{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "8d8584aa",
   "metadata": {},
   "source": [
    "# Lesson 19: Regression demonstration\n",
    "\n",
    "This notebook demonstrates key concepts and tools for training supervised regression models.\n",
    "\n",
    "1. **What is regression**\n",
    "    - Regression problems\n",
    "    - Model training\n",
    "\n",
    "2. **Regression metrics**\n",
    "    - Residuals: RSS, MSE, RMSE and MAE\n",
    "    - R-squared\n",
    "\n",
    "3. **Evaluating regression model performance**\n",
    "    - Train-test split\n",
    "    - Overfitting\n",
    "\n",
    "4. **Dealing with overfitting**\n",
    "    - Ridge (L2) penalty\n",
    "    - Lasso (L1) penalty\n",
    "\n",
    "5. **Optimizing regression models**\n",
    "    - Hyperparameter tuning\n",
    "    - Grid search/Randomized search\n",
    "\n",
    "6. **Scikit-learn pipelines example**"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49f87fdc",
   "metadata": {},
   "source": [
    "## Notebook set up\n",
    "### Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "d839e96b",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3b87cd6",
   "metadata": {},
   "source": [
    "## 1. What is regression?\n",
    "\n",
    "A regression model predicts the value of a continuous output variable (label) from one or more input variables (features).\n",
    "\n",
    "### 1.1. Regression problem: circumference of a circle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "9742c621",
   "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>diameter</th>\n",
       "      <th>circumference</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3.0</td>\n",
       "      <td>9.056466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3.2</td>\n",
       "      <td>10.247696</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.6</td>\n",
       "      <td>11.015775</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4.8</td>\n",
       "      <td>14.788864</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6.1</td>\n",
       "      <td>19.385014</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>7.2</td>\n",
       "      <td>22.025133</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>8.7</td>\n",
       "      <td>27.192756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>10.0</td>\n",
       "      <td>31.244334</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>11.3</td>\n",
       "      <td>35.256537</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>11.9</td>\n",
       "      <td>37.321937</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   diameter  circumference\n",
       "0       3.0       9.056466\n",
       "1       3.2      10.247696\n",
       "2       3.6      11.015775\n",
       "3       4.8      14.788864\n",
       "4       6.1      19.385014\n",
       "5       7.2      22.025133\n",
       "6       8.7      27.192756\n",
       "7      10.0      31.244334\n",
       "8      11.3      35.256537\n",
       "9      11.9      37.321937"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('diameter_circumference.csv')\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "28751100",
   "metadata": {},
   "outputs": [],
   "source": [
    "def regression_model(diameters):\n",
    "    circumferences = np.pi * diameters\n",
    "    return circumferences\n",
    "\n",
    "circumference_predictions = regression_model(df['diameter'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "d2a70546",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title('Regression model predictions')\n",
    "plt.scatter(df['diameter'], df['circumference'], color='black', label='Data')\n",
    "plt.plot(df['diameter'], circumference_predictions, color='teal', label='Model predictions')\n",
    "plt.xlabel('Diameter (inches)')\n",
    "plt.ylabel('Circumference (inches)')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0c959280",
   "metadata": {},
   "source": [
    "### 1.2. Model training"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "b405eb0d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression\n",
    "\n",
    "# Create an instance of sklearn's LinearRegression() class\n",
    "model = LinearRegression()\n",
    "\n",
    "# Train the model\n",
    "result = model.fit(df['diameter'].to_frame(), df['circumference'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "2b655e91",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Slope: 3.141\n"
     ]
    }
   ],
   "source": [
    "# Get predicted circumferences from diameters using the fitted model\n",
    "predicted_circumference = model.predict(df['diameter'].to_frame())\n",
