notebooks/3_training_pipeline.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# <span style=\"font-width:bold; font-size: 3rem; color:#2656a3;\">**Msc. BDS Module - Data Engineering and Machine Learning Operations in Business (MLOPs)** </span> <span style=\"font-width:bold; font-size: 3rem; color:#333;\">- Part 03: Training Pipeline</span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style='color:#2656a3'> 🗒️ This notebook is divided into the following sections:\n",
    "1. Feature selection.\n",
    "2. Creating a Feature View.\n",
    "3. Training datasets creation - splitting into train and test sets.\n",
    "4. Training the model.\n",
    "5. Register the model to Hopsworks Model Registry."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style='color:#2656a3'> ⚙️ Import of libraries and packages\n",
    "We start with importing some of the necessary libraries needed for this notebook and warnings to avoid unnecessary distractions and keep output clean."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the packages and libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Ignore warnings\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#2656a3;\"> 📡 Connecting to Hopsworks Feature Store\n",
    "We connect to Hopsworks Feature Store so we can retrieve the Feature Groups and select features for training data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Connected. Call `.close()` to terminate connection gracefully.\n",
      "\n",
      "Logged in to project, explore it here https://c.app.hopsworks.ai:443/p/550040\n",
      "Connected. Call `.close()` to terminate connection gracefully.\n"
     ]
    }
   ],
   "source": [
    "# Importing the hopsworks module for interacting with the Hopsworks platform\n",
    "import hopsworks\n",
    "\n",
    "# Logging into the Hopsworks project\n",
    "project = hopsworks.login()\n",
    "\n",
    "# Getting the feature store from the project\n",
    "fs = project.get_feature_store() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Retrieve the feature groups\n",
    "electricity_fg = fs.get_feature_group(\n",
    "    name='electricity_prices',\n",
    "    version=1,\n",
    ")\n",
    "\n",
    "weather_fg = fs.get_feature_group(\n",
    "    name='weather_measurements',\n",
    "    version=1,\n",
    ")\n",
    "\n",
    "danish_calendar_fg = fs.get_feature_group(\n",
    "    name='dk_calendar',\n",
    "    version=1,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#2656a3;\"> 🖍 Feature View Creation and Retrieving </span>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We first select the features that we want to include for model training.\n",
    "\n",
    "Since we specified `primary_key`as `date` and `timestamp` in `1_feature_backfill` we can now join them together for the `electricity_fg`, `weather_fg` and `danish_holiday_fg`.\n",
    "\n",
    "`join_type` specifies the type of join to perform. An inner join refers to only retaining the rows based on the keys present in all joined DataFrames."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select features for training data and join them together and except duplicate columns\n",
    "selected_features_training = electricity_fg.select_all()\\\n",
    "    .join(weather_fg.select_except([\"timestamp\", \"datetime\", \"hour\"]), join_type=\"inner\")\\\n",
    "    .join(danish_calendar_fg.select_all(), join_type=\"inner\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finished: Reading data from Hopsworks, using ArrowFlight (3.20s) \n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>timestamp</th>\n",
       "      <th>datetime</th>\n",
       "      <th>date</th>\n",
       "      <th>hour</th>\n",
       "      <th>dk1_spotpricedkk_kwh</th>\n",
       "      <th>temperature_2m</th>\n",
       "      <th>relative_humidity_2m</th>\n",
       "      <th>precipitation</th>\n",
       "      <th>rain</th>\n",
       "      <th>snowfall</th>\n",
       "      <th>weather_code</th>\n",
       "      <th>cloud_cover</th>\n",
       "      <th>wind_speed_10m</th>\n",
       "      <th>wind_gusts_10m</th>\n",
       "      <th>dayofweek</th>\n",
       "      <th>day</th>\n",
       "      <th>month</th>\n",
       "      <th>year</th>\n",
       "      <th>workday</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1682280000000</td>\n",
       "      <td>2023-04-23 20:00:00+00:00</td>\n",
       "      <td>2023-04-23</td>\n",
       "      <td>20</td>\n",
       "      <td>1.02178</td>\n",
       "      <td>10.4</td>\n",
       "      <td>74.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>7.6</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "      <td>23</td>\n",
       "      <td>4</td>\n",
       "      <td>2023</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1678816800000</td>\n",
       "      <td>2023-03-14 18:00:00+00:00</td>\n",
       "      <td>2023-03-14</td>\n",
       "      <td>18</td>\n",
       "      <td>0.77461</td>\n",
       "      <td>0.5</td>\n",
       "      <td>88.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>11.6</td>\n",
       "      <td>22.7</td>\n",
