pycaret-emission-ps3e20.ipynb

{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"source":"<a href=\"https://www.kaggle.com/code/averma111/pycaret-emission-ps3e20?scriptVersionId=139857502\" target=\"_blank\"><img align=\"left\" alt=\"Kaggle\" title=\"Open in Kaggle\" src=\"https://kaggle.com/static/images/open-in-kaggle.svg\"></a>","metadata":{},"cell_type":"markdown"},{"cell_type":"code","source":"%%capture\n!pip install pycaret[full]","metadata":{"execution":{"iopub.status.busy":"2023-08-14T06:55:45.471479Z","iopub.execute_input":"2023-08-14T06:55:45.471971Z","iopub.status.idle":"2023-08-14T06:56:12.397101Z","shell.execute_reply.started":"2023-08-14T06:55:45.471921Z","shell.execute_reply":"2023-08-14T06:56:12.395016Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd\nimport pycaret\nfrom pycaret.regression import *\nfrom pycaret.regression import RegressionExperiment\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","metadata":{"execution":{"iopub.status.busy":"2023-08-14T06:56:12.399347Z","iopub.execute_input":"2023-08-14T06:56:12.399685Z","iopub.status.idle":"2023-08-14T06:56:12.410282Z","shell.execute_reply.started":"2023-08-14T06:56:12.399654Z","shell.execute_reply":"2023-08-14T06:56:12.409336Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stdout","text":"/kaggle/input/playground-series-s3e20/sample_submission.csv\n/kaggle/input/playground-series-s3e20/train.csv\n/kaggle/input/playground-series-s3e20/test.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"class DataAcquisition:\n    \n    def __init__(self):\n        self.X_train=None\n        self.X_val=None\n        self.y_train=None\n        self.y_val=None\n        self.X_test= None\n    \n    def prepare_data(self):\n        path = '/kaggle/input/playground-series-s3e20/train.csv'\n        df = pd.read_csv(\n            path, \n            sep=',', \n            infer_datetime_format=True, \n            low_memory=False\n        )\n        \n        X = df.copy()\n        return X\n    \n    def prepare_data_test(self):\n        path = '/kaggle/input/playground-series-s3e20/test.csv'\n        df = pd.read_csv(\n            path, \n            sep=',', \n            infer_datetime_format=True, \n            low_memory=False\n        )\n        \n        X = df.copy()\n        return X\n    \n    \n    def new_features(self,df):\n        pass\n    \n    \n    def summary(self,text, df):\n        print(f'{text} shape: {df.shape}')\n        summ = pd.DataFrame(df.dtypes, columns=['dtypes'])\n        summ['null'] = df.isnull().sum()\n        summ['unique'] = df.nunique()\n        summ['min'] = df.min()\n        summ['median'] = df.median()\n        summ['max'] = df.max()\n        summ['mean'] = df.mean()\n        summ['std'] = df.std()\n        summ['duplicate'] = df.duplicated().sum()\n        return summ\n    \n    def _get_numerical_features(self,df):\n        numerical_feature = df.select_dtypes(include=['float64'])\n        return numerical_feature\n    \n    \n    def plot_numerical_histogram(self,df):\n        fig, ax = plt.subplots(5, 15, figsize = (5, 15), dpi = 90)\n        ax = ax.flatten()\n\n        for i, column in enumerate(self._get_numerical_features(df)):\n            sns.histplot(df[column], ax=ax[i], color='r')\n    \n            ax[i].set_title(f'{column} Distribution', size = 5)\n            ax[i].set_xlabel(None)\n            ax[i].set_ylabel(None)\n        fig.suptitle('Distribution of Numerical Feature', fontsize = 8)\n        plt.tight_layout()\n        \n        \n    def show_correlation(self,dataset, column_name,cmap):\n        corr = dataset.corr(method = 'kendall')\n        plt.figure(figsize = (10, 10), dpi = 90)\n        mask = np.zeros_like(corr)\n        mask[np.triu_indices_from(mask)] = True\n        sns.heatmap(corr, mask = mask, cmap = cmap, annot = True, annot_kws = {'size' : 12})\n        #plt.title(f'{column_name} Dataset Correlation Matrix\\n', fontsize = 15, weight = 'bold')\n        plt.show()\n    \n    \n    def standardization_data(self,X_data):\n        scaler = MinMaxScaler()\n        std_X_data = scaler.fit_transform(X_data)\n        