 |
+
@st.cache(suppress_st_warning=True, allow_output_mutation=True)
|
42 |
+
def get_feature_view():
|
43 |
+
fv = fs.get_feature_view("cc_trans_fraud", 1)
|
44 |
+
return fv
|
45 |
+
|
46 |
+
|
47 |
+
@st.cache(allow_output_mutation=True,suppress_st_warning=True)
|
48 |
+
def get_model(project = project):
|
49 |
+
mr = project.get_model_registry()
|
50 |
+
model = mr.get_model("cc_fraud", version = 1)
|
51 |
+
model_dir = model.download()
|
52 |
+
return joblib.load(model_dir + "/cc_fraud_model.pkl")
|
53 |
+
|
54 |
+
def explore_data(batch_data):
|
55 |
+
st.write(36 * "-")
|
56 |
+
print_fancy_header('\n👁 Data Exploration...')
|
57 |
+
labels = ["Suspected of Fraud", "Not Suspected of Fraud"]
|
58 |
+
unique, counts = np.unique(batch_data.fraud.values, return_counts=True)
|
59 |
+
values = counts.tolist()
|
60 |
+
|
61 |
+
def plot_pie(values, labels):
|
62 |
+
fig = px.pie(values=values, names=labels, title='Distribution of predicted fraud transactions')
|
63 |
+
return fig
|
64 |
+
|
65 |
+
fig1 = plot_pie(values, labels)
|
66 |
+
st.plotly_chart(fig1)
|
67 |
+
|
68 |
+
|
69 |
+
def print_fancy_header(text, font_size=24):
|
70 |
+
res = f'<span style="color:#ff5f27; font-size: {font_size}px;">{text}</span>'
|
71 |
+
st.markdown(res, unsafe_allow_html=True)
|
72 |
+
|
73 |
+
def transform_preds(predictions):
|
74 |
+
return ['Fraud' if pred == 1 else 'Not Fraud' for pred in predictions]
|
75 |
+
|
76 |
+
progress_bar = st.sidebar.header('⚙️ Working Progress')
|
77 |
+
progress_bar = st.sidebar.progress(0)
|
78 |
+
st.title('🆘 Fraud transactions detection 🆘')
|
79 |
+
|
80 |
+
st.write(36 * "-")
|
81 |
+
print_fancy_header('\n📡 Connecting to Hopsworks Feature Store...')
|
82 |
+
|
83 |
+
st.write(36 * "-")
|
84 |
+
print_fancy_header('\n🤖 Connecting to Model Registry on Hopsworks...')
|
85 |
+
model = get_model(project)
|
86 |
+
st.write(model)
|
87 |
+
st.write("✅ Connected!")
|
88 |
+
|
89 |
+
progress_bar.progress(40)
|
90 |
+
|
91 |
+
st.write(36 * "-")
|
92 |
+
print_fancy_header('\n✨ Fetch batch data and predict')
|
93 |
+
fv = get_feature_view()
|
94 |
+
|
95 |
+
|
96 |
+
if st.button('📊 Make a prediction'):
|
97 |
+
batch_data = retrieve_dataset(fv, start_date, end_date)
|
98 |
+
st.write("✅ Retrieved!")
|
99 |
+
progress_bar.progress(55)
|
100 |
+
predictions = model.predict(batch_data)
|
101 |
+
predictions = transform_preds(predictions)
|
102 |
+
batch_data_to_explore = batch_data.copy()
|
103 |
+
batch_data_to_explore['fraud'] = predictions
|
104 |
+
explore_data(batch_data_to_explore)
|
105 |
+
|
106 |
+
st.button("Re-run")
|
features/__pycache__/calendar.cpython-311.pyc
ADDED
Binary file (1.94 kB). View file
|
|
features/__pycache__/electricity_prices.cpython-311.pyc
CHANGED
Binary files a/features/__pycache__/electricity_prices.cpython-311.pyc and b/features/__pycache__/electricity_prices.cpython-311.pyc differ
|
|
features/__pycache__/weater_measures.cpython-311.pyc
DELETED
Binary file (4.55 kB)
|
|
features/__pycache__/weather_measures.cpython-311.pyc
CHANGED
Binary files a/features/__pycache__/weather_measures.cpython-311.pyc and b/features/__pycache__/weather_measures.cpython-311.pyc differ
|
|
features/calendar.py
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from datetime import datetime, date
|
2 |
+
import numpy as np
|
3 |
+
import pandas as pd
|
4 |
+
|
5 |
+
|
6 |
+
def get_calendar() -> pd.DataFrame:
|
7 |
+
"""
|
8 |
+
Fetches calendar for Denmark.
|
9 |
+
|
10 |
+
Parameters:
|
11 |
+
- ....
|
12 |
+
|
13 |
+
Returns:
|
14 |
+
- pd.DataFrame: DataFrame with danish calendar.
|
15 |
+
"""
|
16 |
+
|
17 |
+
df = pd.read_csv('https://raw.githubusercontent.com/Camillahannesbo/MLOPs-Assignment-/main/data/calendar_incl_holiday.csv', delimiter=';', usecols=['date', 'type'])
|
18 |
+
|
19 |
+
# Formatting the date column to 'YYYY-MM-DD' dateformat
|
20 |
+
df["date"] = df["date"].map(lambda x: datetime.strptime(x, '%d/%m/%Y').strftime("%Y-%m-%d"))
|
21 |
+
|
22 |
+
# Add features to the calender dataframe
|
23 |
+
df['date_'] = pd.to_datetime(df['date'])
|
24 |
+
df['dayofweek'] = df['date_'].dt.dayofweek
|
25 |
+
df['day'] = df['date_'].dt.day
|
26 |
+
df['month'] = df['date_'].dt.month
|
27 |
+
df['year'] = df['date_'].dt.year
|
28 |
+
df['holiday'] = np.where(df['type'] == 'Not a Workday', 1, 0)
|
29 |
+
|
30 |
+
# Drop the columns 'type' and 'date_' to finalize the calender dataframe
|
31 |
+
calendar = df.drop(['type','date_'], axis=1)
|
32 |
+
|
33 |
+
# Return the DataFrame with weather data
|
34 |
+
return calendar
|
features/electricity_prices.py
CHANGED
@@ -31,7 +31,10 @@ def electricity_prices(historical: bool = False, area: list = None, start: str =
|
|
31 |
|
32 |
# Format date and time
|
33 |
df["date"] = df["HourDK"].map(lambda x: datetime.strptime(x, '%Y-%m-%dT%H:%M:%S').strftime("%Y-%m-%d"))
|
34 |
-
df['
|
|
|
|
|
|
|
35 |
|
36 |
# Dicide the price to KWH
|
37 |
df['SpotPriceDKK_KWH'] = df['SpotPriceDKK'] / 1000
|
@@ -53,16 +56,16 @@ def electricity_prices(historical: bool = False, area: list = None, start: str =
|
|
53 |
filtered_df = filtered_df[filtered_df.date == today]
|
54 |
|
55 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
56 |
-
filtered_df["timestamp"] = filtered_df["
|
57 |
|
58 |
# Reset the index to avoid duplicate entries
|
59 |
filtered_df.reset_index(drop=True, inplace=True)
|
60 |
|
61 |
# Select relevant columns for weather data and reorder them
|
62 |
-
reordered_df = filtered_df[['timestamp', 'date', '
|
63 |
|
64 |
# Unpivot DataFrame
|
65 |
-
reordered_df = reordered_df.melt(id_vars=[
|
66 |
|
67 |
# Combine columns into a single "heading" column
|
68 |
reordered_df["heading"] = reordered_df["PriceArea"] + "_" + reordered_df["attribute"]
|
@@ -72,7 +75,7 @@ def electricity_prices(historical: bool = False, area: list = None, start: str =
|
|
72 |
reordered_df.drop(columns=["attribute"], inplace=True)
|
73 |
|
74 |
# Pivot DataFrame
|
75 |
-
electricity_prices = reordered_df.pivot_table(index=[
|
76 |
|
77 |
# Converting column names to lowercase for consistency
|
78 |
electricity_prices.columns = list(map(str.lower, electricity_prices.columns))
|
@@ -109,7 +112,9 @@ def forecast_renewable_energy(historical: bool = False, area: str = None, start:
|
|
109 |
|
110 |
# Format date and time
|
111 |
df["date"] = df["HourDK"].map(lambda x: datetime.strptime(x, '%Y-%m-%dT%H:%M:%S').strftime("%Y-%m-%d"))
|
112 |
-
df['
|
|
|
|
|
113 |
|
114 |
# Drop unnecessary columns
|
115 |
df.drop('Forecast5Hour', axis=1, inplace=True)
|
@@ -135,7 +140,7 @@ def forecast_renewable_energy(historical: bool = False, area: str = None, start:
|
|
135 |
filtered_df = filtered_df[df.date == today]
|
136 |
|
137 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
138 |
-
filtered_df["timestamp"] = filtered_df["
|
139 |
|
140 |
# Divide specified columns by 1000
|
141 |
filtered_df["ForecastIntraday_KWH"] = filtered_df["ForecastIntraday"] / 1000
|
@@ -147,10 +152,10 @@ def forecast_renewable_energy(historical: bool = False, area: str = None, start:
|
|
147 |
filtered_df.reset_index(drop=True, inplace=True)
|
148 |
|
149 |
# Select relevant columns for weather data and reorder them
|
150 |
-
reordered_df = filtered_df[['timestamp', 'date', '
|
151 |
|
152 |
# Unpivot DataFrame
|
153 |
-
reordered_df = reordered_df.melt(id_vars=["timestamp", "
|
154 |
|
155 |
# Combine columns into a single "heading" column
|
156 |
reordered_df["heading"] = reordered_df["PriceArea"] + "_" + reordered_df["ForecastType"] + "_" + reordered_df["attribute"]
|
@@ -161,7 +166,7 @@ def forecast_renewable_energy(historical: bool = False, area: str = None, start:
|
|
161 |
reordered_df.drop(columns=["attribute"], inplace=True)
|
162 |
|
163 |
# Pivot DataFrame
|
164 |
-
forecast_renewable_energy = reordered_df.pivot_table(index=["timestamp", "
|
165 |
|
166 |
# Converting column names to lowercase for consistency
|
167 |
forecast_renewable_energy.columns = list(map(str.lower, forecast_renewable_energy.columns))
|
|
|
31 |
|
32 |
# Format date and time
|
33 |
df["date"] = df["HourDK"].map(lambda x: datetime.strptime(x, '%Y-%m-%dT%H:%M:%S').strftime("%Y-%m-%d"))
|
34 |
+
df['datetime'] = pd.to_datetime(df['HourDK'])
|
35 |
+
# df['time'] = pd.to_datetime(df['datetime']).dt.time
|
36 |
+
df['hour'] = pd.to_datetime(df['datetime']).dt.hour
|
37 |
+
|
38 |
|
39 |
# Dicide the price to KWH
|
40 |
df['SpotPriceDKK_KWH'] = df['SpotPriceDKK'] / 1000
|
|
|
56 |
filtered_df = filtered_df[filtered_df.date == today]
|
57 |
|
58 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
59 |
+
filtered_df["timestamp"] = filtered_df["datetime"].apply(lambda x: int(x.timestamp() * 1000))
|
60 |
|
61 |
# Reset the index to avoid duplicate entries
|
62 |
filtered_df.reset_index(drop=True, inplace=True)
|
63 |
|
64 |
# Select relevant columns for weather data and reorder them
|
65 |
+
reordered_df = filtered_df[['timestamp', 'datetime', 'date', 'hour', 'PriceArea', 'SpotPriceDKK_KWH']]
|
66 |
|
67 |
# Unpivot DataFrame
|
68 |
+
reordered_df = reordered_df.melt(id_vars=['timestamp', 'datetime', 'date', 'hour', "PriceArea"], var_name="attribute", value_name="value")
|
69 |
|
70 |
# Combine columns into a single "heading" column
|
71 |
reordered_df["heading"] = reordered_df["PriceArea"] + "_" + reordered_df["attribute"]
|
|
|
75 |
reordered_df.drop(columns=["attribute"], inplace=True)
|
76 |
|
77 |
# Pivot DataFrame
|
78 |
+
electricity_prices = reordered_df.pivot_table(index=['timestamp', 'datetime', 'date', 'hour'], columns="heading", values="value").reset_index()
|
79 |
|
80 |
# Converting column names to lowercase for consistency
|
81 |
electricity_prices.columns = list(map(str.lower, electricity_prices.columns))
|
|
|
112 |
|
113 |
# Format date and time
|
114 |
df["date"] = df["HourDK"].map(lambda x: datetime.strptime(x, '%Y-%m-%dT%H:%M:%S').strftime("%Y-%m-%d"))
|
115 |
+
df['datetime'] = pd.to_datetime(df['HourDK'])
|
116 |
+
# df['time'] = pd.to_datetime(df['datetime']).dt.time
|
117 |
+
df['hour'] = pd.to_datetime(df['datetime']).dt.hour
|
118 |
|
119 |
# Drop unnecessary columns
|
120 |
df.drop('Forecast5Hour', axis=1, inplace=True)
|
|
|
140 |
filtered_df = filtered_df[df.date == today]
|
141 |
|
142 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
143 |
+
filtered_df["timestamp"] = filtered_df["datetime"].apply(lambda x: int(x.timestamp() * 1000))
|
144 |
|
145 |
# Divide specified columns by 1000
|
146 |
filtered_df["ForecastIntraday_KWH"] = filtered_df["ForecastIntraday"] / 1000
|
|
|
152 |
filtered_df.reset_index(drop=True, inplace=True)
|
153 |
|
154 |
# Select relevant columns for weather data and reorder them
|
155 |
+
reordered_df = filtered_df[['timestamp', 'datetime', 'date', 'hour', 'PriceArea', 'ForecastType', 'ForecastIntraday_KWH']]
|
156 |
|
157 |
# Unpivot DataFrame
|
158 |
+
reordered_df = reordered_df.melt(id_vars=["timestamp", 'datetime', "date", "hour", "PriceArea", "ForecastType"], var_name="attribute", value_name="value")
|
159 |
|
160 |
# Combine columns into a single "heading" column
|
161 |
reordered_df["heading"] = reordered_df["PriceArea"] + "_" + reordered_df["ForecastType"] + "_" + reordered_df["attribute"]
|
|
|
166 |
reordered_df.drop(columns=["attribute"], inplace=True)
|
167 |
|
168 |
# Pivot DataFrame
|
169 |
+
forecast_renewable_energy = reordered_df.pivot_table(index=["timestamp", "datetime", "date", "hour"], columns="heading", values="value").reset_index()
|
170 |
|
171 |
# Converting column names to lowercase for consistency
|
172 |
forecast_renewable_energy.columns = list(map(str.lower, forecast_renewable_energy.columns))
|
features/weather_measures.py
CHANGED
@@ -32,8 +32,9 @@ def historical_weather_measures(historical: bool = False, lat: float = 57.048, l
|
|
32 |
|
33 |
# Extract date from the 'time' column and convert it to datetime format
|
34 |
df["date"] = df['time'].str[:10]
|
35 |
-
df['
|
36 |
-
|
|
|
37 |
|
38 |
# Filter the DataFrame based on whether historical data is requested or not
|
39 |
today = (date.today()).strftime("%Y-%m-%d")
|
@@ -43,10 +44,10 @@ def historical_weather_measures(historical: bool = False, lat: float = 57.048, l
|
|
43 |
df = df[df.date == today]
|
44 |
|
45 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
46 |
-
df["timestamp"] = df["
|
47 |
|
48 |
# Select relevant columns for weather data and reorder them
|
49 |
-
weather = df[['timestamp', 'date', '
|
50 |
|
51 |
# Deleting rows with missing values
|
52 |
weather = weather.dropna()
|
@@ -79,13 +80,20 @@ def forecast_weather_measures(lat: float = 57.048, lon: float = 9.9187, forecast
|
|
79 |
|
80 |
# Extract date from the 'time' column and convert it to datetime format
|
81 |
df["date"] = df['time'].str[:10]
|
82 |
-
df['
|
|
|
|
|
83 |
|
84 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
85 |
-
df["timestamp"] = df["
|
86 |
|
87 |
# Select relevant columns for forecast weather data and reorder them
|
88 |
-
forecast_weather = df[['timestamp', 'date', '
|
|
|
|
|
|
|
|
|
|
|
89 |
|
90 |
# Deleting rows with missing values
|
91 |
forecast_weather = forecast_weather.dropna()
|
|
|
32 |
|
33 |
# Extract date from the 'time' column and convert it to datetime format
|
34 |
df["date"] = df['time'].str[:10]
|
35 |
+
df['datetime'] = pd.to_datetime(df['time'])
|
36 |
+
# df['time'] = pd.to_datetime(df['datetime']).dt.time
|
37 |
+
df['hour'] = pd.to_datetime(df['datetime']).dt.hour
|
38 |
|
39 |
# Filter the DataFrame based on whether historical data is requested or not
|
40 |
today = (date.today()).strftime("%Y-%m-%d")
|
|
|
44 |
df = df[df.date == today]
|
45 |
|
46 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
47 |
+
df["timestamp"] = df["datetime"].apply(lambda x: int(x.timestamp() * 1000))
|
48 |
|
49 |
# Select relevant columns for weather data and reorder them
|
50 |
+
weather = df[['timestamp', 'datetime', 'date', 'hour', 'temperature_2m', 'relative_humidity_2m', 'precipitation', 'rain', 'snowfall', 'weather_code', 'cloud_cover', 'wind_speed_10m', 'wind_gusts_10m']]
|
51 |
|
52 |
# Deleting rows with missing values
|
53 |
weather = weather.dropna()
|
|
|
80 |
|
81 |
# Extract date from the 'time' column and convert it to datetime format
|
82 |
df["date"] = df['time'].str[:10]
|
83 |
+
df['datetime'] = pd.to_datetime(df['time'])
|
84 |
+
# df['time'] = pd.to_datetime(df['datetime']).dt.time
|
85 |
+
df['hour'] = pd.to_datetime(df['datetime']).dt.hour
|
86 |
|
87 |
# Convert datetime to timestamp in milliseconds and add it as a new column
|
88 |
+
df["timestamp"] = df["datetime"].apply(lambda x: int(x.timestamp() * 1000))
|
89 |
|
90 |
# Select relevant columns for forecast weather data and reorder them
|
91 |
+
forecast_weather = df[['timestamp', 'datetime', 'date', 'hour', 'temperature_2m', 'relative_humidity_2m', 'precipitation', 'rain', 'snowfall', 'weather_code', 'cloud_cover', 'wind_speed_10m', 'wind_gusts_10m']]
|
92 |
+
|
93 |
+
# Convert columns to float
|
94 |
+
forecast_weather['relative_humidity_2m'] = forecast_weather['relative_humidity_2m'].astype(float)
|
95 |
+
forecast_weather['weather_code'] = forecast_weather['weather_code'].astype(float)
|
96 |
+
forecast_weather['cloud_cover'] = forecast_weather['cloud_cover'].astype(float)
|
97 |
|
98 |
# Deleting rows with missing values
|
99 |
forecast_weather = forecast_weather.dropna()
|
{Old → hide/Old}/1_feature_backfill_OLD.ipynb
RENAMED
File without changes
|
{Old → hide/Old}/2_feature_pipeline_OLD.ipynb
RENAMED
File without changes
|
hide/Old/3_training_pipeline copy.ipynb
ADDED
The diff for this file is too large to render.
See raw diff
|
|
{Old → hide/Old}/3_training_pipeline_OLD.ipynb
RENAMED
File without changes
|
{Old → hide/Old}/4_batch_inference_OLD.ipynb
RENAMED
File without changes
|
{notebooks → hide/Old}/predict_example.py
RENAMED
File without changes
|
{notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_prophet.ipynb
RENAMED
File without changes
|
{notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_pytorch.ipynb
RENAMED
File without changes
|
{notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_tensorflow.ipynb
RENAMED
File without changes
|
{notebooks_dev → hide/notebooks_dev}/3_training_pipeline_dev_windowtensor.ipynb
RENAMED
File without changes
|
notebooks/1_feature_backfill.ipynb
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
"\n",
|
57 |
"# Now we import the functions from the features folder\n",
|
58 |
"# This is the functions we have created to generate features for electricity prices and weather measures\n",
|
59 |
-
"from features import electricity_prices, weather_measures \n",
|
60 |
"\n",
|
61 |
"# We go back into the notebooks folder\n",
|
62 |
"%cd notebooks"
|
@@ -70,6 +70,7 @@
|
|
70 |
"source": [
|
71 |
"# Importing the packages for the needed libraries for the Jupyter notebook\n",
|
72 |
"import pandas as pd\n",
|
|
|
73 |
"import requests\n",
|
74 |
"from datetime import datetime, timedelta\n",
|
75 |
"\n",
|
@@ -146,8 +147,9 @@
|
|
146 |
" <tr style=\"text-align: right;\">\n",
|
147 |
" <th></th>\n",
|
148 |
" <th>timestamp</th>\n",
|
149 |
-
" <th>
|
150 |
" <th>date</th>\n",
|
|
|
151 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
152 |
" </tr>\n",
|
153 |
" </thead>\n",
|
@@ -157,6 +159,7 @@
|
|
157 |
" <td>1640995200000</td>\n",
|
158 |
" <td>2022-01-01 00:00:00</td>\n",
|
159 |
" <td>2022-01-01</td>\n",
|
|
|
160 |
" <td>0.37220</td>\n",
|
161 |
" </tr>\n",
|
162 |
" <tr>\n",
|
@@ -164,6 +167,7 @@
|
|
164 |
" <td>1640998800000</td>\n",
|
165 |
" <td>2022-01-01 01:00:00</td>\n",
|
166 |
" <td>2022-01-01</td>\n",
|
|
|
167 |
" <td>0.30735</td>\n",
|
168 |
" </tr>\n",
|
169 |
" <tr>\n",
|
@@ -171,6 +175,7 @@
|
|
171 |
" <td>1641002400000</td>\n",
|
172 |
" <td>2022-01-01 02:00:00</td>\n",
|
173 |
" <td>2022-01-01</td>\n",
|
|
|
174 |
" <td>0.32141</td>\n",
|
175 |
" </tr>\n",
|
176 |
" <tr>\n",
|
@@ -178,6 +183,7 @@
|
|
178 |
" <td>1641006000000</td>\n",
|
179 |
" <td>2022-01-01 03:00:00</td>\n",
|
180 |
" <td>2022-01-01</td>\n",
|
|
|
181 |
" <td>0.33806</td>\n",
|
182 |
" </tr>\n",
|
183 |
" <tr>\n",
|
@@ -185,6 +191,7 @@
|
|
185 |
" <td>1641009600000</td>\n",
|
186 |
" <td>2022-01-01 04:00:00</td>\n",
|
187 |
" <td>2022-01-01</td>\n",
|
|
|
188 |
" <td>0.28013</td>\n",
|
189 |
" </tr>\n",
|
190 |
" </tbody>\n",
|
@@ -192,12 +199,12 @@
|
|
192 |
"</div>"
|
193 |
],
|
194 |
"text/plain": [
|
195 |
-
" timestamp
|
196 |
-
"0 1640995200000 2022-01-01 00:00:00 2022-01-01 0.37220\n",
|
197 |
-
"1 1640998800000 2022-01-01 01:00:00 2022-01-01 0.30735\n",
|
198 |
-
"2 1641002400000 2022-01-01 02:00:00 2022-01-01 0.32141\n",
|
199 |
-
"3 1641006000000 2022-01-01 03:00:00 2022-01-01 0.33806\n",
|
200 |
-
"4 1641009600000 2022-01-01 04:00:00 2022-01-01 0.28013"
|
201 |
]
|
202 |
},
|
203 |
"execution_count": 5,
|
@@ -237,58 +244,71 @@
|
|
237 |
" <tr style=\"text-align: right;\">\n",
|
238 |
" <th></th>\n",
|
239 |
" <th>timestamp</th>\n",
|
240 |
-
" <th>
|
241 |
" <th>date</th>\n",
|
|
|
242 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
243 |
" </tr>\n",
|
244 |
" </thead>\n",
|
245 |
" <tbody>\n",
|
246 |
" <tr>\n",
|
247 |
-
" <th>
|
248 |
-
" <td>
|
249 |
-
" <td>2024-
|
250 |
-
" <td>2024-
|
251 |
-
" <td>
|
|
|
252 |
" </tr>\n",
|
253 |
" <tr>\n",
|
254 |
-
" <th>
|
255 |
-
" <td>
|
256 |
-
" <td>2024-
|
257 |
-
" <td>2024-
|
258 |
-
" <td>
|
|
|
259 |
" </tr>\n",
|
260 |
" <tr>\n",
|
261 |
-
" <th>
|
262 |
-
" <td>
|
263 |
-
" <td>2024-
|
264 |
-
" <td>2024-
|
265 |
-
" <td>
|
|
|
266 |
" </tr>\n",
|
267 |
" <tr>\n",
|
268 |
-
" <th>
|
269 |
-
" <td>
|
270 |
-
" <td>2024-
|
271 |
-
" <td>2024-
|
272 |
-
" <td>
|
|
|
273 |
" </tr>\n",
|
274 |
" <tr>\n",
|
275 |
-
" <th>
|
276 |
-
" <td>
|
277 |
-
" <td>2024-
|
278 |
-
" <td>2024-
|
279 |
-
" <td>
|
|
|
280 |
" </tr>\n",
|
281 |
" </tbody>\n",
|
282 |
"</table>\n",
|
283 |
"</div>"
|
284 |
],
|
285 |
"text/plain": [
|
286 |
-
" timestamp
|
287 |
-
"
|
288 |
-
"
|
289 |
-
"
|
290 |
-
"
|
291 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
292 |
]
|
293 |
},
|
294 |
"execution_count": 6,
|
@@ -311,16 +331,17 @@
|
|
311 |
"output_type": "stream",
|
312 |
"text": [
|
313 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
314 |
-
"RangeIndex:
|
315 |
-
"Data columns (total
|
316 |
" # Column Non-Null Count Dtype \n",
|
317 |
"--- ------ -------------- ----- \n",
|
318 |
-
" 0 timestamp
|
319 |
-
" 1
|
320 |
-
" 2 date
|
321 |
-
" 3
|
322 |
-
"
|
323 |
-
"
|
|
|
324 |
]
|
325 |
}
|
326 |
],
|
@@ -381,8 +402,9 @@
|
|
381 |
" <tr style=\"text-align: right;\">\n",
|
382 |
" <th></th>\n",
|
383 |
" <th>timestamp</th>\n",
|
384 |
-
" <th>
|
385 |
" <th>date</th>\n",
|
|
|
386 |
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
387 |
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
388 |
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
@@ -394,6 +416,7 @@
|
|
394 |
" <td>1641024000000</td>\n",
|
395 |
" <td>2022-01-01 08:00:00</td>\n",
|
396 |
" <td>2022-01-01</td>\n",
|
|
|
397 |
" <td>0.611708</td>\n",
|
398 |
" <td>0.236792</td>\n",
|
399 |
" <td>0.000050</td>\n",
|
@@ -403,6 +426,7 @@
|
|
403 |
" <td>1641027600000</td>\n",
|
404 |
" <td>2022-01-01 09:00:00</td>\n",
|
405 |
" <td>2022-01-01</td>\n",
|
|
|
406 |
" <td>0.459708</td>\n",
|
407 |
" <td>0.196667</td>\n",
|
408 |
" <td>0.004841</td>\n",
|
@@ -412,6 +436,7 @@
|
|
412 |
" <td>1641031200000</td>\n",
|
413 |
" <td>2022-01-01 10:00:00</td>\n",
|
414 |
" <td>2022-01-01</td>\n",
|
|
|
415 |
" <td>0.310375</td>\n",
|
416 |
" <td>0.178500</td>\n",
|
417 |
" <td>0.020353</td>\n",
|
@@ -421,6 +446,7 @@
|
|
421 |
" <td>1641034800000</td>\n",
|
422 |
" <td>2022-01-01 11:00:00</td>\n",
|
423 |
" <td>2022-01-01</td>\n",
|
|
|
424 |
" <td>0.320750</td>\n",
|
425 |
" <td>0.201125</td>\n",
|
426 |
" <td>0.035719</td>\n",
|
@@ -430,6 +456,7 @@
|
|
430 |
" <td>1641038400000</td>\n",
|
431 |
" <td>2022-01-01 12:00:00</td>\n",
|
432 |
" <td>2022-01-01</td>\n",
|
|
|
433 |
" <td>0.355667</td>\n",
|
434 |
" <td>0.277667</td>\n",
|
435 |
" <td>0.038027</td>\n",
|
@@ -439,12 +466,12 @@
|
|
439 |
"</div>"
|
440 |
],
|
441 |
"text/plain": [
|
442 |
-
" timestamp
|
443 |
-
"0 1641024000000 2022-01-01 08:00:00 2022-01-01 \n",
|
444 |
-
"1 1641027600000 2022-01-01 09:00:00 2022-01-01 \n",
|
445 |
-
"2 1641031200000 2022-01-01 10:00:00 2022-01-01 \n",
|
446 |
-
"3 1641034800000 2022-01-01 11:00:00 2022-01-01 \n",
|
447 |
-
"4 1641038400000 2022-01-01 12:00:00 2022-01-01 \n",
|
448 |
"\n",
|
449 |
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
450 |
"0 0.611708 \n",
|
@@ -498,8 +525,9 @@
|
|
498 |
" <tr style=\"text-align: right;\">\n",
|
499 |
" <th></th>\n",
|
500 |
" <th>timestamp</th>\n",
|
501 |
-
" <th>
|
502 |
" <th>date</th>\n",
|
|
|
503 |
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
504 |
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
505 |
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
@@ -507,48 +535,53 @@
|
|
507 |
" </thead>\n",
|
508 |
" <tbody>\n",
|
509 |
" <tr>\n",
|
510 |
-
" <th>
|
511 |
-
" <td>
|
512 |
-
" <td>2024-
|
513 |
-
" <td>2024-
|
514 |
-
" <td>
|
515 |
-
" <td>0.
|
516 |
-
" <td>
|
|
|
517 |
" </tr>\n",
|
518 |
" <tr>\n",
|
519 |
-
" <th>
|
520 |
-
" <td>
|
521 |
-
" <td>2024-
|
522 |
-
" <td>2024-
|
523 |
-
" <td>
|
524 |
-
" <td>
|
525 |
-
" <td>
|
|
|
526 |
" </tr>\n",
|
527 |
" <tr>\n",
|
528 |
-
" <th>
|
529 |
-
" <td>
|
530 |
-
" <td>2024-
|
531 |
-
" <td>2024-
|
532 |
-
" <td>
|
533 |
-
" <td>
|
534 |
-
" <td>
|
|
|
535 |
" </tr>\n",
|
536 |
" <tr>\n",
|
537 |
-
" <th>
|
538 |
-
" <td>
|
539 |
-
" <td>2024-
|
540 |
-
" <td>2024-
|
541 |
-
" <td>
|
542 |
-
" <td>
|
|
|
543 |
" <td>0.000000</td>\n",
|
544 |
" </tr>\n",
|
545 |
" <tr>\n",
|
546 |
-
" <th>
|
547 |
-
" <td>
|
548 |
-
" <td>2024-
|
549 |
-
" <td>2024-
|
550 |
-
" <td>
|
551 |
-
" <td>
|
|
|
552 |
" <td>0.000000</td>\n",
|
553 |
" </tr>\n",
|
554 |
" </tbody>\n",
|
@@ -556,26 +589,26 @@
|
|
556 |
"</div>"
|
557 |
],
|
558 |
"text/plain": [
|
559 |
-
" timestamp
|
560 |
-
"
|
561 |
-
"
|
562 |
-
"
|
563 |
-
"
|
564 |
-
"
|
565 |
"\n",
|
566 |
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
567 |
-
"
|
568 |
-
"
|
569 |
-
"
|
570 |
-
"
|
571 |
-
"
|
572 |
"\n",
|
573 |
" dk1_onshore_wind_forecastintraday_kwh dk1_solar_forecastintraday_kwh \n",
|
574 |
-
"
|
575 |
-
"
|
576 |
-
"
|
577 |
-
"
|
578 |
-
"
|
579 |
]
|
580 |
},
|
581 |
"execution_count": 10,
|
@@ -598,18 +631,19 @@
|
|
598 |
"output_type": "stream",
|
599 |
"text": [
|
600 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
601 |
-
"RangeIndex:
|
602 |
-
"Data columns (total
|
603 |
" # Column Non-Null Count Dtype \n",
|
604 |
"--- ------ -------------- ----- \n",
|
605 |
-
" 0 timestamp
|
606 |
-
" 1
|
607 |
-
" 2 date
|
608 |
-
" 3
|
609 |
-
" 4
|
610 |
-
" 5
|
611 |
-
"
|
612 |
-
"
|
|
|
613 |
]
|
614 |
}
|
615 |
],
|
@@ -676,8 +710,9 @@
|
|
676 |
" <tr style=\"text-align: right;\">\n",
|
677 |
" <th></th>\n",
|
678 |
" <th>timestamp</th>\n",
|
|
|
679 |
" <th>date</th>\n",
|
680 |
-
" <th>
|
681 |
" <th>temperature_2m</th>\n",
|
682 |
" <th>relative_humidity_2m</th>\n",
|
683 |
" <th>precipitation</th>\n",
|
@@ -693,8 +728,9 @@
|
|
693 |
" <tr>\n",
|
694 |
" <th>0</th>\n",
|
695 |
" <td>1640995200000</td>\n",
|
696 |
-
" <td>2022-01-01</td>\n",
|
697 |
" <td>2022-01-01 00:00:00</td>\n",
|
|
|
|
|
698 |
" <td>6.7</td>\n",
|
699 |
" <td>100.0</td>\n",
|
700 |
" <td>0.0</td>\n",
|
@@ -708,8 +744,9 @@
|
|
708 |
" <tr>\n",
|
709 |
" <th>1</th>\n",
|
710 |
" <td>1640998800000</td>\n",
|
711 |
-
" <td>2022-01-01</td>\n",
|
712 |
" <td>2022-01-01 01:00:00</td>\n",
|
|
|
|
|
713 |
" <td>6.6</td>\n",
|
714 |
" <td>100.0</td>\n",
|
715 |
" <td>0.0</td>\n",
|
@@ -723,8 +760,9 @@
|
|
723 |
" <tr>\n",
|
724 |
" <th>2</th>\n",
|
725 |
" <td>1641002400000</td>\n",
|
726 |
-
" <td>2022-01-01</td>\n",
|
727 |
" <td>2022-01-01 02:00:00</td>\n",
|
|
|
|
|
728 |
" <td>6.7</td>\n",
|
729 |
" <td>99.0</td>\n",
|
730 |
" <td>0.0</td>\n",
|
@@ -738,8 +776,9 @@
|
|
738 |
" <tr>\n",
|
739 |
" <th>3</th>\n",
|
740 |
" <td>1641006000000</td>\n",
|
741 |
-
" <td>2022-01-01</td>\n",
|
742 |
" <td>2022-01-01 03:00:00</td>\n",
|
|
|
|
|
743 |
" <td>6.7</td>\n",
|
744 |
" <td>100.0</td>\n",
|
745 |
" <td>0.0</td>\n",
|
@@ -753,8 +792,9 @@
|
|
753 |
" <tr>\n",
|
754 |
" <th>4</th>\n",
|
755 |
" <td>1641009600000</td>\n",
|
756 |
-
" <td>2022-01-01</td>\n",
|
757 |
" <td>2022-01-01 04:00:00</td>\n",
|
|
|
|
|
758 |
" <td>6.7</td>\n",
|
759 |
" <td>99.0</td>\n",
|
760 |
" <td>0.0</td>\n",
|
@@ -770,12 +810,12 @@
|
|
770 |
"</div>"
|
771 |
],
|
772 |
"text/plain": [
|
773 |
-
" timestamp date
|
774 |
-
"0 1640995200000
|
775 |
-
"1 1640998800000
|
776 |
-
"2 1641002400000
|
777 |
-
"3 1641006000000
|
778 |
-
"4 1641009600000
|
779 |
"\n",
|
780 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
781 |
"0 100.0 0.0 0.0 0.0 3.0 \n",
|
@@ -829,8 +869,9 @@
|
|
829 |
" <tr style=\"text-align: right;\">\n",
|
830 |
" <th></th>\n",
|
831 |
" <th>timestamp</th>\n",
|
|
|
832 |
" <th>date</th>\n",
|
833 |
-
" <th>
|
834 |
" <th>temperature_2m</th>\n",
|
835 |
" <th>relative_humidity_2m</th>\n",
|
836 |
" <th>precipitation</th>\n",
|
@@ -844,105 +885,110 @@
|
|
844 |
" </thead>\n",
|
845 |
" <tbody>\n",
|
846 |
" <tr>\n",
|
847 |
-
" <th>
|
848 |
-
" <td>
|
849 |
-
" <td>2024-04-
|
850 |
-
" <td>2024-04-
|
851 |
-
" <td>
|
852 |
-
" <td>
|
|
|
853 |
" <td>0.0</td>\n",
|
854 |
" <td>0.0</td>\n",
|
855 |
" <td>0.0</td>\n",
|
856 |
" <td>0.0</td>\n",
|
857 |
-
" <td>
|
858 |
-
" <td>
|
859 |
-
" <td>
|
860 |
" </tr>\n",
|
861 |
" <tr>\n",
|
862 |
-
" <th>
|
863 |
-
" <td>
|
864 |
-
" <td>2024-04-
|
865 |
-
" <td>2024-04-
|
866 |
-
" <td>
|
867 |
-
" <td>
|
868 |
-
" <td>
|
869 |
" <td>0.0</td>\n",
|
870 |
" <td>0.0</td>\n",
|
871 |
" <td>0.0</td>\n",
|
872 |
" <td>0.0</td>\n",
|
873 |
-
" <td>
|
874 |
-
" <td>
|
|
|
875 |
" </tr>\n",
|
876 |
" <tr>\n",
|
877 |
-
" <th>
|
878 |
-
" <td>
|
879 |
-
" <td>2024-04-
|
880 |
-
" <td>2024-04-
|
881 |
-
" <td>
|
882 |
-
" <td>
|
883 |
-
" <td>
|
884 |
" <td>0.0</td>\n",
|
885 |
" <td>0.0</td>\n",
|
886 |
" <td>0.0</td>\n",
|
887 |
" <td>0.0</td>\n",
|
888 |
-
" <td>
|
889 |
-
" <td>
|
|
|
890 |
" </tr>\n",
|
891 |
" <tr>\n",
|
892 |
-
" <th>
|
893 |
-
" <td>
|
894 |
-
" <td>2024-04-
|
895 |
-
" <td>2024-04-
|
896 |
-
" <td>
|
897 |
-
" <td>
|
898 |
-
" <td>
|
899 |
" <td>0.0</td>\n",
|
900 |
" <td>0.0</td>\n",
|
901 |
" <td>0.0</td>\n",
|
902 |
" <td>0.0</td>\n",
|
903 |
-
" <td>
|
904 |
-
" <td>
|
|
|
905 |
" </tr>\n",
|
906 |
" <tr>\n",
|
907 |
-
" <th>
|
908 |
-
" <td>
|
909 |
-
" <td>2024-04-
|
910 |
-
" <td>2024-04-
|
911 |
-
" <td>
|
912 |
-
" <td>
|
913 |
-
" <td>
|
914 |
" <td>0.0</td>\n",
|
915 |
" <td>0.0</td>\n",
|
916 |
" <td>0.0</td>\n",
|
917 |
" <td>0.0</td>\n",
|
918 |
-
" <td>
|
919 |
-
" <td>20.