    "print(f'Slope: {model.coef_[0]:.3f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dda636d3",
   "metadata": {},
   "source": [
    "## 2. Regression metrics\n",
    "\n",
    "### 2.1. Residuals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "6ee95d61",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "residuals = df['circumference'] - predicted_circumference\n",
    "\n",
    "plt.title('Regression model predictions')\n",
    "plt.scatter(df['diameter'][:3], df['circumference'][:3], color='black', label='Data')\n",
    "plt.plot(df['diameter'][:3], predicted_circumference[:3], color='teal', label='Model predictions')\n",
    "\n",
    "# Add vertical dotted lines for residuals\n",
    "for i in range(3):\n",
    "    plt.plot(\n",
    "        [df['diameter'].iloc[i], df['diameter'].iloc[i]], \n",
    "        [predicted_circumference[i], df['circumference'].iloc[i]], \n",
    "        linestyle=':', color='purple', label='Fit residuals' if i == 0 else None\n",
    "    )\n",
    "\n",
    "plt.xlim(2.8, 3.8)\n",
    "plt.ylim(8.5, 11.5)\n",
    "plt.xlabel('Diameter (inches)')\n",
    "plt.ylabel('Circumference (inches)')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "687208ad",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RSS:  0.5529 inches²\n",
      "MSE:  0.0553 inches²\n",
      "RMSE: 0.2351 inches\n",
      "MAE:  0.1842 inches\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import (\n",
    "    mean_squared_error,\n",
    "    root_mean_squared_error,\n",
    "    mean_absolute_error\n",
    ")\n",
    "\n",
    "# Calculate metrics using sklearn\n",
    "MSE = mean_squared_error(df['circumference'], predicted_circumference)\n",
    "RMSE = root_mean_squared_error(df['circumference'], predicted_circumference)\n",
    "MAE = mean_absolute_error(df['circumference'], predicted_circumference)\n",
    "\n",
    "# RSS is not directly available in sklearn, but can be calculated from MSE\n",
    "n = len(df)\n",
    "RSS = MSE * n\n",
    "\n",
    "print(f'RSS:  {RSS:.4f} inches²')\n",
    "print(f'MSE:  {MSE:.4f} inches²')\n",
    "print(f'RMSE: {RMSE:.4f} inches')\n",
    "print(f'MAE:  {MAE:.4f} inches')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bb3d882f",
   "metadata": {},
   "source": [
    "### 2.2. R-squared"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "5d3be23f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x800 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "circumference_variance = np.var(df['circumference'])\n",
    "residual_variance = np.var(residuals)\n",
    "\n",
    "fig, axs = plt.subplots(2,2, figsize=(8,8))\n",
    "axs = axs.flatten()\n",
    "\n",
    "axs[0].set_title('Linear regression')\n",
    "axs[0].scatter(df['diameter'], df['circumference'], color='black', label='Data')\n",
    "axs[0].plot(df['diameter'], circumference_predictions, color='teal', label='Model predictions')\n",
    "axs[0].set_ylim(5, 45)\n",
    "axs[0].set_xlabel('Diameter')\n",
    "axs[0].set_ylabel('Circumference')\n",
    "axs[0].legend(loc='upper left')\n",
    "\n",
    "axs[1].set_title('Fit residuals')\n",
    "axs[1].scatter(df['diameter'], residuals, color='black')\n",
    "axs[1].set_ylim(-20, 20)\n",
    "axs[1].set_xlabel('Diameter')\n",
    "axs[1].set_ylabel('True - predicted circumference')\n",
    "\n",
    "bins = np.linspace(5, 45, 10)\n",
    "axs[2].set_title(f'Original circumference distribution\\nvariance={circumference_variance:.3f}')\n",
    "axs[2].hist(df['circumference'], color='grey', edgecolor='black', bins = bins, orientation='horizontal')\n",
    "axs[2].set_xlabel('Count')\n",
    "axs[2].set_ylabel('Circumference')\n",
    "\n",
    "bins = np.linspace(-20, 20, 10)\n",
    "axs[2].set_title(f'Original circumference distribution\\nvariance={residual_variance:.3f}')\n",
    "axs[3].set_title('Fit residual distribution')\n",
    "axs[3].hist(residuals, color='grey', edgecolor='black', bins=bins, orientation='horizontal')\n",
    "axs[3].set_xlabel('Count')\n",
    "axs[3].set_ylabel('True - predicted circumference')\n",
    "\n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "370dc7b0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fraction of variance explained: 0.999\n"
     ]
    }
   ],
   "source": [
    "variance_explained = 1 - (residual_variance / circumference_variance)\n",
    "print(f'Fraction of variance explained: {variance_explained:.3f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "74e1e17f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Scikit-learn R-squared: 0.999\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import r2_score\n",
    "\n",