return std_X_data\n    \n    def preprocessing(self,df):\n        pass\n    \n    def removenan(self,df,column):\n        df[column].fillna(df[column].mean(), inplace=True)\n        \n    def preprocessing_test(self,df):\n        pass\n    \n        \nacq = DataAcquisition()\n\ntrain_df = acq.prepare_data()\ntest_df = acq.prepare_data_test()","metadata":{"execution":{"iopub.status.busy":"2023-08-14T06:56:12.411712Z","iopub.execute_input":"2023-08-14T06:56:12.412569Z","iopub.status.idle":"2023-08-14T06:56:14.338548Z","shell.execute_reply.started":"2023-08-14T06:56:12.41254Z","shell.execute_reply":"2023-08-14T06:56:14.33753Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"# init setup on exp\ns = setup(train_df, target = 'emission', session_id = 42)","metadata":{"execution":{"iopub.status.busy":"2023-08-14T06:56:14.341108Z","iopub.execute_input":"2023-08-14T06:56:14.34221Z","iopub.status.idle":"2023-08-14T06:56:17.506805Z","shell.execute_reply.started":"2023-08-14T06:56:14.342175Z","shell.execute_reply":"2023-08-14T06:56:17.505511Z"},"trusted":true},"execution_count":13,"outputs":[{"output_type":"display_data","data":{"text/plain":"<pandas.io.formats.style.Styler at 0x7833edb6afe0>","text/html":"<style type=\"text/css\">\n#T_bcd9f_row10_col1 {\n  background-color: lightgreen;\n}\n</style>\n<table id=\"T_bcd9f\">\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_bcd9f_level0_col0\" class=\"col_heading level0 col0\" >Description</th>\n      <th id=\"T_bcd9f_level0_col1\" class=\"col_heading level0 col1\" >Value</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_bcd9f_level0_row0\" class=\"row_heading level0 row0\" >0</th>\n      <td id=\"T_bcd9f_row0_col0\" class=\"data row0 col0\" >Session id</td>\n      <td id=\"T_bcd9f_row0_col1\" class=\"data row0 col1\" >42</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row1\" class=\"row_heading level0 row1\" >1</th>\n      <td id=\"T_bcd9f_row1_col0\" class=\"data row1 col0\" >Target</td>\n      <td id=\"T_bcd9f_row1_col1\" class=\"data row1 col1\" >emission</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row2\" class=\"row_heading level0 row2\" >2</th>\n      <td id=\"T_bcd9f_row2_col0\" class=\"data row2 col0\" >Target type</td>\n      <td id=\"T_bcd9f_row2_col1\" class=\"data row2 col1\" >Regression</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row3\" class=\"row_heading level0 row3\" >3</th>\n      <td id=\"T_bcd9f_row3_col0\" class=\"data row3 col0\" >Original data shape</td>\n      <td id=\"T_bcd9f_row3_col1\" class=\"data row3 col1\" >(79023, 76)</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row4\" class=\"row_heading level0 row4\" >4</th>\n      <td id=\"T_bcd9f_row4_col0\" class=\"data row4 col0\" >Transformed data shape</td>\n      <td id=\"T_bcd9f_row4_col1\" class=\"data row4 col1\" >(79023, 76)</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row5\" class=\"row_heading level0 row5\" >5</th>\n      <td id=\"T_bcd9f_row5_col0\" class=\"data row5 col0\" >Transformed train set shape</td>\n      <td id=\"T_bcd9f_row5_col1\" class=\"data row5 col1\" >(55316, 76)</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row6\" class=\"row_heading level0 row6\" >6</th>\n      <td id=\"T_bcd9f_row6_col0\" class=\"data row6 col0\" >Transformed test set shape</td>\n      <td id=\"T_bcd9f_row6_col1\" class=\"data row6 col1\" >(23707, 76)</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row7\" class=\"row_heading level0 row7\" >7</th>\n      <td id=\"T_bcd9f_row7_col0\" class=\"data row7 col0\" >Numeric features</td>\n      <td id=\"T_bcd9f_row7_col1\" class=\"data row7 col1\" >74</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row8\" class=\"row_heading level0 row8\" >8</th>\n      <td id=\"T_bcd9f_row8_col0\" class=\"data row8 col0\" >Categorical features</td>\n      <td id=\"T_bcd9f_row8_col1\" class=\"data row8 col1\" >1</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row9\" class=\"row_heading level0 row9\" >9</th>\n      <td id=\"T_bcd9f_row9_col0\" class=\"data row9 col0\" >Rows with missing values</td>\n      <td id=\"T_bcd9f_row9_col1\" class=\"data