|
|
|
920 |
" </tr>\n",
|
921 |
" </tbody>\n",
|
922 |
"</table>\n",
|
923 |
"</div>"
|
924 |
],
|
925 |
"text/plain": [
|
926 |
-
" timestamp date
|
927 |
-
"
|
928 |
-
"
|
929 |
-
"
|
930 |
-
"
|
931 |
-
"
|
932 |
"\n",
|
933 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
934 |
-
"
|
935 |
-
"
|
936 |
-
"
|
937 |
-
"
|
938 |
-
"
|
939 |
"\n",
|
940 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
941 |
-
"
|
942 |
-
"
|
943 |
-
"
|
944 |
-
"
|
945 |
-
"
|
946 |
]
|
947 |
},
|
948 |
"execution_count": 14,
|
@@ -965,24 +1011,25 @@
|
|
965 |
"output_type": "stream",
|
966 |
"text": [
|
967 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
968 |
-
"Int64Index:
|
969 |
-
"Data columns (total
|
970 |
" # Column Non-Null Count Dtype \n",
|
971 |
"--- ------ -------------- ----- \n",
|
972 |
-
" 0 timestamp
|
973 |
-
" 1
|
974 |
-
" 2
|
975 |
-
" 3
|
976 |
-
" 4
|
977 |
-
" 5
|
978 |
-
" 6
|
979 |
-
" 7
|
980 |
-
" 8
|
981 |
-
" 9
|
982 |
-
" 10
|
983 |
-
" 11
|
984 |
-
"
|
985 |
-
"
|
|
|
986 |
]
|
987 |
}
|
988 |
],
|
@@ -1038,8 +1085,9 @@
|
|
1038 |
" <tr style=\"text-align: right;\">\n",
|
1039 |
" <th></th>\n",
|
1040 |
" <th>timestamp</th>\n",
|
|
|
1041 |
" <th>date</th>\n",
|
1042 |
-
" <th>
|
1043 |
" <th>temperature_2m</th>\n",
|
1044 |
" <th>relative_humidity_2m</th>\n",
|
1045 |
" <th>precipitation</th>\n",
|
@@ -1054,104 +1102,109 @@
|
|
1054 |
" <tbody>\n",
|
1055 |
" <tr>\n",
|
1056 |
" <th>0</th>\n",
|
1057 |
-
" <td>
|
1058 |
-
" <td>2024-05-
|
1059 |
-
" <td>2024-05-
|
1060 |
-
" <td>
|
1061 |
-
" <td>
|
|
|
1062 |
" <td>0.0</td>\n",
|
1063 |
" <td>0.0</td>\n",
|
1064 |
" <td>0.0</td>\n",
|
1065 |
-
" <td>
|
1066 |
-
" <td>
|
1067 |
-
" <td>
|
1068 |
-
" <td>
|
1069 |
" </tr>\n",
|
1070 |
" <tr>\n",
|
1071 |
" <th>1</th>\n",
|
1072 |
-
" <td>
|
1073 |
-
" <td>2024-05-01</td>\n",
|
1074 |
-
" <td>2024-05-
|
1075 |
-
" <td>
|
1076 |
-
" <td>
|
|
|
1077 |
" <td>0.0</td>\n",
|
1078 |
" <td>0.0</td>\n",
|
1079 |
" <td>0.0</td>\n",
|
1080 |
-
" <td>0</td>\n",
|
1081 |
-
" <td>
|
1082 |
-
" <td>
|
1083 |
-
" <td>
|
1084 |
" </tr>\n",
|
1085 |
" <tr>\n",
|
1086 |
" <th>2</th>\n",
|
1087 |
-
" <td>
|
1088 |
-
" <td>2024-05-
|
1089 |
-
" <td>2024-05-
|
1090 |
-
" <td>
|
1091 |
-
" <td>
|
|
|
1092 |
" <td>0.0</td>\n",
|
1093 |
" <td>0.0</td>\n",
|
1094 |
" <td>0.0</td>\n",
|
1095 |
-
" <td>2</td>\n",
|
1096 |
-
" <td>
|
1097 |
-
" <td>
|
1098 |
-
" <td>
|
1099 |
" </tr>\n",
|
1100 |
" <tr>\n",
|
1101 |
" <th>3</th>\n",
|
1102 |
-
" <td>
|
1103 |
-
" <td>2024-05-
|
1104 |
-
" <td>2024-05-
|
1105 |
-
" <td>11.5</td>\n",
|
1106 |
-
" <td>76</td>\n",
|
1107 |
-
" <td>0.0</td>\n",
|
1108 |
-
" <td>0.0</td>\n",
|
1109 |
-
" <td>0.0</td>\n",
|
1110 |
" <td>3</td>\n",
|
1111 |
-
" <td>
|
1112 |
-
" <td>
|
1113 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
1114 |
" </tr>\n",
|
1115 |
" <tr>\n",
|
1116 |
" <th>4</th>\n",
|
1117 |
-
" <td>
|
1118 |
-
" <td>2024-05-
|
1119 |
-
" <td>2024-05-
|
1120 |
-
" <td>
|
1121 |
-
" <td>
|
|
|
1122 |
" <td>0.0</td>\n",
|
1123 |
" <td>0.0</td>\n",
|
1124 |
" <td>0.0</td>\n",
|
1125 |
-
" <td>
|
1126 |
-
" <td>
|
1127 |
-
" <td>
|
1128 |
-
" <td>
|
1129 |
" </tr>\n",
|
1130 |
" </tbody>\n",
|
1131 |
"</table>\n",
|
1132 |
"</div>"
|
1133 |
],
|
1134 |
"text/plain": [
|
1135 |
-
" timestamp date
|
1136 |
-
"0
|
1137 |
-
"1
|
1138 |
-
"2
|
1139 |
-
"3
|
1140 |
-
"4
|
1141 |
"\n",
|
1142 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1143 |
-
"0
|
1144 |
-
"1
|
1145 |
-
"2
|
1146 |
-
"3
|
1147 |
-
"4
|
1148 |
"\n",
|
1149 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1150 |
-
"0
|
1151 |
-
"1
|
1152 |
-
"2
|
1153 |
-
"3
|
1154 |
-
"4
|
1155 |
]
|
1156 |
},
|
1157 |
"execution_count": 17,
|
@@ -1191,8 +1244,9 @@
|
|
1191 |
" <tr style=\"text-align: right;\">\n",
|
1192 |
" <th></th>\n",
|
1193 |
" <th>timestamp</th>\n",
|
|
|
1194 |
" <th>date</th>\n",
|
1195 |
-
" <th>
|
1196 |
" <th>temperature_2m</th>\n",
|
1197 |
" <th>relative_humidity_2m</th>\n",
|
1198 |
" <th>precipitation</th>\n",
|
@@ -1207,104 +1261,109 @@
|
|
1207 |
" <tbody>\n",
|
1208 |
" <tr>\n",
|
1209 |
" <th>115</th>\n",
|
1210 |
-
" <td>
|
1211 |
-
" <td>2024-05-
|
1212 |
-
" <td>2024-05-
|
1213 |
-
" <td>
|
1214 |
-
" <td>
|
1215 |
-
" <td>
|
1216 |
-
" <td>
|
1217 |
-
" <td>
|
1218 |
-
" <td>
|
1219 |
-
" <td>
|
1220 |
-
" <td>
|
1221 |
-
" <td>
|
|
|
1222 |
" </tr>\n",
|
1223 |
" <tr>\n",
|
1224 |
" <th>116</th>\n",
|
1225 |
-
" <td>
|
1226 |
-
" <td>2024-05-
|
1227 |
-
" <td>2024-05-
|
1228 |
-
" <td>
|
1229 |
-
" <td>83</td>\n",
|
1230 |
-
" <td>0.0</td>\n",
|
1231 |
-
" <td>0.0</td>\n",
|
1232 |
-
" <td>0.0</td>\n",
|
1233 |
-
" <td>3</td>\n",
|
1234 |
-
" <td>91</td>\n",
|
1235 |
" <td>10.1</td>\n",
|
1236 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1237 |
" </tr>\n",
|
1238 |
" <tr>\n",
|
1239 |
" <th>117</th>\n",
|
1240 |
-
" <td>
|
1241 |
-
" <td>2024-05-
|
1242 |
-
" <td>2024-05-
|
1243 |
-
" <td>
|
1244 |
-
" <td>86</td>\n",
|
1245 |
-
" <td>0.0</td>\n",
|
1246 |
-
" <td>0.0</td>\n",
|
1247 |
-
" <td>0.0</td>\n",
|
1248 |
-
" <td>3</td>\n",
|
1249 |
-
" <td>98</td>\n",
|
1250 |
" <td>9.5</td>\n",
|
1251 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1252 |
" </tr>\n",
|
1253 |
" <tr>\n",
|
1254 |
" <th>118</th>\n",
|
1255 |
-
" <td>
|
1256 |
-
" <td>2024-05-
|
1257 |
-
" <td>2024-05-
|
1258 |
-
" <td>
|
1259 |
-
" <td>
|
1260 |
-
" <td>
|
1261 |
-
" <td>0.
|
|
|
1262 |
" <td>0.0</td>\n",
|
1263 |
-
" <td>3</td>\n",
|
1264 |
-
" <td>
|
1265 |
-
" <td>
|
1266 |
-
" <td>
|
1267 |
" </tr>\n",
|
1268 |
" <tr>\n",
|
1269 |
" <th>119</th>\n",
|
1270 |
-
" <td>
|
1271 |
-
" <td>2024-05-
|
1272 |
-
" <td>2024-05-
|
1273 |
-
" <td>
|
1274 |
-
" <td>
|
|
|
|
|
|
|
1275 |
" <td>0.0</td>\n",
|
1276 |
-
" <td>
|
1277 |
-
" <td>
|
1278 |
-
" <td>3</td>\n",
|
1279 |
-
" <td>
|
1280 |
-
" <td>11.9</td>\n",
|
1281 |
-
" <td>24.1</td>\n",
|
1282 |
" </tr>\n",
|
1283 |
" </tbody>\n",
|
1284 |
"</table>\n",
|
1285 |
"</div>"
|
1286 |
],
|
1287 |
"text/plain": [
|
1288 |
-
" timestamp date
|
1289 |
-
"115
|
1290 |
-
"116
|
1291 |
-
"117
|
1292 |
-
"118
|
1293 |
-
"119
|
1294 |
"\n",
|
1295 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1296 |
-
"115
|
1297 |
-
"116
|
1298 |
-
"117
|
1299 |
-
"118
|
1300 |
-
"119
|
1301 |
"\n",
|
1302 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1303 |
-
"115
|
1304 |
-
"116
|
1305 |
-
"117
|
1306 |
-
"118
|
1307 |
-
"119
|
1308 |
]
|
1309 |
},
|
1310 |
"execution_count": 18,
|
@@ -1328,23 +1387,24 @@
|
|
1328 |
"text": [
|
1329 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
1330 |
"RangeIndex: 120 entries, 0 to 119\n",
|
1331 |
-
"Data columns (total
|
1332 |
" # Column Non-Null Count Dtype \n",
|
1333 |
"--- ------ -------------- ----- \n",
|
1334 |
" 0 timestamp 120 non-null int64 \n",
|
1335 |
-
" 1
|
1336 |
-
" 2
|
1337 |
-
" 3
|
1338 |
-
" 4
|
1339 |
-
" 5
|
1340 |
-
" 6
|
1341 |
-
" 7
|
1342 |
-
" 8
|
1343 |
-
" 9
|
1344 |
-
" 10
|
1345 |
-
" 11
|
1346 |
-
"
|
1347 |
-
"
|
|
|
1348 |
]
|
1349 |
}
|
1350 |
],
|
@@ -1365,97 +1425,14 @@
|
|
1365 |
"cell_type": "code",
|
1366 |
"execution_count": 20,
|
1367 |
"metadata": {},
|
1368 |
-
"outputs": [
|
1369 |
-
{
|
1370 |
-
"data": {
|
1371 |
-
"text/html": [
|
1372 |
-
"<div>\n",
|
1373 |
-
"<style scoped>\n",
|
1374 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
1375 |
-
" vertical-align: middle;\n",
|
1376 |
-
" }\n",
|
1377 |
-
"\n",
|
1378 |
-
" .dataframe tbody tr th {\n",
|
1379 |
-
" vertical-align: top;\n",
|
1380 |
-
" }\n",
|
1381 |
-
"\n",
|
1382 |
-
" .dataframe thead th {\n",
|
1383 |
-
" text-align: right;\n",
|
1384 |
-
" }\n",
|
1385 |
-
"</style>\n",
|
1386 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
1387 |
-
" <thead>\n",
|
1388 |
-
" <tr style=\"text-align: right;\">\n",
|
1389 |
-
" <th></th>\n",
|
1390 |
-
" <th>date</th>\n",
|
1391 |
-
" <th>type</th>\n",
|
1392 |
-
" </tr>\n",
|
1393 |
-
" </thead>\n",
|
1394 |
-
" <tbody>\n",
|
1395 |
-
" <tr>\n",
|
1396 |
-
" <th>0</th>\n",
|
1397 |
-
" <td>01/01/2022</td>\n",
|
1398 |
-
" <td>Not a Workday</td>\n",
|
1399 |
-
" </tr>\n",
|
1400 |
-
" <tr>\n",
|
1401 |
-
" <th>1</th>\n",
|
1402 |
-
" <td>02/01/2022</td>\n",
|
1403 |
-
" <td>Not a Workday</td>\n",
|
1404 |
-
" </tr>\n",
|
1405 |
-
" <tr>\n",
|
1406 |
-
" <th>2</th>\n",
|
1407 |
-
" <td>03/01/2022</td>\n",
|
1408 |
-
" <td>Workday</td>\n",
|
1409 |
-
" </tr>\n",
|
1410 |
-
" <tr>\n",
|
1411 |
-
" <th>3</th>\n",
|
1412 |
-
" <td>04/01/2022</td>\n",
|
1413 |
-
" <td>Workday</td>\n",
|
1414 |
-
" </tr>\n",
|
1415 |
-
" <tr>\n",
|
1416 |
-
" <th>4</th>\n",
|
1417 |
-
" <td>05/01/2022</td>\n",
|
1418 |
-
" <td>Workday</td>\n",
|
1419 |
-
" </tr>\n",
|
1420 |
-
" </tbody>\n",
|
1421 |
-
"</table>\n",
|
1422 |
-
"</div>"
|
1423 |
-
],
|
1424 |
-
"text/plain": [
|
1425 |
-
" date type\n",
|
1426 |
-
"0 01/01/2022 Not a Workday\n",
|
1427 |
-
"1 02/01/2022 Not a Workday\n",
|
1428 |
-
"2 03/01/2022 Workday\n",
|
1429 |
-
"3 04/01/2022 Workday\n",
|
1430 |
-
"4 05/01/2022 Workday"
|
1431 |
-
]
|
1432 |
-
},
|
1433 |
-
"execution_count": 20,
|
1434 |
-
"metadata": {},
|
1435 |
-
"output_type": "execute_result"
|
1436 |
-
}
|
1437 |
-
],
|
1438 |
-
"source": [
|
1439 |
-
"# Read csv file with calender\n",
|
1440 |
-
"calender_df = pd.read_csv('https://raw.githubusercontent.com/Camillahannesbo/MLOPs-Assignment-/main/data/calendar_incl_holiday.csv', delimiter=';', usecols=['date', 'type'])\n",
|
1441 |
-
" \n",
|
1442 |
-
"# Display the DataFrame\n",
|
1443 |
-
"calender_df.head()"
|
1444 |
-
]
|
1445 |
-
},
|
1446 |
-
{
|
1447 |
-
"cell_type": "code",
|
1448 |
-
"execution_count": 21,
|
1449 |
-
"metadata": {},
|
1450 |
"outputs": [],
|
1451 |
"source": [
|
1452 |
-
"
|
1453 |
-
"calender_df[\"date\"] = calender_df[\"date\"].map(lambda x: datetime.strptime(x, '%d/%m/%Y').strftime(\"%Y-%m-%d\"))"
|
1454 |
]
|
1455 |
},
|
1456 |
{
|
1457 |
"cell_type": "code",
|
1458 |
-
"execution_count":
|
1459 |
"metadata": {},
|
1460 |
"outputs": [
|
1461 |
{
|
@@ -1480,49 +1457,61 @@
|
|
1480 |
" <tr style=\"text-align: right;\">\n",
|
1481 |
" <th></th>\n",
|
1482 |
" <th>date</th>\n",
|
1483 |
-
" <th>
|
|
|
|
|
1484 |
" </tr>\n",
|
1485 |
" </thead>\n",
|
1486 |
" <tbody>\n",
|
1487 |
" <tr>\n",
|
1488 |
" <th>0</th>\n",
|
1489 |
" <td>2022-01-01</td>\n",
|
1490 |
-
" <td>
|
|
|
|
|
1491 |
" </tr>\n",
|
1492 |
" <tr>\n",
|
1493 |
" <th>1</th>\n",
|
1494 |
" <td>2022-01-02</td>\n",
|
1495 |
-
" <td>
|
|
|
|
|
1496 |
" </tr>\n",
|
1497 |
" <tr>\n",
|
1498 |
" <th>2</th>\n",
|
1499 |
" <td>2022-01-03</td>\n",
|
1500 |
-
" <td>
|
|
|
|
|
1501 |
" </tr>\n",
|
1502 |
" <tr>\n",
|
1503 |
" <th>3</th>\n",
|
1504 |
" <td>2022-01-04</td>\n",
|
1505 |
-
" <td>
|
|
|
|
|
1506 |
" </tr>\n",
|
1507 |
" <tr>\n",
|
1508 |
" <th>4</th>\n",
|
1509 |
" <td>2022-01-05</td>\n",
|
1510 |
-
" <td>
|
|
|
|
|
1511 |
" </tr>\n",
|
1512 |
" </tbody>\n",
|
1513 |
"</table>\n",
|
1514 |
"</div>"
|
1515 |
],
|
1516 |
"text/plain": [
|
1517 |
-
" date
|
1518 |
-
"0 2022-01-01
|
1519 |
-
"1 2022-01-02
|
1520 |
-
"2 2022-01-03
|
1521 |
-
"3 2022-01-04
|
1522 |
-
"4 2022-01-05
|
1523 |
]
|
1524 |
},
|
1525 |
-
"execution_count":
|
1526 |
"metadata": {},
|
1527 |
"output_type": "execute_result"
|
1528 |
}
|
@@ -1534,7 +1523,7 @@
|
|
1534 |
},
|
1535 |
{
|
1536 |
"cell_type": "code",
|
1537 |
-
"execution_count":
|
1538 |
"metadata": {},
|
1539 |
"outputs": [
|
1540 |
{
|
@@ -1559,49 +1548,61 @@
|
|
1559 |
" <tr style=\"text-align: right;\">\n",
|
1560 |
" <th></th>\n",
|
1561 |
" <th>date</th>\n",
|
1562 |
-
" <th>
|
|
|
|
|
1563 |
" </tr>\n",
|
1564 |
" </thead>\n",
|
1565 |
" <tbody>\n",
|
1566 |
" <tr>\n",
|
1567 |
" <th>1091</th>\n",
|
1568 |
" <td>2024-12-27</td>\n",
|
1569 |
-
" <td>
|
|
|
|
|
1570 |
" </tr>\n",
|
1571 |
" <tr>\n",
|
1572 |
" <th>1092</th>\n",
|
1573 |
" <td>2024-12-28</td>\n",
|
1574 |
-
" <td>
|
|
|
|
|
1575 |
" </tr>\n",
|
1576 |
" <tr>\n",
|
1577 |
" <th>1093</th>\n",
|
1578 |
" <td>2024-12-29</td>\n",
|
1579 |
-
" <td>
|
|
|
|
|
1580 |
" </tr>\n",
|
1581 |
" <tr>\n",
|
1582 |
" <th>1094</th>\n",
|
1583 |
" <td>2024-12-30</td>\n",
|
1584 |
-
" <td>
|
|
|
|
|
1585 |
" </tr>\n",
|
1586 |
" <tr>\n",
|
1587 |
" <th>1095</th>\n",
|
1588 |
" <td>2024-12-31</td>\n",
|
1589 |
-
" <td>
|
|
|
|
|
1590 |
" </tr>\n",
|
1591 |
" </tbody>\n",
|
1592 |
"</table>\n",
|
1593 |
"</div>"
|
1594 |
],
|
1595 |
"text/plain": [
|
1596 |
-
" date
|
1597 |
-
"1091 2024-12-27
|
1598 |
-
"1092 2024-12-28
|
1599 |
-
"1093 2024-12-29
|
1600 |
-
"1094 2024-12-30
|
1601 |
-
"1095 2024-12-31
|
1602 |
]
|
1603 |
},
|
1604 |
-
"execution_count":
|
1605 |
"metadata": {},
|
1606 |
"output_type": "execute_result"
|
1607 |
}
|
@@ -1611,6 +1612,34 @@
|
|
1611 |
"calender_df.tail(5)"
|
1612 |
]
|
1613 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1614 |
{
|
1615 |
"cell_type": "code",
|
1616 |
"execution_count": 24,
|
@@ -1622,13 +1651,15 @@
|
|
1622 |
"text": [
|
1623 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
1624 |
"RangeIndex: 1096 entries, 0 to 1095\n",
|
1625 |
-
"Data columns (total
|
1626 |
-
" # Column
|
1627 |
-
"--- ------
|
1628 |
-
" 0 date
|
1629 |
-
" 1
|
1630 |
-
"
|
1631 |
-
"
|
|
|
|
|
1632 |
]
|
1633 |
}
|
1634 |
],
|
@@ -1680,9 +1711,9 @@
|
|
1680 |
"### <span style=\"color:#2656a3;\"> 🪄 Creating Feature Groups\n",
|
1681 |
"A feature group can be seen as a collection of conceptually related features. In this case we create feature groups for the \n",
|
1682 |
"- eletricity price data,\n",
|
|
|
1683 |
"- weather data,\n",
|
1684 |
-
"- calender data
|
1685 |
-
"- forecast_renewable_energy.\n",
|
1686 |
"\n",
|
1687 |
"We specify a `primary_key` as `date`, so we are able to join them when we create a dataset for training later in part 03 the training_pipeline.\n",
|
1688 |
"We define a name and a short describtion of the feature group's contents and a version number. \n",
|
@@ -1698,14 +1729,14 @@
|
|
1698 |
"metadata": {},
|
1699 |
"outputs": [],
|
1700 |
"source": [
|
1701 |
-
"# Creating the feature group for the
|
1702 |
-
"
|
1703 |
-
" name=\"
|
1704 |
" version=1,\n",
|
1705 |
-
" description=\"
|
1706 |
-
" primary_key=[\"date\",\"timestamp\"],
|
1707 |
-
" event_time=\"timestamp\",\n",
|
1708 |
" online_enabled=True,\n",
|
|
|
1709 |
")"
|
1710 |
]
|
1711 |
},
|
@@ -1726,18 +1757,18 @@
|
|
1726 |
"output_type": "stream",
|
1727 |
"text": [
|
1728 |
"Feature Group created successfully, explore it at \n",
|
1729 |
-
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/
|
1730 |
]
|
1731 |
},
|
1732 |
{
|
1733 |
"data": {
|
1734 |
"application/vnd.jupyter.widget-view+json": {
|
1735 |
-
"model_id": "
|
1736 |
"version_major": 2,
|
1737 |
"version_minor": 0
|
1738 |
},
|
1739 |
"text/plain": [
|
1740 |
-
"Uploading Dataframe: 0.00% | | Rows 0/
|
1741 |
]
|
1742 |
},
|
1743 |
"metadata": {},
|
@@ -1747,15 +1778,15 @@
|
|
1747 |
"name": "stdout",
|
1748 |
"output_type": "stream",
|
1749 |
"text": [
|
1750 |
-
"Launching job:
|
1751 |
"Job started successfully, you can follow the progress at \n",
|
1752 |
-
"https://c.app.hopsworks.ai/p/554133/jobs/named/
|
1753 |
]
|
1754 |
},
|
1755 |
{
|
1756 |
"data": {
|
1757 |
"text/plain": [
|
1758 |
-
"(<hsfs.core.job.Job at
|
1759 |
]
|
1760 |
},
|
1761 |
"execution_count": 27,
|
@@ -1764,8 +1795,8 @@
|
|
1764 |
}
|
1765 |
],
|
1766 |
"source": [
|
1767 |
-
"# Inserting the
|
1768 |
-
"
|
1769 |
]
|
1770 |
},
|
1771 |
{
|
@@ -1781,32 +1812,25 @@
|
|
1781 |
"metadata": {},
|
1782 |
"outputs": [],
|
1783 |
"source": [
|
1784 |
-
"# List of descriptions for
|
1785 |
-
"
|
1786 |
" {\"name\": \"timestamp\", \"description\": \"Timestamp for the event_time\"},\n",
|
1787 |
-
" {\"name\": \"date\", \"description\": \"Date of the
|
1788 |
-
" {\"name\": \"
|
1789 |
-
" {\"name\": \"
|
1790 |
-
" {\"name\": \"
|
1791 |
-
" {\"name\": \"precipitation\", \"description\": \"Precipitation\"},\n",
|
1792 |
-
" {\"name\": \"rain\", \"description\": \"Rain\"},\n",
|
1793 |
-
" {\"name\": \"snowfall\", \"description\": \"Snowfall\"}, \n",
|
1794 |
-
" {\"name\": \"weather_code\", \"description\": \"Weather code\"}, \n",
|
1795 |
-
" {\"name\": \"cloud_cover\", \"description\": \"Cloud cover\"}, \n",
|
1796 |
-
" {\"name\": \"wind_speed_10m\", \"description\": \"Wind speed at 10m above ground\"}, \n",
|
1797 |
-
" {\"name\": \"wind_gusts_10m\", \"description\": \"Wind gusts at 10m above ground\"}, \n",
|
1798 |
"]\n",
|
1799 |
"\n",
|
1800 |
"# Updating feature descriptions\n",
|
1801 |
-
"for desc in
|
1802 |
-
"
|
1803 |
]
|
1804 |
},
|
1805 |
{
|
1806 |
"cell_type": "markdown",
|
1807 |
"metadata": {},
|
1808 |
"source": [
|
1809 |
-
"We replicate the process for both the `
|
1810 |
]
|
1811 |
},
|
1812 |
{
|
@@ -1815,67 +1839,25 @@
|
|
1815 |
"metadata": {},
|
1816 |
"outputs": [],
|
1817 |
"source": [
|
1818 |
-
"# Creating the feature group for the electricity prices\n",
|
1819 |
-
"
|
1820 |
-
"
|
1821 |
-
"
|
1822 |
-
"
|
1823 |
-
"
|
1824 |
-
"
|
1825 |
-
"
|
1826 |
-
")"
|
1827 |
]
|
1828 |
},
|
1829 |
{
|
1830 |
"cell_type": "code",
|
1831 |
"execution_count": 30,
|
1832 |
"metadata": {},
|
1833 |
-
"outputs": [
|
1834 |
-
{
|
1835 |
-
"name": "stdout",
|
1836 |
-
"output_type": "stream",
|
1837 |
-
"text": [
|
1838 |
-
"Feature Group created successfully, explore it at \n",
|
1839 |
-
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/768394\n"
|
1840 |
-
]
|
1841 |
-
},
|
1842 |
-
{
|
1843 |
-
"data": {
|
1844 |
-
"application/vnd.jupyter.widget-view+json": {
|
1845 |
-
"model_id": "a07f970e652943e58fd587eacb087548",
|
1846 |
-
"version_major": 2,
|
1847 |
-
"version_minor": 0
|
1848 |
-
},
|
1849 |
-
"text/plain": [
|
1850 |
-
"Uploading Dataframe: 0.00% | | Rows 0/20421 | Elapsed Time: 00:00 | Remaining Time: ?"