    "sk_r2 = r2_score(df['circumference'], predicted_circumference)\n",
    "print(f'Scikit-learn R-squared: {sk_r2:.3f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a84d95e5",
   "metadata": {},
   "source": [
    "## 3. Evaluating regression model performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "a0446b1d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 5000 entries, 0 to 4999\n",
      "Columns: 465 entries, area to distance_to_water\n",
      "dtypes: float64(465)\n",
      "memory usage: 17.7 MB\n"
     ]
    }
   ],
   "source": [
    "url = 'https://gperdrizet.github.io/FSA_devops/assets/data/unit3/distance_to_water_preprocessed.csv'\n",
    "df = pd.read_csv(url)\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "579f25fa",
   "metadata": {},
   "source": [
    "### 3.1. Train-test split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 103,
   "id": "0cbb74b5",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Original dataframe shape: (5000, 465)\n",
      "Training dataframe shape: (3750, 465)\n",
      "Testing dataframe shape: (1250, 465)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "train_df, test_df = train_test_split(df)\n",
    "\n",
    "print(f'Original dataframe shape: {df.shape}')\n",
    "print(f'Training dataframe shape: {train_df.shape}')\n",
    "print(f'Testing dataframe shape: {test_df.shape}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 104,
   "id": "e3f0f025",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Training RMSE: 94.8\n"
     ]
    }
   ],
   "source": [
    "# Fit linear model on training data\n",
    "model = LinearRegression()\n",
    "\n",
    "fit_result = model.fit(\n",
    "    train_df.drop(columns='distance_to_water'),\n",
    "    train_df['distance_to_water']\n",
    ")\n",
    "\n",
    "train_predictions = model.predict(\n",
    "    train_df.drop(columns='distance_to_water')\n",
    ")\n",
    "\n",
    "train_rmse = root_mean_squared_error(train_df['distance_to_water'], train_predictions)\n",
    "print(f'Training RMSE: {train_rmse:.1f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "a2315af2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing RMSE: 105.8\n"
     ]
    }
   ],
   "source": [
    "# Used pre-fitted linear model to make predictions for test set features\n",
    "test_predictions = model.predict(\n",
    "    test_df.drop(columns='distance_to_water')\n",
    ")\n",
    "\n",
    "test_rmse = root_mean_squared_error(test_df['distance_to_water'], test_predictions)\n",
    "print(f'Testing RMSE: {test_rmse:.1f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ead84f10",
   "metadata": {},
   "source": [
    "### 3.2. Cross-validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "59dbb06f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Mean cross-validation RMSE: 105.2 ± 3.7\n",
      "95% CI: ± 101.5 to 108.9\n",
      "Test RMSE: 105.8\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import cross_val_score\n",
    "\n",
    "# Make a linear regression instance\n",
    "model = LinearRegression()\n",
    "\n",
    "# Run cross-validation scoring\n",
    "cv_scores = cross_val_score(\n",
    "    model,\n",
    "    df.drop(columns='distance_to_water'),\n",
    "    df['distance_to_water'],\n",
    "    scoring='neg_root_mean_squared_error',\n",
    "    n_jobs=-1,\n",
    "    cv=5\n",
    ")\n",
    "\n",
    "# Need to flip the sign - cross-validation used negative RMSE \n",
    "cv_scores = -cv_scores\n",
    "\n",
    "# Get mean and standard deviation, construct 95% CI\n",
    "rmse_mean = np.mean(cv_scores)\n",
    "rmse_std = np.std(cv_scores)\n",
    "moe_95 = 1.96 * rmse_std / np.sqrt(len(cv_scores))\n",
    "\n",
    "print(f'Mean cross-validation RMSE: {rmse_mean:.1f} ± {moe_95:.1f}')\n",
    "print(f'95% CI: ± {rmse_mean - moe_95:.1f} to {rmse_mean + moe_95:.1f}')\n",
    "print(f'Test RMSE: {test_rmse:.1f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "03dd9fd2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title('Cross-validation performance')\n",
    "plt.boxplot(cv_scores)\n",
    "plt.axhline(rmse_mean - moe_95, linestyle='--', color='teal', label='95% CI')\n",
    "plt.axhline(rmse_mean + moe_95, linestyle='--', color='teal')\n",
    "plt.axhline(test_rmse, color='purple', label='True test set R-squared')\n",
    "plt.axhline(train_rmse, color='red', label='Training R-squared')\n",
    "plt.ylabel('RMSE')\n",
    "plt.xlabel('')\n",
    "plt.legend(loc='center left')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "id": "2e9b6301",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, axs = plt.subplots(1,2, figsize=(8,4))\n",