row9 col1\" >99.4%</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row10\" class=\"row_heading level0 row10\" >10</th>\n      <td id=\"T_bcd9f_row10_col0\" class=\"data row10 col0\" >Preprocess</td>\n      <td id=\"T_bcd9f_row10_col1\" class=\"data row10 col1\" >True</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row11\" class=\"row_heading level0 row11\" >11</th>\n      <td id=\"T_bcd9f_row11_col0\" class=\"data row11 col0\" >Imputation type</td>\n      <td id=\"T_bcd9f_row11_col1\" class=\"data row11 col1\" >simple</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row12\" class=\"row_heading level0 row12\" >12</th>\n      <td id=\"T_bcd9f_row12_col0\" class=\"data row12 col0\" >Numeric imputation</td>\n      <td id=\"T_bcd9f_row12_col1\" class=\"data row12 col1\" >mean</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row13\" class=\"row_heading level0 row13\" >13</th>\n      <td id=\"T_bcd9f_row13_col0\" class=\"data row13 col0\" >Categorical imputation</td>\n      <td id=\"T_bcd9f_row13_col1\" class=\"data row13 col1\" >mode</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row14\" class=\"row_heading level0 row14\" >14</th>\n      <td id=\"T_bcd9f_row14_col0\" class=\"data row14 col0\" >Maximum one-hot encoding</td>\n      <td id=\"T_bcd9f_row14_col1\" class=\"data row14 col1\" >25</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row15\" class=\"row_heading level0 row15\" >15</th>\n      <td id=\"T_bcd9f_row15_col0\" class=\"data row15 col0\" >Encoding method</td>\n      <td id=\"T_bcd9f_row15_col1\" class=\"data row15 col1\" >None</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row16\" class=\"row_heading level0 row16\" >16</th>\n      <td id=\"T_bcd9f_row16_col0\" class=\"data row16 col0\" >Fold Generator</td>\n      <td id=\"T_bcd9f_row16_col1\" class=\"data row16 col1\" >KFold</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row17\" class=\"row_heading level0 row17\" >17</th>\n      <td id=\"T_bcd9f_row17_col0\" class=\"data row17 col0\" >Fold Number</td>\n      <td id=\"T_bcd9f_row17_col1\" class=\"data row17 col1\" >10</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row18\" class=\"row_heading level0 row18\" >18</th>\n      <td id=\"T_bcd9f_row18_col0\" class=\"data row18 col0\" >CPU Jobs</td>\n      <td id=\"T_bcd9f_row18_col1\" class=\"data row18 col1\" >-1</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row19\" class=\"row_heading level0 row19\" >19</th>\n      <td id=\"T_bcd9f_row19_col0\" class=\"data row19 col0\" >Use GPU</td>\n      <td id=\"T_bcd9f_row19_col1\" class=\"data row19 col1\" >False</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row20\" class=\"row_heading level0 row20\" >20</th>\n      <td id=\"T_bcd9f_row20_col0\" class=\"data row20 col0\" >Log Experiment</td>\n      <td id=\"T_bcd9f_row20_col1\" class=\"data row20 col1\" >False</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row21\" class=\"row_heading level0 row21\" >21</th>\n      <td id=\"T_bcd9f_row21_col0\" class=\"data row21 col0\" >Experiment Name</td>\n      <td id=\"T_bcd9f_row21_col1\" class=\"data row21 col1\" >reg-default-name</td>\n    </tr>\n    <tr>\n      <th id=\"T_bcd9f_level0_row22\" class=\"row_heading level0 row22\" >22</th>\n      <td id=\"T_bcd9f_row22_col0\" class=\"data row22 col0\" >USI</td>\n      <td id=\"T_bcd9f_row22_col1\" class=\"data row22 col1\" >5112</td>\n    </tr>\n  </tbody>\n</table>\n"},"metadata":{}}]},{"cell_type":"code","source":"# compare baseline models\nbest = compare_models()","metadata":{"execution":{"iopub.status.busy":"2023-08-14T06:56:17.508756Z","iopub.execute_input":"2023-08-14T06:56:17.509197Z"},"trusted":true},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":"                                                                       \n                                                                       \nInitiated  . . . . . . . . . . . . . . . . . .                 06:56:17\nStatus     . . . . . . . . . . . . . . . . . .         Fitting 10 Folds\nEstimator  . . . . . . . . . . . . . . . . . .  