|
1851 |
-
]
|
1852 |
-
},
|
1853 |
-
"metadata": {},
|
1854 |
-
"output_type": "display_data"
|
1855 |
-
},
|
1856 |
-
{
|
1857 |
-
"name": "stdout",
|
1858 |
-
"output_type": "stream",
|
1859 |
-
"text": [
|
1860 |
-
"Launching job: electricity_prices_1_offline_fg_materialization\n",
|
1861 |
-
"Job started successfully, you can follow the progress at \n",
|
1862 |
-
"https://c.app.hopsworks.ai/p/554133/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
|
1863 |
-
]
|
1864 |
-
},
|
1865 |
-
{
|
1866 |
-
"data": {
|
1867 |
-
"text/plain": [
|
1868 |
-
"(<hsfs.core.job.Job at 0x17ef31850>, None)"
|
1869 |
-
]
|
1870 |
-
},
|
1871 |
-
"execution_count": 30,
|
1872 |
-
"metadata": {},
|
1873 |
-
"output_type": "execute_result"
|
1874 |
-
}
|
1875 |
-
],
|
1876 |
"source": [
|
1877 |
-
"# Inserting the electricity_df into the feature group named electricity_fg\n",
|
1878 |
-
"
|
1879 |
]
|
1880 |
},
|
1881 |
{
|
@@ -1884,17 +1866,18 @@
|
|
1884 |
"metadata": {},
|
1885 |
"outputs": [],
|
1886 |
"source": [
|
1887 |
-
"# List of descriptions for
|
1888 |
-
"
|
1889 |
-
"
|
1890 |
-
"
|
1891 |
-
"
|
1892 |
-
"
|
1893 |
-
"
|
|
|
1894 |
"\n",
|
1895 |
-
"# Updating feature descriptions\n",
|
1896 |
-
"for desc in
|
1897 |
-
"
|
1898 |
]
|
1899 |
},
|
1900 |
{
|
@@ -1903,14 +1886,14 @@
|
|
1903 |
"metadata": {},
|
1904 |
"outputs": [],
|
1905 |
"source": [
|
1906 |
-
"# Creating the feature group for the
|
1907 |
-
"
|
1908 |
-
" name=\"
|
1909 |
" version=1,\n",
|
1910 |
-
" description=\"
|
1911 |
-
" primary_key=[\"date\"
|
1912 |
-
" online_enabled=True,\n",
|
1913 |
" event_time=\"timestamp\",\n",
|
|
|
1914 |
")"
|
1915 |
]
|
1916 |
},
|
@@ -1924,18 +1907,18 @@
|
|
1924 |
"output_type": "stream",
|
1925 |
"text": [
|
1926 |
"Feature Group created successfully, explore it at \n",
|
1927 |
-
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/
|
1928 |
]
|
1929 |
},
|
1930 |
{
|
1931 |
"data": {
|
1932 |
"application/vnd.jupyter.widget-view+json": {
|
1933 |
-
"model_id": "
|
1934 |
"version_major": 2,
|
1935 |
"version_minor": 0
|
1936 |
},
|
1937 |
"text/plain": [
|
1938 |
-
"Uploading Dataframe: 0.00% | | Rows 0/
|
1939 |
]
|
1940 |
},
|
1941 |
"metadata": {},
|
@@ -1945,15 +1928,15 @@
|
|
1945 |
"name": "stdout",
|
1946 |
"output_type": "stream",
|
1947 |
"text": [
|
1948 |
-
"Launching job:
|
1949 |
"Job started successfully, you can follow the progress at \n",
|
1950 |
-
"https://c.app.hopsworks.ai/p/554133/jobs/named/
|
1951 |
]
|
1952 |
},
|
1953 |
{
|
1954 |
"data": {
|
1955 |
"text/plain": [
|
1956 |
-
"(<hsfs.core.job.Job at
|
1957 |
]
|
1958 |
},
|
1959 |
"execution_count": 33,
|
@@ -1962,8 +1945,8 @@
|
|
1962 |
}
|
1963 |
],
|
1964 |
"source": [
|
1965 |
-
"# Inserting the
|
1966 |
-
"
|
1967 |
]
|
1968 |
},
|
1969 |
{
|
@@ -1972,30 +1955,39 @@
|
|
1972 |
"metadata": {},
|
1973 |
"outputs": [],
|
1974 |
"source": [
|
1975 |
-
"# List of descriptions for
|
1976 |
-
"
|
1977 |
-
" {\"name\": \"timestamp\", \"description\": \"Timestamp for the
|
1978 |
-
" {\"name\": \"date\", \"description\": \"Date\"},\n",
|
1979 |
-
" {\"name\": \"
|
1980 |
-
" {\"name\": \"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1981 |
"]\n",
|
1982 |
"\n",
|
1983 |
"# Updating feature descriptions\n",
|
1984 |
-
"for desc in
|
1985 |
-
"
|
1986 |
]
|
1987 |
},
|
1988 |
{
|
1989 |
"cell_type": "code",
|
1990 |
-
"execution_count":
|
1991 |
"metadata": {},
|
1992 |
"outputs": [],
|
1993 |
"source": [
|
1994 |
-
"# Creating the feature group for the danish
|
1995 |
-
"
|
1996 |
-
" name=\"
|
1997 |
-
" version=
|
1998 |
-
" description=\"Danish
|
1999 |
" online_enabled=True,\n",
|
2000 |
" primary_key=[\"date\"],\n",
|
2001 |
")"
|
@@ -2003,7 +1995,7 @@
|
|
2003 |
},
|
2004 |
{
|
2005 |
"cell_type": "code",
|
2006 |
-
"execution_count":
|
2007 |
"metadata": {},
|
2008 |
"outputs": [
|
2009 |
{
|
@@ -2011,13 +2003,13 @@
|
|
2011 |
"output_type": "stream",
|
2012 |
"text": [
|
2013 |
"Feature Group created successfully, explore it at \n",
|
2014 |
-
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/
|
2015 |
]
|
2016 |
},
|
2017 |
{
|
2018 |
"data": {
|
2019 |
"application/vnd.jupyter.widget-view+json": {
|
2020 |
-
"model_id": "
|
2021 |
"version_major": 2,
|
2022 |
"version_minor": 0
|
2023 |
},
|
@@ -2032,42 +2024,44 @@
|
|
2032 |
"name": "stdout",
|
2033 |
"output_type": "stream",
|
2034 |
"text": [
|
2035 |
-
"Launching job:
|
2036 |
"Job started successfully, you can follow the progress at \n",
|
2037 |
-
"https://c.app.hopsworks.ai/p/554133/jobs/named/
|
2038 |
]
|
2039 |
},
|
2040 |
{
|
2041 |
"data": {
|
2042 |
"text/plain": [
|
2043 |
-
"(<hsfs.core.job.Job at
|
2044 |
]
|
2045 |
},
|
2046 |
-
"execution_count":
|
2047 |
"metadata": {},
|
2048 |
"output_type": "execute_result"
|
2049 |
}
|
2050 |
],
|
2051 |
"source": [
|
2052 |
-
"# Inserting the calender_df into the feature group named
|
2053 |
-
"
|
2054 |
]
|
2055 |
},
|
2056 |
{
|
2057 |
"cell_type": "code",
|
2058 |
-
"execution_count":
|
2059 |
"metadata": {},
|
2060 |
"outputs": [],
|
2061 |
"source": [
|
2062 |
-
"# List of descriptions for
|
2063 |
-
"
|
2064 |
" {\"name\": \"date\", \"description\": \"Date in the calendar\"},\n",
|
2065 |
-
" {\"name\": \"
|
|
|
|
|
2066 |
"]\n",
|
2067 |
"\n",
|
2068 |
"# Updating feature descriptions\n",
|
2069 |
-
"for desc in
|
2070 |
-
"
|
2071 |
]
|
2072 |
},
|
2073 |
{
|
|
|
56 |
"\n",
|
57 |
"# Now we import the functions from the features folder\n",
|
58 |
"# This is the functions we have created to generate features for electricity prices and weather measures\n",
|
59 |
+
"from features import electricity_prices, weather_measures, calendar\n",
|
60 |
"\n",
|
61 |
"# We go back into the notebooks folder\n",
|
62 |
"%cd notebooks"
|
|
|
70 |
"source": [
|
71 |
"# Importing the packages for the needed libraries for the Jupyter notebook\n",
|
72 |
"import pandas as pd\n",
|
73 |
+
"import numpy as np\n",
|
74 |
"import requests\n",
|
75 |
"from datetime import datetime, timedelta\n",
|
76 |
"\n",
|
|
|
147 |
" <tr style=\"text-align: right;\">\n",
|
148 |
" <th></th>\n",
|
149 |
" <th>timestamp</th>\n",
|
150 |
+
" <th>datetime</th>\n",
|
151 |
" <th>date</th>\n",
|
152 |
+
" <th>hour</th>\n",
|
153 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
154 |
" </tr>\n",
|
155 |
" </thead>\n",
|
|
|
159 |
" <td>1640995200000</td>\n",
|
160 |
" <td>2022-01-01 00:00:00</td>\n",
|
161 |
" <td>2022-01-01</td>\n",
|
162 |
+
" <td>0</td>\n",
|
163 |
" <td>0.37220</td>\n",
|
164 |
" </tr>\n",
|
165 |
" <tr>\n",
|
|
|
167 |
" <td>1640998800000</td>\n",
|
168 |
" <td>2022-01-01 01:00:00</td>\n",
|
169 |
" <td>2022-01-01</td>\n",
|
170 |
+
" <td>1</td>\n",
|
171 |
" <td>0.30735</td>\n",
|
172 |
" </tr>\n",
|
173 |
" <tr>\n",
|
|
|
175 |
" <td>1641002400000</td>\n",
|
176 |
" <td>2022-01-01 02:00:00</td>\n",
|
177 |
" <td>2022-01-01</td>\n",
|
178 |
+
" <td>2</td>\n",
|
179 |
" <td>0.32141</td>\n",
|
180 |
" </tr>\n",
|
181 |
" <tr>\n",
|
|
|
183 |
" <td>1641006000000</td>\n",
|
184 |
" <td>2022-01-01 03:00:00</td>\n",
|
185 |
" <td>2022-01-01</td>\n",
|
186 |
+
" <td>3</td>\n",
|
187 |
" <td>0.33806</td>\n",
|
188 |
" </tr>\n",
|
189 |
" <tr>\n",
|
|
|
191 |
" <td>1641009600000</td>\n",
|
192 |
" <td>2022-01-01 04:00:00</td>\n",
|
193 |
" <td>2022-01-01</td>\n",
|
194 |
+
" <td>4</td>\n",
|
195 |
" <td>0.28013</td>\n",
|
196 |
" </tr>\n",
|
197 |
" </tbody>\n",
|
|
|
199 |
"</div>"
|
200 |
],
|
201 |
"text/plain": [
|
202 |
+
" timestamp datetime date hour dk1_spotpricedkk_kwh\n",
|
203 |
+
"0 1640995200000 2022-01-01 00:00:00 2022-01-01 0 0.37220\n",
|
204 |
+
"1 1640998800000 2022-01-01 01:00:00 2022-01-01 1 0.30735\n",
|
205 |
+
"2 1641002400000 2022-01-01 02:00:00 2022-01-01 2 0.32141\n",
|
206 |
+
"3 1641006000000 2022-01-01 03:00:00 2022-01-01 3 0.33806\n",
|
207 |
+
"4 1641009600000 2022-01-01 04:00:00 2022-01-01 4 0.28013"
|
208 |
]
|
209 |
},
|
210 |
"execution_count": 5,
|
|
|
244 |
" <tr style=\"text-align: right;\">\n",
|
245 |
" <th></th>\n",
|
246 |
" <th>timestamp</th>\n",
|
247 |
+
" <th>datetime</th>\n",
|
248 |
" <th>date</th>\n",
|
249 |
+
" <th>hour</th>\n",
|
250 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
251 |
" </tr>\n",
|
252 |
" </thead>\n",
|
253 |
" <tbody>\n",
|
254 |
" <tr>\n",
|
255 |
+
" <th>20440</th>\n",
|
256 |
+
" <td>1714590000000</td>\n",
|
257 |
+
" <td>2024-05-01 19:00:00</td>\n",
|
258 |
+
" <td>2024-05-01</td>\n",
|
259 |
+
" <td>19</td>\n",
|
260 |
+
" <td>0.37590</td>\n",
|
261 |
" </tr>\n",
|
262 |
" <tr>\n",
|
263 |
+
" <th>20441</th>\n",
|
264 |
+
" <td>1714593600000</td>\n",
|
265 |
+
" <td>2024-05-01 20:00:00</td>\n",
|
266 |
+
" <td>2024-05-01</td>\n",
|
267 |
+
" <td>20</td>\n",
|
268 |
+
" <td>0.37292</td>\n",
|
269 |
" </tr>\n",
|
270 |
" <tr>\n",
|
271 |
+
" <th>20442</th>\n",
|
272 |
+
" <td>1714597200000</td>\n",
|
273 |
+
" <td>2024-05-01 21:00:00</td>\n",
|
274 |
+
" <td>2024-05-01</td>\n",
|
275 |
+
" <td>21</td>\n",
|
276 |
+
" <td>0.25366</td>\n",
|
277 |
" </tr>\n",
|
278 |
" <tr>\n",
|
279 |
+
" <th>20443</th>\n",
|
280 |
+
" <td>1714600800000</td>\n",
|
281 |
+
" <td>2024-05-01 22:00:00</td>\n",
|
282 |
+
" <td>2024-05-01</td>\n",
|
283 |
+
" <td>22</td>\n",
|
284 |
+
" <td>0.22315</td>\n",
|
285 |
" </tr>\n",
|
286 |
" <tr>\n",
|
287 |
+
" <th>20444</th>\n",
|
288 |
+
" <td>1714604400000</td>\n",
|
289 |
+
" <td>2024-05-01 23:00:00</td>\n",
|
290 |
+
" <td>2024-05-01</td>\n",
|
291 |
+
" <td>23</td>\n",
|
292 |
+
" <td>0.16408</td>\n",
|
293 |
" </tr>\n",
|
294 |
" </tbody>\n",
|
295 |
"</table>\n",
|
296 |
"</div>"
|
297 |
],
|
298 |
"text/plain": [
|
299 |
+
" timestamp datetime date hour \\\n",
|
300 |
+
"20440 1714590000000 2024-05-01 19:00:00 2024-05-01 19 \n",
|
301 |
+
"20441 1714593600000 2024-05-01 20:00:00 2024-05-01 20 \n",
|
302 |
+
"20442 1714597200000 2024-05-01 21:00:00 2024-05-01 21 \n",
|
303 |
+
"20443 1714600800000 2024-05-01 22:00:00 2024-05-01 22 \n",
|
304 |
+
"20444 1714604400000 2024-05-01 23:00:00 2024-05-01 23 \n",
|
305 |
+
"\n",
|
306 |
+
" dk1_spotpricedkk_kwh \n",
|
307 |
+
"20440 0.37590 \n",
|
308 |
+
"20441 0.37292 \n",
|
309 |
+
"20442 0.25366 \n",
|
310 |
+
"20443 0.22315 \n",
|
311 |
+
"20444 0.16408 "
|
312 |
]
|
313 |
},
|
314 |
"execution_count": 6,
|
|
|
331 |
"output_type": "stream",
|
332 |
"text": [
|
333 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
334 |
+
"RangeIndex: 20445 entries, 0 to 20444\n",
|
335 |
+
"Data columns (total 5 columns):\n",
|
336 |
" # Column Non-Null Count Dtype \n",
|
337 |
"--- ------ -------------- ----- \n",
|
338 |
+
" 0 timestamp 20445 non-null int64 \n",
|
339 |
+
" 1 datetime 20445 non-null datetime64[ns]\n",
|
340 |
+
" 2 date 20445 non-null object \n",
|
341 |
+
" 3 hour 20445 non-null int64 \n",
|
342 |
+
" 4 dk1_spotpricedkk_kwh 20445 non-null float64 \n",
|
343 |
+
"dtypes: datetime64[ns](1), float64(1), int64(2), object(1)\n",
|
344 |
+
"memory usage: 798.8+ KB\n"
|
345 |
]
|
346 |
}
|
347 |
],
|
|
|
402 |
" <tr style=\"text-align: right;\">\n",
|
403 |
" <th></th>\n",
|
404 |
" <th>timestamp</th>\n",
|
405 |
+
" <th>datetime</th>\n",
|
406 |
" <th>date</th>\n",
|
407 |
+
" <th>hour</th>\n",
|
408 |
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
409 |
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
410 |
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
|
|
416 |
" <td>1641024000000</td>\n",
|
417 |
" <td>2022-01-01 08:00:00</td>\n",
|
418 |
" <td>2022-01-01</td>\n",
|
419 |
+
" <td>8</td>\n",
|
420 |
" <td>0.611708</td>\n",
|
421 |
" <td>0.236792</td>\n",
|
422 |
" <td>0.000050</td>\n",
|
|
|
426 |
" <td>1641027600000</td>\n",
|
427 |
" <td>2022-01-01 09:00:00</td>\n",
|
428 |
" <td>2022-01-01</td>\n",
|
429 |
+
" <td>9</td>\n",
|
430 |
" <td>0.459708</td>\n",
|
431 |
" <td>0.196667</td>\n",
|
432 |
" <td>0.004841</td>\n",
|
|
|
436 |
" <td>1641031200000</td>\n",
|
437 |
" <td>2022-01-01 10:00:00</td>\n",
|
438 |
" <td>2022-01-01</td>\n",
|
439 |
+
" <td>10</td>\n",
|
440 |
" <td>0.310375</td>\n",
|
441 |
" <td>0.178500</td>\n",
|
442 |
" <td>0.020353</td>\n",
|
|
|
446 |
" <td>1641034800000</td>\n",
|
447 |
" <td>2022-01-01 11:00:00</td>\n",
|
448 |
" <td>2022-01-01</td>\n",
|
449 |
+
" <td>11</td>\n",
|
450 |
" <td>0.320750</td>\n",
|
451 |
" <td>0.201125</td>\n",
|
452 |
" <td>0.035719</td>\n",
|
|
|
456 |
" <td>1641038400000</td>\n",
|
457 |
" <td>2022-01-01 12:00:00</td>\n",
|
458 |
" <td>2022-01-01</td>\n",
|
459 |
+
" <td>12</td>\n",
|
460 |
" <td>0.355667</td>\n",
|
461 |
" <td>0.277667</td>\n",
|
462 |
" <td>0.038027</td>\n",
|
|
|
466 |
"</div>"
|
467 |
],
|
468 |
"text/plain": [
|
469 |
+
" timestamp datetime date hour \\\n",
|
470 |
+
"0 1641024000000 2022-01-01 08:00:00 2022-01-01 8 \n",
|
471 |
+
"1 1641027600000 2022-01-01 09:00:00 2022-01-01 9 \n",
|
472 |
+
"2 1641031200000 2022-01-01 10:00:00 2022-01-01 10 \n",
|
473 |
+
"3 1641034800000 2022-01-01 11:00:00 2022-01-01 11 \n",
|
474 |
+
"4 1641038400000 2022-01-01 12:00:00 2022-01-01 12 \n",
|
475 |
"\n",
|
476 |
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
477 |
"0 0.611708 \n",
|
|
|
525 |
" <tr style=\"text-align: right;\">\n",
|
526 |
" <th></th>\n",
|
527 |
" <th>timestamp</th>\n",
|
528 |
+
" <th>datetime</th>\n",
|
529 |
" <th>date</th>\n",
|
530 |
+
" <th>hour</th>\n",
|
531 |
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
532 |
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
533 |
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
|
|
535 |
" </thead>\n",
|
536 |
" <tbody>\n",
|
537 |
" <tr>\n",
|
538 |
+
" <th>14426</th>\n",
|
539 |
+
" <td>1714590000000</td>\n",
|
540 |
+
" <td>2024-05-01 19:00:00</td>\n",
|
541 |
+
" <td>2024-05-01</td>\n",
|
542 |
+
" <td>19</td>\n",
|
543 |
+
" <td>0.816250</td>\n",
|
544 |
+
" <td>1.382208</td>\n",
|
545 |
+
" <td>0.272911</td>\n",
|
546 |
" </tr>\n",
|
547 |
" <tr>\n",
|
548 |
+
" <th>14427</th>\n",
|
549 |
+
" <td>1714593600000</td>\n",
|
550 |
+
" <td>2024-05-01 20:00:00</td>\n",
|
551 |
+
" <td>2024-05-01</td>\n",
|
552 |
+
" <td>20</td>\n",
|
553 |
+
" <td>0.848500</td>\n",
|
554 |
+
" <td>1.388583</td>\n",
|
555 |
+
" <td>0.046087</td>\n",
|
556 |
" </tr>\n",
|
557 |
" <tr>\n",
|
558 |
+
" <th>14428</th>\n",
|
559 |
+
" <td>1714597200000</td>\n",
|
560 |
+
" <td>2024-05-01 21:00:00</td>\n",
|
561 |
+
" <td>2024-05-01</td>\n",
|
562 |
+
" <td>21</td>\n",
|
563 |
+
" <td>0.886042</td>\n",
|
564 |
+
" <td>1.554792</td>\n",
|
565 |
+
" <td>0.001339</td>\n",
|
566 |
" </tr>\n",
|
567 |
" <tr>\n",
|
568 |
+
" <th>14429</th>\n",
|
569 |
+
" <td>1714600800000</td>\n",
|
570 |
+
" <td>2024-05-01 22:00:00</td>\n",
|
571 |
+
" <td>2024-05-01</td>\n",
|
572 |
+
" <td>22</td>\n",
|
573 |
+
" <td>0.919417</td>\n",
|
574 |
+
" <td>1.698875</td>\n",
|
575 |
" <td>0.000000</td>\n",
|
576 |
" </tr>\n",
|
577 |
" <tr>\n",
|
578 |
+
" <th>14430</th>\n",
|
579 |
+
" <td>1714604400000</td>\n",
|
580 |
+
" <td>2024-05-01 23:00:00</td>\n",
|
581 |
+
" <td>2024-05-01</td>\n",
|
582 |
+
" <td>23</td>\n",
|
583 |
+
" <td>0.934708</td>\n",
|
584 |
+
" <td>1.739375</td>\n",
|
585 |
" <td>0.000000</td>\n",
|
586 |
" </tr>\n",
|
587 |
" </tbody>\n",
|
|
|
589 |
"</div>"
|
590 |
],
|
591 |
"text/plain": [
|
592 |
+
" timestamp datetime date hour \\\n",
|
593 |
+
"14426 1714590000000 2024-05-01 19:00:00 2024-05-01 19 \n",
|
594 |
+
"14427 1714593600000 2024-05-01 20:00:00 2024-05-01 20 \n",
|
595 |
+
"14428 1714597200000 2024-05-01 21:00:00 2024-05-01 21 \n",
|
596 |
+
"14429 1714600800000 2024-05-01 22:00:00 2024-05-01 22 \n",
|
597 |
+
"14430 1714604400000 2024-05-01 23:00:00 2024-05-01 23 \n",
|
598 |
"\n",
|
599 |
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
600 |
+
"14426 0.816250 \n",
|
601 |
+
"14427 0.848500 \n",
|
602 |
+
"14428 0.886042 \n",
|
603 |
+
"14429 0.919417 \n",
|
604 |
+
"14430 0.934708 \n",
|
605 |
"\n",
|
606 |
" dk1_onshore_wind_forecastintraday_kwh dk1_solar_forecastintraday_kwh \n",
|
607 |
+
"14426 1.382208 0.272911 \n",
|
608 |
+
"14427 1.388583 0.046087 \n",
|
609 |
+
"14428 1.554792 0.001339 \n",
|
610 |
+
"14429 1.698875 0.000000 \n",
|
611 |
+
"14430 1.739375 0.000000 "
|
612 |
]
|
613 |
},
|
614 |
"execution_count": 10,
|
|
|
631 |
"output_type": "stream",
|
632 |
"text": [
|
633 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
634 |
+
"RangeIndex: 14431 entries, 0 to 14430\n",
|
635 |
+
"Data columns (total 7 columns):\n",
|
636 |
" # Column Non-Null Count Dtype \n",
|
637 |
"--- ------ -------------- ----- \n",
|
638 |
+
" 0 timestamp 14431 non-null int64 \n",
|
639 |
+
" 1 datetime 14431 non-null datetime64[ns]\n",
|
640 |
+
" 2 date 14431 non-null object \n",
|
641 |
+
" 3 hour 14431 non-null int64 \n",
|
642 |
+
" 4 dk1_offshore_wind_forecastintraday_kwh 14415 non-null float64 \n",
|
643 |
+
" 5 dk1_onshore_wind_forecastintraday_kwh 14415 non-null float64 \n",
|
644 |
+
" 6 dk1_solar_forecastintraday_kwh 14415 non-null float64 \n",
|
645 |
+
"dtypes: datetime64[ns](1), float64(3), int64(2), object(1)\n",
|
646 |
+
"memory usage: 789.3+ KB\n"
|
647 |
]
|
648 |
}
|
649 |
],
|
|
|
710 |
" <tr style=\"text-align: right;\">\n",
|
711 |
" <th></th>\n",
|
712 |
" <th>timestamp</th>\n",
|
713 |
+
" <th>datetime</th>\n",
|
714 |
" <th>date</th>\n",
|
715 |
+
" <th>hour</th>\n",
|
716 |
" <th>temperature_2m</th>\n",
|
717 |
" <th>relative_humidity_2m</th>\n",
|
718 |
" <th>precipitation</th>\n",
|
|
|
728 |
" <tr>\n",
|
729 |
" <th>0</th>\n",
|
730 |
" <td>1640995200000</td>\n",
|
|
|
731 |
" <td>2022-01-01 00:00:00</td>\n",
|
732 |
+
" <td>2022-01-01</td>\n",
|
733 |
+
" <td>0</td>\n",
|
734 |
" <td>6.7</td>\n",
|
735 |
" <td>100.0</td>\n",
|
736 |
" <td>0.0</td>\n",
|
|
|
744 |
" <tr>\n",
|
745 |
" <th>1</th>\n",
|
746 |
" <td>1640998800000</td>\n",
|
|
|
747 |
" <td>2022-01-01 01:00:00</td>\n",
|
748 |
+
" <td>2022-01-01</td>\n",
|
749 |
+
" <td>1</td>\n",
|
750 |
" <td>6.6</td>\n",
|
751 |
" <td>100.0</td>\n",
|
752 |
" <td>0.0</td>\n",
|
|
|
760 |
" <tr>\n",
|
761 |
" <th>2</th>\n",
|
762 |
" <td>1641002400000</td>\n",
|
|
|
763 |
" <td>2022-01-01 02:00:00</td>\n",
|
764 |
+
" <td>2022-01-01</td>\n",
|
765 |
+
" <td>2</td>\n",
|
766 |
" <td>6.7</td>\n",
|
767 |
" <td>99.0</td>\n",
|
768 |
" <td>0.0</td>\n",
|
|
|
776 |
" <tr>\n",
|
777 |
" <th>3</th>\n",
|
778 |
" <td>1641006000000</td>\n",
|
|
|
779 |
" <td>2022-01-01 03:00:00</td>\n",
|
780 |
+
" <td>2022-01-01</td>\n",
|
781 |
+
" <td>3</td>\n",
|
782 |
" <td>6.7</td>\n",
|
783 |
" <td>100.0</td>\n",
|
784 |
" <td>0.0</td>\n",
|
|
|
792 |
" <tr>\n",
|
793 |
" <th>4</th>\n",
|
794 |
" <td>1641009600000</td>\n",
|
|
|
795 |
" <td>2022-01-01 04:00:00</td>\n",
|
796 |
+
" <td>2022-01-01</td>\n",
|
797 |
+
" <td>4</td>\n",
|
798 |
" <td>6.7</td>\n",
|
799 |
" <td>99.0</td>\n",
|
800 |
" <td>0.0</td>\n",
|
|
|
810 |
"</div>"
|
811 |
],
|
812 |
"text/plain": [
|
813 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
814 |
+
"0 1640995200000 2022-01-01 00:00:00 2022-01-01 0 6.7 \n",
|
815 |
+
"1 1640998800000 2022-01-01 01:00:00 2022-01-01 1 6.6 \n",
|
816 |
+
"2 1641002400000 2022-01-01 02:00:00 2022-01-01 2 6.7 \n",
|
817 |
+
"3 1641006000000 2022-01-01 03:00:00 2022-01-01 3 6.7 \n",
|
818 |
+
"4 1641009600000 2022-01-01 04:00:00 2022-01-01 4 6.7 \n",
|
819 |
"\n",
|
820 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
821 |
"0 100.0 0.0 0.0 0.0 3.0 \n",
|
|
|
869 |
" <tr style=\"text-align: right;\">\n",
|
870 |
" <th></th>\n",
|
871 |
" <th>timestamp</th>\n",
|
872 |
+
" <th>datetime</th>\n",
|
873 |
" <th>date</th>\n",
|
874 |
+
" <th>hour</th>\n",
|
875 |
" <th>temperature_2m</th>\n",
|
876 |
" <th>relative_humidity_2m</th>\n",
|
877 |
" <th>precipitation</th>\n",
|
|
|
885 |
" </thead>\n",
|
886 |
" <tbody>\n",
|
887 |
" <tr>\n",
|
888 |
+
" <th>20419</th>\n",
|
889 |
+
" <td>1714503600000</td>\n",
|
890 |
+
" <td>2024-04-30 19:00:00</td>\n",
|
891 |
+
" <td>2024-04-30</td>\n",
|
892 |
+
" <td>19</td>\n",
|
893 |
+
" <td>13.8</td>\n",
|
894 |
+
" <td>64.0</td>\n",
|
895 |
" <td>0.0</td>\n",
|
896 |
" <td>0.0</td>\n",
|
897 |
" <td>0.0</td>\n",
|
898 |
" <td>0.0</td>\n",
|
899 |
+
" <td>6.0</td>\n",
|
900 |
+
" <td>15.3</td>\n",
|
901 |
+
" <td>26.3</td>\n",
|
902 |
" </tr>\n",
|
903 |
" <tr>\n",
|
904 |
+
" <th>20420</th>\n",
|
905 |
+
" <td>1714507200000</td>\n",
|
906 |
+
" <td>2024-04-30 20:00:00</td>\n",
|
907 |
+
" <td>2024-04-30</td>\n",
|
908 |
+
" <td>20</td>\n",
|
909 |
+
" <td>13.5</td>\n",
|
910 |
+
" <td>66.0</td>\n",
|
911 |
" <td>0.0</td>\n",
|
912 |
" <td>0.0</td>\n",
|
913 |
" <td>0.0</td>\n",
|
914 |
" <td>0.0</td>\n",
|
915 |
+
" <td>2.0</td>\n",
|
916 |
+
" <td>18.7</td>\n",
|
917 |
+
" <td>32.8</td>\n",
|
918 |
" </tr>\n",
|
919 |
" <tr>\n",
|
920 |
+
" <th>20421</th>\n",
|
921 |
+
" <td>1714510800000</td>\n",
|
922 |
+
" <td>2024-04-30 21:00:00</td>\n",
|
923 |
+
" <td>2024-04-30</td>\n",
|
924 |
+
" <td>21</td>\n",
|
925 |
+
" <td>13.4</td>\n",
|
926 |
+
" <td>67.0</td>\n",
|
927 |
" <td>0.0</td>\n",
|
928 |
" <td>0.0</td>\n",
|
929 |
" <td>0.0</td>\n",
|
930 |
" <td>0.0</td>\n",
|
931 |
+
" <td>13.0</td>\n",
|
932 |
+
" <td>21.1</td>\n",
|
933 |
+
" <td>38.2</td>\n",
|
934 |
" </tr>\n",
|
935 |
" <tr>\n",
|
936 |
+
" <th>20422</th>\n",
|
937 |
+
" <td>1714514400000</td>\n",
|
938 |
+
" <td>2024-04-30 22:00:00</td>\n",
|
939 |
+
" <td>2024-04-30</td>\n",
|
940 |
+
" <td>22</td>\n",
|
941 |
+
" <td>12.8</td>\n",
|
942 |
+
" <td>67.0</td>\n",
|
943 |
" <td>0.0</td>\n",
|
944 |
" <td>0.0</td>\n",
|
945 |
" <td>0.0</td>\n",
|
946 |
" <td>0.0</td>\n",
|
947 |
+
" <td>9.0</td>\n",
|
948 |
+
" <td>21.0</td>\n",
|
949 |
+
" <td>38.5</td>\n",
|
950 |
" </tr>\n",
|
951 |
" <tr>\n",
|
952 |
+
" <th>20423</th>\n",
|
953 |
+
" <td>1714518000000</td>\n",
|
954 |
+
" <td>2024-04-30 23:00:00</td>\n",
|
955 |
+
" <td>2024-04-30</td>\n",
|
956 |
+
" <td>23</td>\n",
|
957 |
+
" <td>12.0</td>\n",
|
958 |
+
" <td>70.0</td>\n",
|
959 |
" <td>0.0</td>\n",
|
960 |
" <td>0.0</td>\n",
|
961 |
" <td>0.0</td>\n",
|
962 |
" <td>0.0</td>\n",
|
963 |
+
" <td>18.0</td>\n",
|
964 |
+
" <td>20.7</td>\n",
|
965 |
+
" <td>38.5</td>\n",
|
966 |
" </tr>\n",
|
967 |
" </tbody>\n",
|
968 |
"</table>\n",
|
969 |
"</div>"
|
970 |
],
|
971 |
"text/plain": [
|
972 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
973 |
+
"20419 1714503600000 2024-04-30 19:00:00 2024-04-30 19 13.8 \n",
|
974 |
+
"20420 1714507200000 2024-04-30 20:00:00 2024-04-30 20 13.5 \n",
|
975 |
+
"20421 1714510800000 2024-04-30 21:00:00 2024-04-30 21 13.4 \n",
|
976 |
+
"20422 1714514400000 2024-04-30 22:00:00 2024-04-30 22 12.8 \n",
|
977 |
+
"20423 1714518000000 2024-04-30 23:00:00 2024-04-30 23 12.0 \n",
|
978 |
"\n",
|
979 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
980 |
+
"20419 64.0 0.0 0.0 0.0 0.0 \n",
|
981 |
+
"20420 66.0 0.0 0.0 0.0 0.0 \n",
|
982 |
+
"20421 67.0 0.0 0.0 0.0 0.0 \n",
|
983 |
+
"20422 67.0 0.0 0.0 0.0 0.0 \n",
|
984 |
+
"20423 70.0 0.0 0.0 0.0 0.0 \n",
|
985 |
"\n",
|
986 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
987 |
+
"20419 6.0 15.3 26.3 \n",
|
988 |
+
"20420 2.0 18.7 32.8 \n",
|
989 |
+
"20421 13.0 21.1 38.2 \n",
|
990 |
+
"20422 9.0 21.0 38.5 \n",
|
991 |
+
"20423 18.0 20.7 38.5 "
|
992 |
]
|
993 |
},
|
994 |
"execution_count": 14,
|
|
|
1011 |
"output_type": "stream",
|
1012 |
"text": [
|
1013 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
1014 |
+
"Int64Index: 20424 entries, 0 to 20423\n",
|
1015 |
+
"Data columns (total 13 columns):\n",
|
1016 |
" # Column Non-Null Count Dtype \n",
|
1017 |
"--- ------ -------------- ----- \n",
|
1018 |
+
" 0 timestamp 20424 non-null int64 \n",
|
1019 |
+
" 1 datetime 20424 non-null datetime64[ns]\n",
|
1020 |
+
" 2 date 20424 non-null object \n",
|
1021 |
+
" 3 hour 20424 non-null int64 \n",
|
1022 |
+
" 4 temperature_2m 20424 non-null float64 \n",
|
1023 |
+
" 5 relative_humidity_2m 20424 non-null float64 \n",
|
1024 |
+
" 6 precipitation 20424 non-null float64 \n",
|
1025 |
+
" 7 rain 20424 non-null float64 \n",
|
1026 |
+
" 8 snowfall 20424 non-null float64 \n",
|
1027 |
+
" 9 weather_code 20424 non-null float64 \n",
|
1028 |
+
" 10 cloud_cover 20424 non-null float64 \n",
|
1029 |
+
" 11 wind_speed_10m 20424 non-null float64 \n",
|
1030 |
+
" 12 wind_gusts_10m 20424 non-null float64 \n",
|
1031 |
+
"dtypes: datetime64[ns](1), float64(9), int64(2), object(1)\n",
|
1032 |
+
"memory usage: 2.2+ MB\n"
|
1033 |
]
|
1034 |
}
|
1035 |
],
|
|
|
1085 |
" <tr style=\"text-align: right;\">\n",
|
1086 |
" <th></th>\n",
|
1087 |
" <th>timestamp</th>\n",
|
1088 |
+
" <th>datetime</th>\n",
|
1089 |
" <th>date</th>\n",
|
1090 |
+
" <th>hour</th>\n",
|
1091 |
" <th>temperature_2m</th>\n",
|
1092 |
" <th>relative_humidity_2m</th>\n",
|
1093 |
" <th>precipitation</th>\n",
|
|
|
1102 |
" <tbody>\n",
|
1103 |
" <tr>\n",
|
1104 |
" <th>0</th>\n",
|
1105 |
+
" <td>1714608000000</td>\n",
|
1106 |
+
" <td>2024-05-02 00:00:00</td>\n",
|
1107 |
+
" <td>2024-05-02</td>\n",
|
1108 |
+
" <td>0</td>\n",
|
1109 |
+
" <td>14.9</td>\n",
|
1110 |
+
" <td>66.0</td>\n",
|
1111 |
" <td>0.0</td>\n",
|
1112 |
" <td>0.0</td>\n",
|
1113 |
" <td>0.0</td>\n",
|
1114 |
+
" <td>0.0</td>\n",
|
1115 |
+
" <td>13.0</td>\n",
|
1116 |
+
" <td>21.6</td>\n",
|
1117 |
+
" <td>41.4</td>\n",
|
1118 |
" </tr>\n",
|
1119 |
" <tr>\n",
|
1120 |
" <th>1</th>\n",
|
1121 |
+
" <td>1714611600000</td>\n",
|
1122 |
+
" <td>2024-05-02 01:00:00</td>\n",
|
1123 |
+
" <td>2024-05-02</td>\n",
|
1124 |
+
" <td>1</td>\n",
|
1125 |
+
" <td>14.2</td>\n",
|
1126 |
+
" <td>71.0</td>\n",
|
1127 |
" <td>0.0</td>\n",
|
1128 |
" <td>0.0</td>\n",
|
1129 |
" <td>0.0</td>\n",
|
1130 |
+
" <td>0.0</td>\n",
|
1131 |
+
" <td>4.0</td>\n",
|
1132 |
+
" <td>20.5</td>\n",
|
1133 |
+
" <td>37.1</td>\n",
|
1134 |
" </tr>\n",
|
1135 |
" <tr>\n",
|
1136 |
" <th>2</th>\n",
|
1137 |
+
" <td>1714615200000</td>\n",
|
1138 |
+
" <td>2024-05-02 02:00:00</td>\n",
|
1139 |
+
" <td>2024-05-02</td>\n",
|
1140 |
+
" <td>2</td>\n",
|
1141 |
+
" <td>13.4</td>\n",
|
1142 |
+
" <td>73.0</td>\n",
|
1143 |