    "axs = axs.flatten()\n",
    "\n",
    "axs[0].set_title('True vs predicted values')\n",
    "axs[0].scatter(\n",
    "    train_df['distance_to_water'], train_predictions,\n",
    "    s=1, alpha=0.25, color='black', label='Data'\n",
    ")\n",
    "axs[0].plot(\n",
    "    list(range(-100, 700, 10)), list(range(-100, 700, 10)), \n",
    "    color='red', label='perfect predictions'\n",
    ")\n",
    "axs[0].set_xlabel('True value')\n",
    "axs[0].set_ylabel('Predicted value')\n",
    "axs[0].set_aspect('equal', adjustable='box')\n",
    "axs[0].set_ylim(-100, 700)\n",
    "axs[0].set_xlim(-100, 700)\n",
    "leg = axs[0].legend(loc='upper left', markerscale=5)\n",
    "leg.legend_handles[0].set_alpha(1)\n",
    "\n",
    "axs[1].set_title('Fit residuals')\n",
    "axs[1].scatter(\n",
    "    train_predictions, train_predictions - train_df['distance_to_water'], \n",
    "    s=1, alpha=0.25, color='black'\n",
    ")\n",
    "axs[1].axhline(0, color='red', label='perfect predictions' )\n",
    "axs[1].set_xlabel('Predicted value')\n",
    "axs[1].set_ylabel('True - predicted value')\n",
    "\n",
    "fig.tight_layout()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3f48e00a",
   "metadata": {},
   "source": [
    "### 3.3. Over fitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "7365b365",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x_training=np.array([1,2,3,4,5]) + np.random.normal(-0.5,0.5,5)\n",
    "y_training=np.array([1,2,3,4,5]) + np.random.normal(-0.5,0.5,5)\n",
    "\n",
    "x_test=np.array([2.5,3.5]) + np.random.normal(-0.5,0.5,2)\n",
    "y_test=np.array([2.5,3.5]) + np.random.normal(-0.5,0.5,2)\n",
    "\n",
    "poly_fit=np.polyfit(x_training,y_training,4)\n",
    "poly_model=np.poly1d(poly_fit)\n",
    "\n",
    "x_range=np.linspace(0,8)\n",
    "y_poly=poly_model(x_range)\n",
    "\n",
    "linear_model=LinearRegression()\n",
    "linear_model.fit(x_training.reshape(-1, 1), y_training)\n",
    "y_linear=linear_model.predict(x_range.reshape(-1, 1))\n",
    "\n",
    "plt.scatter(x_training,y_training, color='black', label='Training data')\n",
    "plt.scatter(x_test,y_test, color='red', label='Testing data')\n",
    "plt.plot(x_range, y_poly, linestyle='dashed', color='grey', label='Polynomial fit')\n",
    "plt.plot(x_range, y_linear, color='black', label='Linear fit')\n",
    "plt.xlim(0.5,6.5)\n",
    "plt.ylim(-5,8)\n",
    "plt.xlabel('x')\n",
    "plt.ylabel('y')\n",
    "plt.legend(loc='best')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "836488e7",
   "metadata": {},
   "source": [
    "## 4. Dealing with overfitting\n",
    "\n",
    "Regularization adds penalty terms to prevent overfitting by shrinking coefficients."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8754a2e6",
   "metadata": {},
   "source": [
    "### 4.2. Ridge regression (L2)\n",
    "\n",
    "Penalizes model with an extra term: 'alpha' times the coefficients' sum-of-squares.\n",
    "- Large coefficient -> large penalty\n",
    "- Makes coefficients tend to be small but not zero\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 118,
   "id": "adde6f1f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import Ridge\n",
    "\n",
    "# Train Ridge regression with different alpha values\n",
    "alphas = [0.01, 0.1, 1.0, 10.0, 100.0]\n",
    "training_scores = []\n",
    "testing_scores = []\n",
    "\n",
    "for alpha in alphas:\n",
    "\n",
    "    ridge_model = Ridge(alpha=alpha)\n",
    "\n",
    "    ridge_model.fit(\n",
    "        train_df.drop(columns='distance_to_water'),\n",
    "        train_df['distance_to_water']\n",
    "    )\n",
    "\n",
    "    ridge_training_predictions = ridge_model.predict(\n",
    "        train_df.drop(columns='distance_to_water')\n",
    "    )\n",
    "\n",
    "    ridge_testing_predictions = ridge_model.predict(\n",
    "        test_df.drop(columns='distance_to_water')\n",
    "    )\n",
    "\n",
    "    training_scores.append(\n",
    "        root_mean_squared_error(train_df['distance_to_water'], ridge_training_predictions)\n",
    "    )\n",
    "\n",
    "    testing_scores.append(\n",
    "        root_mean_squared_error(test_df['distance_to_water'], ridge_testing_predictions)\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "id": "8115e39f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title('Ridge performance')\n",
    "plt.plot(alphas, training_scores, color='purple', label='Ridge training')\n",
    "plt.plot(alphas, testing_scores, color='teal', label='Ridge testing')\n",
    "plt.axhline(train_rmse, color='purple', linestyle='--', label='Linear training')\n",