       "      <td>1</td>\n",
       "      <td>14</td>\n",
       "      <td>3</td>\n",
       "      <td>2023</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1697259600000</td>\n",
       "      <td>2023-10-14 05:00:00+00:00</td>\n",
       "      <td>2023-10-14</td>\n",
       "      <td>5</td>\n",
       "      <td>-0.01551</td>\n",
       "      <td>9.8</td>\n",
       "      <td>71.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>23.0</td>\n",
       "      <td>29.5</td>\n",
       "      <td>54.7</td>\n",
       "      <td>5</td>\n",
       "      <td>14</td>\n",
       "      <td>10</td>\n",
       "      <td>2023</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1657170000000</td>\n",
       "      <td>2022-07-07 05:00:00+00:00</td>\n",
       "      <td>2022-07-07</td>\n",
       "      <td>5</td>\n",
       "      <td>1.15795</td>\n",
       "      <td>15.0</td>\n",
       "      <td>90.0</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.1</td>\n",
       "      <td>0.0</td>\n",
       "      <td>51.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>16.6</td>\n",
       "      <td>31.3</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>2022</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1647597600000</td>\n",
       "      <td>2022-03-18 10:00:00+00:00</td>\n",
       "      <td>2022-03-18</td>\n",
       "      <td>10</td>\n",
       "      <td>1.48754</td>\n",
       "      <td>8.4</td>\n",
       "      <td>60.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>21.9</td>\n",
       "      <td>45.4</td>\n",
       "      <td>4</td>\n",
       "      <td>18</td>\n",
       "      <td>3</td>\n",
       "      <td>2022</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       timestamp                  datetime        date  hour  \\\n",
       "0  1682280000000 2023-04-23 20:00:00+00:00  2023-04-23    20   \n",
       "1  1678816800000 2023-03-14 18:00:00+00:00  2023-03-14    18   \n",
       "2  1697259600000 2023-10-14 05:00:00+00:00  2023-10-14     5   \n",
       "3  1657170000000 2022-07-07 05:00:00+00:00  2022-07-07     5   \n",
       "4  1647597600000 2022-03-18 10:00:00+00:00  2022-03-18    10   \n",
       "\n",
       "   dk1_spotpricedkk_kwh  temperature_2m  relative_humidity_2m  precipitation  \\\n",
       "0               1.02178            10.4                  74.0            0.0   \n",
       "1               0.77461             0.5                  88.0            0.0   \n",
       "2              -0.01551             9.8                  71.0            0.0   \n",
       "3               1.15795            15.0                  90.0            0.1   \n",
       "4               1.48754             8.4                  60.0            0.0   \n",
       "\n",
       "   rain  snowfall  weather_code  cloud_cover  wind_speed_10m  wind_gusts_10m  \\\n",
       "0   0.0       0.0           3.0        100.0             7.6            10.1   \n",
       "1   0.0       0.0           0.0          0.0            11.6            22.7   \n",
       "2   0.0       0.0           1.0         23.0            29.5            54.7   \n",
       "3   0.1       0.0          51.0         59.0            16.6            31.3   \n",
       "4   0.0       0.0           0.0          0.0            21.9            45.4   \n",
       "\n",
       "   dayofweek  day  month  year  workday  \n",
       "0          6   23      4  2023        0  \n",
       "1          1   14      3  2023        1  \n",
       "2          5   14     10  2023        0  \n",
       "3          3    7      7  2022        1  \n",
       "4          4   18      3  2022        1  "
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the first 5 rows of the selected features\n",
    "selected_features_training.show(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A `Feature View` stands between the **Feature Groups** and **Training Dataset**. Сombining **Feature Groups** we can create a **Feature View** which stores a metadata of our data. Having the **Feature View** we can create a **Training Dataset**.\n",
    "\n",
    "In order to create Feature View we can use `fs.get_or_create_feature_view()` method.\n",
    "\n",
    "We can specify parameters:\n",
    "\n",
    "- `name` - Name of the feature view to create.\n",
    "- `version` - Version of the feature view to create.\n",
    "- `query` - Query object with the data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Feature view created successfully, explore it at \n",
      "https://c.app.hopsworks.ai:443/p/550040/fs/545863/fv/dk1_electricity_training_feature_view/version/1\n"
     ]
    }
   ],
   "source": [
    "# Getting or creating a feature view named 'dk1_electricity_training_feature_view'\n",
    "version = 1\n",
    "feature_view_training = fs.get_or_create_feature_view(\n",
    "    name='dk1_electricity_training_feature_view',\n",
    "    version=version,\n",
    "    query=selected_features_training,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#2656a3;\"> 🏋️ Training Dataset Creation</span>\n",
    "\n",