" <td>0.0</td>\n",
|
1144 |
" <td>0.0</td>\n",
|
1145 |
" <td>0.0</td>\n",
|
1146 |
+
" <td>2.0</td>\n",
|
1147 |
+
" <td>70.0</td>\n",
|
1148 |
+
" <td>21.2</td>\n",
|
1149 |
+
" <td>36.7</td>\n",
|
1150 |
" </tr>\n",
|
1151 |
" <tr>\n",
|
1152 |
" <th>3</th>\n",
|
1153 |
+
" <td>1714618800000</td>\n",
|
1154 |
+
" <td>2024-05-02 03:00:00</td>\n",
|
1155 |
+
" <td>2024-05-02</td>\n",
|
|
|
|
|
|
|
|
|
|
|
1156 |
" <td>3</td>\n",
|
1157 |
+
" <td>13.2</td>\n",
|
1158 |
+
" <td>72.0</td>\n",
|
1159 |
+
" <td>0.1</td>\n",
|
1160 |
+
" <td>0.1</td>\n",
|
1161 |
+
" <td>0.0</td>\n",
|
1162 |
+
" <td>51.0</td>\n",
|
1163 |
+
" <td>51.0</td>\n",
|
1164 |
+
" <td>22.3</td>\n",
|
1165 |
+
" <td>39.2</td>\n",
|
1166 |
" </tr>\n",
|
1167 |
" <tr>\n",
|
1168 |
" <th>4</th>\n",
|
1169 |
+
" <td>1714622400000</td>\n",
|
1170 |
+
" <td>2024-05-02 04:00:00</td>\n",
|
1171 |
+
" <td>2024-05-02</td>\n",
|
1172 |
+
" <td>4</td>\n",
|
1173 |
+
" <td>12.7</td>\n",
|
1174 |
+
" <td>73.0</td>\n",
|
1175 |
" <td>0.0</td>\n",
|
1176 |
" <td>0.0</td>\n",
|
1177 |
" <td>0.0</td>\n",
|
1178 |
+
" <td>2.0</td>\n",
|
1179 |
+
" <td>78.0</td>\n",
|
1180 |
+
" <td>21.6</td>\n",
|
1181 |
+
" <td>38.9</td>\n",
|
1182 |
" </tr>\n",
|
1183 |
" </tbody>\n",
|
1184 |
"</table>\n",
|
1185 |
"</div>"
|
1186 |
],
|
1187 |
"text/plain": [
|
1188 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
1189 |
+
"0 1714608000000 2024-05-02 00:00:00 2024-05-02 0 14.9 \n",
|
1190 |
+
"1 1714611600000 2024-05-02 01:00:00 2024-05-02 1 14.2 \n",
|
1191 |
+
"2 1714615200000 2024-05-02 02:00:00 2024-05-02 2 13.4 \n",
|
1192 |
+
"3 1714618800000 2024-05-02 03:00:00 2024-05-02 3 13.2 \n",
|
1193 |
+
"4 1714622400000 2024-05-02 04:00:00 2024-05-02 4 12.7 \n",
|
1194 |
"\n",
|
1195 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1196 |
+
"0 66.0 0.0 0.0 0.0 0.0 \n",
|
1197 |
+
"1 71.0 0.0 0.0 0.0 0.0 \n",
|
1198 |
+
"2 73.0 0.0 0.0 0.0 2.0 \n",
|
1199 |
+
"3 72.0 0.1 0.1 0.0 51.0 \n",
|
1200 |
+
"4 73.0 0.0 0.0 0.0 2.0 \n",
|
1201 |
"\n",
|
1202 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1203 |
+
"0 13.0 21.6 41.4 \n",
|
1204 |
+
"1 4.0 20.5 37.1 \n",
|
1205 |
+
"2 70.0 21.2 36.7 \n",
|
1206 |
+
"3 51.0 22.3 39.2 \n",
|
1207 |
+
"4 78.0 21.6 38.9 "
|
1208 |
]
|
1209 |
},
|
1210 |
"execution_count": 17,
|
|
|
1244 |
" <tr style=\"text-align: right;\">\n",
|
1245 |
" <th></th>\n",
|
1246 |
" <th>timestamp</th>\n",
|
1247 |
+
" <th>datetime</th>\n",
|
1248 |
" <th>date</th>\n",
|
1249 |
+
" <th>hour</th>\n",
|
1250 |
" <th>temperature_2m</th>\n",
|
1251 |
" <th>relative_humidity_2m</th>\n",
|
1252 |
" <th>precipitation</th>\n",
|
|
|
1261 |
" <tbody>\n",
|
1262 |
" <tr>\n",
|
1263 |
" <th>115</th>\n",
|
1264 |
+
" <td>1715022000000</td>\n",
|
1265 |
+
" <td>2024-05-06 19:00:00</td>\n",
|
1266 |
+
" <td>2024-05-06</td>\n",
|
1267 |
+
" <td>19</td>\n",
|
1268 |
+
" <td>10.7</td>\n",
|
1269 |
+
" <td>91.0</td>\n",
|
1270 |
+
" <td>1.4</td>\n",
|
1271 |
+
" <td>1.4</td>\n",
|
1272 |
+
" <td>0.0</td>\n",
|
1273 |
+
" <td>61.0</td>\n",
|
1274 |
+
" <td>100.0</td>\n",
|
1275 |
+
" <td>16.6</td>\n",
|
1276 |
+
" <td>32.0</td>\n",
|
1277 |
" </tr>\n",
|
1278 |
" <tr>\n",
|
1279 |
" <th>116</th>\n",
|
1280 |
+
" <td>1715025600000</td>\n",
|
1281 |
+
" <td>2024-05-06 20:00:00</td>\n",
|
1282 |
+
" <td>2024-05-06</td>\n",
|
1283 |
+
" <td>20</td>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
1284 |
" <td>10.1</td>\n",
|
1285 |
+
" <td>90.0</td>\n",
|
1286 |
+
" <td>1.4</td>\n",
|
1287 |
+
" <td>1.4</td>\n",
|
1288 |
+
" <td>0.0</td>\n",
|
1289 |
+
" <td>61.0</td>\n",
|
1290 |
+
" <td>100.0</td>\n",
|
1291 |
+
" <td>19.5</td>\n",
|
1292 |
+
" <td>37.1</td>\n",
|
1293 |
" </tr>\n",
|
1294 |
" <tr>\n",
|
1295 |
" <th>117</th>\n",
|
1296 |
+
" <td>1715029200000</td>\n",
|
1297 |
+
" <td>2024-05-06 21:00:00</td>\n",
|
1298 |
+
" <td>2024-05-06</td>\n",
|
1299 |
+
" <td>21</td>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
1300 |
" <td>9.5</td>\n",
|
1301 |
+
" <td>88.0</td>\n",
|
1302 |
+
" <td>1.4</td>\n",
|
1303 |
+
" <td>1.4</td>\n",
|
1304 |
+
" <td>0.0</td>\n",
|
1305 |
+
" <td>61.0</td>\n",
|
1306 |
+
" <td>100.0</td>\n",
|
1307 |
+
" <td>21.6</td>\n",
|
1308 |
+
" <td>42.1</td>\n",
|
1309 |
" </tr>\n",
|
1310 |
" <tr>\n",
|
1311 |
" <th>118</th>\n",
|
1312 |
+
" <td>1715032800000</td>\n",
|
1313 |
+
" <td>2024-05-06 22:00:00</td>\n",
|
1314 |
+
" <td>2024-05-06</td>\n",
|
1315 |
+
" <td>22</td>\n",
|
1316 |
+
" <td>9.3</td>\n",
|
1317 |
+
" <td>86.0</td>\n",
|
1318 |
+
" <td>0.6</td>\n",
|
1319 |
+
" <td>0.6</td>\n",
|
1320 |
" <td>0.0</td>\n",
|
1321 |
+
" <td>3.0</td>\n",
|
1322 |
+
" <td>100.0</td>\n",
|
1323 |
+
" <td>22.0</td>\n",
|
1324 |
+
" <td>41.0</td>\n",
|
1325 |
" </tr>\n",
|
1326 |
" <tr>\n",
|
1327 |
" <th>119</th>\n",
|
1328 |
+
" <td>1715036400000</td>\n",
|
1329 |
+
" <td>2024-05-06 23:00:00</td>\n",
|
1330 |
+
" <td>2024-05-06</td>\n",
|
1331 |
+
" <td>23</td>\n",
|
1332 |
+
" <td>9.1</td>\n",
|
1333 |
+
" <td>84.0</td>\n",
|
1334 |
+
" <td>0.6</td>\n",
|
1335 |
+
" <td>0.6</td>\n",
|
1336 |
" <td>0.0</td>\n",
|
1337 |
+
" <td>3.0</td>\n",
|
1338 |
+
" <td>100.0</td>\n",
|
1339 |
+
" <td>21.3</td>\n",
|
1340 |
+
" <td>40.3</td>\n",
|
|
|
|
|
1341 |
" </tr>\n",
|
1342 |
" </tbody>\n",
|
1343 |
"</table>\n",
|
1344 |
"</div>"
|
1345 |
],
|
1346 |
"text/plain": [
|
1347 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
1348 |
+
"115 1715022000000 2024-05-06 19:00:00 2024-05-06 19 10.7 \n",
|
1349 |
+
"116 1715025600000 2024-05-06 20:00:00 2024-05-06 20 10.1 \n",
|
1350 |
+
"117 1715029200000 2024-05-06 21:00:00 2024-05-06 21 9.5 \n",
|
1351 |
+
"118 1715032800000 2024-05-06 22:00:00 2024-05-06 22 9.3 \n",
|
1352 |
+
"119 1715036400000 2024-05-06 23:00:00 2024-05-06 23 9.1 \n",
|
1353 |
"\n",
|
1354 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1355 |
+
"115 91.0 1.4 1.4 0.0 61.0 \n",
|
1356 |
+
"116 90.0 1.4 1.4 0.0 61.0 \n",
|
1357 |
+
"117 88.0 1.4 1.4 0.0 61.0 \n",
|
1358 |
+
"118 86.0 0.6 0.6 0.0 3.0 \n",
|
1359 |
+
"119 84.0 0.6 0.6 0.0 3.0 \n",
|
1360 |
"\n",
|
1361 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1362 |
+
"115 100.0 16.6 32.0 \n",
|
1363 |
+
"116 100.0 19.5 37.1 \n",
|
1364 |
+
"117 100.0 21.6 42.1 \n",
|
1365 |
+
"118 100.0 22.0 41.0 \n",
|
1366 |
+
"119 100.0 21.3 40.3 "
|
1367 |
]
|
1368 |
},
|
1369 |
"execution_count": 18,
|
|
|
1387 |
"text": [
|
1388 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
1389 |
"RangeIndex: 120 entries, 0 to 119\n",
|
1390 |
+
"Data columns (total 13 columns):\n",
|
1391 |
" # Column Non-Null Count Dtype \n",
|
1392 |
"--- ------ -------------- ----- \n",
|
1393 |
" 0 timestamp 120 non-null int64 \n",
|
1394 |
+
" 1 datetime 120 non-null datetime64[ns]\n",
|
1395 |
+
" 2 date 120 non-null object \n",
|
1396 |
+
" 3 hour 120 non-null int64 \n",
|
1397 |
+
" 4 temperature_2m 120 non-null float64 \n",
|
1398 |
+
" 5 relative_humidity_2m 120 non-null float64 \n",
|
1399 |
+
" 6 precipitation 120 non-null float64 \n",
|
1400 |
+
" 7 rain 120 non-null float64 \n",
|
1401 |
+
" 8 snowfall 120 non-null float64 \n",
|
1402 |
+
" 9 weather_code 120 non-null float64 \n",
|
1403 |
+
" 10 cloud_cover 120 non-null float64 \n",
|
1404 |
+
" 11 wind_speed_10m 120 non-null float64 \n",
|
1405 |
+
" 12 wind_gusts_10m 120 non-null float64 \n",
|
1406 |
+
"dtypes: datetime64[ns](1), float64(9), int64(2), object(1)\n",
|
1407 |
+
"memory usage: 12.3+ KB\n"
|
1408 |
]
|
1409 |
}
|
1410 |
],
|
|
|
1425 |
"cell_type": "code",
|
1426 |
"execution_count": 20,
|
1427 |
"metadata": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1428 |
"outputs": [],
|
1429 |
"source": [
|
1430 |
+
"calender_df = calendar.get_calendar()"
|
|
|
1431 |
]
|
1432 |
},
|
1433 |
{
|
1434 |
"cell_type": "code",
|
1435 |
+
"execution_count": 21,
|
1436 |
"metadata": {},
|
1437 |
"outputs": [
|
1438 |
{
|
|
|
1457 |
" <tr style=\"text-align: right;\">\n",
|
1458 |
" <th></th>\n",
|
1459 |
" <th>date</th>\n",
|
1460 |
+
" <th>day</th>\n",
|
1461 |
+
" <th>month</th>\n",
|
1462 |
+
" <th>holiday</th>\n",
|
1463 |
" </tr>\n",
|
1464 |
" </thead>\n",
|
1465 |
" <tbody>\n",
|
1466 |
" <tr>\n",
|
1467 |
" <th>0</th>\n",
|
1468 |
" <td>2022-01-01</td>\n",
|
1469 |
+
" <td>5</td>\n",
|
1470 |
+
" <td>1</td>\n",
|
1471 |
+
" <td>1</td>\n",
|
1472 |
" </tr>\n",
|
1473 |
" <tr>\n",
|
1474 |
" <th>1</th>\n",
|
1475 |
" <td>2022-01-02</td>\n",
|
1476 |
+
" <td>6</td>\n",
|
1477 |
+
" <td>1</td>\n",
|
1478 |
+
" <td>1</td>\n",
|
1479 |
" </tr>\n",
|
1480 |
" <tr>\n",
|
1481 |
" <th>2</th>\n",
|
1482 |
" <td>2022-01-03</td>\n",
|
1483 |
+
" <td>0</td>\n",
|
1484 |
+
" <td>1</td>\n",
|
1485 |
+
" <td>0</td>\n",
|
1486 |
" </tr>\n",
|
1487 |
" <tr>\n",
|
1488 |
" <th>3</th>\n",
|
1489 |
" <td>2022-01-04</td>\n",
|
1490 |
+
" <td>1</td>\n",
|
1491 |
+
" <td>1</td>\n",
|
1492 |
+
" <td>0</td>\n",
|
1493 |
" </tr>\n",
|
1494 |
" <tr>\n",
|
1495 |
" <th>4</th>\n",
|
1496 |
" <td>2022-01-05</td>\n",
|
1497 |
+
" <td>2</td>\n",
|
1498 |
+
" <td>1</td>\n",
|
1499 |
+
" <td>0</td>\n",
|
1500 |
" </tr>\n",
|
1501 |
" </tbody>\n",
|
1502 |
"</table>\n",
|
1503 |
"</div>"
|
1504 |
],
|
1505 |
"text/plain": [
|
1506 |
+
" date day month holiday\n",
|
1507 |
+
"0 2022-01-01 5 1 1\n",
|
1508 |
+
"1 2022-01-02 6 1 1\n",
|
1509 |
+
"2 2022-01-03 0 1 0\n",
|
1510 |
+
"3 2022-01-04 1 1 0\n",
|
1511 |
+
"4 2022-01-05 2 1 0"
|
1512 |
]
|
1513 |
},
|
1514 |
+
"execution_count": 21,
|
1515 |
"metadata": {},
|
1516 |
"output_type": "execute_result"
|
1517 |
}
|
|
|
1523 |
},
|
1524 |
{
|
1525 |
"cell_type": "code",
|
1526 |
+
"execution_count": 22,
|
1527 |
"metadata": {},
|
1528 |
"outputs": [
|
1529 |
{
|
|
|
1548 |
" <tr style=\"text-align: right;\">\n",
|
1549 |
" <th></th>\n",
|
1550 |
" <th>date</th>\n",
|
1551 |
+
" <th>day</th>\n",
|
1552 |
+
" <th>month</th>\n",
|
1553 |
+
" <th>holiday</th>\n",
|
1554 |
" </tr>\n",
|
1555 |
" </thead>\n",
|
1556 |
" <tbody>\n",
|
1557 |
" <tr>\n",
|
1558 |
" <th>1091</th>\n",
|
1559 |
" <td>2024-12-27</td>\n",
|
1560 |
+
" <td>4</td>\n",
|
1561 |
+
" <td>12</td>\n",
|
1562 |
+
" <td>0</td>\n",
|
1563 |
" </tr>\n",
|
1564 |
" <tr>\n",
|
1565 |
" <th>1092</th>\n",
|
1566 |
" <td>2024-12-28</td>\n",
|
1567 |
+
" <td>5</td>\n",
|
1568 |
+
" <td>12</td>\n",
|
1569 |
+
" <td>1</td>\n",
|
1570 |
" </tr>\n",
|
1571 |
" <tr>\n",
|
1572 |
" <th>1093</th>\n",
|
1573 |
" <td>2024-12-29</td>\n",
|
1574 |
+
" <td>6</td>\n",
|
1575 |
+
" <td>12</td>\n",
|
1576 |
+
" <td>1</td>\n",
|
1577 |
" </tr>\n",
|
1578 |
" <tr>\n",
|
1579 |
" <th>1094</th>\n",
|
1580 |
" <td>2024-12-30</td>\n",
|
1581 |
+
" <td>0</td>\n",
|
1582 |
+
" <td>12</td>\n",
|
1583 |
+
" <td>0</td>\n",
|
1584 |
" </tr>\n",
|
1585 |
" <tr>\n",
|
1586 |
" <th>1095</th>\n",
|
1587 |
" <td>2024-12-31</td>\n",
|
1588 |
+
" <td>1</td>\n",
|
1589 |
+
" <td>12</td>\n",
|
1590 |
+
" <td>0</td>\n",
|
1591 |
" </tr>\n",
|
1592 |
" </tbody>\n",
|
1593 |
"</table>\n",
|
1594 |
"</div>"
|
1595 |
],
|
1596 |
"text/plain": [
|
1597 |
+
" date day month holiday\n",
|
1598 |
+
"1091 2024-12-27 4 12 0\n",
|
1599 |
+
"1092 2024-12-28 5 12 1\n",
|
1600 |
+
"1093 2024-12-29 6 12 1\n",
|
1601 |
+
"1094 2024-12-30 0 12 0\n",
|
1602 |
+
"1095 2024-12-31 1 12 0"
|
1603 |
]
|
1604 |
},
|
1605 |
+
"execution_count": 22,
|
1606 |
"metadata": {},
|
1607 |
"output_type": "execute_result"
|
1608 |
}
|
|
|
1612 |
"calender_df.tail(5)"
|
1613 |
]
|
1614 |
},
|
1615 |
+
{
|
1616 |
+
"cell_type": "code",
|
1617 |
+
"execution_count": 23,
|
1618 |
+
"metadata": {},
|
1619 |
+
"outputs": [
|
1620 |
+
{
|
1621 |
+
"name": "stdout",
|
1622 |
+
"output_type": "stream",
|
1623 |
+
"text": [
|
1624 |
+
"<class 'pandas.core.frame.DataFrame'>\n",
|
1625 |
+
"RangeIndex: 1096 entries, 0 to 1095\n",
|
1626 |
+
"Data columns (total 4 columns):\n",
|
1627 |
+
" # Column Non-Null Count Dtype \n",
|
1628 |
+
"--- ------ -------------- ----- \n",
|
1629 |
+
" 0 date 1096 non-null object\n",
|
1630 |
+
" 1 day 1096 non-null int64 \n",
|
1631 |
+
" 2 month 1096 non-null int64 \n",
|
1632 |
+
" 3 holiday 1096 non-null int64 \n",
|
1633 |
+
"dtypes: int64(3), object(1)\n",
|
1634 |
+
"memory usage: 34.4+ KB\n"
|
1635 |
+
]
|
1636 |
+
}
|
1637 |
+
],
|
1638 |
+
"source": [
|
1639 |
+
"# Showing the information for the calender dataframe\n",
|
1640 |
+
"calender_df.info()"
|
1641 |
+
]
|
1642 |
+
},
|
1643 |
{
|
1644 |
"cell_type": "code",
|
1645 |
"execution_count": 24,
|
|
|
1651 |
"text": [
|
1652 |
"<class 'pandas.core.frame.DataFrame'>\n",
|
1653 |
"RangeIndex: 1096 entries, 0 to 1095\n",
|
1654 |
+
"Data columns (total 4 columns):\n",
|
1655 |
+
" # Column Non-Null Count Dtype \n",
|
1656 |
+
"--- ------ -------------- ----- \n",
|
1657 |
+
" 0 date 1096 non-null object\n",
|
1658 |
+
" 1 day 1096 non-null int64 \n",
|
1659 |
+
" 2 month 1096 non-null int64 \n",
|
1660 |
+
" 3 holiday 1096 non-null int64 \n",
|
1661 |
+
"dtypes: int64(3), object(1)\n",
|
1662 |
+
"memory usage: 34.4+ KB\n"
|
1663 |
]
|
1664 |
}
|
1665 |
],
|
|
|
1711 |
"### <span style=\"color:#2656a3;\"> 🪄 Creating Feature Groups\n",
|
1712 |
"A feature group can be seen as a collection of conceptually related features. In this case we create feature groups for the \n",
|
1713 |
"- eletricity price data,\n",
|
1714 |
+
"- forecast_renewable_energy,\n",
|
1715 |
"- weather data,\n",
|
1716 |
+
"- calender data.\n",
|
|
|
1717 |
"\n",
|
1718 |
"We specify a `primary_key` as `date`, so we are able to join them when we create a dataset for training later in part 03 the training_pipeline.\n",
|
1719 |
"We define a name and a short describtion of the feature group's contents and a version number. \n",
|
|
|
1729 |
"metadata": {},
|
1730 |
"outputs": [],
|
1731 |
"source": [
|
1732 |
+
"# Creating the feature group for the electricity prices\n",
|
1733 |
+
"electricity_fg = fs.get_or_create_feature_group(\n",
|
1734 |
+
" name=\"electricity_prices\",\n",
|
1735 |
" version=1,\n",
|
1736 |
+
" description=\"Electricity prices from Energidata API\",\n",
|
1737 |
+
" primary_key=[\"date\",\"timestamp\"], \n",
|
|
|
1738 |
" online_enabled=True,\n",
|
1739 |
+
" event_time=\"timestamp\",\n",
|
1740 |
")"
|
1741 |
]
|
1742 |
},
|
|
|
1757 |
"output_type": "stream",
|
1758 |
"text": [
|
1759 |
"Feature Group created successfully, explore it at \n",
|
1760 |
+
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/774496\n"
|
1761 |
]
|
1762 |
},
|
1763 |
{
|
1764 |
"data": {
|
1765 |
"application/vnd.jupyter.widget-view+json": {
|
1766 |
+
"model_id": "a746b736b329402299dc55c4ebd07d53",
|
1767 |
"version_major": 2,
|
1768 |
"version_minor": 0
|
1769 |
},
|
1770 |
"text/plain": [
|
1771 |
+
"Uploading Dataframe: 0.00% | | Rows 0/20445 | Elapsed Time: 00:00 | Remaining Time: ?"
|
1772 |
]
|
1773 |
},
|
1774 |
"metadata": {},
|
|
|
1778 |
"name": "stdout",
|
1779 |
"output_type": "stream",
|
1780 |
"text": [
|
1781 |
+
"Launching job: electricity_prices_1_offline_fg_materialization\n",
|
1782 |
"Job started successfully, you can follow the progress at \n",
|
1783 |
+
"https://c.app.hopsworks.ai/p/554133/jobs/named/electricity_prices_1_offline_fg_materialization/executions\n"
|
1784 |
]
|
1785 |
},
|
1786 |
{
|
1787 |
"data": {
|
1788 |
"text/plain": [
|
1789 |
+
"(<hsfs.core.job.Job at 0x16ff23950>, None)"
|
1790 |
]
|
1791 |
},
|
1792 |
"execution_count": 27,
|
|
|
1795 |
}
|
1796 |
],
|
1797 |
"source": [
|
1798 |
+
"# Inserting the electricity_df into the feature group named electricity_fg\n",
|
1799 |
+
"electricity_fg.insert(electricity_df)"
|
1800 |
]
|
1801 |
},
|
1802 |
{
|
|
|
1812 |
"metadata": {},
|
1813 |
"outputs": [],
|
1814 |
"source": [
|
1815 |
+
"# List of descriptions for electricity features\n",
|
1816 |
+
"electricity_feature_descriptions = [\n",
|
1817 |
" {\"name\": \"timestamp\", \"description\": \"Timestamp for the event_time\"},\n",
|
1818 |
+
" {\"name\": \"date\", \"description\": \"Date of the electricity measurement\"},\n",
|
1819 |
+
" {\"name\": \"datetime\", \"description\": \"Date and time of the electricity measurement\"},\n",
|
1820 |
+
" {\"name\": \"hour\", \"description\": \"Hour of day\"},\n",
|
1821 |
+
" {\"name\": \"dk1_spotpricedkk_kwh\", \"description\": \"Spot price in DKK per KWH\"}, \n",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1822 |
"]\n",
|
1823 |
"\n",
|
1824 |
"# Updating feature descriptions\n",
|
1825 |
+
"for desc in electricity_feature_descriptions: \n",
|
1826 |
+
" electricity_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
|
1827 |
]
|
1828 |
},
|
1829 |
{
|
1830 |
"cell_type": "markdown",
|
1831 |
"metadata": {},
|
1832 |
"source": [
|
1833 |
+
"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."
|
1834 |
]
|
1835 |
},
|
1836 |
{
|
|
|
1839 |
"metadata": {},
|
1840 |
"outputs": [],
|
1841 |
"source": [
|
1842 |
+
"# # Creating the feature group for the electricity prices\n",
|
1843 |
+
"# forecast_renewable_energy_fg = fs.get_or_create_feature_group(\n",
|
1844 |
+
"# name=\"forecast_renewable_energy\",\n",
|
1845 |
+
"# version=1,\n",
|
1846 |
+
"# description=\"Forecast on Renewable Energy on ForecastType from Energidata API\",\n",
|
1847 |
+
"# primary_key=[\"date\",\"timestamp\"], \n",
|
1848 |
+
"# online_enabled=True,\n",
|
1849 |
+
"# event_time=\"timestamp\",\n",
|
1850 |
+
"# )"
|
1851 |
]
|
1852 |
},
|
1853 |
{
|
1854 |
"cell_type": "code",
|
1855 |
"execution_count": 30,
|
1856 |
"metadata": {},
|
1857 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1858 |
"source": [
|
1859 |
+
"# # Inserting the electricity_df into the feature group named electricity_fg\n",
|
1860 |
+
"# forecast_renewable_energy_fg.insert(forecast_renewable_energy_df)"
|
1861 |
]
|
1862 |
},
|
1863 |
{
|
|
|
1866 |
"metadata": {},
|
1867 |
"outputs": [],
|
1868 |
"source": [
|
1869 |
+
"# # List of descriptions for forecast_renewable_energy features\n",
|
1870 |
+
"# forecast_renewable_energy_feature_descriptions = [\n",
|
1871 |
+
"# {\"name\": \"timestamp\", \"description\": \"Timestamp for the event_time\"},\n",
|
1872 |
+
"# {\"name\": \"date\", \"description\": \"Date of the forecast\"},\n",
|
1873 |
+
"# {\"name\": \"datetime\", \"description\": \"Date and time for the forecast\"},\n",
|
1874 |
+
"# {\"name\": \"hour\", \"description\": \"Hour of day\"},\n",
|
1875 |
+
"# {\"name\": \"dk1_offshore_wind_forecastintraday_kwh\", \"description\": \"The forecast for the coming day at 6am Danish time zone\"},\n",
|
1876 |
+
"# ]\n",
|
1877 |
"\n",
|
1878 |
+
"# # Updating feature descriptions\n",
|
1879 |
+
"# for desc in forecast_renewable_energy_feature_descriptions: \n",
|
1880 |
+
"# forecast_renewable_energy_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
|
1881 |
]
|
1882 |
},
|
1883 |
{
|
|
|
1886 |
"metadata": {},
|
1887 |
"outputs": [],
|
1888 |
"source": [
|
1889 |
+
"# Creating the feature group for the weather data\n",
|
1890 |
+
"weather_fg = fs.get_or_create_feature_group(\n",
|
1891 |
+
" name=\"weather_measurements\",\n",
|
1892 |
" version=1,\n",
|
1893 |
+
" description=\"Weather measurements from Open Meteo API\",\n",
|
1894 |
+
" primary_key=[\"date\", \"timestamp\"], \n",
|
|
|
1895 |
" event_time=\"timestamp\",\n",
|
1896 |
+
" online_enabled=True,\n",
|
1897 |
")"
|
1898 |
]
|
1899 |
},
|
|
|
1907 |
"output_type": "stream",
|
1908 |
"text": [
|
1909 |
"Feature Group created successfully, explore it at \n",
|
1910 |
+
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/775512\n"
|
1911 |
]
|
1912 |
},
|
1913 |
{
|
1914 |
"data": {
|
1915 |
"application/vnd.jupyter.widget-view+json": {
|
1916 |
+
"model_id": "a172ef7a47d14b8ab9643d864c8189d1",
|
1917 |
"version_major": 2,
|
1918 |
"version_minor": 0
|
1919 |
},
|
1920 |
"text/plain": [
|
1921 |
+
"Uploading Dataframe: 0.00% | | Rows 0/20424 | Elapsed Time: 00:00 | Remaining Time: ?"
|
1922 |
]
|
1923 |
},
|
1924 |
"metadata": {},
|
|
|
1928 |
"name": "stdout",
|
1929 |
"output_type": "stream",
|
1930 |
"text": [
|
1931 |
+
"Launching job: weather_measurements_1_offline_fg_materialization\n",
|
1932 |
"Job started successfully, you can follow the progress at \n",
|
1933 |
+
"https://c.app.hopsworks.ai/p/554133/jobs/named/weather_measurements_1_offline_fg_materialization/executions\n"
|
1934 |
]
|
1935 |
},
|
1936 |
{
|
1937 |
"data": {
|
1938 |
"text/plain": [
|
1939 |
+
"(<hsfs.core.job.Job at 0x16ffda610>, None)"
|
1940 |
]
|
1941 |
},
|
1942 |
"execution_count": 33,
|
|
|
1945 |
}
|
1946 |
],
|
1947 |
"source": [
|
1948 |
+
"# Inserting the weather_df into the feature group named weather_fg\n",
|
1949 |
+
"weather_fg.insert(historical_weather_df)"
|
1950 |
]
|
1951 |
},
|
1952 |
{
|
|
|
1955 |
"metadata": {},
|
1956 |
"outputs": [],
|
1957 |
"source": [
|
1958 |
+
"# List of descriptions for weather features\n",
|
1959 |
+
"weather_feature_descriptions = [\n",
|
1960 |
+
" {\"name\": \"timestamp\", \"description\": \"Timestamp for the weather measurement\"},\n",
|
1961 |
+
" {\"name\": \"date\", \"description\": \"Date of the weather measurement\"},\n",
|
1962 |
+
" {\"name\": \"datetime\", \"description\": \"Date and time of the weather measurement\"},\n",
|
1963 |
+
" {\"name\": \"hour\", \"description\": \"Hour of day\"},\n",
|
1964 |
+
" {\"name\": \"temperature_2m\", \"description\": \"Temperature at 2m above ground\"},\n",
|
1965 |
+
" {\"name\": \"relative_humidity_2m\", \"description\": \"Relative humidity at 2m above ground\"},\n",
|
1966 |
+
" {\"name\": \"precipitation\", \"description\": \"Precipitation\"},\n",
|
1967 |
+
" {\"name\": \"rain\", \"description\": \"Rain\"},\n",
|
1968 |
+
" {\"name\": \"snowfall\", \"description\": \"Snowfall\"}, \n",
|
1969 |
+
" {\"name\": \"weather_code\", \"description\": \"Weather code\"}, \n",
|
1970 |
+
" {\"name\": \"cloud_cover\", \"description\": \"Cloud cover\"}, \n",
|
1971 |
+
" {\"name\": \"wind_speed_10m\", \"description\": \"Wind speed at 10m above ground\"}, \n",
|
1972 |
+
" {\"name\": \"wind_gusts_10m\", \"description\": \"Wind gusts at 10m above ground\"}, \n",
|
1973 |
"]\n",
|
1974 |
"\n",
|
1975 |
"# Updating feature descriptions\n",
|
1976 |
+
"for desc in weather_feature_descriptions: \n",
|
1977 |
+
" weather_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
|
1978 |
]
|
1979 |
},
|
1980 |
{
|
1981 |
"cell_type": "code",
|
1982 |
+
"execution_count": 47,
|
1983 |
"metadata": {},
|
1984 |
"outputs": [],
|
1985 |
"source": [
|
1986 |
+
"# Creating the feature group for the danish calendar\n",
|
1987 |
+
"danish_calendar_fg = fs.get_or_create_feature_group(\n",
|
1988 |
+
" name=\"danish_calendar\",\n",
|
1989 |
+
" version=2,\n",
|
1990 |
+
" description=\"Danish calendar.\",\n",
|
1991 |
" online_enabled=True,\n",
|
1992 |
" primary_key=[\"date\"],\n",
|
1993 |
")"
|
|
|
1995 |
},
|
1996 |
{
|
1997 |
"cell_type": "code",
|
1998 |
+
"execution_count": 48,
|
1999 |
"metadata": {},
|
2000 |
"outputs": [
|
2001 |
{
|
|
|
2003 |
"output_type": "stream",
|
2004 |
"text": [
|
2005 |
"Feature Group created successfully, explore it at \n",
|
2006 |
+
"https://c.app.hopsworks.ai:443/p/554133/fs/549956/fg/774498\n"
|
2007 |
]
|
2008 |
},
|
2009 |
{
|
2010 |
"data": {
|
2011 |
"application/vnd.jupyter.widget-view+json": {
|
2012 |
+
"model_id": "3b61548e0184416180285726772cd490",
|
2013 |
"version_major": 2,
|
2014 |
"version_minor": 0
|
2015 |
},
|
|
|
2024 |
"name": "stdout",
|
2025 |
"output_type": "stream",
|
2026 |
"text": [
|
2027 |
+
"Launching job: danish_calendar_2_offline_fg_materialization\n",
|
2028 |
"Job started successfully, you can follow the progress at \n",
|
2029 |
+
"https://c.app.hopsworks.ai/p/554133/jobs/named/danish_calendar_2_offline_fg_materialization/executions\n"
|
2030 |
]
|
2031 |
},
|
2032 |
{
|
2033 |
"data": {
|
2034 |
"text/plain": [
|
2035 |
+
"(<hsfs.core.job.Job at 0x16ff71050>, None)"
|
2036 |
]
|
2037 |
},
|
2038 |
+
"execution_count": 48,
|
2039 |
"metadata": {},
|
2040 |
"output_type": "execute_result"
|
2041 |
}
|
2042 |
],
|
2043 |
"source": [
|
2044 |
+
"# Inserting the calender_df into the feature group named danish_calendar_fg\n",
|
2045 |
+
"danish_calendar_fg.insert(calender_df)"
|
2046 |
]
|
2047 |
},
|
2048 |
{
|
2049 |
"cell_type": "code",
|
2050 |
+
"execution_count": 49,
|
2051 |
"metadata": {},
|
2052 |
"outputs": [],
|
2053 |
"source": [
|
2054 |
+
"# List of descriptions for danish_calendar features\n",
|
2055 |
+
"danish_calendar_feature_descriptions = [\n",
|
2056 |
" {\"name\": \"date\", \"description\": \"Date in the calendar\"},\n",
|
2057 |
+
" {\"name\": \"day\", \"description\": \"Day number of the week. Monday is 0 and Sunday is 6\"},\n",
|
2058 |
+
" {\"name\": \"month\", \"description\": \"Month number of the year\"},\n",
|
2059 |
+
" {\"name\": \"holiday\", \"description\": \"Holiday or not holiday\"},\n",
|
2060 |
"]\n",
|
2061 |
"\n",
|
2062 |
"# Updating feature descriptions\n",
|
2063 |
+
"for desc in danish_calendar_feature_descriptions: \n",
|
2064 |
+
" danish_calendar_fg.update_feature_description(desc[\"name\"], desc[\"description\"])"
|
2065 |
]
|
2066 |
},
|
2067 |
{
|
notebooks/2_feature_pipeline.ipynb
CHANGED
@@ -45,7 +45,7 @@
|
|
45 |
"\n",
|
46 |
"# Now we import the functions from the features folder\n",
|
47 |
"# This is the functions we have created to generate features for electricity prices and weather measures\n",
|
48 |
-
"from features import electricity_prices, weather_measures \n",
|
49 |
"\n",
|
50 |
"# We go back into the notebooks folder\n",
|
51 |
"%cd notebooks"
|
@@ -126,210 +126,235 @@
|
|
126 |
" <tr style=\"text-align: right;\">\n",
|
127 |
" <th></th>\n",
|
128 |
" <th>timestamp</th>\n",
|
129 |
-
" <th>
|
130 |
" <th>date</th>\n",
|
|
|
131 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
132 |
" </tr>\n",
|
133 |
" </thead>\n",
|
134 |
" <tbody>\n",
|
135 |
" <tr>\n",
|
136 |
" <th>0</th>\n",
|
137 |
-
" <td>
|
138 |
-
" <td>2024-05-
|
139 |
-
" <td>2024-05-
|
140 |
-
" <td>0
|
|
|
141 |
" </tr>\n",
|
142 |
" <tr>\n",
|
143 |
" <th>1</th>\n",
|
144 |
-
" <td>
|
145 |