    "plt.axhline(test_rmse, color='teal', linestyle='--', label='Linear testing')\n",
    "plt.xlabel('Alpha value')\n",
    "plt.ylabel('RMSE')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27f4db7b",
   "metadata": {},
   "source": [
    "### 4.2. Lasso regression (L1)\n",
    "\n",
    "Penalizes model with an extra term: 'alpha' times the sum of the absolute value of the coefficients.\n",
    "- Larger coefficients -> larger penalty\n",
    "- Will drive coefficients to zero (feature selection)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "89c10514",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import Lasso\n",
    "\n",
    "# Train Lasso regression with different alpha values\n",
    "alphas = [0.025, 0.05, 0.1]\n",
    "\n",
    "training_scores = []\n",
    "testing_scores = []\n",
    "\n",
    "for alpha in alphas:\n",
    "\n",
    "    lasso_model = Lasso(alpha=alpha, max_iter=20000)\n",
    "\n",
    "    lasso_model.fit(\n",
    "        train_df.drop(columns='distance_to_water'),\n",
    "        train_df['distance_to_water']\n",
    "    )\n",
    "\n",
    "    lasso_training_predictions = lasso_model.predict(\n",
    "        train_df.drop(columns='distance_to_water')\n",
    "    )\n",
    "\n",
    "    lasso_testing_predictions = lasso_model.predict(\n",
    "        test_df.drop(columns='distance_to_water')\n",
    "    )\n",
    "\n",
    "    training_scores.append(\n",
    "        root_mean_squared_error(train_df['distance_to_water'], lasso_training_predictions)\n",
    "    )\n",
    "\n",
    "    testing_scores.append(\n",
    "        root_mean_squared_error(test_df['distance_to_water'], lasso_testing_predictions)\n",
    "    )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 129,
   "id": "54a68b6c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.title('Lasso performance')\n",
    "plt.plot(alphas, training_scores, color='purple', label='Lasso training')\n",
    "plt.plot(alphas, testing_scores, color='teal', label='Lasso testing')\n",
    "plt.axhline(train_rmse, color='purple', linestyle='--', label='Linear training')\n",
    "plt.axhline(test_rmse, color='teal', linestyle='--', label='Linear testing')\n",
    "plt.xlabel('Alpha value')\n",
    "plt.ylabel('RMSE')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "945bfb5a",
   "metadata": {},
   "source": [
    "## 5. Optimizing regression models\n",
    "\n",
    "Alpha is the first good example of a 'hyperparameter' we have encountered and there are many, many others. In general a hyperparameter is a value you can tune or a setting choice you can make that effects how the model learns from the data. The best values need to be determined empirically for the specific model and dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "bf1b3427",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Best alpha: 0.061\n",
      "Best CV RMSE: 104.0\n"
     ]
    }
   ],
   "source": [
    "from scipy.stats import uniform\n",
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "\n",
    "# Define parameter grid for Ridge regression\n",
    "param_grid = {'alpha': uniform(loc=0.03, scale=0.04)}\n",
    "\n",
    "# Create GridSearchCV object\n",
    "grid_search = RandomizedSearchCV(\n",
    "    Lasso(max_iter=20000),\n",
    "    param_grid,\n",
    "    n_iter=10,\n",
    "    cv=3,\n",
    "    scoring='neg_root_mean_squared_error',\n",
    "    n_jobs=16\n",
    ")\n",
    "\n",
    "# Fit on training data\n",
    "grid_search.fit(\n",
    "    train_df.drop(columns='distance_to_water'),\n",
    "    train_df['distance_to_water']\n",
    ")\n",
    "\n",
    "print(f'Best alpha: {grid_search.best_params_[\"alpha\"]:.3f}')\n",
    "print(f'Best CV RMSE: {-grid_search.best_score_:.1f}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "f6569f6d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train RMSE (linear):  94.8\n",
      "Test RMSE (linear):   105.8\n",
      "\n",
      "Train RMSE (lasso):   97.3\n",
      "Test RMSE (lasso):    97.2\n"
     ]
    }
   ],
   "source": [
    "# Evaluate best model on test set\n",
    "lasso = Lasso(alpha=grid_search.best_params_[\"alpha\"], max_iter=20000)\n",
    "\n",
    "result = lasso.fit(\n",
    "    train_df.drop(columns='distance_to_water'),\n",
    "    train_df['distance_to_water']\n",
    ")\n",
    "\n",
    "train_predictions_lasso = lasso.predict(train_df.drop(columns='distance_to_water'))\n",
    "train_rmse_lasso = root_mean_squared_error(train_df['distance_to_water'], train_predictions_lasso)\n",
    "test_predictions_lasso = lasso.predict(test_df.drop(columns='distance_to_water'))\n",