    "In Hopsworks, a training dataset is generated from a query defined by the parent FeatureView, which determines the set of features.\n",
    "\n",
    "**Training Dataset may contain splits such as:** \n",
    "* Training set: This subset of the training data is utilized for model training.\n",
    "* Validation set: Used for evaluating hyperparameters during model training. *(We have not included a validation set for this project)*\n",
    "* Test set: Reserved as a holdout subset of training data for evaluating a trained model's performance.\n",
    "\n",
    "Training dataset is created using `fs.training_data()` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Finished: Reading data from Hopsworks, using ArrowFlight (5.01s) \n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "VersionWarning: Incremented version to `2`.\n"
     ]
    }
   ],
   "source": [
    "# Retrieve training data from the feature view 'feature_view_training', assigning the features to 'X'.\n",
    "X, _ = feature_view_training.training_data(\n",
    "    description = 'Electricity Prices Training Dataset',\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 20530 entries, 0 to 20529\n",
      "Data columns (total 19 columns):\n",
      " #   Column                Non-Null Count  Dtype  \n",
      "---  ------                --------------  -----  \n",
      " 0   timestamp             20530 non-null  int64  \n",
      " 1   datetime              20530 non-null  object \n",
      " 2   date                  20530 non-null  object \n",
      " 3   hour                  20530 non-null  int64  \n",
      " 4   dk1_spotpricedkk_kwh  20530 non-null  float64\n",
      " 5   temperature_2m        20530 non-null  float64\n",
      " 6   relative_humidity_2m  20530 non-null  float64\n",
      " 7   precipitation         20530 non-null  float64\n",
      " 8   rain                  20530 non-null  float64\n",
      " 9   snowfall              20530 non-null  float64\n",
      " 10  weather_code          20530 non-null  float64\n",
      " 11  cloud_cover           20530 non-null  float64\n",
      " 12  wind_speed_10m        20530 non-null  float64\n",
      " 13  wind_gusts_10m        20530 non-null  float64\n",
      " 14  dayofweek             20530 non-null  int64  \n",
      " 15  day                   20530 non-null  int64  \n",
      " 16  month                 20530 non-null  int64  \n",
      " 17  year                  20530 non-null  int64  \n",
      " 18  workday               20530 non-null  int64  \n",
      "dtypes: float64(10), int64(7), object(2)\n",
      "memory usage: 3.0+ MB\n"
     ]
    }
   ],
   "source": [
    "# Show the information for the training data\n",
    "X.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#2656a3;\"> ⛳️ Dataset with train and test splits</span>\n",
    "\n",
    "Here we define our train and test splits for traning the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing function for splitting the data into training and testing sets\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop the columns 'date', 'datetime', and 'timestamp' from the DataFrame 'X' which contain the features\n",
    "X = X.drop(columns=['date', 'datetime', 'timestamp'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Remove the dependent variable 'dk1_spotpricedkk_kwh' from the DataFrame 'X' and assign it to the variable 'y'\n",
    "y = X.pop('dk1_spotpricedkk_kwh')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Split the features and the dependent variable into training and testing sets using the train_test_split function\n",
    "# This splits the data randomly into 80% training and 20% testing sets. We set the random_state to 42 to ensure reproducibility.\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, \n",
    "    y, \n",
    "    test_size=0.2, \n",
    "    random_state=42,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>hour</th>\n",
       "      <th>temperature_2m</th>\n",
       "      <th>relative_humidity_2m</th>\n",
       "      <th>precipitation</th>\n",
       "      <th>rain</th>\n",
       "      <th>snowfall</th>\n",
       "      <th>weather_code</th>\n",
       "      <th>cloud_cover</th>\n",
       "      <th>wind_speed_10m</th>\n",
       "      <th>wind_gusts_10m</th>\n",
       "      <th>dayofweek</th>\n",
       "      <th>day</th>\n",
       "      <th>month</th>\n",
       "      <th>year</th>\n",
       "      <th>workday</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>16085</th>\n",
       "      <td>20</td>\n",
       "      <td>2.6</td>\n",
       "      <td>90.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>9.0</td>\n",
       "      <td>16.9</td>\n",
       "      <td>4</td>\n",
       "      <td>18</td>\n",
       "      <td>3</td>\n",
       "      <td>2022</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6561</th>\n",
       "      <td>21</td>\n",
       "      <td>16.1</td>\n",
       "      <td>93.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>11.4</td>\n",
       "      <td>20.2</td>\n",
       "      <td>0</td>\n",
       "      <td>21</td>\n",
       "      <td>8</td>\n",