-
" <td>2024-05-
|
146 |
-
" <td>2024-05-
|
147 |
-
" <td>
|
|
|
148 |
" </tr>\n",
|
149 |
" <tr>\n",
|
150 |
" <th>2</th>\n",
|
151 |
-
" <td>
|
152 |
-
" <td>2024-05-
|
153 |
-
" <td>2024-05-
|
154 |
-
" <td>
|
|
|
155 |
" </tr>\n",
|
156 |
" <tr>\n",
|
157 |
" <th>3</th>\n",
|
158 |
-
" <td>
|
159 |
-
" <td>2024-05-
|
160 |
-
" <td>2024-05-
|
161 |
-
" <td>
|
|
|
162 |
" </tr>\n",
|
163 |
" <tr>\n",
|
164 |
" <th>4</th>\n",
|
165 |
-
" <td>
|
166 |
-
" <td>2024-05-
|
167 |
-
" <td>2024-05-
|
168 |
-
" <td>
|
|
|
169 |
" </tr>\n",
|
170 |
" <tr>\n",
|
171 |
" <th>5</th>\n",
|
172 |
-
" <td>
|
173 |
-
" <td>2024-05-
|
174 |
-
" <td>2024-05-
|
175 |
-
" <td>
|
|
|
176 |
" </tr>\n",
|
177 |
" <tr>\n",
|
178 |
" <th>6</th>\n",
|
179 |
-
" <td>
|
180 |
-
" <td>2024-05-
|
181 |
-
" <td>2024-05-
|
182 |
-
" <td>
|
|
|
183 |
" </tr>\n",
|
184 |
" <tr>\n",
|
185 |
" <th>7</th>\n",
|
186 |
-
" <td>
|
187 |
-
" <td>2024-05-
|
188 |
-
" <td>2024-05-
|
189 |
-
" <td>
|
|
|
190 |
" </tr>\n",
|
191 |
" <tr>\n",
|
192 |
" <th>8</th>\n",
|
193 |
-
" <td>
|
194 |
-
" <td>2024-05-
|
195 |
-
" <td>2024-05-
|
196 |
-
" <td>
|
|
|
197 |
" </tr>\n",
|
198 |
" <tr>\n",
|
199 |
" <th>9</th>\n",
|
200 |
-
" <td>
|
201 |
-
" <td>2024-05-
|
202 |
-
" <td>2024-05-
|
203 |
-
" <td>
|
|
|
204 |
" </tr>\n",
|
205 |
" <tr>\n",
|
206 |
" <th>10</th>\n",
|
207 |
-
" <td>
|
208 |
-
" <td>2024-05-
|
209 |
-
" <td>2024-05-
|
210 |
-
" <td
|
|
|
211 |
" </tr>\n",
|
212 |
" <tr>\n",
|
213 |
" <th>11</th>\n",
|
214 |
-
" <td>
|
215 |
-
" <td>2024-05-
|
216 |
-
" <td>2024-05-
|
217 |
-
" <td
|
|
|
218 |
" </tr>\n",
|
219 |
" <tr>\n",
|
220 |
" <th>12</th>\n",
|
221 |
-
" <td>
|
222 |
-
" <td>2024-05-
|
223 |
-
" <td>2024-05-
|
224 |
-
" <td
|
|
|
225 |
" </tr>\n",
|
226 |
" <tr>\n",
|
227 |
" <th>13</th>\n",
|
228 |
-
" <td>
|
229 |
-
" <td>2024-05-
|
230 |
-
" <td>2024-05-
|
231 |
-
" <td
|
|
|
232 |
" </tr>\n",
|
233 |
" <tr>\n",
|
234 |
" <th>14</th>\n",
|
235 |
-
" <td>
|
236 |
-
" <td>2024-05-
|
237 |
-
" <td>2024-05-
|
238 |
-
" <td
|
|
|
239 |
" </tr>\n",
|
240 |
" <tr>\n",
|
241 |
" <th>15</th>\n",
|
242 |
-
" <td>
|
243 |
-
" <td>2024-05-
|
244 |
-
" <td>2024-05-
|
245 |
-
" <td
|
|
|
246 |
" </tr>\n",
|
247 |
" <tr>\n",
|
248 |
" <th>16</th>\n",
|
249 |
-
" <td>
|
250 |
-
" <td>2024-05-
|
251 |
-
" <td>2024-05-
|
252 |
-
" <td
|
|
|
253 |
" </tr>\n",
|
254 |
" <tr>\n",
|
255 |
" <th>17</th>\n",
|
256 |
-
" <td>
|
257 |
-
" <td>2024-05-
|
258 |
-
" <td>2024-05-
|
259 |
-
" <td
|
|
|
260 |
" </tr>\n",
|
261 |
" <tr>\n",
|
262 |
" <th>18</th>\n",
|
263 |
-
" <td>
|
264 |
-
" <td>2024-05-
|
265 |
-
" <td>2024-05-
|
266 |
-
" <td>
|
|
|
267 |
" </tr>\n",
|
268 |
" <tr>\n",
|
269 |
" <th>19</th>\n",
|
270 |
-
" <td>
|
271 |
-
" <td>2024-05-
|
272 |
-
" <td>2024-05-
|
273 |
-
" <td>
|
|
|
274 |
" </tr>\n",
|
275 |
" <tr>\n",
|
276 |
" <th>20</th>\n",
|
277 |
-
" <td>
|
278 |
-
" <td>2024-05-
|
279 |
-
" <td>2024-05-
|
280 |
-
" <td>
|
|
|
281 |
" </tr>\n",
|
282 |
" <tr>\n",
|
283 |
" <th>21</th>\n",
|
284 |
-
" <td>
|
285 |
-
" <td>2024-05-
|
286 |
-
" <td>2024-05-
|
287 |
-
" <td>
|
|
|
288 |
" </tr>\n",
|
289 |
" <tr>\n",
|
290 |
" <th>22</th>\n",
|
291 |
-
" <td>
|
292 |
-
" <td>2024-05-
|
293 |
-
" <td>2024-05-
|
294 |
-
" <td>
|
|
|
295 |
" </tr>\n",
|
296 |
" <tr>\n",
|
297 |
" <th>23</th>\n",
|
298 |
-
" <td>
|
299 |
-
" <td>2024-05-
|
300 |
-
" <td>2024-05-
|
301 |
-
" <td>
|
|
|
302 |
" </tr>\n",
|
303 |
" </tbody>\n",
|
304 |
"</table>\n",
|
305 |
"</div>"
|
306 |
],
|
307 |
"text/plain": [
|
308 |
-
" timestamp
|
309 |
-
"0
|
310 |
-
"1
|
311 |
-
"2
|
312 |
-
"3
|
313 |
-
"4
|
314 |
-
"5
|
315 |
-
"6
|
316 |
-
"7
|
317 |
-
"8
|
318 |
-
"9
|
319 |
-
"10
|
320 |
-
"11
|
321 |
-
"12
|
322 |
-
"13
|
323 |
-
"14
|
324 |
-
"15
|
325 |
-
"16
|
326 |
-
"17
|
327 |
-
"18
|
328 |
-
"19
|
329 |
-
"20
|
330 |
-
"21
|
331 |
-
"22
|
332 |
-
"23
|
333 |
]
|
334 |
},
|
335 |
"execution_count": 4,
|
@@ -355,356 +380,21 @@
|
|
355 |
"metadata": {},
|
356 |
"outputs": [],
|
357 |
"source": [
|
358 |
-
"# Fetching non-historical forecast of renewable energy data for area DK1\n",
|
359 |
-
"forecast_renewable_energy_df = electricity_prices.forecast_renewable_energy(\n",
|
360 |
-
"
|
361 |
-
"
|
362 |
-
")"
|
363 |
]
|
364 |
},
|
365 |
{
|
366 |
"cell_type": "code",
|
367 |
"execution_count": 6,
|
368 |
"metadata": {},
|
369 |
-
"outputs": [
|
370 |
-
{
|
371 |
-
"data": {
|
372 |
-
"text/html": [
|
373 |
-
"<div>\n",
|
374 |
-
"<style scoped>\n",
|
375 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
376 |
-
" vertical-align: middle;\n",
|
377 |
-
" }\n",
|
378 |
-
"\n",
|
379 |
-
" .dataframe tbody tr th {\n",
|
380 |
-
" vertical-align: top;\n",
|
381 |
-
" }\n",
|
382 |
-
"\n",
|
383 |
-
" .dataframe thead th {\n",
|
384 |
-
" text-align: right;\n",
|
385 |
-
" }\n",
|
386 |
-
"</style>\n",
|
387 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
388 |
-
" <thead>\n",
|
389 |
-
" <tr style=\"text-align: right;\">\n",
|
390 |
-
" <th></th>\n",
|
391 |
-
" <th>timestamp</th>\n",
|
392 |
-
" <th>time</th>\n",
|
393 |
-
" <th>date</th>\n",
|
394 |
-
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
395 |
-
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
396 |
-
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
397 |
-
" </tr>\n",
|
398 |
-
" </thead>\n",
|
399 |
-
" <tbody>\n",
|
400 |
-
" <tr>\n",
|
401 |
-
" <th>0</th>\n",
|
402 |
-
" <td>1714521600000</td>\n",
|
403 |
-
" <td>2024-05-01 00:00:00</td>\n",
|
404 |
-
" <td>2024-05-01</td>\n",
|
405 |
-
" <td>0.794000</td>\n",
|
406 |
-
" <td>1.710417</td>\n",
|
407 |
-
" <td>0.000170</td>\n",
|
408 |
-
" </tr>\n",
|
409 |
-
" <tr>\n",
|
410 |
-
" <th>1</th>\n",
|
411 |
-
" <td>1714525200000</td>\n",
|
412 |
-
" <td>2024-05-01 01:00:00</td>\n",
|
413 |
-
" <td>2024-05-01</td>\n",
|
414 |
-
" <td>0.759667</td>\n",
|
415 |
-
" <td>1.738500</td>\n",
|
416 |
-
" <td>0.000169</td>\n",
|
417 |
-
" </tr>\n",
|
418 |
-
" <tr>\n",
|
419 |
-
" <th>2</th>\n",
|
420 |
-
" <td>1714528800000</td>\n",
|
421 |
-
" <td>2024-05-01 02:00:00</td>\n",
|
422 |
-
" <td>2024-05-01</td>\n",
|
423 |
-
" <td>0.688625</td>\n",
|
424 |
-
" <td>1.527958</td>\n",
|
425 |
-
" <td>0.000175</td>\n",
|
426 |
-
" </tr>\n",
|
427 |
-
" <tr>\n",
|
428 |
-
" <th>3</th>\n",
|
429 |
-
" <td>1714532400000</td>\n",
|
430 |
-
" <td>2024-05-01 03:00:00</td>\n",
|
431 |
-
" <td>2024-05-01</td>\n",
|
432 |
-
" <td>0.577083</td>\n",
|
433 |
-
" <td>1.347667</td>\n",
|
434 |
-
" <td>0.000189</td>\n",
|
435 |
-
" </tr>\n",
|
436 |
-
" <tr>\n",
|
437 |
-
" <th>4</th>\n",
|
438 |
-
" <td>1714536000000</td>\n",
|
439 |
-
" <td>2024-05-01 04:00:00</td>\n",
|
440 |
-
" <td>2024-05-01</td>\n",
|
441 |
-
" <td>0.605792</td>\n",
|
442 |
-
" <td>1.227542</td>\n",
|
443 |
-
" <td>0.000218</td>\n",
|
444 |
-
" </tr>\n",
|
445 |
-
" <tr>\n",
|
446 |
-
" <th>5</th>\n",
|
447 |
-
" <td>1714539600000</td>\n",
|
448 |
-
" <td>2024-05-01 05:00:00</td>\n",
|
449 |
-
" <td>2024-05-01</td>\n",
|
450 |
-
" <td>0.590542</td>\n",
|
451 |
-
" <td>1.316083</td>\n",
|
452 |
-
" <td>0.004533</td>\n",
|
453 |
-
" </tr>\n",
|
454 |
-
" <tr>\n",
|
455 |
-
" <th>6</th>\n",
|
456 |
-
" <td>1714543200000</td>\n",
|
457 |
-
" <td>2024-05-01 06:00:00</td>\n",
|
458 |
-
" <td>2024-05-01</td>\n",
|
459 |
-
" <td>0.627333</td>\n",
|
460 |
-
" <td>1.346875</td>\n",
|
461 |
-
" <td>0.144934</td>\n",
|
462 |
-
" </tr>\n",
|
463 |
-
" <tr>\n",
|
464 |
-
" <th>7</th>\n",
|
465 |
-
" <td>1714546800000</td>\n",
|
466 |
-
" <td>2024-05-01 07:00:00</td>\n",
|
467 |
-
" <td>2024-05-01</td>\n",
|
468 |
-
" <td>0.482625</td>\n",
|
469 |
-
" <td>1.287417</td>\n",
|
470 |
-
" <td>0.366274</td>\n",
|
471 |
-
" </tr>\n",
|
472 |
-
" <tr>\n",
|
473 |
-
" <th>8</th>\n",
|
474 |
-
" <td>1714550400000</td>\n",
|
475 |
-
" <td>2024-05-01 08:00:00</td>\n",
|
476 |
-
" <td>2024-05-01</td>\n",
|
477 |
-
" <td>0.474042</td>\n",
|
478 |
-
" <td>1.279458</td>\n",
|
479 |
-
" <td>0.786889</td>\n",
|
480 |
-
" </tr>\n",
|
481 |
-
" <tr>\n",
|
482 |
-
" <th>9</th>\n",
|
483 |
-
" <td>1714554000000</td>\n",
|
484 |
-
" <td>2024-05-01 09:00:00</td>\n",
|
485 |
-
" <td>2024-05-01</td>\n",
|
486 |
-
" <td>0.493583</td>\n",
|
487 |
-
" <td>1.367208</td>\n",
|
488 |
-
" <td>1.208868</td>\n",
|
489 |
-
" </tr>\n",
|
490 |
-
" <tr>\n",
|
491 |
-
" <th>10</th>\n",
|
492 |
-
" <td>1714557600000</td>\n",
|
493 |
-
" <td>2024-05-01 10:00:00</td>\n",
|
494 |
-
" <td>2024-05-01</td>\n",
|
495 |
-
" <td>0.522458</td>\n",
|
496 |
-
" <td>1.342625</td>\n",
|
497 |
-
" <td>1.197411</td>\n",
|
498 |
-
" </tr>\n",
|
499 |
-
" <tr>\n",
|
500 |
-
" <th>11</th>\n",
|
501 |
-
" <td>1714561200000</td>\n",
|
502 |
-
" <td>2024-05-01 11:00:00</td>\n",
|
503 |
-
" <td>2024-05-01</td>\n",
|
504 |
-
" <td>0.566417</td>\n",
|
505 |
-
" <td>1.223500</td>\n",
|
506 |
-
" <td>1.282508</td>\n",
|
507 |
-
" </tr>\n",
|
508 |
-
" <tr>\n",
|
509 |
-
" <th>12</th>\n",
|
510 |
-
" <td>1714564800000</td>\n",
|
511 |
-
" <td>2024-05-01 12:00:00</td>\n",
|
512 |
-
" <td>2024-05-01</td>\n",
|
513 |
-
" <td>0.609958</td>\n",
|
514 |
-
" <td>1.231542</td>\n",
|
515 |
-
" <td>1.362772</td>\n",
|
516 |
-
" </tr>\n",
|
517 |
-
" <tr>\n",
|
518 |
-
" <th>13</th>\n",
|
519 |
-
" <td>1714568400000</td>\n",
|
520 |
-
" <td>2024-05-01 13:00:00</td>\n",
|
521 |
-
" <td>2024-05-01</td>\n",
|
522 |
-
" <td>0.637292</td>\n",
|
523 |
-
" <td>1.213167</td>\n",
|
524 |
-
" <td>1.375432</td>\n",
|
525 |
-
" </tr>\n",
|
526 |
-
" <tr>\n",
|
527 |
-
" <th>14</th>\n",
|
528 |
-
" <td>1714572000000</td>\n",
|
529 |
-
" <td>2024-05-01 14:00:00</td>\n",
|
530 |
-
" <td>2024-05-01</td>\n",
|
531 |
-
" <td>0.662375</td>\n",
|
532 |
-
" <td>1.187667</td>\n",
|
533 |
-
" <td>1.347302</td>\n",
|
534 |
-
" </tr>\n",
|
535 |
-
" <tr>\n",
|
536 |
-
" <th>15</th>\n",
|
537 |
-
" <td>1714575600000</td>\n",
|
538 |
-
" <td>2024-05-01 15:00:00</td>\n",
|
539 |
-
" <td>2024-05-01</td>\n",
|
540 |
-
" <td>0.704667</td>\n",
|
541 |
-
" <td>1.169292</td>\n",
|
542 |
-
" <td>1.269182</td>\n",
|
543 |
-
" </tr>\n",
|
544 |
-
" <tr>\n",
|
545 |
-
" <th>16</th>\n",
|
546 |
-
" <td>1714579200000</td>\n",
|
547 |
-
" <td>2024-05-01 16:00:00</td>\n",
|
548 |
-
" <td>2024-05-01</td>\n",
|
549 |
-
" <td>0.728542</td>\n",
|
550 |
-
" <td>1.286833</td>\n",
|
551 |
-
" <td>1.147561</td>\n",
|
552 |
-
" </tr>\n",
|
553 |
-
" <tr>\n",
|
554 |
-
" <th>17</th>\n",
|
555 |
-
" <td>1714582800000</td>\n",
|
556 |
-
" <td>2024-05-01 17:00:00</td>\n",
|
557 |
-
" <td>2024-05-01</td>\n",
|
558 |
-
" <td>0.744292</td>\n",
|
559 |
-
" <td>1.393458</td>\n",
|
560 |
-
" <td>1.062930</td>\n",
|
561 |
-
" </tr>\n",
|
562 |
-
" <tr>\n",
|
563 |
-
" <th>18</th>\n",
|
564 |
-
" <td>1714586400000</td>\n",
|
565 |
-
" <td>2024-05-01 18:00:00</td>\n",
|
566 |
-
" <td>2024-05-01</td>\n",
|
567 |
-
" <td>0.771792</td>\n",
|
568 |
-
" <td>1.502625</td>\n",
|
569 |
-
" <td>0.664276</td>\n",
|
570 |
-
" </tr>\n",
|
571 |
-
" <tr>\n",
|
572 |
-
" <th>19</th>\n",
|
573 |
-
" <td>1714590000000</td>\n",
|
574 |
-
" <td>2024-05-01 19:00:00</td>\n",
|
575 |
-
" <td>2024-05-01</td>\n",
|
576 |
-
" <td>0.816250</td>\n",
|
577 |
-
" <td>1.382208</td>\n",
|
578 |
-
" <td>0.272911</td>\n",
|
579 |
-
" </tr>\n",
|
580 |
-
" <tr>\n",
|
581 |
-
" <th>20</th>\n",
|
582 |
-
" <td>1714593600000</td>\n",
|
583 |
-
" <td>2024-05-01 20:00:00</td>\n",
|
584 |
-
" <td>2024-05-01</td>\n",
|
585 |
-
" <td>0.848500</td>\n",
|
586 |
-
" <td>1.388583</td>\n",
|
587 |
-
" <td>0.046087</td>\n",
|
588 |
-
" </tr>\n",
|
589 |
-
" <tr>\n",
|
590 |
-
" <th>21</th>\n",
|
591 |
-
" <td>1714597200000</td>\n",
|
592 |
-
" <td>2024-05-01 21:00:00</td>\n",
|
593 |
-
" <td>2024-05-01</td>\n",
|
594 |
-
" <td>0.886042</td>\n",
|
595 |
-
" <td>1.554792</td>\n",
|
596 |
-
" <td>0.001339</td>\n",
|
597 |
-
" </tr>\n",
|
598 |
-
" <tr>\n",
|
599 |
-
" <th>22</th>\n",
|
600 |
-
" <td>1714600800000</td>\n",
|
601 |
-
" <td>2024-05-01 22:00:00</td>\n",
|
602 |
-
" <td>2024-05-01</td>\n",
|
603 |
-
" <td>0.919417</td>\n",
|
604 |
-
" <td>1.698875</td>\n",
|
605 |
-
" <td>0.000000</td>\n",
|
606 |
-
" </tr>\n",
|
607 |
-
" <tr>\n",
|
608 |
-
" <th>23</th>\n",
|
609 |
-
" <td>1714604400000</td>\n",
|
610 |
-
" <td>2024-05-01 23:00:00</td>\n",
|
611 |
-
" <td>2024-05-01</td>\n",
|
612 |
-
" <td>0.934708</td>\n",
|
613 |
-
" <td>1.739375</td>\n",
|
614 |
-
" <td>0.000000</td>\n",
|
615 |
-
" </tr>\n",
|
616 |
-
" </tbody>\n",
|
617 |
-
"</table>\n",
|
618 |
-
"</div>"
|
619 |
-
],
|
620 |
-
"text/plain": [
|
621 |
-
" timestamp time date \\\n",
|
622 |
-
"0 1714521600000 2024-05-01 00:00:00 2024-05-01 \n",
|
623 |
-
"1 1714525200000 2024-05-01 01:00:00 2024-05-01 \n",
|
624 |
-
"2 1714528800000 2024-05-01 02:00:00 2024-05-01 \n",
|
625 |
-
"3 1714532400000 2024-05-01 03:00:00 2024-05-01 \n",
|
626 |
-
"4 1714536000000 2024-05-01 04:00:00 2024-05-01 \n",
|
627 |
-
"5 1714539600000 2024-05-01 05:00:00 2024-05-01 \n",
|
628 |
-
"6 1714543200000 2024-05-01 06:00:00 2024-05-01 \n",
|
629 |
-
"7 1714546800000 2024-05-01 07:00:00 2024-05-01 \n",
|
630 |
-
"8 1714550400000 2024-05-01 08:00:00 2024-05-01 \n",
|
631 |
-
"9 1714554000000 2024-05-01 09:00:00 2024-05-01 \n",
|
632 |
-
"10 1714557600000 2024-05-01 10:00:00 2024-05-01 \n",
|
633 |
-
"11 1714561200000 2024-05-01 11:00:00 2024-05-01 \n",
|
634 |
-
"12 1714564800000 2024-05-01 12:00:00 2024-05-01 \n",
|
635 |
-
"13 1714568400000 2024-05-01 13:00:00 2024-05-01 \n",
|
636 |
-
"14 1714572000000 2024-05-01 14:00:00 2024-05-01 \n",
|
637 |
-
"15 1714575600000 2024-05-01 15:00:00 2024-05-01 \n",
|
638 |
-
"16 1714579200000 2024-05-01 16:00:00 2024-05-01 \n",
|
639 |
-
"17 1714582800000 2024-05-01 17:00:00 2024-05-01 \n",
|
640 |
-
"18 1714586400000 2024-05-01 18:00:00 2024-05-01 \n",
|
641 |
-
"19 1714590000000 2024-05-01 19:00:00 2024-05-01 \n",
|
642 |
-
"20 1714593600000 2024-05-01 20:00:00 2024-05-01 \n",
|
643 |
-
"21 1714597200000 2024-05-01 21:00:00 2024-05-01 \n",
|
644 |
-
"22 1714600800000 2024-05-01 22:00:00 2024-05-01 \n",
|
645 |
-
"23 1714604400000 2024-05-01 23:00:00 2024-05-01 \n",
|
646 |
-
"\n",
|
647 |
-
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
648 |
-
"0 0.794000 \n",
|
649 |
-
"1 0.759667 \n",
|
650 |
-
"2 0.688625 \n",
|
651 |
-
"3 0.577083 \n",
|
652 |
-
"4 0.605792 \n",
|
653 |
-
"5 0.590542 \n",
|
654 |
-
"6 0.627333 \n",
|
655 |
-
"7 0.482625 \n",
|
656 |
-
"8 0.474042 \n",
|
657 |
-
"9 0.493583 \n",
|
658 |
-
"10 0.522458 \n",
|
659 |
-
"11 0.566417 \n",
|
660 |
-
"12 0.609958 \n",
|
661 |
-
"13 0.637292 \n",
|
662 |
-
"14 0.662375 \n",
|
663 |
-
"15 0.704667 \n",
|
664 |
-
"16 0.728542 \n",
|
665 |
-
"17 0.744292 \n",
|
666 |
-
"18 0.771792 \n",
|
667 |
-
"19 0.816250 \n",
|
668 |
-
"20 0.848500 \n",
|
669 |
-
"21 0.886042 \n",
|
670 |
-
"22 0.919417 \n",
|
671 |
-
"23 0.934708 \n",
|
672 |
-
"\n",
|
673 |
-
" dk1_onshore_wind_forecastintraday_kwh dk1_solar_forecastintraday_kwh \n",
|
674 |
-
"0 1.710417 0.000170 \n",
|
675 |
-
"1 1.738500 0.000169 \n",
|
676 |
-
"2 1.527958 0.000175 \n",
|
677 |
-
"3 1.347667 0.000189 \n",
|
678 |
-
"4 1.227542 0.000218 \n",
|
679 |
-
"5 1.316083 0.004533 \n",
|
680 |
-
"6 1.346875 0.144934 \n",
|
681 |
-
"7 1.287417 0.366274 \n",
|
682 |
-
"8 1.279458 0.786889 \n",
|
683 |
-
"9 1.367208 1.208868 \n",
|
684 |
-
"10 1.342625 1.197411 \n",
|
685 |
-
"11 1.223500 1.282508 \n",
|
686 |
-
"12 1.231542 1.362772 \n",
|
687 |
-
"13 1.213167 1.375432 \n",
|
688 |
-
"14 1.187667 1.347302 \n",
|
689 |
-
"15 1.169292 1.269182 \n",
|
690 |
-
"16 1.286833 1.147561 \n",
|
691 |
-
"17 1.393458 1.062930 \n",
|
692 |
-
"18 1.502625 0.664276 \n",
|
693 |
-
"19 1.382208 0.272911 \n",
|
694 |
-
"20 1.388583 0.046087 \n",
|
695 |
-
"21 1.554792 0.001339 \n",
|
696 |
-
"22 1.698875 0.000000 \n",
|
697 |
-
"23 1.739375 0.000000 "
|
698 |
-
]
|
699 |
-
},
|
700 |
-
"execution_count": 6,
|
701 |
-
"metadata": {},
|
702 |
-
"output_type": "execute_result"
|
703 |
-
}
|
704 |
-
],
|
705 |
"source": [
|
706 |
-
"# Display the forecast_renewable_energy dataframe\n",
|
707 |
-
"forecast_renewable_energy_df"
|
708 |
]
|
709 |
},
|
710 |
{
|
@@ -789,8 +479,9 @@
|
|
789 |
" <tr style=\"text-align: right;\">\n",
|
790 |
" <th></th>\n",
|
791 |
" <th>timestamp</th>\n",
|
|
|
792 |
" <th>date</th>\n",
|
793 |
-
" <th>
|
794 |
" <th>temperature_2m</th>\n",
|
795 |
" <th>relative_humidity_2m</th>\n",
|
796 |
" <th>precipitation</th>\n",
|
@@ -805,78 +496,83 @@
|
|
805 |
" <tbody>\n",
|
806 |
" <tr>\n",
|
807 |
" <th>0</th>\n",
|
808 |
-
" <td>
|
809 |
-
" <td>2024-05-
|
810 |
-
" <td>2024-05-
|
811 |
-
" <td>
|
812 |
-
" <td>
|
|
|
813 |
" <td>0.0</td>\n",
|
814 |
" <td>0.0</td>\n",
|
815 |
" <td>0.0</td>\n",
|
816 |
-
" <td>
|
817 |
-
" <td>
|
818 |
-
" <td>
|
819 |
-
" <td>
|
820 |
" </tr>\n",
|
821 |
" <tr>\n",
|
822 |
" <th>1</th>\n",
|
823 |
-
" <td>
|
824 |
-
" <td>2024-05-01</td>\n",
|
825 |
-
" <td>2024-05-
|
826 |
-
" <td>
|
827 |
-
" <td>
|
|
|
828 |
" <td>0.0</td>\n",
|
829 |
" <td>0.0</td>\n",
|
830 |
" <td>0.0</td>\n",
|
831 |
-
" <td>0</td>\n",
|
832 |
-
" <td>
|
833 |
-
" <td>
|
834 |
-
" <td>
|
835 |
" </tr>\n",
|
836 |
" <tr>\n",
|
837 |
" <th>2</th>\n",
|
838 |
-
" <td>
|
839 |
-
" <td>2024-05-
|
840 |
-
" <td>2024-05-
|
841 |
-
" <td>
|
842 |
-
" <td>
|
|
|
843 |
" <td>0.0</td>\n",
|
844 |
" <td>0.0</td>\n",
|
845 |
" <td>0.0</td>\n",
|
846 |
-
" <td>2</td>\n",
|
847 |
-
" <td>
|
848 |
-
" <td>
|
849 |
-
" <td>
|
850 |
" </tr>\n",
|
851 |
" <tr>\n",
|
852 |
" <th>3</th>\n",
|
853 |
-
" <td>
|
854 |
-
" <td>2024-05-
|
855 |
-
" <td>2024-05-
|
856 |
-
" <td>11.5</td>\n",
|
857 |
-
" <td>76</td>\n",
|
858 |
-
" <td>0.0</td>\n",
|
859 |
-
" <td>0.0</td>\n",
|
860 |
-
" <td>0.0</td>\n",
|
861 |
" <td>3</td>\n",
|
862 |
-
" <td>
|
863 |
-
" <td>
|
864 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
865 |
" </tr>\n",
|
866 |
" <tr>\n",
|
867 |
" <th>4</th>\n",
|
868 |
-
" <td>
|
869 |
-
" <td>2024-05-
|
870 |
-
" <td>2024-05-
|
871 |
-
" <td>
|
872 |
-
" <td>
|
|
|
873 |
" <td>0.0</td>\n",
|
874 |
" <td>0.0</td>\n",
|
875 |
" <td>0.0</td>\n",
|
876 |
-
" <td>
|
877 |
-
" <td>
|
878 |
-
" <td>
|
879 |
-
" <td>
|
880 |
" </tr>\n",
|
881 |
" <tr>\n",
|
882 |
" <th>...</th>\n",
|
@@ -892,128 +588,134 @@
|
|
892 |
" <td>...</td>\n",
|
893 |
" <td>...</td>\n",
|
894 |
" <td>...</td>\n",
|
|
|
895 |
" </tr>\n",
|
896 |
" <tr>\n",
|
897 |
" <th>115</th>\n",
|
898 |
-
" <td>
|
899 |
-
" <td>2024-05-
|
900 |
-
" <td>2024-05-
|
901 |
-
" <td>
|
902 |
-
" <td>
|
903 |
-
" <td>
|
|
|
|
|
904 |
" <td>0.0</td>\n",
|
905 |
-
" <td>
|
906 |
-
" <td>
|
907 |
-
" <td>
|
908 |
-
" <td>
|
909 |
-
" <td>25.9</td>\n",
|
910 |
" </tr>\n",
|
911 |
" <tr>\n",
|
912 |
" <th>116</th>\n",
|
913 |
-
" <td>
|
914 |
-
" <td>2024-05-
|
915 |
-
" <td>2024-05-
|
916 |
-
" <td>
|
917 |
-
" <td>83</td>\n",
|
918 |
-
" <td>0.0</td>\n",
|
919 |
-
" <td>0.0</td>\n",
|
920 |
-
" <td>0.0</td>\n",
|
921 |
-
" <td>3</td>\n",
|
922 |
-
" <td>91</td>\n",
|
923 |
" <td>10.1</td>\n",
|
924 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
925 |
" </tr>\n",
|
926 |
" <tr>\n",
|
927 |
" <th>117</th>\n",
|
928 |
-
" <td>
|
929 |
-
" <td>2024-05-
|
930 |
-
" <td>2024-05-
|
931 |
-
" <td>
|
932 |
-
" <td>86</td>\n",
|
933 |
-
" <td>0.0</td>\n",
|
934 |
-
" <td>0.0</td>\n",
|
935 |
-
" <td>0.0</td>\n",
|
936 |
-
" <td>3</td>\n",
|
937 |
-
" <td>98</td>\n",
|
938 |
" <td>9.5</td>\n",
|
939 |
-
" <td>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
940 |
" </tr>\n",
|
941 |
" <tr>\n",
|
942 |
" <th>118</th>\n",
|
943 |
-
" <td>
|
944 |
-
" <td>2024-05-
|
945 |
-
" <td>2024-05-
|
946 |
-
" <td>
|
947 |
-
" <td>
|
948 |
-
" <td>
|
|
|
|
|
949 |
" <td>0.0</td>\n",
|
950 |
-
" <td>
|
951 |
-
" <td>
|
952 |
-
" <td>
|
953 |
-
" <td>
|
954 |
-
" <td>22.3</td>\n",
|
955 |
" </tr>\n",
|
956 |
" <tr>\n",
|
957 |
" <th>119</th>\n",
|
958 |
-
" <td>
|
959 |
-
" <td>2024-05-
|
960 |
-
" <td>2024-05-
|
961 |
-
" <td>
|
962 |
-
" <td>
|
963 |
-
" <td>
|
|
|
|
|
964 |
" <td>0.0</td>\n",
|
965 |
-
" <td>
|
966 |
-
" <td>
|
967 |
-
" <td>
|
968 |
-
" <td>
|
969 |
-
" <td>24.1</td>\n",
|
970 |
" </tr>\n",
|
971 |
" </tbody>\n",
|
972 |
"</table>\n",
|
973 |
-
"<p>120 rows ×
|
974 |
"</div>"
|
975 |
],
|
976 |
"text/plain": [
|
977 |
-
" timestamp date
|
978 |
-
"0
|
979 |
-
"1
|
980 |
-
"2
|
981 |
-
"3
|
982 |
-
"4
|
983 |
-
".. ... ...
|
984 |
-
"115
|
985 |
-
"116
|
986 |
-
"117
|
987 |
-
"118
|
988 |
-
"119
|
989 |
"\n",
|
990 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
991 |
-
"0
|
992 |
-
"1
|
993 |
-
"2
|
994 |
-
"3
|
995 |
-
"4
|
996 |
".. ... ... ... ... ... \n",
|
997 |
-
"115
|
998 |
-
"116
|
999 |
-
"117
|
1000 |
-
"118
|
1001 |
-
"119
|
1002 |
"\n",
|
1003 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1004 |
-
"0
|
1005 |
-
"1
|
1006 |
-
"2
|
1007 |
-
"3
|
1008 |
-
"4
|
1009 |
".. ... ... ... \n",
|
1010 |
-
"115
|
1011 |
-
"116
|
1012 |
-
"117
|
1013 |
-
"118
|
1014 |
-
"119
|
1015 |
"\n",
|
1016 |
-
"[120 rows x
|
1017 |
]
|
1018 |
},
|
1019 |
"execution_count": 10,
|
@@ -1030,20 +732,6 @@
|
|
1030 |
"cell_type": "code",
|
1031 |
"execution_count": 11,
|
1032 |
"metadata": {},
|
1033 |
-
"outputs": [],
|
1034 |
-
"source": [
|
1035 |
-
"# Converting to float type to align with Hopworks Feature Group as it converts the data to float automatically\n",
|
1036 |
-
"\n",
|
1037 |
-
"# Converting 'relative_humidity_2m', 'weather_code' and 'cloud_cover' columns to float type\n",
|
1038 |
-
"weather_forecast_df['relative_humidity_2m'] = weather_forecast_df['relative_humidity_2m'].astype(float)\n",
|
1039 |
-
"weather_forecast_df['weather_code'] = weather_forecast_df['weather_code'].astype(float)\n",
|
1040 |
-
"weather_forecast_df['cloud_cover'] = weather_forecast_df['cloud_cover'].astype(float)"
|
1041 |
-
]
|
1042 |
-
},
|
1043 |
-
{
|
1044 |
-
"cell_type": "code",
|
1045 |
-
"execution_count": 12,
|
1046 |
-
"metadata": {},
|
1047 |
"outputs": [
|
1048 |
{
|
1049 |
"data": {
|
@@ -1067,8 +755,9 @@
|
|
1067 |
" <tr style=\"text-align: right;\">\n",
|
1068 |
" <th></th>\n",
|
1069 |
" <th>timestamp</th>\n",
|
|
|
1070 |
" <th>date</th>\n",
|
1071 |
-
" <th>
|
1072 |
" <th>temperature_2m</th>\n",
|
1073 |
" <th>relative_humidity_2m</th>\n",
|
1074 |
" <th>precipitation</th>\n",
|
@@ -1083,107 +772,112 @@
|
|
1083 |
" <tbody>\n",
|
1084 |
" <tr>\n",
|
1085 |
" <th>0</th>\n",
|
1086 |
-
" <td>
|
1087 |
-
" <td>2024-05-
|
1088 |
-
" <td>2024-05-
|
1089 |
-
" <td>
|
1090 |
-
" <td>
|
|
|
1091 |
" <td>0.0</td>\n",
|
1092 |
" <td>0.0</td>\n",
|
1093 |
" <td>0.0</td>\n",
|
1094 |
-
" <td>
|
1095 |
-
" <td>
|
1096 |
-
" <td>
|
1097 |
-
" <td>
|
1098 |
" </tr>\n",
|
1099 |
" <tr>\n",
|
1100 |
" <th>1</th>\n",
|
1101 |
-
" <td>
|
1102 |
-
" <td>2024-05-01</td>\n",
|
1103 |
-
" <td>2024-05-
|
1104 |
-
" <td>
|
1105 |
-
" <td>
|
|
|
1106 |
" <td>0.0</td>\n",
|
1107 |
" <td>0.0</td>\n",
|
1108 |
" <td>0.0</td>\n",
|
1109 |
" <td>0.0</td>\n",
|
1110 |
-
" <td>
|
1111 |
-
" <td>
|
1112 |
-
" <td>
|
1113 |
" </tr>\n",
|
1114 |
" <tr>\n",
|
1115 |
" <th>2</th>\n",
|
1116 |
-
" <td>
|
1117 |
-
" <td>2024-05-
|
1118 |
-
" <td>2024-05-
|
1119 |
-
" <td>
|
1120 |
-
" <td>
|
|
|
1121 |
" <td>0.0</td>\n",
|
1122 |
" <td>0.0</td>\n",
|
1123 |
" <td>0.0</td>\n",
|
1124 |
" <td>2.0</td>\n",
|
1125 |
-
" <td>
|
1126 |
-
" <td>
|
1127 |
-
" <td>
|
1128 |
" </tr>\n",
|
1129 |
" <tr>\n",
|
1130 |
" <th>3</th>\n",
|
1131 |
-
" <td>
|
1132 |
-
" <td>2024-05-
|
1133 |
-
" <td>2024-05-
|
1134 |
-
" <td>
|
1135 |
-
" <td>
|
1136 |
-
" <td>
|
1137 |
-
" <td>0.
|
|
|
1138 |
" <td>0.0</td>\n",
|
1139 |
-
" <td>
|
1140 |
-
" <td>
|
1141 |
-
" <td>
|
1142 |
-
" <td>
|
1143 |
" </tr>\n",
|
1144 |
" <tr>\n",
|
1145 |
" <th>4</th>\n",
|
1146 |
-
" <td>
|
1147 |
-
" <td>2024-05-
|
1148 |
-
" <td>2024-05-
|
1149 |
-
" <td>
|
1150 |
-
" <td>
|
|
|
1151 |
" <td>0.0</td>\n",
|
1152 |
" <td>0.0</td>\n",
|
1153 |
" <td>0.0</td>\n",
|
1154 |
-
" <td>
|
1155 |
-
" <td>
|
1156 |
-
" <td>
|
1157 |
-
" <td>
|
1158 |
" </tr>\n",
|
1159 |
" </tbody>\n",
|
1160 |
"</table>\n",
|
1161 |
"</div>"
|
1162 |
],
|
1163 |
"text/plain": [
|
1164 |
-
" timestamp date
|
1165 |
-
"0
|
1166 |
-
"1
|
1167 |
-
"2
|
1168 |
-
"3
|
1169 |
-
"4
|
1170 |
"\n",
|
1171 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1172 |
-
"0
|
1173 |
-
"1
|
1174 |
-
"2
|
1175 |
-
"3
|
1176 |
-
"4
|
1177 |
"\n",
|
1178 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1179 |
-
"0
|
1180 |
-
"1
|
1181 |
-
"2
|
1182 |
-
"3
|
1183 |
-
"4
|
1184 |
]
|
1185 |
},
|
1186 |
-
"execution_count":
|
1187 |
"metadata": {},
|
1188 |
"output_type": "execute_result"
|
1189 |
}
|
@@ -1193,6 +887,164 @@
|
|
1193 |
"weather_forecast_df.head(5)"
|
1194 |
]
|
1195 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1196 |
{
|
1197 |
"cell_type": "markdown",
|
1198 |
"metadata": {},
|
@@ -1241,10 +1093,10 @@
|
|
1241 |
" version=1,\n",
|
1242 |
")\n",
|
1243 |
"\n",
|
1244 |
-
"forecast_renewable_energy_fg = fs.get_feature_group(\n",
|
1245 |
-
"
|
1246 |
-
"
|
1247 |
-
")\n",
|
1248 |
"\n",
|
1249 |
"weather_fg = fs.get_feature_group(\n",
|
1250 |
" name=\"weather_measurements\",\n",
|
@@ -1268,7 +1120,7 @@
|
|
1268 |
{
|
1269 |
"data": {
|
1270 |
"application/vnd.jupyter.widget-view+json": {
|
1271 |
-
"model_id": "
|
1272 |
"version_major": 2,
|
1273 |
"version_minor": 0
|
1274 |
},
|
@@ -1291,7 +1143,7 @@
|
|
1291 |
{
|
1292 |
"data": {
|
1293 |
"text/plain": [
|
1294 |
-
"(<hsfs.core.job.Job at
|
1295 |
]
|
1296 |
},
|
1297 |
"execution_count": 15,
|
@@ -1307,58 +1159,24 @@
|
|
1307 |
},
|
1308 |
{
|
1309 |
"cell_type": "code",
|
1310 |
-
"execution_count":
|
1311 |
"metadata": {},
|
1312 |
-
"outputs": [
|
1313 |
-
{
|
1314 |
-
"data": {
|
1315 |
-
"application/vnd.jupyter.widget-view+json": {
|
1316 |
-
"model_id": "b2c640cab44b4d66add7c785eb9fd16b",
|
1317 |
-
"version_major": 2,
|
1318 |
-
"version_minor": 0
|
1319 |
-
},
|
1320 |
-
"text/plain": [
|
1321 |
-
"Uploading Dataframe: 0.00% | | Rows 0/24 | Elapsed Time: 00:00 | Remaining Time: ?"