    "test_rmse_lasso = root_mean_squared_error(test_df['distance_to_water'], test_predictions_lasso)\n",
    "\n",
    "print(f'Train RMSE (linear):  {train_rmse:.1f}')\n",
    "print(f'Test RMSE (linear):   {test_rmse:.1f}')\n",
    "print()\n",
    "print(f'Train RMSE (lasso):   {train_rmse_lasso:.1f}')\n",
    "print(f'Test RMSE (lasso):    {test_rmse_lasso:.1f}')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e526070b",
   "metadata": {},
   "source": [
    "## 6. Scikit-learn pipelines\n",
    "\n",
    "Pipelines combine preprocessing and modeling steps to prevent data leakage and simplify workflow."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 132,
   "id": "e9c03118",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load raw data again for pipeline demo\n",
    "url = 'https://gperdrizet.github.io/FSA_devops/assets/data/unit3/distance_to_water.csv'\n",
    "raw_df = pd.read_csv(url)\n",
    "\n",
    "# Split before any preprocessing\n",
    "train_df, test_df = train_test_split(raw_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "570d55a0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\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: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: start;\n",
       "  justify-content: space-between;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\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",
       "  display: none;\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",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\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: 0.5em;\n",
       "  text-align: center;\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",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    font-family: monospace;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table td {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td.value pre {\n",
       "    color:rgb(255, 94, 0) !important;\n",
       "    background-color: transparent !important;\n",
       "}\n",
       "\n",
       ".default td {\n",
       "    color: black;\n",
       "    text-align: left;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;Preprocessor&#x27;,\n",
       "                 ColumnTransformer(transformers=[(&#x27;Numerical&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;scaler&#x27;,\n",
       "                                                                   StandardScaler())]),\n",
       "                                                  [&#x27;area&#x27;, &#x27;temperature&#x27;,\n",
       "                                                   &#x27;humidity&#x27;, &#x27;wind_speed&#x27;,\n",
       "                                                   &#x27;rainfall&#x27;]),\n",
       "                                                 (&#x27;Categorical&#x27;,\n",
       "                                                  Pipeline(steps=[(&#x27;encoder&#x27;,\n",
       "                                                                   OneHotEncoder(drop=&#x27;first&#x27;,\n",
       "                                                                                 sparse_output=False))]),\n",
       "                                                  [&#x27;quality&#x27;, &#x27;region&#x27;])])),\n",
       "                (&#x27;Model&#x27;,\n",
       "                 Lasso(alpha=np.float64(0.06058140216592638), max_iter=20000))])</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 sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>Pipeline</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.pipeline.Pipeline.html\">?<span>Documentation for Pipeline</span></a><span class=\"sk-estimator-doc-link \">i<span>Not fitted</span></span></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('steps',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">steps&nbsp;</td>\n",
       "            <td class=\"value\">[(&#x27;Preprocessor&#x27;, ...), (&#x27;Model&#x27;, ...)]</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('transform_input',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">transform_input&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('memory',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">memory&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbose&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>Preprocessor: ColumnTransformer</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for Preprocessor: ColumnTransformer</span></a></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Preprocessor__\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('transformers',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">transformers&nbsp;</td>\n",