       "      <td>2023</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11568</th>\n",
       "      <td>2</td>\n",
       "      <td>12.7</td>\n",
       "      <td>80.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>19.7</td>\n",
       "      <td>40.0</td>\n",
       "      <td>2</td>\n",
       "      <td>27</td>\n",
       "      <td>7</td>\n",
       "      <td>2022</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7530</th>\n",
       "      <td>4</td>\n",
       "      <td>12.8</td>\n",
       "      <td>96.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>39.0</td>\n",
       "      <td>6.9</td>\n",
       "      <td>13.3</td>\n",
       "      <td>1</td>\n",
       "      <td>26</td>\n",
       "      <td>9</td>\n",
       "      <td>2023</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18489</th>\n",
       "      <td>4</td>\n",
       "      <td>6.5</td>\n",
       "      <td>93.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>100.0</td>\n",
       "      <td>23.2</td>\n",
       "      <td>44.3</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>2022</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       hour  temperature_2m  relative_humidity_2m  precipitation  rain  \\\n",
       "16085    20             2.6                  90.0            0.0   0.0   \n",
       "6561     21            16.1                  93.0            0.0   0.0   \n",
       "11568     2            12.7                  80.0            0.0   0.0   \n",
       "7530      4            12.8                  96.0            0.0   0.0   \n",
       "18489     4             6.5                  93.0            0.0   0.0   \n",
       "\n",
       "       snowfall  weather_code  cloud_cover  wind_speed_10m  wind_gusts_10m  \\\n",
       "16085       0.0           0.0          0.0             9.0            16.9   \n",
       "6561        0.0           0.0          1.0            11.4            20.2   \n",
       "11568       0.0           0.0         10.0            19.7            40.0   \n",
       "7530        0.0           1.0         39.0             6.9            13.3   \n",
       "18489       0.0           3.0        100.0            23.2            44.3   \n",
       "\n",
       "       dayofweek  day  month  year  workday  \n",
       "16085          4   18      3  2022        1  \n",
       "6561           0   21      8  2023        1  \n",
       "11568          2   27      7  2022        1  \n",
       "7530           1   26      9  2023        1  \n",
       "18489          4    4      2  2022        1  "
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the first 5 rows of the features in the training data\n",
    "X_train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "16085    1.86011\n",
       "6561     1.23962\n",
       "11568    1.02308\n",
       "7530     0.77978\n",
       "18489    0.85414\n",
       "Name: dk1_spotpricedkk_kwh, dtype: float64"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Display the first 5 rows of the dependent variable in the training data\n",
    "y_train.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#2656a3;\">🧬 Modeling</span>\n",
    "\n",
    "For Modeling we initialize the `XGBoost Regressor`.\n",
    "\n",
    "The XGBoost Regressor is a powerful and versatile algorithm known for its effectiveness in a wide range of regression tasks, including predictive modeling and time series forecasting. Specifically tailored for regression tasks, it aims to predict continuous numerical values. The algorithm constructs an ensemble of regression trees, optimizing them to minimize a specified loss function, commonly the mean squared error for regression tasks. Ultimately, the final prediction is derived by aggregating the predictions of individual trees."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the XGBoost Regressor\n",
    "import xgboost as xgb\n",
    "\n",
    "# Initialize the XGBoost Regressor\n",
    "model = xgb.XGBRegressor()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "DeprecationWarning: np.find_common_type is deprecated.  Please use `np.result_type` or `np.promote_types`.\n",
      "See https://numpy.org/devdocs/release/1.25.0-notes.html and the docs for more information.  (Deprecated NumPy 1.25)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</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",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "             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\">&nbsp;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",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "             num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "XGBRegressor(base_score=None, booster=None, callbacks=None,\n",
       "             colsample_bylevel=None, colsample_bynode=None,\n",
       "             colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
       "             enable_categorical=False, eval_metric=None, feature_types=None,\n",
       "             gamma=None, grow_policy=None, importance_type=None,\n",
       "             interaction_constraints=None, learning_rate=None, max_bin=None,\n",