|
1322 |
-
]
|
1323 |
-
},
|
1324 |
-
"metadata": {},
|
1325 |
-
"output_type": "display_data"
|
1326 |
-
},
|
1327 |
-
{
|
1328 |
-
"name": "stdout",
|
1329 |
-
"output_type": "stream",
|
1330 |
-
"text": [
|
1331 |
-
"Launching job: forecast_renewable_energy_1_offline_fg_materialization\n",
|
1332 |
-
"Job started successfully, you can follow the progress at \n",
|
1333 |
-
"https://c.app.hopsworks.ai/p/554133/jobs/named/forecast_renewable_energy_1_offline_fg_materialization/executions\n"
|
1334 |
-
]
|
1335 |
-
},
|
1336 |
-
{
|
1337 |
-
"data": {
|
1338 |
-
"text/plain": [
|
1339 |
-
"(<hsfs.core.job.Job at 0x15f0fa910>, None)"
|
1340 |
-
]
|
1341 |
-
},
|
1342 |
-
"execution_count": 18,
|
1343 |
-
"metadata": {},
|
1344 |
-
"output_type": "execute_result"
|
1345 |
-
}
|
1346 |
-
],
|
1347 |
"source": [
|
1348 |
-
"# Inserting the forecast_renewable_energy_df into the feature group named forecast_renewable_energy_fg\n",
|
1349 |
-
"forecast_renewable_energy_fg.insert(forecast_renewable_energy_df, \n",
|
1350 |
-
"
|
1351 |
]
|
1352 |
},
|
1353 |
{
|
1354 |
"cell_type": "code",
|
1355 |
-
"execution_count":
|
1356 |
"metadata": {},
|
1357 |
"outputs": [
|
1358 |
{
|
1359 |
"data": {
|
1360 |
"application/vnd.jupyter.widget-view+json": {
|
1361 |
-
"model_id": "
|
1362 |
"version_major": 2,
|
1363 |
"version_minor": 0
|
1364 |
},
|
@@ -1381,10 +1199,10 @@
|
|
1381 |
{
|
1382 |
"data": {
|
1383 |
"text/plain": [
|
1384 |
-
"(<hsfs.core.job.Job at
|
1385 |
]
|
1386 |
},
|
1387 |
-
"execution_count":
|
1388 |
"metadata": {},
|
1389 |
"output_type": "execute_result"
|
1390 |
}
|
|
|
45 |
"\n",
|
46 |
"# Now we import the functions from the features folder\n",
|
47 |
"# This is the functions we have created to generate features for electricity prices and weather measures\n",
|
48 |
+
"from features import electricity_prices, weather_measures, calendar\n",
|
49 |
"\n",
|
50 |
"# We go back into the notebooks folder\n",
|
51 |
"%cd notebooks"
|
|
|
126 |
" <tr style=\"text-align: right;\">\n",
|
127 |
" <th></th>\n",
|
128 |
" <th>timestamp</th>\n",
|
129 |
+
" <th>datetime</th>\n",
|
130 |
" <th>date</th>\n",
|
131 |
+
" <th>hour</th>\n",
|
132 |
" <th>dk1_spotpricedkk_kwh</th>\n",
|
133 |
" </tr>\n",
|
134 |
" </thead>\n",
|
135 |
" <tbody>\n",
|
136 |
" <tr>\n",
|
137 |
" <th>0</th>\n",
|
138 |
+
" <td>1714608000000</td>\n",
|
139 |
+
" <td>2024-05-02 00:00:00</td>\n",
|
140 |
+
" <td>2024-05-02</td>\n",
|
141 |
+
" <td>0</td>\n",
|
142 |
+
" <td>0.10859</td>\n",
|
143 |
" </tr>\n",
|
144 |
" <tr>\n",
|
145 |
" <th>1</th>\n",
|
146 |
+
" <td>1714611600000</td>\n",
|
147 |
+
" <td>2024-05-02 01:00:00</td>\n",
|
148 |
+
" <td>2024-05-02</td>\n",
|
149 |
+
" <td>1</td>\n",
|
150 |
+
" <td>0.08160</td>\n",
|
151 |
" </tr>\n",
|
152 |
" <tr>\n",
|
153 |
" <th>2</th>\n",
|
154 |
+
" <td>1714615200000</td>\n",
|
155 |
+
" <td>2024-05-02 02:00:00</td>\n",
|
156 |
+
" <td>2024-05-02</td>\n",
|
157 |
+
" <td>2</td>\n",
|
158 |
+
" <td>0.07458</td>\n",
|
159 |
" </tr>\n",
|
160 |
" <tr>\n",
|
161 |
" <th>3</th>\n",
|
162 |
+
" <td>1714618800000</td>\n",
|
163 |
+
" <td>2024-05-02 03:00:00</td>\n",
|
164 |
+
" <td>2024-05-02</td>\n",
|
165 |
+
" <td>3</td>\n",
|
166 |
+
" <td>0.05818</td>\n",
|
167 |
" </tr>\n",
|
168 |
" <tr>\n",
|
169 |
" <th>4</th>\n",
|
170 |
+
" <td>1714622400000</td>\n",
|
171 |
+
" <td>2024-05-02 04:00:00</td>\n",
|
172 |
+
" <td>2024-05-02</td>\n",
|
173 |
+
" <td>4</td>\n",
|
174 |
+
" <td>0.07928</td>\n",
|
175 |
" </tr>\n",
|
176 |
" <tr>\n",
|
177 |
" <th>5</th>\n",
|
178 |
+
" <td>1714626000000</td>\n",
|
179 |
+
" <td>2024-05-02 05:00:00</td>\n",
|
180 |
+
" <td>2024-05-02</td>\n",
|
181 |
+
" <td>5</td>\n",
|
182 |
+
" <td>0.22920</td>\n",
|
183 |
" </tr>\n",
|
184 |
" <tr>\n",
|
185 |
" <th>6</th>\n",
|
186 |
+
" <td>1714629600000</td>\n",
|
187 |
+
" <td>2024-05-02 06:00:00</td>\n",
|
188 |
+
" <td>2024-05-02</td>\n",
|
189 |
+
" <td>6</td>\n",
|
190 |
+
" <td>0.29699</td>\n",
|
191 |
" </tr>\n",
|
192 |
" <tr>\n",
|
193 |
" <th>7</th>\n",
|
194 |
+
" <td>1714633200000</td>\n",
|
195 |
+
" <td>2024-05-02 07:00:00</td>\n",
|
196 |
+
" <td>2024-05-02</td>\n",
|
197 |
+
" <td>7</td>\n",
|
198 |
+
" <td>0.38605</td>\n",
|
199 |
" </tr>\n",
|
200 |
" <tr>\n",
|
201 |
" <th>8</th>\n",
|
202 |
+
" <td>1714636800000</td>\n",
|
203 |
+
" <td>2024-05-02 08:00:00</td>\n",
|
204 |
+
" <td>2024-05-02</td>\n",
|
205 |
+
" <td>8</td>\n",
|
206 |
+
" <td>0.43729</td>\n",
|
207 |
" </tr>\n",
|
208 |
" <tr>\n",
|
209 |
" <th>9</th>\n",
|
210 |
+
" <td>1714640400000</td>\n",
|
211 |
+
" <td>2024-05-02 09:00:00</td>\n",
|
212 |
+
" <td>2024-05-02</td>\n",
|
213 |
+
" <td>9</td>\n",
|
214 |
+
" <td>0.23457</td>\n",
|
215 |
" </tr>\n",
|
216 |
" <tr>\n",
|
217 |
" <th>10</th>\n",
|
218 |
+
" <td>1714644000000</td>\n",
|
219 |
+
" <td>2024-05-02 10:00:00</td>\n",
|
220 |
+
" <td>2024-05-02</td>\n",
|
221 |
+
" <td>10</td>\n",
|
222 |
+
" <td>0.03804</td>\n",
|
223 |
" </tr>\n",
|
224 |
" <tr>\n",
|
225 |
" <th>11</th>\n",
|
226 |
+
" <td>1714647600000</td>\n",
|
227 |
+
" <td>2024-05-02 11:00:00</td>\n",
|
228 |
+
" <td>2024-05-02</td>\n",
|
229 |
+
" <td>11</td>\n",
|
230 |
+
" <td>-0.00060</td>\n",
|
231 |
" </tr>\n",
|
232 |
" <tr>\n",
|
233 |
" <th>12</th>\n",
|
234 |
+
" <td>1714651200000</td>\n",
|
235 |
+
" <td>2024-05-02 12:00:00</td>\n",
|
236 |
+
" <td>2024-05-02</td>\n",
|
237 |
+
" <td>12</td>\n",
|
238 |
+
" <td>-0.01290</td>\n",
|
239 |
" </tr>\n",
|
240 |
" <tr>\n",
|
241 |
" <th>13</th>\n",
|
242 |
+
" <td>1714654800000</td>\n",
|
243 |
+
" <td>2024-05-02 13:00:00</td>\n",
|
244 |
+
" <td>2024-05-02</td>\n",
|
245 |
+
" <td>13</td>\n",
|
246 |
+
" <td>-0.02014</td>\n",
|
247 |
" </tr>\n",
|
248 |
" <tr>\n",
|
249 |
" <th>14</th>\n",
|
250 |
+
" <td>1714658400000</td>\n",
|
251 |
+
" <td>2024-05-02 14:00:00</td>\n",
|
252 |
+
" <td>2024-05-02</td>\n",
|
253 |
+
" <td>14</td>\n",
|
254 |
+
" <td>-0.00037</td>\n",
|
255 |
" </tr>\n",
|
256 |
" <tr>\n",
|
257 |
" <th>15</th>\n",
|
258 |
+
" <td>1714662000000</td>\n",
|
259 |
+
" <td>2024-05-02 15:00:00</td>\n",
|
260 |
+
" <td>2024-05-02</td>\n",
|
261 |
+
" <td>15</td>\n",
|
262 |
+
" <td>-0.01037</td>\n",
|
263 |
" </tr>\n",
|
264 |
" <tr>\n",
|
265 |
" <th>16</th>\n",
|
266 |
+
" <td>1714665600000</td>\n",
|
267 |
+
" <td>2024-05-02 16:00:00</td>\n",
|
268 |
+
" <td>2024-05-02</td>\n",
|
269 |
+
" <td>16</td>\n",
|
270 |
+
" <td>0.03013</td>\n",
|
271 |
" </tr>\n",
|
272 |
" <tr>\n",
|
273 |
" <th>17</th>\n",
|
274 |
+
" <td>1714669200000</td>\n",
|
275 |
+
" <td>2024-05-02 17:00:00</td>\n",
|
276 |
+
" <td>2024-05-02</td>\n",
|
277 |
+
" <td>17</td>\n",
|
278 |
+
" <td>0.26045</td>\n",
|
279 |
" </tr>\n",
|
280 |
" <tr>\n",
|
281 |
" <th>18</th>\n",
|
282 |
+
" <td>1714672800000</td>\n",
|
283 |
+
" <td>2024-05-02 18:00:00</td>\n",
|
284 |
+
" <td>2024-05-02</td>\n",
|
285 |
+
" <td>18</td>\n",
|
286 |
+
" <td>0.29125</td>\n",
|
287 |
" </tr>\n",
|
288 |
" <tr>\n",
|
289 |
" <th>19</th>\n",
|
290 |
+
" <td>1714676400000</td>\n",
|
291 |
+
" <td>2024-05-02 19:00:00</td>\n",
|
292 |
+
" <td>2024-05-02</td>\n",
|
293 |
+
" <td>19</td>\n",
|
294 |
+
" <td>0.31266</td>\n",
|
295 |
" </tr>\n",
|
296 |
" <tr>\n",
|
297 |
" <th>20</th>\n",
|
298 |
+
" <td>1714680000000</td>\n",
|
299 |
+
" <td>2024-05-02 20:00:00</td>\n",
|
300 |
+
" <td>2024-05-02</td>\n",
|
301 |
+
" <td>20</td>\n",
|
302 |
+
" <td>0.31318</td>\n",
|
303 |
" </tr>\n",
|
304 |
" <tr>\n",
|
305 |
" <th>21</th>\n",
|
306 |
+
" <td>1714683600000</td>\n",
|
307 |
+
" <td>2024-05-02 21:00:00</td>\n",
|
308 |
+
" <td>2024-05-02</td>\n",
|
309 |
+
" <td>21</td>\n",
|
310 |
+
" <td>0.31266</td>\n",
|
311 |
" </tr>\n",
|
312 |
" <tr>\n",
|
313 |
" <th>22</th>\n",
|
314 |
+
" <td>1714687200000</td>\n",
|
315 |
+
" <td>2024-05-02 22:00:00</td>\n",
|
316 |
+
" <td>2024-05-02</td>\n",
|
317 |
+
" <td>22</td>\n",
|
318 |
+
" <td>0.28245</td>\n",
|
319 |
" </tr>\n",
|
320 |
" <tr>\n",
|
321 |
" <th>23</th>\n",
|
322 |
+
" <td>1714690800000</td>\n",
|
323 |
+
" <td>2024-05-02 23:00:00</td>\n",
|
324 |
+
" <td>2024-05-02</td>\n",
|
325 |
+
" <td>23</td>\n",
|
326 |
+
" <td>0.25306</td>\n",
|
327 |
" </tr>\n",
|
328 |
" </tbody>\n",
|
329 |
"</table>\n",
|
330 |
"</div>"
|
331 |
],
|
332 |
"text/plain": [
|
333 |
+
" timestamp datetime date hour dk1_spotpricedkk_kwh\n",
|
334 |
+
"0 1714608000000 2024-05-02 00:00:00 2024-05-02 0 0.10859\n",
|
335 |
+
"1 1714611600000 2024-05-02 01:00:00 2024-05-02 1 0.08160\n",
|
336 |
+
"2 1714615200000 2024-05-02 02:00:00 2024-05-02 2 0.07458\n",
|
337 |
+
"3 1714618800000 2024-05-02 03:00:00 2024-05-02 3 0.05818\n",
|
338 |
+
"4 1714622400000 2024-05-02 04:00:00 2024-05-02 4 0.07928\n",
|
339 |
+
"5 1714626000000 2024-05-02 05:00:00 2024-05-02 5 0.22920\n",
|
340 |
+
"6 1714629600000 2024-05-02 06:00:00 2024-05-02 6 0.29699\n",
|
341 |
+
"7 1714633200000 2024-05-02 07:00:00 2024-05-02 7 0.38605\n",
|
342 |
+
"8 1714636800000 2024-05-02 08:00:00 2024-05-02 8 0.43729\n",
|
343 |
+
"9 1714640400000 2024-05-02 09:00:00 2024-05-02 9 0.23457\n",
|
344 |
+
"10 1714644000000 2024-05-02 10:00:00 2024-05-02 10 0.03804\n",
|
345 |
+
"11 1714647600000 2024-05-02 11:00:00 2024-05-02 11 -0.00060\n",
|
346 |
+
"12 1714651200000 2024-05-02 12:00:00 2024-05-02 12 -0.01290\n",
|
347 |
+
"13 1714654800000 2024-05-02 13:00:00 2024-05-02 13 -0.02014\n",
|
348 |
+
"14 1714658400000 2024-05-02 14:00:00 2024-05-02 14 -0.00037\n",
|
349 |
+
"15 1714662000000 2024-05-02 15:00:00 2024-05-02 15 -0.01037\n",
|
350 |
+
"16 1714665600000 2024-05-02 16:00:00 2024-05-02 16 0.03013\n",
|
351 |
+
"17 1714669200000 2024-05-02 17:00:00 2024-05-02 17 0.26045\n",
|
352 |
+
"18 1714672800000 2024-05-02 18:00:00 2024-05-02 18 0.29125\n",
|
353 |
+
"19 1714676400000 2024-05-02 19:00:00 2024-05-02 19 0.31266\n",
|
354 |
+
"20 1714680000000 2024-05-02 20:00:00 2024-05-02 20 0.31318\n",
|
355 |
+
"21 1714683600000 2024-05-02 21:00:00 2024-05-02 21 0.31266\n",
|
356 |
+
"22 1714687200000 2024-05-02 22:00:00 2024-05-02 22 0.28245\n",
|
357 |
+
"23 1714690800000 2024-05-02 23:00:00 2024-05-02 23 0.25306"
|
358 |
]
|
359 |
},
|
360 |
"execution_count": 4,
|
|
|
380 |
"metadata": {},
|
381 |
"outputs": [],
|
382 |
"source": [
|
383 |
+
"# # Fetching non-historical forecast of renewable energy data for area DK1\n",
|
384 |
+
"# forecast_renewable_energy_df = electricity_prices.forecast_renewable_energy(\n",
|
385 |
+
"# historical=False,\n",
|
386 |
+
"# area=[\"DK1\"]\n",
|
387 |
+
"# )"
|
388 |
]
|
389 |
},
|
390 |
{
|
391 |
"cell_type": "code",
|
392 |
"execution_count": 6,
|
393 |
"metadata": {},
|
394 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
395 |
"source": [
|
396 |
+
"# # Display the forecast_renewable_energy dataframe\n",
|
397 |
+
"# forecast_renewable_energy_df"
|
398 |
]
|
399 |
},
|
400 |
{
|
|
|
479 |
" <tr style=\"text-align: right;\">\n",
|
480 |
" <th></th>\n",
|
481 |
" <th>timestamp</th>\n",
|
482 |
+
" <th>datetime</th>\n",
|
483 |
" <th>date</th>\n",
|
484 |
+
" <th>hour</th>\n",
|
485 |
" <th>temperature_2m</th>\n",
|
486 |
" <th>relative_humidity_2m</th>\n",
|
487 |
" <th>precipitation</th>\n",
|
|
|
496 |
" <tbody>\n",
|
497 |
" <tr>\n",
|
498 |
" <th>0</th>\n",
|
499 |
+
" <td>1714608000000</td>\n",
|
500 |
+
" <td>2024-05-02 00:00:00</td>\n",
|
501 |
+
" <td>2024-05-02</td>\n",
|
502 |
+
" <td>0</td>\n",
|
503 |
+
" <td>14.9</td>\n",
|
504 |
+
" <td>66.0</td>\n",
|
505 |
" <td>0.0</td>\n",
|
506 |
" <td>0.0</td>\n",
|
507 |
" <td>0.0</td>\n",
|
508 |
+
" <td>0.0</td>\n",
|
509 |
+
" <td>13.0</td>\n",
|
510 |
+
" <td>21.6</td>\n",
|
511 |
+
" <td>41.4</td>\n",
|
512 |
" </tr>\n",
|
513 |
" <tr>\n",
|
514 |
" <th>1</th>\n",
|
515 |
+
" <td>1714611600000</td>\n",
|
516 |
+
" <td>2024-05-02 01:00:00</td>\n",
|
517 |
+
" <td>2024-05-02</td>\n",
|
518 |
+
" <td>1</td>\n",
|
519 |
+
" <td>14.2</td>\n",
|
520 |
+
" <td>71.0</td>\n",
|
521 |
" <td>0.0</td>\n",
|
522 |
" <td>0.0</td>\n",
|
523 |
" <td>0.0</td>\n",
|
524 |
+
" <td>0.0</td>\n",
|
525 |
+
" <td>4.0</td>\n",
|
526 |
+
" <td>20.5</td>\n",
|
527 |
+
" <td>37.1</td>\n",
|
528 |
" </tr>\n",
|
529 |
" <tr>\n",
|
530 |
" <th>2</th>\n",
|
531 |
+
" <td>1714615200000</td>\n",
|
532 |
+
" <td>2024-05-02 02:00:00</td>\n",
|
533 |
+
" <td>2024-05-02</td>\n",
|
534 |
+
" <td>2</td>\n",
|
535 |
+
" <td>13.4</td>\n",
|
536 |
+
" <td>73.0</td>\n",
|
537 |
" <td>0.0</td>\n",
|
538 |
" <td>0.0</td>\n",
|
539 |
" <td>0.0</td>\n",
|
540 |
+
" <td>2.0</td>\n",
|
541 |
+
" <td>70.0</td>\n",
|
542 |
+
" <td>21.2</td>\n",
|
543 |
+
" <td>36.7</td>\n",
|
544 |
" </tr>\n",
|
545 |
" <tr>\n",
|
546 |
" <th>3</th>\n",
|
547 |
+
" <td>1714618800000</td>\n",
|
548 |
+
" <td>2024-05-02 03:00:00</td>\n",
|
549 |
+
" <td>2024-05-02</td>\n",
|
|
|
|
|
|
|
|
|
|
|
550 |
" <td>3</td>\n",
|
551 |
+
" <td>13.2</td>\n",
|
552 |
+
" <td>72.0</td>\n",
|
553 |
+
" <td>0.1</td>\n",
|
554 |
+
" <td>0.1</td>\n",
|
555 |
+
" <td>0.0</td>\n",
|
556 |
+
" <td>51.0</td>\n",
|
557 |
+
" <td>51.0</td>\n",
|
558 |
+
" <td>22.3</td>\n",
|
559 |
+
" <td>39.2</td>\n",
|
560 |
" </tr>\n",
|
561 |
" <tr>\n",
|
562 |
" <th>4</th>\n",
|
563 |
+
" <td>1714622400000</td>\n",
|
564 |
+
" <td>2024-05-02 04:00:00</td>\n",
|
565 |
+
" <td>2024-05-02</td>\n",
|
566 |
+
" <td>4</td>\n",
|
567 |
+
" <td>12.7</td>\n",
|
568 |
+
" <td>73.0</td>\n",
|
569 |
" <td>0.0</td>\n",
|
570 |
" <td>0.0</td>\n",
|
571 |
" <td>0.0</td>\n",
|
572 |
+
" <td>2.0</td>\n",
|
573 |
+
" <td>78.0</td>\n",
|
574 |
+
" <td>21.6</td>\n",
|
575 |
+
" <td>38.9</td>\n",
|
576 |
" </tr>\n",
|
577 |
" <tr>\n",
|
578 |
" <th>...</th>\n",
|
|
|
588 |
" <td>...</td>\n",
|
589 |
" <td>...</td>\n",
|
590 |
" <td>...</td>\n",
|
591 |
+
" <td>...</td>\n",
|
592 |
" </tr>\n",
|
593 |
" <tr>\n",
|
594 |
" <th>115</th>\n",
|
595 |
+
" <td>1715022000000</td>\n",
|
596 |
+
" <td>2024-05-06 19:00:00</td>\n",
|
597 |
+
" <td>2024-05-06</td>\n",
|
598 |
+
" <td>19</td>\n",
|
599 |
+
" <td>10.7</td>\n",
|
600 |
+
" <td>91.0</td>\n",
|
601 |
+
" <td>1.4</td>\n",
|
602 |
+
" <td>1.4</td>\n",
|
603 |
" <td>0.0</td>\n",
|
604 |
+
" <td>61.0</td>\n",
|
605 |
+
" <td>100.0</td>\n",
|
606 |
+
" <td>16.6</td>\n",
|
607 |
+
" <td>32.0</td>\n",
|
|
|
608 |
" </tr>\n",
|
609 |
" <tr>\n",
|
610 |
" <th>116</th>\n",
|
611 |
+
" <td>1715025600000</td>\n",
|
612 |
+
" <td>2024-05-06 20:00:00</td>\n",
|
613 |
+
" <td>2024-05-06</td>\n",
|
614 |
+
" <td>20</td>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
615 |
" <td>10.1</td>\n",
|
616 |
+
" <td>90.0</td>\n",
|
617 |
+
" <td>1.4</td>\n",
|
618 |
+
" <td>1.4</td>\n",
|
619 |
+
" <td>0.0</td>\n",
|
620 |
+
" <td>61.0</td>\n",
|
621 |
+
" <td>100.0</td>\n",
|
622 |
+
" <td>19.5</td>\n",
|
623 |
+
" <td>37.1</td>\n",
|
624 |
" </tr>\n",
|
625 |
" <tr>\n",
|
626 |
" <th>117</th>\n",
|
627 |
+
" <td>1715029200000</td>\n",
|
628 |
+
" <td>2024-05-06 21:00:00</td>\n",
|
629 |
+
" <td>2024-05-06</td>\n",
|
630 |
+
" <td>21</td>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
631 |
" <td>9.5</td>\n",
|
632 |
+
" <td>88.0</td>\n",
|
633 |
+
" <td>1.4</td>\n",
|
634 |
+
" <td>1.4</td>\n",
|
635 |
+
" <td>0.0</td>\n",
|
636 |
+
" <td>61.0</td>\n",
|
637 |
+
" <td>100.0</td>\n",
|
638 |
+
" <td>21.6</td>\n",
|
639 |
+
" <td>42.1</td>\n",
|
640 |
" </tr>\n",
|
641 |
" <tr>\n",
|
642 |
" <th>118</th>\n",
|
643 |
+
" <td>1715032800000</td>\n",
|
644 |
+
" <td>2024-05-06 22:00:00</td>\n",
|
645 |
+
" <td>2024-05-06</td>\n",
|
646 |
+
" <td>22</td>\n",
|
647 |
+
" <td>9.3</td>\n",
|
648 |
+
" <td>86.0</td>\n",
|
649 |
+
" <td>0.6</td>\n",
|
650 |
+
" <td>0.6</td>\n",
|
651 |
" <td>0.0</td>\n",
|
652 |
+
" <td>3.0</td>\n",
|
653 |
+
" <td>100.0</td>\n",
|
654 |
+
" <td>22.0</td>\n",
|
655 |
+
" <td>41.0</td>\n",
|
|
|
656 |
" </tr>\n",
|
657 |
" <tr>\n",
|
658 |
" <th>119</th>\n",
|
659 |
+
" <td>1715036400000</td>\n",
|
660 |
+
" <td>2024-05-06 23:00:00</td>\n",
|
661 |
+
" <td>2024-05-06</td>\n",
|
662 |
+
" <td>23</td>\n",
|
663 |
+
" <td>9.1</td>\n",
|
664 |
+
" <td>84.0</td>\n",
|
665 |
+
" <td>0.6</td>\n",
|
666 |
+
" <td>0.6</td>\n",
|
667 |
" <td>0.0</td>\n",
|
668 |
+
" <td>3.0</td>\n",
|
669 |
+
" <td>100.0</td>\n",
|
670 |
+
" <td>21.3</td>\n",
|
671 |
+
" <td>40.3</td>\n",
|
|
|
672 |
" </tr>\n",
|
673 |
" </tbody>\n",
|
674 |
"</table>\n",
|
675 |
+
"<p>120 rows × 13 columns</p>\n",
|
676 |
"</div>"
|
677 |
],
|
678 |
"text/plain": [
|
679 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
680 |
+
"0 1714608000000 2024-05-02 00:00:00 2024-05-02 0 14.9 \n",
|
681 |
+
"1 1714611600000 2024-05-02 01:00:00 2024-05-02 1 14.2 \n",
|
682 |
+
"2 1714615200000 2024-05-02 02:00:00 2024-05-02 2 13.4 \n",
|
683 |
+
"3 1714618800000 2024-05-02 03:00:00 2024-05-02 3 13.2 \n",
|
684 |
+
"4 1714622400000 2024-05-02 04:00:00 2024-05-02 4 12.7 \n",
|
685 |
+
".. ... ... ... ... ... \n",
|
686 |
+
"115 1715022000000 2024-05-06 19:00:00 2024-05-06 19 10.7 \n",
|
687 |
+
"116 1715025600000 2024-05-06 20:00:00 2024-05-06 20 10.1 \n",
|
688 |
+
"117 1715029200000 2024-05-06 21:00:00 2024-05-06 21 9.5 \n",
|
689 |
+
"118 1715032800000 2024-05-06 22:00:00 2024-05-06 22 9.3 \n",
|
690 |
+
"119 1715036400000 2024-05-06 23:00:00 2024-05-06 23 9.1 \n",
|
691 |
"\n",
|
692 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
693 |
+
"0 66.0 0.0 0.0 0.0 0.0 \n",
|
694 |
+
"1 71.0 0.0 0.0 0.0 0.0 \n",
|
695 |
+
"2 73.0 0.0 0.0 0.0 2.0 \n",
|
696 |
+
"3 72.0 0.1 0.1 0.0 51.0 \n",
|
697 |
+
"4 73.0 0.0 0.0 0.0 2.0 \n",
|
698 |
".. ... ... ... ... ... \n",
|
699 |
+
"115 91.0 1.4 1.4 0.0 61.0 \n",
|
700 |
+
"116 90.0 1.4 1.4 0.0 61.0 \n",
|
701 |
+
"117 88.0 1.4 1.4 0.0 61.0 \n",
|
702 |
+
"118 86.0 0.6 0.6 0.0 3.0 \n",
|
703 |
+
"119 84.0 0.6 0.6 0.0 3.0 \n",
|
704 |
"\n",
|
705 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
706 |
+
"0 13.0 21.6 41.4 \n",
|
707 |
+
"1 4.0 20.5 37.1 \n",
|
708 |
+
"2 70.0 21.2 36.7 \n",
|
709 |
+
"3 51.0 22.3 39.2 \n",
|
710 |
+
"4 78.0 21.6 38.9 \n",
|
711 |
".. ... ... ... \n",
|
712 |
+
"115 100.0 16.6 32.0 \n",
|
713 |
+
"116 100.0 19.5 37.1 \n",
|
714 |
+
"117 100.0 21.6 42.1 \n",
|
715 |
+
"118 100.0 22.0 41.0 \n",
|
716 |
+
"119 100.0 21.3 40.3 \n",
|
717 |
"\n",
|
718 |
+
"[120 rows x 13 columns]"
|
719 |
]
|
720 |
},
|
721 |
"execution_count": 10,
|
|
|
732 |
"cell_type": "code",
|
733 |
"execution_count": 11,
|
734 |
"metadata": {},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
735 |
"outputs": [
|
736 |
{
|
737 |
"data": {
|
|
|
755 |
" <tr style=\"text-align: right;\">\n",
|
756 |
" <th></th>\n",
|
757 |
" <th>timestamp</th>\n",
|
758 |
+
" <th>datetime</th>\n",
|
759 |
" <th>date</th>\n",
|
760 |
+
" <th>hour</th>\n",
|
761 |
" <th>temperature_2m</th>\n",
|
762 |
" <th>relative_humidity_2m</th>\n",
|
763 |
" <th>precipitation</th>\n",
|
|
|
772 |
" <tbody>\n",
|
773 |
" <tr>\n",
|
774 |
" <th>0</th>\n",
|
775 |
+
" <td>1714608000000</td>\n",
|
776 |
+
" <td>2024-05-02 00:00:00</td>\n",
|
777 |
+
" <td>2024-05-02</td>\n",
|
778 |
+
" <td>0</td>\n",
|
779 |
+
" <td>14.9</td>\n",
|
780 |
+
" <td>66.0</td>\n",
|
781 |
" <td>0.0</td>\n",
|
782 |
" <td>0.0</td>\n",
|
783 |
" <td>0.0</td>\n",
|
784 |
+
" <td>0.0</td>\n",
|
785 |
+
" <td>13.0</td>\n",
|
786 |
+
" <td>21.6</td>\n",
|
787 |
+
" <td>41.4</td>\n",
|
788 |
" </tr>\n",
|
789 |
" <tr>\n",
|
790 |
" <th>1</th>\n",
|
791 |
+
" <td>1714611600000</td>\n",
|
792 |
+
" <td>2024-05-02 01:00:00</td>\n",
|
793 |
+
" <td>2024-05-02</td>\n",
|
794 |
+
" <td>1</td>\n",
|
795 |
+
" <td>14.2</td>\n",
|
796 |
+
" <td>71.0</td>\n",
|
797 |
" <td>0.0</td>\n",
|
798 |
" <td>0.0</td>\n",
|
799 |
" <td>0.0</td>\n",
|
800 |
" <td>0.0</td>\n",
|
801 |
+
" <td>4.0</td>\n",
|
802 |
+
" <td>20.5</td>\n",
|
803 |
+
" <td>37.1</td>\n",
|
804 |
" </tr>\n",
|
805 |
" <tr>\n",
|
806 |
" <th>2</th>\n",
|
807 |
+
" <td>1714615200000</td>\n",
|
808 |
+
" <td>2024-05-02 02:00:00</td>\n",
|
809 |
+
" <td>2024-05-02</td>\n",
|
810 |
+
" <td>2</td>\n",
|
811 |
+
" <td>13.4</td>\n",
|
812 |
+
" <td>73.0</td>\n",
|
813 |
" <td>0.0</td>\n",
|
814 |
" <td>0.0</td>\n",
|
815 |
" <td>0.0</td>\n",
|
816 |
" <td>2.0</td>\n",
|
817 |
+
" <td>70.0</td>\n",
|
818 |
+
" <td>21.2</td>\n",
|
819 |
+
" <td>36.7</td>\n",
|
820 |
" </tr>\n",
|
821 |
" <tr>\n",
|
822 |
" <th>3</th>\n",
|
823 |
+
" <td>1714618800000</td>\n",
|
824 |
+
" <td>2024-05-02 03:00:00</td>\n",
|
825 |
+
" <td>2024-05-02</td>\n",
|
826 |
+
" <td>3</td>\n",
|
827 |
+
" <td>13.2</td>\n",
|
828 |
+
" <td>72.0</td>\n",
|
829 |
+
" <td>0.1</td>\n",
|
830 |
+
" <td>0.1</td>\n",
|
831 |
" <td>0.0</td>\n",
|
832 |
+
" <td>51.0</td>\n",
|
833 |
+
" <td>51.0</td>\n",
|
834 |
+
" <td>22.3</td>\n",
|
835 |
+
" <td>39.2</td>\n",
|
836 |
" </tr>\n",
|
837 |
" <tr>\n",
|
838 |
" <th>4</th>\n",
|
839 |
+
" <td>1714622400000</td>\n",
|
840 |
+
" <td>2024-05-02 04:00:00</td>\n",
|
841 |
+
" <td>2024-05-02</td>\n",
|
842 |
+
" <td>4</td>\n",
|
843 |
+
" <td>12.7</td>\n",
|
844 |
+
" <td>73.0</td>\n",
|
845 |
" <td>0.0</td>\n",
|
846 |
" <td>0.0</td>\n",
|
847 |
" <td>0.0</td>\n",
|
848 |
+
" <td>2.0</td>\n",
|
849 |
+
" <td>78.0</td>\n",
|
850 |
+
" <td>21.6</td>\n",
|
851 |
+
" <td>38.9</td>\n",
|
852 |
" </tr>\n",
|
853 |
" </tbody>\n",
|
854 |
"</table>\n",
|
855 |
"</div>"
|
856 |
],
|
857 |
"text/plain": [
|
858 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
859 |
+
"0 1714608000000 2024-05-02 00:00:00 2024-05-02 0 14.9 \n",
|
860 |
+
"1 1714611600000 2024-05-02 01:00:00 2024-05-02 1 14.2 \n",
|
861 |
+
"2 1714615200000 2024-05-02 02:00:00 2024-05-02 2 13.4 \n",
|
862 |
+
"3 1714618800000 2024-05-02 03:00:00 2024-05-02 3 13.2 \n",
|
863 |
+
"4 1714622400000 2024-05-02 04:00:00 2024-05-02 4 12.7 \n",
|
864 |
"\n",
|
865 |
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
866 |
+
"0 66.0 0.0 0.0 0.0 0.0 \n",
|
867 |
+
"1 71.0 0.0 0.0 0.0 0.0 \n",
|
868 |
+
"2 73.0 0.0 0.0 0.0 2.0 \n",
|
869 |
+
"3 72.0 0.1 0.1 0.0 51.0 \n",
|
870 |
+
"4 73.0 0.0 0.0 0.0 2.0 \n",
|
871 |
"\n",
|
872 |
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
873 |
+
"0 13.0 21.6 41.4 \n",
|
874 |
+
"1 4.0 20.5 37.1 \n",
|
875 |
+
"2 70.0 21.2 36.7 \n",
|
876 |
+
"3 51.0 22.3 39.2 \n",
|
877 |
+
"4 78.0 21.6 38.9 "
|
878 |
]
|
879 |
},
|
880 |
+
"execution_count": 11,
|
881 |
"metadata": {},
|
882 |
"output_type": "execute_result"
|
883 |
}
|
|
|
887 |
"weather_forecast_df.head(5)"
|
888 |
]
|
889 |
},
|
890 |
+
{
|
891 |
+
"cell_type": "code",
|
892 |
+
"execution_count": 12,
|
893 |
+
"metadata": {},
|
894 |
+
"outputs": [
|
895 |
+
{
|
896 |
+
"data": {
|
897 |
+
"text/html": [
|
898 |
+
"<div>\n",
|
899 |
+
"<style scoped>\n",
|
900 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
901 |
+
" vertical-align: middle;\n",
|
902 |
+
" }\n",
|
903 |
+
"\n",
|
904 |
+
" .dataframe tbody tr th {\n",
|
905 |
+
" vertical-align: top;\n",
|
906 |
+
" }\n",
|
907 |
+
"\n",
|
908 |
+
" .dataframe thead th {\n",
|
909 |
+
" text-align: right;\n",
|
910 |
+
" }\n",
|
911 |
+
"</style>\n",
|
912 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
913 |
+
" <thead>\n",
|
914 |
+
" <tr style=\"text-align: right;\">\n",
|
915 |
+
" <th></th>\n",
|
916 |
+
" <th>timestamp</th>\n",
|
917 |
+
" <th>datetime</th>\n",
|
918 |
+
" <th>date</th>\n",
|
919 |
+
" <th>hour</th>\n",
|
920 |
+
" <th>temperature_2m</th>\n",
|
921 |
+
" <th>relative_humidity_2m</th>\n",
|
922 |
+
" <th>precipitation</th>\n",
|
923 |
+
" <th>rain</th>\n",
|
924 |
+
" <th>snowfall</th>\n",
|
925 |
+
" <th>weather_code</th>\n",
|
926 |
+
" <th>cloud_cover</th>\n",
|
927 |
+
" <th>wind_speed_10m</th>\n",
|
928 |
+
" <th>wind_gusts_10m</th>\n",
|
929 |
+
" </tr>\n",
|
930 |
+
" </thead>\n",
|
931 |
+
" <tbody>\n",
|
932 |
+
" <tr>\n",
|
933 |
+
" <th>115</th>\n",
|
934 |
+
" <td>1715022000000</td>\n",
|
935 |
+
" <td>2024-05-06 19:00:00</td>\n",
|
936 |
+
" <td>2024-05-06</td>\n",
|
937 |
+
" <td>19</td>\n",
|
938 |
+
" <td>10.7</td>\n",
|
939 |
+
" <td>91.0</td>\n",
|
940 |
+
" <td>1.4</td>\n",
|
941 |
+
" <td>1.4</td>\n",
|
942 |
+
" <td>0.0</td>\n",
|
943 |
+
" <td>61.0</td>\n",
|
944 |
+
" <td>100.0</td>\n",
|
945 |
+
" <td>16.6</td>\n",
|
946 |
+
" <td>32.0</td>\n",
|
947 |
+
" </tr>\n",
|
948 |
+
" <tr>\n",
|
949 |
+
" <th>116</th>\n",
|
950 |
+
" <td>1715025600000</td>\n",
|
951 |
+
" <td>2024-05-06 20:00:00</td>\n",
|
952 |
+
" <td>2024-05-06</td>\n",
|
953 |
+
" <td>20</td>\n",
|
954 |
+
" <td>10.1</td>\n",
|
955 |
+
" <td>90.0</td>\n",
|
956 |
+
" <td>1.4</td>\n",
|
957 |
+
" <td>1.4</td>\n",
|
958 |
+
" <td>0.0</td>\n",
|
959 |
+
" <td>61.0</td>\n",
|
960 |
+
" <td>100.0</td>\n",
|
961 |
+
" <td>19.5</td>\n",
|
962 |
+
" <td>37.1</td>\n",
|
963 |
+
" </tr>\n",
|
964 |
+
" <tr>\n",
|
965 |
+
" <th>117</th>\n",
|
966 |
+
" <td>1715029200000</td>\n",
|
967 |
+
" <td>2024-05-06 21:00:00</td>\n",
|
968 |
+
" <td>2024-05-06</td>\n",
|
969 |
+
" <td>21</td>\n",
|
970 |
+
" <td>9.5</td>\n",
|
971 |
+
" <td>88.0</td>\n",
|
972 |
+
" <td>1.4</td>\n",
|
973 |
+
" <td>1.4</td>\n",
|
974 |
+
" <td>0.0</td>\n",
|
975 |
+
" <td>61.0</td>\n",
|
976 |
+
" <td>100.0</td>\n",
|
977 |
+
" <td>21.6</td>\n",
|
978 |
+
" <td>42.1</td>\n",
|
979 |
+
" </tr>\n",
|
980 |
+
" <tr>\n",
|
981 |
+
" <th>118</th>\n",
|
982 |
+
" <td>1715032800000</td>\n",
|
983 |
+
" <td>2024-05-06 22:00:00</td>\n",
|
984 |
+
" <td>2024-05-06</td>\n",
|
985 |
+
" <td>22</td>\n",
|
986 |
+
" <td>9.3</td>\n",
|
987 |
+
" <td>86.0</td>\n",
|
988 |
+
" <td>0.6</td>\n",
|
989 |
+
" <td>0.6</td>\n",
|
990 |
+
" <td>0.0</td>\n",
|
991 |
+
" <td>3.0</td>\n",
|
992 |
+
" <td>100.0</td>\n",
|
993 |
+
" <td>22.0</td>\n",
|
994 |
+
" <td>41.0</td>\n",
|
995 |
+
" </tr>\n",
|
996 |
+
" <tr>\n",
|
997 |
+
" <th>119</th>\n",
|
998 |
+
" <td>1715036400000</td>\n",
|
999 |
+
" <td>2024-05-06 23:00:00</td>\n",
|
1000 |
+
" <td>2024-05-06</td>\n",
|
1001 |
+
" <td>23</td>\n",
|
1002 |
+
" <td>9.1</td>\n",
|
1003 |
+
" <td>84.0</td>\n",
|
1004 |
+
" <td>0.6</td>\n",
|
1005 |
+
" <td>0.6</td>\n",
|
1006 |
+
" <td>0.0</td>\n",
|
1007 |
+
" <td>3.0</td>\n",
|
1008 |
+
" <td>100.0</td>\n",
|
1009 |
+
" <td>21.3</td>\n",
|
1010 |
+
" <td>40.3</td>\n",
|
1011 |
+
" </tr>\n",
|
1012 |
+
" </tbody>\n",
|
1013 |
+
"</table>\n",
|
1014 |
+
"</div>"
|
1015 |
+
],
|
1016 |
+
"text/plain": [
|
1017 |
+
" timestamp datetime date hour temperature_2m \\\n",
|
1018 |
+
"115 1715022000000 2024-05-06 19:00:00 2024-05-06 19 10.7 \n",
|
1019 |
+
"116 1715025600000 2024-05-06 20:00:00 2024-05-06 20 10.1 \n",
|
1020 |
+
"117 1715029200000 2024-05-06 21:00:00 2024-05-06 21 9.5 \n",
|
1021 |
+
"118 1715032800000 2024-05-06 22:00:00 2024-05-06 22 9.3 \n",
|
1022 |
+
"119 1715036400000 2024-05-06 23:00:00 2024-05-06 23 9.1 \n",
|
1023 |
+
"\n",
|
1024 |
+
" relative_humidity_2m precipitation rain snowfall weather_code \\\n",
|
1025 |
+
"115 91.0 1.4 1.4 0.0 61.0 \n",
|
1026 |
+
"116 90.0 1.4 1.4 0.0 61.0 \n",
|
1027 |
+
"117 88.0 1.4 1.4 0.0 61.0 \n",
|
1028 |
+
"118 86.0 0.6 0.6 0.0 3.0 \n",
|
1029 |
+
"119 84.0 0.6 0.6 0.0 3.0 \n",
|
1030 |
+
"\n",
|
1031 |
+
" cloud_cover wind_speed_10m wind_gusts_10m \n",
|
1032 |
+
"115 100.0 16.6 32.0 \n",
|
1033 |
+
"116 100.0 19.5 37.1 \n",
|
1034 |
+
"117 100.0 21.6 42.1 \n",
|
1035 |
+
"118 100.0 22.0 41.0 \n",
|
1036 |
+
"119 100.0 21.3 40.3 "
|
1037 |
+
]
|
1038 |
+
},
|
1039 |
+
"execution_count": 12,
|
1040 |
+
"metadata": {},
|
1041 |
+
"output_type": "execute_result"
|
1042 |
+
}
|
1043 |
+
],
|
1044 |
+
"source": [
|
1045 |
+
"weather_forecast_df.tail(5)"
|
1046 |
+
]
|
1047 |
+
},
|
1048 |
{
|
1049 |
"cell_type": "markdown",
|
1050 |
"metadata": {},
|
|
|
1093 |
" version=1,\n",
|
1094 |
")\n",
|
1095 |
"\n",
|
1096 |
+
"# forecast_renewable_energy_fg = fs.get_feature_group(\n",
|
1097 |
+
"# name=\"forecast_renewable_energy\",\n",
|
1098 |
+
"# version=1,\n",
|
1099 |
+
"# )\n",
|
1100 |
"\n",
|
1101 |
"weather_fg = fs.get_feature_group(\n",
|
1102 |
" name=\"weather_measurements\",\n",
|
|
|
1120 |
{
|
1121 |
"data": {
|
1122 |
"application/vnd.jupyter.widget-view+json": {
|
1123 |
+
"model_id": "0620fe280bda4631b98959a633d0c782",
|
1124 |
"version_major": 2,
|
1125 |
"version_minor": 0
|
1126 |
},
|
|
|
1143 |
{
|
1144 |
"data": {
|
1145 |
"text/plain": [
|
1146 |
+
"(<hsfs.core.job.Job at 0x1782b1810>, None)"
|
1147 |
]
|
1148 |
},
|
1149 |
"execution_count": 15,
|
|
|
1159 |
},
|
1160 |
{
|
1161 |
"cell_type": "code",
|
1162 |
+
"execution_count": 16,
|
1163 |
"metadata": {},
|
1164 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1165 |
"source": [
|
1166 |
+
"# # Inserting the forecast_renewable_energy_df into the feature group named forecast_renewable_energy_fg\n",
|
1167 |
+
"# forecast_renewable_energy_fg.insert(forecast_renewable_energy_df, \n",
|
1168 |
+
"# write_options={\"wait_for_job\" : False})"
|
1169 |
]
|
1170 |
},
|
1171 |
{
|
1172 |
"cell_type": "code",
|
1173 |
+
"execution_count": 17,
|
1174 |
"metadata": {},
|
1175 |
"outputs": [
|
1176 |
{
|
1177 |
"data": {
|
1178 |
"application/vnd.jupyter.widget-view+json": {
|
1179 |
+
"model_id": "e39a33b92b7e48fab45022e590e78157",
|
1180 |
"version_major": 2,
|
1181 |
"version_minor": 0
|
1182 |
},
|
|
|
1199 |
{
|
1200 |
"data": {
|
1201 |
"text/plain": [
|
1202 |
+
"(<hsfs.core.job.Job at 0x1782e7ed0>, None)"
|
1203 |
]
|
1204 |
},
|
1205 |
+
"execution_count": 17,
|
1206 |
"metadata": {},
|
1207 |
"output_type": "execute_result"
|
1208 |
}
|
notebooks/3_training_pipeline.ipynb
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
notebooks/4_batch_inference copy.ipynb
ADDED
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"metadata": {},
|
6 |
+
"source": [
|
7 |
+
"# <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>"
|
8 |
+
]
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"cell_type": "markdown",
|
12 |
+
"metadata": {},
|
13 |
+
"source": [
|
14 |
+
"## <span style='color:#2656a3'> 🗒️ This notebook is divided into the following sections:\n",
|
15 |
+
"\n",
|
16 |
+
"1. Load batch data.\n",
|
17 |
+
"2. Predict using model from Model Registry."
|
18 |
+
]
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"cell_type": "markdown",
|
22 |
+
"metadata": {},
|
23 |
+
"source": [
|
24 |
+
"## <span style='color:#2656a3'> ⚙️ Import of libraries and packages\n",
|
25 |
+
"\n",
|
26 |
+
"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."