       "            <td class=\"value\">[(&#x27;Numerical&#x27;, ...), (&#x27;Categorical&#x27;, ...)]</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('remainder',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">remainder&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;drop&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('sparse_threshold',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">sparse_threshold&nbsp;</td>\n",
       "            <td class=\"value\">0.3</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">n_jobs&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('transformer_weights',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">transformer_weights&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbose&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose_feature_names_out',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">verbose_feature_names_out&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('force_int_remainder_cols',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">force_int_remainder_cols&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>Numerical</div></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Preprocessor__Numerical__\"><pre>[&#x27;area&#x27;, &#x27;temperature&#x27;, &#x27;humidity&#x27;, &#x27;wind_speed&#x27;, &#x27;rainfall&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>StandardScaler</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Preprocessor__Numerical__scaler__\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('copy',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">copy&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('with_mean',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">with_mean&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('with_std',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">with_std&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>Categorical</div></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Preprocessor__Categorical__\"><pre>[&#x27;quality&#x27;, &#x27;region&#x27;]</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>OneHotEncoder</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.preprocessing.OneHotEncoder.html\">?<span>Documentation for OneHotEncoder</span></a></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Preprocessor__Categorical__encoder__\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('categories',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">categories&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;auto&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('drop',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">drop&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;first&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('sparse_output',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">sparse_output&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('dtype',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">dtype&nbsp;</td>\n",
       "            <td class=\"value\">&lt;class &#x27;numpy.float64&#x27;&gt;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('handle_unknown',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">handle_unknown&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;error&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('min_frequency',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">min_frequency&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_categories',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_categories&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('feature_name_combiner',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">feature_name_combiner&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;concat&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label  sk-toggleable__label-arrow\"><div><div>Lasso</div></div><div><a class=\"sk-estimator-doc-link \" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.7/modules/generated/sklearn.linear_model.Lasso.html\">?<span>Documentation for Lasso</span></a></div></label><div class=\"sk-toggleable__content \" data-param-prefix=\"Model__\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('alpha',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">alpha&nbsp;</td>\n",
       "            <td class=\"value\">np.float64(0....8140216592638)</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('fit_intercept',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">fit_intercept&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('precompute',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">precompute&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('copy_X',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">copy_X&nbsp;</td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_iter',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">max_iter&nbsp;</td>\n",