       "             max_cat_threshold=None, max_cat_to_onehot=None,\n",
       "             max_delta_step=None, max_depth=None, max_leaves=None,\n",
       "             min_child_weight=None, missing=nan, monotone_constraints=None,\n",
       "             multi_strategy=None, n_estimators=None, n_jobs=None,\n",
       "             num_parallel_tree=None, random_state=None, ...)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Train the model on the training data\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style='color:#ff5f27'> ⚖️ Model Validation\n",
    "\n",
    "After fitting the XGBoost Regressor, we evaluate the performance using the following validation metrics.\n",
    "\n",
    "**Mean Squared Error (MSE):**\n",
    "- Measures the average squared difference between the actual and predicted values in a regression problem. \n",
    "- It squares the differences between predicted and actual values to penalize larger errors more heavily.\n",
    "- Lower MSE values indicate better model performance.\n",
    "\n",
    "**R-squared (R²):**\n",
    "- Measures the proportion of the variance in the dependent variable (target) that is predictable from the independent variables (features) in a regression model.\n",
    "- R-squared values range from 0 to 1, where 0 indicates that the model does not explain any variability in the target variable, and 1 indicates that the model explains all the variability.\n",
    "- R-squared is a useful metric for assessing how well the regression model fits the observed data. However, it does not provide information about the goodness of fit on new, unseen data.\n",
    "\n",
    "**Mean Absolute Error (MAE):**\n",
    "- Measures the average absolute difference between the actual and predicted values.\n",
    "- MAE is less sensitive to outliers compared to MSE because it does not square the errors.\n",
    "- Like MSE and RMSE, lower MAE values indicate better model performance.\n",
    "\n",
    "MSE focus on the magnitude of errors, while R-squared provides insight into the proportion of variance explained by the model. MAE provides a measure of average error without considering the direction of errors."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the model validation metric functions from the sklearn library\n",
    "from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "⛳️ MSE: 0.058650463336654024\n",
      "⛳️ R^2: 0.932941138051651\n",
      "⛳️ MAE: 0.1659344568393483\n"
     ]
    }
   ],
   "source": [
    "# Predict target values on the test set\n",
    "y_pred = model.predict(X_test)\n",
    "\n",
    "# Calculate Mean Squared Error (MSE) using sklearn\n",
    "mse = mean_squared_error(y_test, y_pred)\n",
    "print(\"⛳️ MSE:\", mse)\n",
    "\n",
    "# Calculate R squared using sklearn\n",
    "r2 = r2_score(y_test, y_pred)\n",
    "print(\"⛳️ R^2:\", r2)\n",
    "\n",
    "# Calculate Mean Absolute Error (MAE) using sklearn\n",
    "mae = mean_absolute_error(y_test, y_pred)\n",
    "print(\"⛳️ MAE:\", mae)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this case, the `MSE` is 0.0546, which suggests that on average, the squared difference between the actual and predicted values is relatively low. An `R^2` value of 0.933 indicates that approximately 93.33% of the variance in the dependent variable is predictable from the feature variables in the model. This is a high value, suggesting that the model explains a significant portion of the variability in the data. A `MAE` of 0.1604 suggests that, on average, the model's predictions are off by approximately 0.1604 units from the actual values. Similar to MSE, a lower MAE indicates better accuracy of the model.\n",
    "\n",
    "In summary, based on these metrics, the model seems to perform quite well. It has relatively low error (both in terms of MSE and MAE), and a high percentage of the variance in the dependent variable is explained by the feature variables, as indicated by the high R-squared value."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Importing the matplotlib library for plotting the predictions against the expected values\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Plot the predictions against the expected values\n",
    "plt.title('Expected vs Predicted Electricity Prices for area DK1')\n",
    "\n",
    "# Plot the predicted values\n",
    "plt.bar(x=np.arange(len(y_pred)), height=y_pred, label='predicted', alpha=0.7)\n",
    "\n",
    "# Plot the expected values\n",
    "plt.bar(x=np.arange(len(y_pred)), height=y_test, label='expected', alpha=0.7)\n",
    "\n",
    "# Add labels to the x-axis and y-axis\n",
    "plt.xlabel('Time')\n",
    "plt.ylabel('Price in DKK')\n",
    "\n",
    "# Add a legend and display the plot\n",
    "plt.legend()\n",
    "plt.show() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Import the plot_importance function from XGBoost\n",
    "from xgboost import plot_importance\n",
    "\n",
    "# Plot feature importances using the plot_importance function from XGBoost\n",
    "plot_importance(\n",
    "    model, \n",