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"cell_type": "code",
|
31 |
+
"execution_count": null,
|
32 |
+
"metadata": {},
|
33 |
+
"outputs": [],
|
34 |
+
"source": [
|
35 |
+
"# Importing the packages for the needed libraries for the Jupyter notebook\n",
|
36 |
+
"import joblib\n",
|
37 |
+
"import inspect \n",
|
38 |
+
"import pandas as pd\n",
|
39 |
+
"import matplotlib.pyplot as plt\n",
|
40 |
+
"from matplotlib.ticker import FuncFormatter\n",
|
41 |
+
"import os\n",
|
42 |
+
"\n",
|
43 |
+
"#%config InlineBackend.figure_format='retina'\n",
|
44 |
+
"#%matplotlib inline"
|
45 |
+
]
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"cell_type": "markdown",
|
49 |
+
"metadata": {},
|
50 |
+
"source": [
|
51 |
+
"## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store"
|
52 |
+
]
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"cell_type": "code",
|
56 |
+
"execution_count": null,
|
57 |
+
"metadata": {},
|
58 |
+
"outputs": [],
|
59 |
+
"source": [
|
60 |
+
"# Importing the hopsworks module\n",
|
61 |
+
"import hopsworks\n",
|
62 |
+
"\n",
|
63 |
+
"# Logging in to the Hopsworks project\n",
|
64 |
+
"project = hopsworks.login()\n",
|
65 |
+
"\n",
|
66 |
+
"# Getting the feature store from the project\n",
|
67 |
+
"fs = project.get_feature_store() "
|
68 |
+
]
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"cell_type": "markdown",
|
72 |
+
"metadata": {},
|
73 |
+
"source": [
|
74 |
+
"### <span style='color:#2656a3'> ⚙️ Feature View Retrieval"
|
75 |
+
]
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"cell_type": "code",
|
79 |
+
"execution_count": null,
|
80 |
+
"metadata": {},
|
81 |
+
"outputs": [],
|
82 |
+
"source": [
|
83 |
+
"# Retrieve the 'electricity_feature_view' feature view\n",
|
84 |
+
"feature_view = fs.get_feature_view(\n",
|
85 |
+
" name='electricity_feature_view',\n",
|
86 |
+
" version=1,\n",
|
87 |
+
")"
|
88 |
+
]
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"cell_type": "markdown",
|
92 |
+
"metadata": {},
|
93 |
+
"source": [
|
94 |
+
"### <span style='color:#2656a3'> 🗄 Model Registry"
|
95 |
+
]
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"cell_type": "code",
|
99 |
+
"execution_count": null,
|
100 |
+
"metadata": {},
|
101 |
+
"outputs": [],
|
102 |
+
"source": [
|
103 |
+
"# Retrieve the model registry\n",
|
104 |
+
"mr = project.get_model_registry()"
|
105 |
+
]
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"cell_type": "markdown",
|
109 |
+
"metadata": {},
|
110 |
+
"source": [
|
111 |
+
"## <span style='color:#2656a3'> 📮 Retrieving model from Model Registry"
|
112 |
+
]
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"cell_type": "code",
|
116 |
+
"execution_count": null,
|
117 |
+
"metadata": {},
|
118 |
+
"outputs": [],
|
119 |
+
"source": [
|
120 |
+
"# Retrieving the model from the Model Registry\n",
|
121 |
+
"retrieved_model = mr.get_model(\n",
|
122 |
+
" name=\"electricity_price_prediction_model\", \n",
|
123 |
+
" version=1,\n",
|
124 |
+
")\n",
|
125 |
+
"\n",
|
126 |
+
"# Downloading the saved model to a local directory\n",
|
127 |
+
"saved_model_dir = retrieved_model.download()\n",
|
128 |
+
"\n",
|
129 |
+
"# Loading the saved XGB model\n",
|
130 |
+
"retrieved_xgboost_model = joblib.load(saved_model_dir + \"/dk_electricity_model.pkl\")"
|
131 |
+
]
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"cell_type": "code",
|
135 |
+
"execution_count": null,
|
136 |
+
"metadata": {},
|
137 |
+
"outputs": [],
|
138 |
+
"source": [
|
139 |
+
"# Display the retrieved XGBoost regressor model\n",
|
140 |
+
"retrieved_xgboost_model"
|
141 |
+
]
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"cell_type": "markdown",
|
145 |
+
"metadata": {},
|
146 |
+
"source": [
|
147 |
+
"## <span style='color:#2656a3'> ✨ Load Batch Data"
|
148 |
+
]
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"cell_type": "code",
|
152 |
+
"execution_count": null,
|
153 |
+
"metadata": {},
|
154 |
+
"outputs": [],
|
155 |
+
"source": [
|
156 |
+
"import datetime\n",
|
157 |
+
"\n",
|
158 |
+
"# Calculating the start date as 5 days ago from the current date\n",
|
159 |
+
"start_date = datetime.datetime.now() - datetime.timedelta(days=5)\n",
|
160 |
+
"\n",
|
161 |
+
"# Converting the start date to a timestamp in milliseconds\n",
|
162 |
+
"start_time = int(start_date.timestamp()) * 1000\n",
|
163 |
+
"\n",
|
164 |
+
"# Displaying the start date in timestamp format\n",
|
165 |
+
"start_time"
|
166 |
+
]
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"cell_type": "code",
|
170 |
+
"execution_count": null,
|
171 |
+
"metadata": {},
|
172 |
+
"outputs": [],
|
173 |
+
"source": [
|
174 |
+
"# Initializing batch scoring\n",
|
175 |
+
"feature_view.init_batch_scoring(1)\n",
|
176 |
+
"\n",
|
177 |
+
"# Retrieving batch data from the feature view starting from the specified start time\n",
|
178 |
+
"batch_data = feature_view.get_batch_data(\n",
|
179 |
+
" start_time=start_time,\n",
|
180 |
+
")\n",
|
181 |
+
"\n",
|
182 |
+
"batch_data"
|
183 |
+
]
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"cell_type": "code",
|
187 |
+
"execution_count": null,
|
188 |
+
"metadata": {},
|
189 |
+
"outputs": [],
|
190 |
+
"source": [
|
191 |
+
"# First we go one back in our directory to access the folder with our functions\n",
|
192 |
+
"%cd ..\n",
|
193 |
+
"\n",
|
194 |
+
"# Now we import the functions from the features folder\n",
|
195 |
+
"# This is the functions we have created to generate features for electricity prices and weather measures\n",
|
196 |
+
"from features import electricity_prices, weather_measures \n",
|
197 |
+
"\n",
|
198 |
+
"# We go back into the notebooks folder\n",
|
199 |
+
"%cd notebooks"
|
200 |
+
]
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"cell_type": "code",
|
204 |
+
"execution_count": null,
|
205 |
+
"metadata": {},
|
206 |
+
"outputs": [],
|
207 |
+
"source": [
|
208 |
+
"# Fetching weather forecast measures for the next 5 days\n",
|
209 |
+
"weather_forecast_df = weather_measures.forecast_weather_measures(\n",
|
210 |
+
" forecast_length=5\n",
|
211 |
+
")"
|
212 |
+
]
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"cell_type": "code",
|
216 |
+
"execution_count": null,
|
217 |
+
"metadata": {},
|
218 |
+
"outputs": [],
|
219 |
+
"source": [
|
220 |
+
"# Read csv file with calender\n",
|
221 |
+
"calender_df = pd.read_csv('https://raw.githubusercontent.com/Camillahannesbo/MLOPs-Assignment-/main/data/calendar_incl_holiday.csv', delimiter=';', usecols=['date', 'type'])\n",
|
222 |
+
"\n",
|
223 |
+
"calender_df"
|
224 |
+
]
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"cell_type": "code",
|
228 |
+
"execution_count": null,
|
229 |
+
"metadata": {},
|
230 |
+
"outputs": [],
|
231 |
+
"source": [
|
232 |
+
"from datetime import datetime, timedelta\n",
|
233 |
+
"\n",
|
234 |
+
"# Formatting the date column to 'YYYY-MM-DD' dateformat\n",
|
235 |
+
"calender_df[\"date\"] = calender_df[\"date\"].map(lambda x: datetime.strptime(x, '%d/%m/%Y').strftime(\"%Y-%m-%d\"))"
|
236 |
+
]
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"cell_type": "code",
|
240 |
+
"execution_count": null,
|
241 |
+
"metadata": {},
|
242 |
+
"outputs": [],
|
243 |
+
"source": [
|
244 |
+
"# Add features to the calender dataframe\n",
|
245 |
+
"calender_df['date_'] = pd.to_datetime(calender_df['date'])\n",
|
246 |
+
"calender_df['day'] = calender_df['date_'].dt.dayofweek\n",
|
247 |
+
"calender_df['month'] = calender_df['date_'].dt.month\n",
|
248 |
+
"calender_df['holiday'] = np.where(calender_df['type'] == 'Not a Workday', 1, 0)\n",
|
249 |
+
"\n",
|
250 |
+
"# Drop the columns 'type' and 'date_' to finalize the calender dataframe\n",
|
251 |
+
"calender_df = calender_df.drop(['type','date_'], axis=1)\n",
|
252 |
+
"\n",
|
253 |
+
"merged_df = pd.merge(weather_forecast_df, calender_df, how='inner', left_on='date', right_on='date')"
|
254 |
+
]
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"cell_type": "code",
|
258 |
+
"execution_count": null,
|
259 |
+
"metadata": {},
|
260 |
+
"outputs": [],
|
261 |
+
"source": [
|
262 |
+
"import numpy as np"
|
263 |
+
]
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"cell_type": "code",
|
267 |
+
"execution_count": null,
|
268 |
+
"metadata": {},
|
269 |
+
"outputs": [],
|
270 |
+
"source": [
|
271 |
+
"# Display the first 5 rows of the batch data\n",
|
272 |
+
"batch_data = merged_df\n",
|
273 |
+
"\n",
|
274 |
+
"batch_data.tail()"
|
275 |
+
]
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"cell_type": "markdown",
|
279 |
+
"metadata": {},
|
280 |
+
"source": [
|
281 |
+
"### <span style=\"color:#ff5f27;\">🤖 Making the predictions</span>"
|
282 |
+
]
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"cell_type": "code",
|
286 |
+
"execution_count": null,
|
287 |
+
"metadata": {},
|
288 |
+
"outputs": [],
|
289 |
+
"source": [
|
290 |
+
"# from sklearn.preprocessing import LabelEncoder\n",
|
291 |
+
"\n",
|
292 |
+
"# # Create a LabelEncoder object\n",
|
293 |
+
"# label_encoder = LabelEncoder()\n",
|
294 |
+
"\n",
|
295 |
+
"# # Fit the encoder to the data in the 'city_name' column\n",
|
296 |
+
"# label_encoder.fit(batch_data[['type']])\n",
|
297 |
+
"\n",
|
298 |
+
"# # Transform the 'city_name' column data using the fitted encoder\n",
|
299 |
+
"# encoded = label_encoder.transform(batch_data[['type']])"
|
300 |
+
]
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"cell_type": "code",
|
304 |
+
"execution_count": null,
|
305 |
+
"metadata": {},
|
306 |
+
"outputs": [],
|
307 |
+
"source": [
|
308 |
+
"batch_data"
|
309 |
+
]
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"cell_type": "code",
|
313 |
+
"execution_count": null,
|
314 |
+
"metadata": {},
|
315 |
+
"outputs": [],
|
316 |
+
"source": []
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"cell_type": "code",
|
320 |
+
"execution_count": null,
|
321 |
+
"metadata": {},
|
322 |
+
"outputs": [],
|
323 |
+
"source": []
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"cell_type": "code",
|
327 |
+
"execution_count": null,
|
328 |
+
"metadata": {},
|
329 |
+
"outputs": [],
|
330 |
+
"source": [
|
331 |
+
"# # Convert the output of the label encoding to a dense array and concatenate with the original data\n",
|
332 |
+
"# X_batch = pd.concat([batch_data, pd.DataFrame(encoded)], axis=1)\n",
|
333 |
+
"\n",
|
334 |
+
"X_batch = batch_data\n",
|
335 |
+
"\n",
|
336 |
+
"# Drop columns 'date', 'city_name', 'unix_time' from the DataFrame 'X'\n",
|
337 |
+
"X_batch = X_batch.drop(columns=['date', 'time', 'timestamp'])\n",
|
338 |
+
"\n",
|
339 |
+
"# # Rename the newly added column with label-encoded city names to 'city_name_encoded'\n",
|
340 |
+
"# X_batch = X_batch.rename(columns={0: \"type_encoded\"})\n",
|
341 |
+
"\n",
|
342 |
+
"# Displaying the first 5 rows of the modified DataFrame\n",
|
343 |
+
"X_batch.head()"
|
344 |
+
]
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"cell_type": "code",
|
348 |
+
"execution_count": null,
|
349 |
+
"metadata": {},
|
350 |
+
"outputs": [],
|
351 |
+
"source": [
|
352 |
+
"# Extract the target variable 'dk1_spotpricedkk_kwh' from the batch data\n",
|
353 |
+
"y_batch = X_batch.pop('dk1_spotpricedkk_kwh')\n",
|
354 |
+
"\n",
|
355 |
+
"# Displaying the first 5 rows of the modified DataFrame\n",
|
356 |
+
"y_batch.head()"
|
357 |
+
]
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"cell_type": "code",
|
361 |
+
"execution_count": null,
|
362 |
+
"metadata": {},
|
363 |
+
"outputs": [],
|
364 |
+
"source": [
|
365 |
+
"X_batch"
|
366 |
+
]
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"cell_type": "code",
|
370 |
+
"execution_count": null,
|
371 |
+
"metadata": {},
|
372 |
+
"outputs": [],
|
373 |
+
"source": [
|
374 |
+
"# Make predictions on the batch data using the retrieved XGBoost regressor model\n",
|
375 |
+
"predictions = retrieved_xgboost_model.predict(X_batch)\n",
|
376 |
+
"\n",
|
377 |
+
"# Display the first 5 predictions\n",
|
378 |
+
"predictions[:5]"
|
379 |
+
]
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"cell_type": "code",
|
383 |
+
"execution_count": null,
|
384 |
+
"metadata": {},
|
385 |
+
"outputs": [],
|
386 |
+
"source": [
|
387 |
+
"label = batch_data[\"time\"]\n",
|
388 |
+
"y_pred = retrieved_xgboost_model.predict(X_batch)\n",
|
389 |
+
"\n",
|
390 |
+
"data = {\n",
|
391 |
+
" 'prediction': [y_pred],\n",
|
392 |
+
" 'time': [label],\n",
|
393 |
+
"}\n",
|
394 |
+
"\n",
|
395 |
+
"monitor_df = pd.DataFrame(data)\n",
|
396 |
+
"monitor_df"
|
397 |
+
]
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"cell_type": "code",
|
401 |
+
"execution_count": null,
|
402 |
+
"metadata": {},
|
403 |
+
"outputs": [],
|
404 |
+
"source": [
|
405 |
+
"label = batch_data[\"time\"]\n",
|
406 |
+
"y_pred = retrieved_xgboost_model.predict(X_batch)\n",
|
407 |
+
"\n",
|
408 |
+
"data = {\n",
|
409 |
+
" 'prediction': y_pred,\n",
|
410 |
+
" 'time': label,\n",
|
411 |
+
"}\n",
|
412 |
+
"\n",
|
413 |
+
"monitor_df = pd.DataFrame(data)\n",
|
414 |
+
"monitor_df"
|
415 |
+
]
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"cell_type": "markdown",
|
419 |
+
"metadata": {},
|
420 |
+
"source": [
|
421 |
+
"---\n",
|
422 |
+
"## <span style=\"color:#ff5f27;\">👾 Next is creating our Streamlit App?</span>"
|
423 |
+
]
|
424 |
+
}
|
425 |
+
],
|
426 |
+
"metadata": {
|
427 |
+
"kernelspec": {
|
428 |
+
"display_name": "bds-mlops",
|
429 |
+
"language": "python",
|
430 |
+
"name": "python3"
|
431 |
+
},
|
432 |
+
"language_info": {
|
433 |
+
"codemirror_mode": {
|
434 |
+
"name": "ipython",
|
435 |
+
"version": 3
|
436 |
+
},
|
437 |
+
"file_extension": ".py",
|
438 |
+
"mimetype": "text/x-python",
|
439 |
+
"name": "python",
|
440 |
+
"nbconvert_exporter": "python",
|
441 |
+
"pygments_lexer": "ipython3",
|
442 |
+
"version": "3.11.8"
|
443 |
+
},
|
444 |
+
"orig_nbformat": 4
|
445 |
+
},
|
446 |
+
"nbformat": 4,
|
447 |
+
"nbformat_minor": 2
|
448 |
+
}
|
notebooks/4_batch_inference.ipynb
CHANGED
@@ -28,7 +28,7 @@
|
|
28 |
},
|
29 |
{
|
30 |
"cell_type": "code",
|
31 |
-
"execution_count":
|
32 |
"metadata": {},
|
33 |
"outputs": [],
|
34 |
"source": [
|
@@ -53,20 +53,9 @@
|
|
53 |
},
|
54 |
{
|
55 |
"cell_type": "code",
|
56 |
-
"execution_count":
|
57 |
"metadata": {},
|
58 |
-
"outputs": [
|
59 |
-
{
|
60 |
-
"name": "stdout",
|
61 |
-
"output_type": "stream",
|
62 |
-
"text": [
|
63 |
-
"Connected. Call `.close()` to terminate connection gracefully.\n",
|
64 |
-
"\n",
|
65 |
-
"Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/554133\n",
|
66 |
-
"Connected. Call `.close()` to terminate connection gracefully.\n"
|
67 |
-
]
|
68 |
-
}
|
69 |
-
],
|
70 |
"source": [
|
71 |
"# Importing the hopsworks module\n",
|
72 |
"import hopsworks\n",
|
@@ -87,7 +76,7 @@
|
|
87 |
},
|
88 |
{
|
89 |
"cell_type": "code",
|
90 |
-
"execution_count":
|
91 |
"metadata": {},
|
92 |
"outputs": [],
|
93 |
"source": [
|
@@ -107,17 +96,9 @@
|
|
107 |
},
|
108 |
{
|
109 |
"cell_type": "code",
|
110 |
-
"execution_count":
|
111 |
"metadata": {},
|
112 |
-
"outputs": [
|
113 |
-
{
|
114 |
-
"name": "stdout",
|
115 |
-
"output_type": "stream",
|
116 |
-
"text": [
|
117 |
-
"Connected. Call `.close()` to terminate connection gracefully.\n"
|
118 |
-
]
|
119 |
-
}
|
120 |
-
],
|
121 |
"source": [
|
122 |
"# Retrieve the model registry\n",
|
123 |
"mr = project.get_model_registry()"
|
@@ -132,17 +113,9 @@
|
|
132 |
},
|
133 |
{
|
134 |
"cell_type": "code",
|
135 |
-
"execution_count":
|
136 |
"metadata": {},
|
137 |
-
"outputs": [
|
138 |
-
{
|
139 |
-
"name": "stdout",
|
140 |
-
"output_type": "stream",
|
141 |
-
"text": [
|
142 |
-
"Downloading model artifact (0 dirs, 3 files)... DONE\r"
|
143 |
-
]
|
144 |
-
}
|
145 |
-
],
|
146 |
"source": [
|
147 |
"# Retrieving the model from the Model Registry\n",
|
148 |
"retrieved_model = mr.get_model(\n",
|
@@ -159,457 +132,9 @@
|
|
159 |
},
|
160 |
{
|
161 |
"cell_type": "code",
|
162 |
-
"execution_count":
|
163 |
"metadata": {},
|
164 |
-
"outputs": [
|
165 |
-
{
|
166 |
-
"data": {
|
167 |
-
"text/html": [
|
168 |
-
"<style>#sk-container-id-1 {\n",
|
169 |
-
" /* Definition of color scheme common for light and dark mode */\n",
|
170 |
-
" --sklearn-color-text: black;\n",
|
171 |
-
" --sklearn-color-line: gray;\n",
|
172 |
-
" /* Definition of color scheme for unfitted estimators */\n",
|
173 |
-
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
|
174 |
-
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
|
175 |
-
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
|
176 |
-
" --sklearn-color-unfitted-level-3: chocolate;\n",
|
177 |
-
" /* Definition of color scheme for fitted estimators */\n",
|
178 |
-
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
|
179 |
-
" --sklearn-color-fitted-level-1: #d4ebff;\n",
|
180 |
-
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
|
181 |
-
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
|
182 |
-
"\n",
|
183 |
-
" /* Specific color for light theme */\n",
|
184 |
-
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
185 |
-
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
|
186 |
-
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
187 |
-
" --sklearn-color-icon: #696969;\n",
|
188 |
-
"\n",
|
189 |
-
" @media (prefers-color-scheme: dark) {\n",
|
190 |
-
" /* Redefinition of color scheme for dark theme */\n",
|
191 |
-
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
192 |
-
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
|
193 |
-
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
194 |
-
" --sklearn-color-icon: #878787;\n",
|
195 |
-
" }\n",
|
196 |
-
"}\n",
|
197 |
-
"\n",
|
198 |
-
"#sk-container-id-1 {\n",
|
199 |
-
" color: var(--sklearn-color-text);\n",
|
200 |
-
"}\n",
|
201 |
-
"\n",
|
202 |
-
"#sk-container-id-1 pre {\n",
|
203 |
-
" padding: 0;\n",
|
204 |
-
"}\n",
|
205 |
-
"\n",
|
206 |
-
"#sk-container-id-1 input.sk-hidden--visually {\n",
|
207 |
-
" border: 0;\n",
|
208 |
-
" clip: rect(1px 1px 1px 1px);\n",
|
209 |
-
" clip: rect(1px, 1px, 1px, 1px);\n",
|
210 |
-
" height: 1px;\n",
|
211 |
-
" margin: -1px;\n",
|
212 |
-
" overflow: hidden;\n",
|
213 |
-
" padding: 0;\n",
|
214 |
-
" position: absolute;\n",
|
215 |
-
" width: 1px;\n",
|
216 |
-
"}\n",
|
217 |
-
"\n",
|
218 |
-
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
|
219 |
-
" border: 1px dashed var(--sklearn-color-line);\n",
|
220 |
-
" margin: 0 0.4em 0.5em 0.4em;\n",
|
221 |
-
" box-sizing: border-box;\n",
|
222 |
-
" padding-bottom: 0.4em;\n",
|
223 |
-
" background-color: var(--sklearn-color-background);\n",
|
224 |
-
"}\n",
|
225 |
-
"\n",
|
226 |
-
"#sk-container-id-1 div.sk-container {\n",
|
227 |
-
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
228 |
-
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
229 |
-
" so we also need the `!important` here to be able to override the\n",
|
230 |
-
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
231 |
-
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
232 |
-
" display: inline-block !important;\n",
|
233 |
-
" position: relative;\n",
|
234 |
-
"}\n",
|
235 |
-
"\n",
|
236 |
-
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
|
237 |
-
" display: none;\n",
|
238 |
-
"}\n",
|
239 |
-
"\n",
|
240 |
-
"div.sk-parallel-item,\n",
|
241 |
-
"div.sk-serial,\n",
|
242 |
-
"div.sk-item {\n",
|
243 |
-
" /* draw centered vertical line to link estimators */\n",
|
244 |
-
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
245 |
-
" background-size: 2px 100%;\n",
|
246 |
-
" background-repeat: no-repeat;\n",
|
247 |
-
" background-position: center center;\n",
|
248 |
-
"}\n",
|
249 |
-
"\n",
|
250 |
-
"/* Parallel-specific style estimator block */\n",
|
251 |
-
"\n",
|
252 |
-
"#sk-container-id-1 div.sk-parallel-item::after {\n",
|
253 |
-
" content: \"\";\n",
|
254 |
-
" width: 100%;\n",
|
255 |
-
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
256 |
-
" flex-grow: 1;\n",
|
257 |
-
"}\n",
|
258 |
-
"\n",
|
259 |
-
"#sk-container-id-1 div.sk-parallel {\n",
|
260 |
-
" display: flex;\n",
|
261 |
-
" align-items: stretch;\n",
|
262 |
-
" justify-content: center;\n",
|
263 |
-
" background-color: var(--sklearn-color-background);\n",
|
264 |
-
" position: relative;\n",
|
265 |
-
"}\n",
|
266 |
-
"\n",
|
267 |
-
"#sk-container-id-1 div.sk-parallel-item {\n",
|
268 |
-
" display: flex;\n",
|
269 |
-
" flex-direction: column;\n",
|
270 |
-
"}\n",
|
271 |
-
"\n",
|
272 |
-
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
|
273 |
-
" align-self: flex-end;\n",
|
274 |
-
" width: 50%;\n",
|
275 |
-
"}\n",
|
276 |
-
"\n",
|
277 |
-
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
|
278 |
-
" align-self: flex-start;\n",
|
279 |
-
" width: 50%;\n",
|
280 |
-
"}\n",
|
281 |
-
"\n",
|
282 |
-
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
|
283 |
-
" width: 0;\n",
|
284 |
-
"}\n",
|
285 |
-
"\n",
|
286 |
-
"/* Serial-specific style estimator block */\n",
|
287 |
-
"\n",
|
288 |
-
"#sk-container-id-1 div.sk-serial {\n",
|
289 |
-
" display: flex;\n",
|
290 |
-
" flex-direction: column;\n",
|
291 |
-
" align-items: center;\n",
|
292 |
-
" background-color: var(--sklearn-color-background);\n",
|
293 |
-
" padding-right: 1em;\n",
|
294 |
-
" padding-left: 1em;\n",
|
295 |
-
"}\n",
|
296 |
-
"\n",
|
297 |
-
"\n",
|
298 |
-
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
299 |
-
"clickable and can be expanded/collapsed.\n",
|
300 |
-
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
301 |
-
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
302 |
-
"*/\n",
|
303 |
-
"\n",
|
304 |
-
"/* Pipeline and ColumnTransformer style (default) */\n",
|
305 |
-
"\n",
|
306 |
-
"#sk-container-id-1 div.sk-toggleable {\n",
|
307 |
-
" /* Default theme specific background. It is overwritten whether we have a\n",
|
308 |
-
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
309 |
-
" background-color: var(--sklearn-color-background);\n",
|
310 |
-
"}\n",
|
311 |
-
"\n",
|
312 |
-
"/* Toggleable label */\n",
|
313 |
-
"#sk-container-id-1 label.sk-toggleable__label {\n",
|
314 |
-
" cursor: pointer;\n",
|
315 |
-
" display: block;\n",
|
316 |
-
" width: 100%;\n",
|
317 |
-
" margin-bottom: 0;\n",
|
318 |
-
" padding: 0.5em;\n",
|
319 |
-
" box-sizing: border-box;\n",
|
320 |
-
" text-align: center;\n",
|
321 |
-
"}\n",
|
322 |
-
"\n",
|
323 |
-
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
|
324 |
-
" /* Arrow on the left of the label */\n",
|
325 |
-
" content: \"▸\";\n",
|
326 |
-
" float: left;\n",
|
327 |
-
" margin-right: 0.25em;\n",
|
328 |
-
" color: var(--sklearn-color-icon);\n",
|
329 |
-
"}\n",
|
330 |
-
"\n",
|
331 |
-
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
|
332 |
-
" color: var(--sklearn-color-text);\n",
|
333 |
-
"}\n",
|
334 |
-
"\n",
|
335 |
-
"/* Toggleable content - dropdown */\n",
|
336 |
-
"\n",
|
337 |
-
"#sk-container-id-1 div.sk-toggleable__content {\n",
|
338 |
-
" max-height: 0;\n",
|
339 |
-
" max-width: 0;\n",
|
340 |
-
" overflow: hidden;\n",
|
341 |
-
" text-align: left;\n",
|
342 |
-
" /* unfitted */\n",
|
343 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
344 |
-
"}\n",
|
345 |
-
"\n",
|
346 |
-
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
|
347 |
-
" /* fitted */\n",
|
348 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
349 |
-
"}\n",
|
350 |
-
"\n",
|
351 |
-
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
|
352 |
-
" margin: 0.2em;\n",
|
353 |
-
" border-radius: 0.25em;\n",
|
354 |
-
" color: var(--sklearn-color-text);\n",
|
355 |
-
" /* unfitted */\n",
|
356 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
357 |
-
"}\n",
|
358 |
-
"\n",
|
359 |
-
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
|
360 |
-
" /* unfitted */\n",
|
361 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
362 |
-
"}\n",
|
363 |
-
"\n",
|
364 |
-
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
365 |
-
" /* Expand drop-down */\n",
|
366 |
-
" max-height: 200px;\n",
|
367 |
-
" max-width: 100%;\n",
|
368 |
-
" overflow: auto;\n",
|
369 |
-
"}\n",
|
370 |
-
"\n",
|
371 |
-
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
372 |
-
" content: \"▾\";\n",
|
373 |
-
"}\n",
|
374 |
-
"\n",
|
375 |
-
"/* Pipeline/ColumnTransformer-specific style */\n",
|
376 |
-
"\n",
|
377 |
-
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
378 |
-
" color: var(--sklearn-color-text);\n",
|
379 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
380 |
-
"}\n",
|
381 |
-
"\n",
|
382 |
-
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
383 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
384 |
-
"}\n",
|
385 |
-
"\n",
|
386 |
-
"/* Estimator-specific style */\n",
|
387 |
-
"\n",
|
388 |
-
"/* Colorize estimator box */\n",
|
389 |
-
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
390 |
-
" /* unfitted */\n",
|
391 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
392 |
-
"}\n",
|
393 |
-
"\n",
|
394 |
-
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
395 |
-
" /* fitted */\n",
|
396 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
397 |
-
"}\n",
|
398 |
-
"\n",
|
399 |
-
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
|
400 |
-
"#sk-container-id-1 div.sk-label label {\n",
|
401 |
-
" /* The background is the default theme color */\n",
|
402 |
-
" color: var(--sklearn-color-text-on-default-background);\n",
|
403 |
-
"}\n",
|
404 |
-
"\n",
|
405 |
-
"/* On hover, darken the color of the background */\n",
|
406 |
-
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
|
407 |
-
" color: var(--sklearn-color-text);\n",
|
408 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
409 |
-
"}\n",
|
410 |
-
"\n",
|
411 |
-
"/* Label box, darken color on hover, fitted */\n",
|
412 |
-
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
413 |
-
" color: var(--sklearn-color-text);\n",
|
414 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
415 |
-
"}\n",
|
416 |
-
"\n",
|
417 |
-
"/* Estimator label */\n",
|
418 |
-
"\n",
|
419 |
-
"#sk-container-id-1 div.sk-label label {\n",
|
420 |
-
" font-family: monospace;\n",
|
421 |
-
" font-weight: bold;\n",
|
422 |
-
" display: inline-block;\n",
|
423 |
-
" line-height: 1.2em;\n",
|
424 |
-
"}\n",
|
425 |
-
"\n",
|
426 |
-
"#sk-container-id-1 div.sk-label-container {\n",
|
427 |
-
" text-align: center;\n",
|
428 |
-
"}\n",
|
429 |
-
"\n",
|
430 |
-
"/* Estimator-specific */\n",
|
431 |
-
"#sk-container-id-1 div.sk-estimator {\n",
|
432 |
-
" font-family: monospace;\n",
|
433 |
-
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
434 |
-
" border-radius: 0.25em;\n",
|
435 |
-
" box-sizing: border-box;\n",
|
436 |
-
" margin-bottom: 0.5em;\n",
|
437 |
-
" /* unfitted */\n",
|
438 |
-
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
439 |
-
"}\n",
|
440 |
-
"\n",
|
441 |
-
"#sk-container-id-1 div.sk-estimator.fitted {\n",
|
442 |
-
" /* fitted */\n",
|
443 |
-
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
444 |
-
"}\n",
|
445 |
-
"\n",
|
446 |
-
"/* on hover */\n",
|
447 |
-
"#sk-container-id-1 div.sk-estimator:hover {\n",
|
448 |
-
" /* unfitted */\n",
|
449 |
-
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
450 |
-
"}\n",
|
451 |
-
"\n",
|
452 |
-
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
|
453 |
-
" /* fitted */\n",
|
454 |
-
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
455 |
-
"}\n",
|
456 |
-
"\n",
|
457 |
-
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
458 |
-
"\n",
|
459 |
-
"/* Common style for \"i\" and \"?\" */\n",
|
460 |
-
"\n",
|
461 |
-
".sk-estimator-doc-link,\n",
|
462 |
-
"a:link.sk-estimator-doc-link,\n",
|
463 |
-
"a:visited.sk-estimator-doc-link {\n",
|
464 |
-
" float: right;\n",
|
465 |
-
" font-size: smaller;\n",
|
466 |
-
" line-height: 1em;\n",
|
467 |
-
" font-family: monospace;\n",
|
468 |
-
" background-color: var(--sklearn-color-background);\n",
|
469 |
-
" border-radius: 1em;\n",
|
470 |
-
" height: 1em;\n",
|
471 |
-
" width: 1em;\n",
|
472 |
-
" text-decoration: none !important;\n",
|
473 |
-
" margin-left: 1ex;\n",
|
474 |
-
" /* unfitted */\n",
|
475 |
-
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
476 |
-
" color: var(--sklearn-color-unfitted-level-1);\n",
|
477 |
-
"}\n",
|
478 |
-
"\n",
|
479 |
-
".sk-estimator-doc-link.fitted,\n",
|
480 |
-
"a:link.sk-estimator-doc-link.fitted,\n",
|
481 |
-
"a:visited.sk-estimator-doc-link.fitted {\n",
|
482 |
-
" /* fitted */\n",
|
483 |
-
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
484 |
-
" color: var(--sklearn-color-fitted-level-1);\n",
|
485 |
-
"}\n",
|
486 |
-
"\n",
|
487 |
-
"/* On hover */\n",
|
488 |
-
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
|
489 |
-
".sk-estimator-doc-link:hover,\n",
|
490 |
-
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
|
491 |
-
".sk-estimator-doc-link:hover {\n",
|
492 |
-
" /* unfitted */\n",
|
493 |
-
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
494 |
-
" color: var(--sklearn-color-background);\n",
|
495 |
-
" text-decoration: none;\n",
|
496 |
-
"}\n",
|
497 |
-
"\n",
|
498 |
-
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
|
499 |
-
".sk-estimator-doc-link.fitted:hover,\n",
|
500 |
-
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
|
501 |
-
".sk-estimator-doc-link.fitted:hover {\n",
|
502 |
-
" /* fitted */\n",
|
503 |
-
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
504 |
-
" color: var(--sklearn-color-background);\n",
|
505 |
-
" text-decoration: none;\n",
|
506 |
-
"}\n",
|
507 |
-
"\n",
|
508 |
-
"/* Span, style for the box shown on hovering the info icon */\n",
|
509 |
-
".sk-estimator-doc-link span {\n",
|
510 |
-
" display: none;\n",
|
511 |
-
" z-index: 9999;\n",
|
512 |
-
" position: relative;\n",
|
513 |
-
" font-weight: normal;\n",
|
514 |
-
" right: .2ex;\n",
|
515 |
-
" padding: .5ex;\n",
|
516 |
-
" margin: .5ex;\n",
|
517 |
-
" width: min-content;\n",
|
518 |
-
" min-width: 20ex;\n",
|
519 |
-
" max-width: 50ex;\n",
|
520 |
-
" color: var(--sklearn-color-text);\n",
|
521 |
-
" box-shadow: 2pt 2pt 4pt #999;\n",
|
522 |
-
" /* unfitted */\n",
|
523 |
-
" background: var(--sklearn-color-unfitted-level-0);\n",
|
524 |
-
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
|
525 |
-
"}\n",
|
526 |
-
"\n",
|
527 |
-
".sk-estimator-doc-link.fitted span {\n",
|
528 |
-
" /* fitted */\n",
|
529 |
-
" background: var(--sklearn-color-fitted-level-0);\n",
|
530 |
-
" border: var(--sklearn-color-fitted-level-3);\n",
|
531 |
-
"}\n",
|
532 |
-
"\n",
|
533 |
-
".sk-estimator-doc-link:hover span {\n",
|
534 |
-
" display: block;\n",
|
535 |
-
"}\n",
|
536 |
-
"\n",
|
537 |
-
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
|
538 |
-
"\n",
|
539 |
-
"#sk-container-id-1 a.estimator_doc_link {\n",
|
540 |
-
" float: right;\n",
|
541 |
-
" font-size: 1rem;\n",
|
542 |
-
" line-height: 1em;\n",
|
543 |
-
" font-family: monospace;\n",
|
544 |
-
" background-color: var(--sklearn-color-background);\n",
|
545 |
-
" border-radius: 1rem;\n",
|
546 |
-
" height: 1rem;\n",
|
547 |
-
" width: 1rem;\n",
|
548 |
-
" text-decoration: none;\n",
|
549 |
-
" /* unfitted */\n",
|
550 |
-
" color: var(--sklearn-color-unfitted-level-1);\n",
|
551 |
-
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
552 |
-
"}\n",
|
553 |
-
"\n",
|
554 |
-
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
|
555 |
-
" /* fitted */\n",
|
556 |
-
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
557 |
-
" color: var(--sklearn-color-fitted-level-1);\n",
|
558 |
-
"}\n",
|
559 |
-
"\n",
|
560 |
-
"/* On hover */\n",
|
561 |
-
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
|
562 |
-
" /* unfitted */\n",
|
563 |
-
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
564 |
-
" color: var(--sklearn-color-background);\n",
|
565 |
-
" text-decoration: none;\n",
|
566 |
-
"}\n",
|
567 |
-
"\n",
|
568 |
-
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
|
569 |
-
" /* fitted */\n",
|
570 |
-
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
571 |
-
"}\n",
|
572 |
-
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
|
573 |
-
" colsample_bylevel=None, colsample_bynode=None,\n",
|
574 |
-
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
|
575 |
-
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
|
576 |
-
" gamma=None, grow_policy=None, importance_type=None,\n",
|
577 |
-
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
|
578 |
-
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
|
579 |
-
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
|
580 |
-
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
|
581 |
-
" multi_strategy=None, n_estimators=None, n_jobs=None,\n",
|
582 |
-
" num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> XGBRegressor<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
|
583 |
-
" colsample_bylevel=None, colsample_bynode=None,\n",
|
584 |
-
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
|
585 |
-
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
|
586 |
-
" gamma=None, grow_policy=None, importance_type=None,\n",
|
587 |
-
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
|
588 |
-
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
|
589 |
-
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
|
590 |
-
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
|
591 |
-
" multi_strategy=None, n_estimators=None, n_jobs=None,\n",
|
592 |
-
" num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
|
593 |
-
],
|
594 |
-
"text/plain": [
|
595 |
-
"XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
|
596 |
-
" colsample_bylevel=None, colsample_bynode=None,\n",
|
597 |
-
" colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
|
598 |
-
" enable_categorical=False, eval_metric=None, feature_types=None,\n",
|
599 |
-
" gamma=None, grow_policy=None, importance_type=None,\n",
|
600 |
-
" interaction_constraints=None, learning_rate=None, max_bin=None,\n",
|
601 |
-
" max_cat_threshold=None, max_cat_to_onehot=None,\n",
|
602 |
-
" max_delta_step=None, max_depth=None, max_leaves=None,\n",
|
603 |
-
" min_child_weight=None, missing=nan, monotone_constraints=None,\n",
|
604 |
-
" multi_strategy=None, n_estimators=None, n_jobs=None,\n",
|
605 |
-
" num_parallel_tree=None, random_state=None, ...)"