       "            <td class=\"value\">20000</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('tol',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">tol&nbsp;</td>\n",
       "            <td class=\"value\">0.0001</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('warm_start',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">warm_start&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('positive',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">positive&nbsp;</td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">random_state&nbsp;</td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('selection',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">selection&nbsp;</td>\n",
       "            <td class=\"value\">&#x27;cyclic&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div></div></div><script>function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.fa-regular.fa-copy').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const paramName = element.parentElement.nextElementSibling.textContent.trim();\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "</script></body>"
      ],
      "text/plain": [
       "Pipeline(steps=[('Preprocessor',\n",
       "                 ColumnTransformer(transformers=[('Numerical',\n",
       "                                                  Pipeline(steps=[('scaler',\n",
       "                                                                   StandardScaler())]),\n",
       "                                                  ['area', 'temperature',\n",
       "                                                   'humidity', 'wind_speed',\n",
       "                                                   'rainfall']),\n",
       "                                                 ('Categorical',\n",
       "                                                  Pipeline(steps=[('encoder',\n",
       "                                                                   OneHotEncoder(drop='first',\n",
       "                                                                                 sparse_output=False))]),\n",
       "                                                  ['quality', 'region'])])),\n",
       "                ('Model',\n",
       "                 Lasso(alpha=np.float64(0.06058140216592638), max_iter=20000))])"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
    "from sklearn.compose import ColumnTransformer\n",
    "\n",
    "# Define numeric and categorical columns\n",
    "numeric_features = ['area','temperature', 'humidity', 'wind_speed','rainfall']\n",
    "categorical_features = ['quality', 'region']\n",
    "\n",
    "# Create preprocessing steps\n",
    "numeric_transformer = Pipeline(steps=[\n",
    "    ('scaler', StandardScaler())\n",
    "])\n",
    "\n",
    "categorical_transformer = Pipeline(steps=[\n",
    "    ('encoder', OneHotEncoder(drop='first', sparse_output=False))\n",
    "])\n",
    "\n",
    "# Combine preprocessing steps\n",
    "preprocessor = ColumnTransformer(\n",
    "    transformers=[\n",
    "        ('Numerical', numeric_transformer, numeric_features),\n",
    "        ('Categorical', categorical_transformer, categorical_features)\n",
    "    ]\n",
    ")\n",
    "\n",
    "# Create full pipeline with preprocessing and model\n",
    "pipeline = Pipeline(steps=[\n",
    "    ('Preprocessor', preprocessor),\n",
    "    ('Model', Lasso(alpha=grid_search.best_params_[\"alpha\"], max_iter=20000))\n",
    "])\n",
    "\n",
    "pipeline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "48a04eec",
   "metadata": {},
   "source": [
    "### 6.2. Train and evaluate pipeline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "id": "acc2cb5c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pipeline RMSE: 93.7\n"
     ]
    }
   ],
   "source": [
    "# Fit pipeline on training data\n",
    "pipeline.fit(train_df.drop(columns='distance_to_water'), train_df['distance_to_water'])\n",
    "\n",
    "# Make predictions on test set\n",
    "predictions = pipeline.predict(test_df.drop(columns='distance_to_water'))\n",
    "\n",
    "# Evaluate performance\n",
    "pipeline_rmse = root_mean_squared_error(test_df['distance_to_water'], predictions)\n",
    "\n",
    "print(f'Pipeline RMSE: {pipeline_rmse:.1f}')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.12.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}