    "    max_num_features=25,  # Display the top 25 most important features\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As shown in the above feature importance plot features like `temperature`, `day`, `hour` and `month` are most important for predicting the dependent variable. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style='color:#2656a3'>🗄 Model Registry</span>\n",
    "\n",
    "The Model Registry in Hopsworks enable us to store the trained model. The model registry centralizes model management, enabling models to be securely accessed and governed. We can also save model metrics with the model, enabling the user to understand performance of the model on test (or unseen) data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Importing the libraries for saving the model\n",
    "from hsml.schema import Schema\n",
    "from hsml.model_schema import ModelSchema\n",
    "import joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Connected. Call `.close()` to terminate connection gracefully.\n"
     ]
    }
   ],
   "source": [
    "# Retrieving the Model Registry from Hopsworks\n",
    "mr = project.get_model_registry()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### <span style=\"color:#ff5f27;\">⚙️ Model Schema</span>\n",
    "A model schema defines the structure and format of the input and output data that a machine learning model expects and produces, respectively. It serves as a **blueprint** for understanding how to interact with the model in terms of input features and output predictions. In the context of the Hopsworks platform, a model schema is typically defined using the Schema class, which specifies the features expected in the input data and the target variable in the output data. This schema helps ensure consistency and compatibility between the model and the data it operates on."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Imoprt the os library to interact with the operating system\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Specify the schema of the model's input and output using the features (X_train) and dependent variable (y_train)\n",
    "input_schema = Schema(X_train)\n",
    "output_schema = Schema(y_train)\n",
    "\n",
    "# Create a model schema using the input and output schemas\n",
    "model_schema = ModelSchema(input_schema, output_schema)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the directory path (folder path) where the trained model will be exported\n",
    "model_dir = \"model\"\n",
    "\n",
    "# Check if the directory already exists, if not create it\n",
    "if not os.path.isdir(model_dir):\n",
    "    os.mkdir(model_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['model/dk_electricity_model.pkl']"
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Save the XGBoost Regressor model as joblib file in the model directory\n",
    "joblib.dump(model, model_dir + \"/dk_electricity_model.pkl\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create an entry in the model registry with the specified details \n",
    "xgb_model = mr.python.create_model(\n",
    "    name=\"electricity_price_prediction_model\", # Name of the model\n",
    "    metrics={ # Evaluation metrics for the model\n",
    "        \"MSE\": mse,\n",
    "        \"R squared\": r2,\n",
    "        \"MAE\": mae,\n",
    "    },\n",
    "    model_schema=model_schema, # Schema defining the input and output data structure of the model\n",
    "    input_example=X_train.sample(), # Example input data for the model\n",
    "    description=\"DK1 Electricity Price Predictor\" # Description of the model\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Uploading: 100.000%|██████████| 455148/455148 elapsed<00:02 remaining<00:00  3.33it/s]\n",
      "Uploading input_example and model_schema:  33%|███▎      | 2/6 [00:02<00:05,  1.47s/it]DeprecationWarning: np.find_common_type is deprecated.  Please use `np.result_type` or `np.promote_types`.\n",
      "See https://numpy.org/devdocs/release/1.25.0-notes.html and the docs for more information.  (Deprecated NumPy 1.25)\n",
      "Uploading: 100.000%|██████████| 82/82 elapsed<00:01 remaining<00:00\n",
      "Uploading: 100.000%|██████████| 1271/1271 elapsed<00:01 remaining<00:00\n",
      "Model export complete: 100%|██████████| 6/6 [00:11<00:00,  1.88s/it]                   "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model created, explore it at https://c.app.hopsworks.ai:443/p/550040/models/electricity_price_prediction_model/1\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "Model(name: 'electricity_price_prediction_model', version: 1)"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Upload the model to Hopsworks\n",
    "xgb_model.save(model_dir)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## <span style=\"color:#2656a3;\">⏭️ **Next:** Part 04: Batch Inference </span>\n",
    "\n",
    "Next notebook we will use the registered model to make predictions based on the batch data."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "bds-mlops",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.9"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}