|
606 |
-
]
|
607 |
-
},
|
608 |
-
"execution_count": 6,
|
609 |
-
"metadata": {},
|
610 |
-
"output_type": "execute_result"
|
611 |
-
}
|
612 |
-
],
|
613 |
"source": [
|
614 |
"# Display the retrieved XGBoost regressor model\n",
|
615 |
"retrieved_xgboost_model"
|
@@ -624,20 +149,9 @@
|
|
624 |
},
|
625 |
{
|
626 |
"cell_type": "code",
|
627 |
-
"execution_count":
|
628 |
"metadata": {},
|
629 |
-
"outputs": [
|
630 |
-
{
|
631 |
-
"data": {
|
632 |
-
"text/plain": [
|
633 |
-
"1714138328000"
|
634 |
-
]
|
635 |
-
},
|
636 |
-
"execution_count": 7,
|
637 |
-
"metadata": {},
|
638 |
-
"output_type": "execute_result"
|
639 |
-
}
|
640 |
-
],
|
641 |
"source": [
|
642 |
"import datetime\n",
|
643 |
"\n",
|
@@ -653,17 +167,9 @@
|
|
653 |
},
|
654 |
{
|
655 |
"cell_type": "code",
|
656 |
-
"execution_count":
|
657 |
"metadata": {},
|
658 |
-
"outputs": [
|
659 |
-
{
|
660 |
-
"name": "stdout",
|
661 |
-
"output_type": "stream",
|
662 |
-
"text": [
|
663 |
-
"Finished: Reading data from Hopsworks, using ArrowFlight (2.85s) \n"
|
664 |
-
]
|
665 |
-
}
|
666 |
-
],
|
667 |
"source": [
|
668 |
"# Initializing batch scoring\n",
|
669 |
"feature_view.init_batch_scoring(training_dataset_version=1)\n",
|
@@ -676,199 +182,12 @@
|
|
676 |
},
|
677 |
{
|
678 |
"cell_type": "code",
|
679 |
-
"execution_count":
|
680 |
"metadata": {},
|
681 |
-
"outputs": [
|
682 |
-
{
|
683 |
-
"data": {
|
684 |
-
"text/html": [
|
685 |
-
"<div>\n",
|
686 |
-
"<style scoped>\n",
|
687 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
688 |
-
" vertical-align: middle;\n",
|
689 |
-
" }\n",
|
690 |
-
"\n",
|
691 |
-
" .dataframe tbody tr th {\n",
|
692 |
-
" vertical-align: top;\n",
|
693 |
-
" }\n",
|
694 |
-
"\n",
|
695 |
-
" .dataframe thead th {\n",
|
696 |
-
" text-align: right;\n",
|
697 |
-
" }\n",
|
698 |
-
"</style>\n",
|
699 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
700 |
-
" <thead>\n",
|
701 |
-
" <tr style=\"text-align: right;\">\n",
|
702 |
-
" <th></th>\n",
|
703 |
-
" <th>timestamp</th>\n",
|
704 |
-
" <th>time</th>\n",
|
705 |
-
" <th>date</th>\n",
|
706 |
-
" <th>dk1_spotpricedkk_kwh</th>\n",
|
707 |
-
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
708 |
-
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
709 |
-
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
710 |
-
" <th>temperature_2m</th>\n",
|
711 |
-
" <th>relative_humidity_2m</th>\n",
|
712 |
-
" <th>precipitation</th>\n",
|
713 |
-
" <th>rain</th>\n",
|
714 |
-
" <th>snowfall</th>\n",
|
715 |
-
" <th>weather_code</th>\n",
|
716 |
-
" <th>cloud_cover</th>\n",
|
717 |
-
" <th>wind_speed_10m</th>\n",
|
718 |
-
" <th>wind_gusts_10m</th>\n",
|
719 |
-
" <th>type</th>\n",
|
720 |
-
" </tr>\n",
|
721 |
-
" </thead>\n",
|
722 |
-
" <tbody>\n",
|
723 |
-
" <tr>\n",
|
724 |
-
" <th>0</th>\n",
|
725 |
-
" <td>1714287600000</td>\n",
|
726 |
-
" <td>2024-04-28 07:00:00+00:00</td>\n",
|
727 |
-
" <td>2024-04-28</td>\n",
|
728 |
-
" <td>0.00186</td>\n",
|
729 |
-
" <td>0.959167</td>\n",
|
730 |
-
" <td>0.771750</td>\n",
|
731 |
-
" <td>0.184346</td>\n",
|
732 |
-
" <td>8.5</td>\n",
|
733 |
-
" <td>91.0</td>\n",
|
734 |
-
" <td>0.0</td>\n",
|
735 |
-
" <td>0.0</td>\n",
|
736 |
-
" <td>0.0</td>\n",
|
737 |
-
" <td>2.0</td>\n",
|
738 |
-
" <td>62.0</td>\n",
|
739 |
-
" <td>12.8</td>\n",
|
740 |
-
" <td>22.3</td>\n",
|
741 |
-
" <td>Not a Workday</td>\n",
|
742 |
-
" </tr>\n",
|
743 |
-
" <tr>\n",
|
744 |
-
" <th>1</th>\n",
|
745 |
-
" <td>1714392000000</td>\n",
|
746 |
-
" <td>2024-04-29 12:00:00+00:00</td>\n",
|
747 |
-
" <td>2024-04-29</td>\n",
|
748 |
-
" <td>0.26984</td>\n",
|
749 |
-
" <td>0.649292</td>\n",
|
750 |
-
" <td>1.123000</td>\n",
|
751 |
-
" <td>1.615064</td>\n",
|
752 |
-
" <td>14.1</td>\n",
|
753 |
-
" <td>48.0</td>\n",
|
754 |
-
" <td>0.0</td>\n",
|
755 |
-
" <td>0.0</td>\n",
|
756 |
-
" <td>0.0</td>\n",
|
757 |
-
" <td>1.0</td>\n",
|
758 |
-
" <td>32.0</td>\n",
|
759 |
-
" <td>17.8</td>\n",
|
760 |
-
" <td>39.2</td>\n",
|
761 |
-
" <td>Workday</td>\n",
|
762 |
-
" </tr>\n",
|
763 |
-
" <tr>\n",
|
764 |
-
" <th>2</th>\n",
|
765 |
-
" <td>1714536000000</td>\n",
|
766 |
-
" <td>2024-05-01 04:00:00+00:00</td>\n",
|
767 |
-
" <td>2024-05-01</td>\n",
|
768 |
-
" <td>0.35659</td>\n",
|
769 |
-
" <td>0.605792</td>\n",
|
770 |
-
" <td>1.227542</td>\n",
|
771 |
-
" <td>0.000218</td>\n",
|
772 |
-
" <td>11.2</td>\n",
|
773 |
-
" <td>78.0</td>\n",
|
774 |
-
" <td>0.0</td>\n",
|
775 |
-
" <td>0.0</td>\n",
|
776 |
-
" <td>0.0</td>\n",
|
777 |
-
" <td>3.0</td>\n",
|
778 |
-
" <td>96.0</td>\n",
|
779 |
-
" <td>18.0</td>\n",
|
780 |
-
" <td>33.5</td>\n",
|
781 |
-
" <td>Workday</td>\n",
|
782 |
-
" </tr>\n",
|
783 |
-
" <tr>\n",
|
784 |
-
" <th>3</th>\n",
|
785 |
-
" <td>1714172400000</td>\n",
|
786 |
-
" <td>2024-04-26 23:00:00+00:00</td>\n",
|
787 |
-
" <td>2024-04-26</td>\n",
|
788 |
-
" <td>0.65829</td>\n",
|
789 |
-
" <td>0.178042</td>\n",
|
790 |
-
" <td>0.244625</td>\n",
|
791 |
-
" <td>0.000000</td>\n",
|
792 |
-
" <td>3.9</td>\n",
|
793 |
-
" <td>96.0</td>\n",
|
794 |
-
" <td>0.0</td>\n",
|
795 |
-
" <td>0.0</td>\n",
|
796 |
-
" <td>0.0</td>\n",
|
797 |
-
" <td>1.0</td>\n",
|
798 |
-
" <td>36.0</td>\n",
|
799 |
-
" <td>3.9</td>\n",
|
800 |
-
" <td>8.6</td>\n",
|
801 |
-
" <td>Workday</td>\n",
|
802 |
-
" </tr>\n",
|
803 |
-
" <tr>\n",
|
804 |
-
" <th>4</th>\n",
|
805 |
-
" <td>1714258800000</td>\n",
|
806 |
-
" <td>2024-04-27 23:00:00+00:00</td>\n",
|
807 |
-
" <td>2024-04-27</td>\n",
|
808 |
-
" <td>0.48644</td>\n",
|
809 |
-
" <td>0.657625</td>\n",
|
810 |
-
" <td>0.999583</td>\n",
|
811 |
-
" <td>0.000000</td>\n",
|
812 |
-
" <td>6.9</td>\n",
|
813 |
-
" <td>93.0</td>\n",
|
814 |
-
" <td>0.0</td>\n",
|
815 |
-
" <td>0.0</td>\n",
|
816 |
-
" <td>0.0</td>\n",
|
817 |
-
" <td>1.0</td>\n",
|
818 |
-
" <td>40.0</td>\n",
|
819 |
-
" <td>16.2</td>\n",
|
820 |
-
" <td>29.9</td>\n",
|
821 |
-
" <td>Not a Workday</td>\n",
|
822 |
-
" </tr>\n",
|
823 |
-
" </tbody>\n",
|
824 |
-
"</table>\n",
|
825 |
-
"</div>"
|
826 |
-
],
|
827 |
-
"text/plain": [
|
828 |
-
" timestamp time date dk1_spotpricedkk_kwh \\\n",
|
829 |
-
"0 1714287600000 2024-04-28 07:00:00+00:00 2024-04-28 0.00186 \n",
|
830 |
-
"1 1714392000000 2024-04-29 12:00:00+00:00 2024-04-29 0.26984 \n",
|
831 |
-
"2 1714536000000 2024-05-01 04:00:00+00:00 2024-05-01 0.35659 \n",
|
832 |
-
"3 1714172400000 2024-04-26 23:00:00+00:00 2024-04-26 0.65829 \n",
|
833 |
-
"4 1714258800000 2024-04-27 23:00:00+00:00 2024-04-27 0.48644 \n",
|
834 |
-
"\n",
|
835 |
-
" dk1_offshore_wind_forecastintraday_kwh \\\n",
|
836 |
-
"0 0.959167 \n",
|
837 |
-
"1 0.649292 \n",
|
838 |
-
"2 0.605792 \n",
|
839 |
-
"3 0.178042 \n",
|
840 |
-
"4 0.657625 \n",
|
841 |
-
"\n",
|
842 |
-
" dk1_onshore_wind_forecastintraday_kwh dk1_solar_forecastintraday_kwh \\\n",
|
843 |
-
"0 0.771750 0.184346 \n",
|
844 |
-
"1 1.123000 1.615064 \n",
|
845 |
-
"2 1.227542 0.000218 \n",
|
846 |
-
"3 0.244625 0.000000 \n",
|
847 |
-
"4 0.999583 0.000000 \n",
|
848 |
-
"\n",
|
849 |
-
" temperature_2m relative_humidity_2m precipitation rain snowfall \\\n",
|
850 |
-
"0 8.5 91.0 0.0 0.0 0.0 \n",
|
851 |
-
"1 14.1 48.0 0.0 0.0 0.0 \n",
|
852 |
-
"2 11.2 78.0 0.0 0.0 0.0 \n",
|
853 |
-
"3 3.9 96.0 0.0 0.0 0.0 \n",
|
854 |
-
"4 6.9 93.0 0.0 0.0 0.0 \n",
|
855 |
-
"\n",
|
856 |
-
" weather_code cloud_cover wind_speed_10m wind_gusts_10m type \n",
|
857 |
-
"0 2.0 62.0 12.8 22.3 Not a Workday \n",
|
858 |
-
"1 1.0 32.0 17.8 39.2 Workday \n",
|
859 |
-
"2 3.0 96.0 18.0 33.5 Workday \n",
|
860 |
-
"3 1.0 36.0 3.9 8.6 Workday \n",
|
861 |
-
"4 1.0 40.0 16.2 29.9 Not a Workday "
|
862 |
-
]
|
863 |
-
},
|
864 |
-
"execution_count": 11,
|
865 |
-
"metadata": {},
|
866 |
-
"output_type": "execute_result"
|
867 |
-
}
|
868 |
-
],
|
869 |
"source": [
|
870 |
"# Display the first 5 rows of the batch data\n",
|
871 |
-
"batch_data
|
872 |
]
|
873 |
},
|
874 |
{
|
@@ -880,215 +199,61 @@
|
|
880 |
},
|
881 |
{
|
882 |
"cell_type": "code",
|
883 |
-
"execution_count":
|
884 |
"metadata": {},
|
885 |
-
"outputs": [
|
886 |
-
{
|
887 |
-
"name": "stderr",
|
888 |
-
"output_type": "stream",
|
889 |
-
"text": [
|
890 |
-
"DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
891 |
-
"DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n"
|
892 |
-
]
|
893 |
-
}
|
894 |
-
],
|
895 |
"source": [
|
896 |
-
"from sklearn.preprocessing import LabelEncoder\n",
|
897 |
"\n",
|
898 |
-
"# Create a LabelEncoder object\n",
|
899 |
-
"label_encoder = LabelEncoder()\n",
|
900 |
"\n",
|
901 |
-
"# Fit the encoder to the data in the 'city_name' column\n",
|
902 |
-
"label_encoder.fit(batch_data[['type']])\n",
|
903 |
"\n",
|
904 |
-
"# Transform the 'city_name' column data using the fitted encoder\n",
|
905 |
-
"encoded = label_encoder.transform(batch_data[['type']])"
|
906 |
]
|
907 |
},
|
908 |
{
|
909 |
"cell_type": "code",
|
910 |
-
"execution_count":
|
911 |
"metadata": {},
|
912 |
-
"outputs": [
|
913 |
-
{
|
914 |
-
"name": "stderr",
|
915 |
-
"output_type": "stream",
|
916 |
-
"text": [
|
917 |
-
"DeprecationWarning: np.find_common_type is deprecated. Please use `np.result_type` or `np.promote_types`.\n",
|
918 |
-
"See https://numpy.org/devdocs/release/1.25.0-notes.html and the docs for more information. (Deprecated NumPy 1.25)\n"
|
919 |
-
]
|
920 |
-
},
|
921 |
-
{
|
922 |
-
"data": {
|
923 |
-
"text/html": [
|
924 |
-
"<div>\n",
|
925 |
-
"<style scoped>\n",
|
926 |
-
" .dataframe tbody tr th:only-of-type {\n",
|
927 |
-
" vertical-align: middle;\n",
|
928 |
-
" }\n",
|
929 |
-
"\n",
|
930 |
-
" .dataframe tbody tr th {\n",
|
931 |
-
" vertical-align: top;\n",
|
932 |
-
" }\n",
|
933 |
-
"\n",
|
934 |
-
" .dataframe thead th {\n",
|
935 |
-
" text-align: right;\n",
|
936 |
-
" }\n",
|
937 |
-
"</style>\n",
|
938 |
-
"<table border=\"1\" class=\"dataframe\">\n",
|
939 |
-
" <thead>\n",
|
940 |
-
" <tr style=\"text-align: right;\">\n",
|
941 |
-
" <th></th>\n",
|
942 |
-
" <th>dk1_spotpricedkk_kwh</th>\n",
|
943 |
-
" <th>dk1_offshore_wind_forecastintraday_kwh</th>\n",
|
944 |
-
" <th>dk1_onshore_wind_forecastintraday_kwh</th>\n",
|
945 |
-
" <th>dk1_solar_forecastintraday_kwh</th>\n",
|
946 |
-
" <th>temperature_2m</th>\n",
|
947 |
-
" <th>relative_humidity_2m</th>\n",
|
948 |
-
" <th>precipitation</th>\n",
|
949 |
-
" <th>rain</th>\n",
|
950 |
-
" <th>snowfall</th>\n",
|
951 |
-
" <th>weather_code</th>\n",
|
952 |
-
" <th>cloud_cover</th>\n",
|
953 |
-
" <th>wind_speed_10m</th>\n",
|
954 |
-
" <th>wind_gusts_10m</th>\n",
|
955 |
-
" <th>type_encoded</th>\n",
|
956 |
-
" </tr>\n",
|
957 |
-
" </thead>\n",
|
958 |
-
" <tbody>\n",
|
959 |
-
" <tr>\n",
|
960 |
-
" <th>48</th>\n",
|
961 |
-
" <td>0.48757</td>\n",
|
962 |
-
" <td>0.428250</td>\n",
|
963 |
-
" <td>1.065542</td>\n",
|
964 |
-
" <td>0.712989</td>\n",
|
965 |
-
" <td>7.9</td>\n",
|
966 |
-
" <td>67.0</td>\n",
|
967 |
-
" <td>0.1</td>\n",
|
968 |
-
" <td>0.1</td>\n",
|
969 |
-
" <td>0.0</td>\n",
|
970 |
-
" <td>51.0</td>\n",
|
971 |
-
" <td>100.0</td>\n",
|
972 |
-
" <td>24.5</td>\n",
|
973 |
-
" <td>49.3</td>\n",
|
974 |
-
" <td>0</td>\n",
|
975 |
-
" </tr>\n",
|
976 |
-
" <tr>\n",
|
977 |
-
" <th>38</th>\n",
|
978 |
-
" <td>0.52150</td>\n",
|
979 |
-
" <td>0.374083</td>\n",
|
980 |
-
" <td>0.968125</td>\n",
|
981 |
-
" <td>0.740813</td>\n",
|
982 |
-
" <td>7.5</td>\n",
|
983 |
-
" <td>67.0</td>\n",
|
984 |
-
" <td>0.1</td>\n",
|
985 |
-
" <td>0.1</td>\n",
|
986 |
-
" <td>0.0</td>\n",
|
987 |
-
" <td>51.0</td>\n",
|
988 |
-
" <td>100.0</td>\n",
|
989 |
-
" <td>23.1</td>\n",
|
990 |
-
" <td>47.5</td>\n",
|
991 |
-
" <td>0</td>\n",
|
992 |
-
" </tr>\n",
|
993 |
-
" <tr>\n",
|
994 |
-
" <th>33</th>\n",
|
995 |
-
" <td>0.53478</td>\n",
|
996 |
-
" <td>0.322542</td>\n",
|
997 |
-
" <td>0.848917</td>\n",
|
998 |
-
" <td>0.666078</td>\n",
|
999 |
-
" <td>6.8</td>\n",
|
1000 |
-
" <td>73.0</td>\n",
|
1001 |
-
" <td>0.1</td>\n",
|
1002 |
-
" <td>0.1</td>\n",
|
1003 |
-
" <td>0.0</td>\n",
|
1004 |
-
" <td>51.0</td>\n",
|
1005 |
-
" <td>100.0</td>\n",
|
1006 |
-
" <td>21.2</td>\n",
|
1007 |
-
" <td>43.9</td>\n",
|
1008 |
-
" <td>0</td>\n",
|
1009 |
-
" </tr>\n",
|
1010 |
-
" <tr>\n",
|
1011 |
-
" <th>23</th>\n",
|
1012 |
-
" <td>0.60012</td>\n",
|
1013 |
-
" <td>0.297750</td>\n",
|
1014 |
-
" <td>0.743667</td>\n",
|
1015 |
-
" <td>0.498373</td>\n",
|
1016 |
-
" <td>6.4</td>\n",
|
1017 |
-
" <td>76.0</td>\n",
|
1018 |
-
" <td>0.2</td>\n",
|
1019 |
-
" <td>0.2</td>\n",
|
1020 |
-
" <td>0.0</td>\n",
|
1021 |
-
" <td>51.0</td>\n",
|
1022 |
-
" <td>81.0</td>\n",
|
1023 |
-
" <td>19.6</td>\n",
|
1024 |
-
" <td>40.0</td>\n",
|
1025 |
-
" <td>0</td>\n",
|
1026 |
-
" </tr>\n",
|
1027 |
-
" <tr>\n",
|
1028 |
-
" <th>18</th>\n",
|
1029 |
-
" <td>0.70021</td>\n",
|
1030 |
-
" <td>0.281875</td>\n",
|
1031 |
-
" <td>0.633917</td>\n",
|
1032 |
-
" <td>0.315199</td>\n",
|
1033 |
-
" <td>5.8</td>\n",
|
1034 |
-
" <td>81.0</td>\n",
|
1035 |
-
" <td>0.1</td>\n",
|
1036 |
-
" <td>0.1</td>\n",
|
1037 |
-
" <td>0.0</td>\n",
|
1038 |
-
" <td>51.0</td>\n",
|
1039 |
-
" <td>61.0</td>\n",
|
1040 |
-
" <td>15.3</td>\n",
|
1041 |
-
" <td>37.1</td>\n",
|
1042 |
-
" <td>0</td>\n",
|
1043 |
-
" </tr>\n",
|
1044 |
-
" </tbody>\n",
|
1045 |
-
"</table>\n",
|
1046 |
-
"</div>"
|
1047 |
-
],
|
1048 |
-
"text/plain": [
|
1049 |
-
" dk1_spotpricedkk_kwh dk1_offshore_wind_forecastintraday_kwh \\\n",
|
1050 |
-
"48 0.48757 0.428250 \n",
|
1051 |
-
"38 0.52150 0.374083 \n",
|
1052 |
-
"33 0.53478 0.322542 \n",
|
1053 |
-
"23 0.60012 0.297750 \n",
|
1054 |
-
"18 0.70021 0.281875 \n",
|
1055 |
-
"\n",
|
1056 |
-
" dk1_onshore_wind_forecastintraday_kwh dk1_solar_forecastintraday_kwh \\\n",
|
1057 |
-
"48 1.065542 0.712989 \n",
|
1058 |
-
"38 0.968125 0.740813 \n",
|
1059 |
-
"33 0.848917 0.666078 \n",
|
1060 |
-
"23 0.743667 0.498373 \n",
|
1061 |
-
"18 0.633917 0.315199 \n",
|
1062 |
-
"\n",
|
1063 |
-
" temperature_2m relative_humidity_2m precipitation rain snowfall \\\n",
|
1064 |
-
"48 7.9 67.0 0.1 0.1 0.0 \n",
|
1065 |
-
"38 7.5 67.0 0.1 0.1 0.0 \n",
|
1066 |
-
"33 6.8 73.0 0.1 0.1 0.0 \n",
|
1067 |
-
"23 6.4 76.0 0.2 0.2 0.0 \n",
|
1068 |
-
"18 5.8 81.0 0.1 0.1 0.0 \n",
|
1069 |
-
"\n",
|
1070 |
-
" weather_code cloud_cover wind_speed_10m wind_gusts_10m type_encoded \n",
|
1071 |
-
"48 51.0 100.0 24.5 49.3 0 \n",
|
1072 |
-
"38 51.0 100.0 23.1 47.5 0 \n",
|
1073 |
-
"33 51.0 100.0 21.2 43.9 0 \n",
|
1074 |
-
"23 51.0 81.0 19.6 40.0 0 \n",
|
1075 |
-
"18 51.0 61.0 15.3 37.1 0 "
|
1076 |
-
]
|
1077 |
-
},
|
1078 |
-
"execution_count": 17,
|
1079 |
-
"metadata": {},
|
1080 |
-
"output_type": "execute_result"
|
1081 |
-
}
|
1082 |
-
],
|
1083 |
"source": [
|
1084 |
-
"
|
1085 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1086 |
"\n",
|
1087 |
"# Drop columns 'date', 'city_name', 'unix_time' from the DataFrame 'X'\n",
|
1088 |
-
"X_batch = X_batch.drop(columns=['date', 'time', 'timestamp'
|
1089 |
"\n",
|
1090 |
-
"# Rename the newly added column with label-encoded city names to 'city_name_encoded'\n",
|
1091 |
-
"X_batch = X_batch.rename(columns={0: \"type_encoded\"})\n",
|
1092 |
"\n",
|
1093 |
"# Displaying the first 5 rows of the modified DataFrame\n",
|
1094 |
"X_batch.head()"
|
@@ -1096,25 +261,9 @@
|
|
1096 |
},
|
1097 |
{
|
1098 |
"cell_type": "code",
|
1099 |
-
"execution_count":
|
1100 |
"metadata": {},
|
1101 |
-
"outputs": [
|
1102 |
-
{
|
1103 |
-
"data": {
|
1104 |
-
"text/plain": [
|
1105 |
-
"48 0.48757\n",
|
1106 |
-
"38 0.52150\n",
|
1107 |
-
"33 0.53478\n",
|
1108 |
-
"23 0.60012\n",
|
1109 |
-
"18 0.70021\n",
|
1110 |
-
"Name: dk1_spotpricedkk_kwh, dtype: float64"
|
1111 |
-
]
|
1112 |
-
},
|
1113 |
-
"execution_count": 18,
|
1114 |
-
"metadata": {},
|
1115 |
-
"output_type": "execute_result"
|
1116 |
-
}
|
1117 |
-
],
|
1118 |
"source": [
|
1119 |
"# Extract the target variable 'dk1_spotpricedkk_kwh' from the batch data\n",
|
1120 |
"y_batch = X_batch.pop('dk1_spotpricedkk_kwh')\n",
|
@@ -1125,67 +274,51 @@
|
|
1125 |
},
|
1126 |
{
|
1127 |
"cell_type": "code",
|
1128 |
-
"execution_count":
|
1129 |
"metadata": {},
|
1130 |
-
"outputs": [
|
1131 |
-
{
|
1132 |
-
"data": {
|
1133 |
-
"text/plain": [
|
1134 |
-
"48 0.48757\n",
|
1135 |
-
"38 0.52150\n",
|
1136 |
-
"33 0.53478\n",
|
1137 |
-
"23 0.60012\n",
|
1138 |
-
"18 0.70021\n",
|
1139 |
-
" ... \n",
|
1140 |
-
"32 0.37590\n",
|
1141 |
-
"47 0.37292\n",
|
1142 |
-
"27 0.25366\n",
|
1143 |
-
"64 0.22315\n",
|
1144 |
-
"96 0.16408\n",
|
1145 |
-
"Name: dk1_spotpricedkk_kwh, Length: 106, dtype: float64"
|
1146 |
-
]
|
1147 |
-
},
|
1148 |
-
"execution_count": 19,
|
1149 |
-
"metadata": {},
|
1150 |
-
"output_type": "execute_result"
|
1151 |
-
}
|
1152 |
-
],
|
1153 |
"source": [
|
1154 |
-
"#
|
1155 |
-
"
|
|
|
|
|
|
|
1156 |
]
|
1157 |
},
|
1158 |
{
|
1159 |
"cell_type": "code",
|
1160 |
-
"execution_count":
|
1161 |
"metadata": {},
|
1162 |
-
"outputs": [
|
1163 |
-
{
|
1164 |
-
"name": "stderr",
|
1165 |
-
"output_type": "stream",
|
1166 |
-
"text": [
|
1167 |
-
"DeprecationWarning: np.find_common_type is deprecated. Please use `np.result_type` or `np.promote_types`.\n",
|
1168 |
-
"See https://numpy.org/devdocs/release/1.25.0-notes.html and the docs for more information. (Deprecated NumPy 1.25)\n"
|
1169 |
-
]
|
1170 |
-
},
|
1171 |
-
{
|
1172 |
-
"data": {
|
1173 |
-
"text/plain": [
|
1174 |
-
"array([0.25547686, 0.37913612, 0.33905983, 0.3961694 , 0.5968245 ],\n",
|
1175 |
-
" dtype=float32)"
|
1176 |
-
]
|
1177 |
-
},
|
1178 |
-
"execution_count": 20,
|
1179 |
-
"metadata": {},
|
1180 |
-
"output_type": "execute_result"
|
1181 |
-
}
|
1182 |
-
],
|
1183 |
"source": [
|
1184 |
-
"
|
1185 |
-
"
|
1186 |
"\n",
|
1187 |
-
"
|
1188 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1189 |
]
|
1190 |
},
|
1191 |
{
|
|
|
28 |
},
|
29 |
{
|
30 |
"cell_type": "code",
|
31 |
+
"execution_count": null,
|
32 |
"metadata": {},
|
33 |
"outputs": [],
|
34 |
"source": [
|
|
|
53 |
},
|
54 |
{
|
55 |
"cell_type": "code",
|
56 |
+
"execution_count": null,
|
57 |
"metadata": {},
|
58 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
"source": [
|
60 |
"# Importing the hopsworks module\n",
|
61 |
"import hopsworks\n",
|
|
|
76 |
},
|
77 |
{
|
78 |
"cell_type": "code",
|
79 |
+
"execution_count": null,
|
80 |
"metadata": {},
|
81 |
"outputs": [],
|
82 |
"source": [
|
|
|
96 |
},
|
97 |
{
|
98 |
"cell_type": "code",
|
99 |
+
"execution_count": null,
|
100 |
"metadata": {},
|
101 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
102 |
"source": [
|
103 |
"# Retrieve the model registry\n",
|
104 |
"mr = project.get_model_registry()"
|
|
|
113 |
},
|
114 |
{
|
115 |
"cell_type": "code",
|
116 |
+
"execution_count": null,
|
117 |
"metadata": {},
|
118 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
119 |
"source": [
|
120 |
"# Retrieving the model from the Model Registry\n",
|
121 |
"retrieved_model = mr.get_model(\n",
|
|
|
132 |
},
|
133 |
{
|
134 |
"cell_type": "code",
|
135 |
+
"execution_count": null,
|
136 |
"metadata": {},
|
137 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
138 |
"source": [
|
139 |
"# Display the retrieved XGBoost regressor model\n",
|
140 |
"retrieved_xgboost_model"
|
|
|
149 |
},
|
150 |
{
|
151 |
"cell_type": "code",
|
152 |
+
"execution_count": null,
|
153 |
"metadata": {},
|
154 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
155 |
"source": [
|
156 |
"import datetime\n",
|
157 |
"\n",
|
|
|
167 |
},
|
168 |
{
|
169 |
"cell_type": "code",
|
170 |
+
"execution_count": null,
|
171 |
"metadata": {},
|
172 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
173 |
"source": [
|
174 |
"# Initializing batch scoring\n",
|
175 |
"feature_view.init_batch_scoring(training_dataset_version=1)\n",
|
|
|
182 |
},
|
183 |
{
|
184 |
"cell_type": "code",
|
185 |
+
"execution_count": null,
|
186 |
"metadata": {},
|
187 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
188 |
"source": [
|
189 |
"# Display the first 5 rows of the batch data\n",
|
190 |
+
"batch_data"
|
191 |
]
|
192 |
},
|
193 |
{
|
|
|
199 |
},
|
200 |
{
|
201 |
"cell_type": "code",
|
202 |
+
"execution_count": null,
|
203 |
"metadata": {},
|
204 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
205 |
"source": [
|
206 |
+
"# from sklearn.preprocessing import LabelEncoder\n",
|
207 |
"\n",
|
208 |
+
"# # Create a LabelEncoder object\n",
|
209 |
+
"# label_encoder = LabelEncoder()\n",
|
210 |
"\n",
|
211 |
+
"# # Fit the encoder to the data in the 'city_name' column\n",
|
212 |
+
"# label_encoder.fit(batch_data[['type']])\n",
|
213 |
"\n",
|
214 |
+
"# # Transform the 'city_name' column data using the fitted encoder\n",
|
215 |
+
"# encoded = label_encoder.transform(batch_data[['type']])"
|
216 |
]
|
217 |
},
|
218 |
{
|
219 |
"cell_type": "code",
|
220 |
+
"execution_count": null,
|
221 |
"metadata": {},
|
222 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
223 |
"source": [
|
224 |
+
"batch_data"
|
225 |
+
]
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"cell_type": "code",
|
229 |
+
"execution_count": null,
|
230 |
+
"metadata": {},
|
231 |
+
"outputs": [],
|
232 |
+
"source": []
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"cell_type": "code",
|
236 |
+
"execution_count": null,
|
237 |
+
"metadata": {},
|
238 |
+
"outputs": [],
|
239 |
+
"source": []
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"cell_type": "code",
|
243 |
+
"execution_count": null,
|
244 |
+
"metadata": {},
|
245 |
+
"outputs": [],
|
246 |
+
"source": [
|
247 |
+
"# # Convert the output of the label encoding to a dense array and concatenate with the original data\n",
|
248 |
+
"# X_batch = pd.concat([batch_data, pd.DataFrame(encoded)], axis=1)\n",
|
249 |
+
"\n",
|
250 |
+
"X_batch = batch_data\n",
|
251 |
"\n",
|
252 |
"# Drop columns 'date', 'city_name', 'unix_time' from the DataFrame 'X'\n",
|
253 |
+
"X_batch = X_batch.drop(columns=['date', 'time', 'timestamp'])\n",
|
254 |
"\n",
|
255 |
+
"# # Rename the newly added column with label-encoded city names to 'city_name_encoded'\n",
|
256 |
+
"# X_batch = X_batch.rename(columns={0: \"type_encoded\"})\n",
|
257 |
"\n",
|
258 |
"# Displaying the first 5 rows of the modified DataFrame\n",
|
259 |
"X_batch.head()"
|
|
|
261 |
},
|
262 |
{
|
263 |
"cell_type": "code",
|
264 |
+
"execution_count": null,
|
265 |
"metadata": {},
|
266 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
267 |
"source": [
|
268 |
"# Extract the target variable 'dk1_spotpricedkk_kwh' from the batch data\n",
|
269 |
"y_batch = X_batch.pop('dk1_spotpricedkk_kwh')\n",
|
|
|
274 |
},
|
275 |
{
|
276 |
"cell_type": "code",
|
277 |
+
"execution_count": null,
|
278 |
"metadata": {},
|
279 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
280 |
"source": [
|
281 |
+
"# Make predictions on the batch data using the retrieved XGBoost regressor model\n",
|
282 |
+
"predictions = retrieved_xgboost_model.predict(X_batch)\n",
|
283 |
+
"\n",
|
284 |
+
"# Display the first 5 predictions\n",
|
285 |
+
"predictions[:5]"
|
286 |
]
|
287 |
},
|
288 |
{
|
289 |
"cell_type": "code",
|
290 |
+
"execution_count": null,
|
291 |
"metadata": {},
|
292 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
293 |
"source": [
|
294 |
+
"label = batch_data[\"dk1_spotpricedkk_kwh\"]\n",
|
295 |
+
"y_pred = retrieved_xgboost_model.predict(X_batch)\n",
|
296 |
"\n",
|
297 |
+
"data = {\n",
|
298 |
+
" 'prediction': [y_pred],\n",
|
299 |
+
" 'label': [label],\n",
|
300 |
+
"}\n",
|
301 |
+
"\n",
|
302 |
+
"monitor_df = pd.DataFrame(data)\n",
|
303 |
+
"monitor_df"
|
304 |
+
]
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"cell_type": "code",
|
308 |
+
"execution_count": null,
|
309 |
+
"metadata": {},
|
310 |
+
"outputs": [],
|
311 |
+
"source": [
|
312 |
+
"label = batch_data[\"dk1_spotpricedkk_kwh\"]\n",
|
313 |
+
"y_pred = retrieved_xgboost_model.predict(X_batch)\n",
|
314 |
+
"\n",
|
315 |
+
"data = {\n",
|
316 |
+
" 'prediction': y_pred,\n",
|
317 |
+
" 'label': label,\n",
|
318 |
+
"}\n",
|
319 |
+
"\n",
|
320 |
+
"monitor_df = pd.DataFrame(data)\n",
|
321 |
+
"monitor_df"
|
322 |
]
|
323 |
},
|
324 |
{
|
notebooks/model/dk_electricity_model.pkl
CHANGED
Binary files a/notebooks/model/dk_electricity_model.pkl and b/notebooks/model/dk_electricity_model.pkl differ
|
|
notebooks/test.ipynb
CHANGED
The diff for this file is too large to render.
See raw diff
|
|