Random Forest Regressor","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></th>\n      <th></th>\n    </tr>\n    <tr>\n      <th></th>\n      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>Initiated</th>\n      <td>. . . . . . . . . . . . . . . . . .</td>\n      <td>06:56:17</td>\n    </tr>\n    <tr>\n      <th>Status</th>\n      <td>. . . . . . . . . . . . . . . . . .</td>\n      <td>Fitting 10 Folds</td>\n    </tr>\n    <tr>\n      <th>Estimator</th>\n      <td>. . . . . . . . . . . . . . . . . .</td>\n      <td>Random Forest Regressor</td>\n    </tr>\n  </tbody>\n</table>\n</div>"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"<pandas.io.formats.style.Styler at 0x78341f8d6ce0>","text/html":"<style type=\"text/css\">\n#T_71f02 th {\n  text-align: left;\n}\n#T_71f02_row0_col0, #T_71f02_row0_col1, #T_71f02_row0_col2, #T_71f02_row0_col3, #T_71f02_row0_col4, #T_71f02_row0_col5, #T_71f02_row0_col6, #T_71f02_row0_col7, #T_71f02_row1_col0, #T_71f02_row1_col1, #T_71f02_row1_col2, #T_71f02_row1_col3, #T_71f02_row1_col4, #T_71f02_row1_col5, #T_71f02_row1_col6, #T_71f02_row1_col7, #T_71f02_row2_col0, #T_71f02_row2_col1, #T_71f02_row2_col2, #T_71f02_row2_col3, #T_71f02_row2_col4, #T_71f02_row2_col5, #T_71f02_row2_col6, #T_71f02_row2_col7, #T_71f02_row3_col0, #T_71f02_row3_col1, #T_71f02_row3_col2, #T_71f02_row3_col3, #T_71f02_row3_col4, #T_71f02_row3_col5, #T_71f02_row3_col6, #T_71f02_row3_col7, #T_71f02_row4_col0, #T_71f02_row4_col1, #T_71f02_row4_col2, #T_71f02_row4_col3, #T_71f02_row4_col4, #T_71f02_row4_col5, #T_71f02_row4_col6, #T_71f02_row4_col7, #T_71f02_row5_col0, #T_71f02_row5_col1, #T_71f02_row5_col2, #T_71f02_row5_col3, #T_71f02_row5_col4, #T_71f02_row5_col5, #T_71f02_row5_col6, #T_71f02_row5_col7, #T_71f02_row6_col0, #T_71f02_row6_col1, #T_71f02_row6_col2, #T_71f02_row6_col3, #T_71f02_row6_col4, #T_71f02_row6_col5, #T_71f02_row6_col6, #T_71f02_row6_col7, #T_71f02_row7_col0, #T_71f02_row7_col1, #T_71f02_row7_col2, #T_71f02_row7_col3, #T_71f02_row7_col4, #T_71f02_row7_col5, #T_71f02_row7_col6, #T_71f02_row7_col7, #T_71f02_row8_col0, #T_71f02_row8_col1, #T_71f02_row8_col2, #T_71f02_row8_col3, #T_71f02_row8_col4, #T_71f02_row8_col5, #T_71f02_row8_col6, #T_71f02_row8_col7, #T_71f02_row9_col0, #T_71f02_row9_col1, #T_71f02_row9_col2, #T_71f02_row9_col3, #T_71f02_row9_col4, #T_71f02_row9_col5, #T_71f02_row9_col6, #T_71f02_row9_col7, #T_71f02_row10_col0, #T_71f02_row10_col1, #T_71f02_row10_col2, #T_71f02_row10_col3, #T_71f02_row10_col4, #T_71f02_row10_col5, #T_71f02_row10_col6, #T_71f02_row10_col7, #T_71f02_row11_col0, #T_71f02_row11_col1, #T_71f02_row11_col2, #T_71f02_row11_col3, #T_71f02_row11_col4, #T_71f02_row11_col5, #T_71f02_row11_col6, #T_71f02_row11_col7 {\n  text-align: left;\n}\n</style>\n<table id=\"T_71f02\">\n  <thead>\n    <tr>\n      <th class=\"blank level0\" >&nbsp;</th>\n      <th id=\"T_71f02_level0_col0\" class=\"col_heading level0 col0\" >Model</th>\n      <th id=\"T_71f02_level0_col1\" class=\"col_heading level0 col1\" >MAE</th>\n      <th id=\"T_71f02_level0_col2\" class=\"col_heading level0 col2\" >MSE</th>\n      <th id=\"T_71f02_level0_col3\" class=\"col_heading level0 col3\" >RMSE</th>\n      <th id=\"T_71f02_level0_col4\" class=\"col_heading level0 col4\" >R2</th>\n      <th id=\"T_71f02_level0_col5\" class=\"col_heading level0 col5\" >RMSLE</th>\n      <th id=\"T_71f02_level0_col6\" class=\"col_heading level0 col6\" >MAPE</th>\n      <th id=\"T_71f02_level0_col7\" class=\"col_heading level0 col7\" >TT (Sec)</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th id=\"T_71f02_level0_row0\" class=\"row_heading level0 row0\" >lr</th>\n      <td id=\"T_71f02_row0_col0\" class=\"data row0 col0\" >Linear Regression</td>\n      <td id=\"T_71f02_row0_col1\" class=\"data row0 col1\" >73.7573</td>\n      <td id=\"T_71f02_row0_col2\" class=\"data row0 col2\" >21737.5817</td>\n      <td id=\"T_71f02_row0_col3\" class=\"data row0 col3\" >147.0069</td>\n      <td id=\"T_71f02_row0_col4\" class=\"data row0 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row0_col5\" class=\"data row0 col5\" >1.9453</td>\n      <td id=\"T_71f02_row0_col6\" class=\"data row0 col6\" >102.5632</td>\n      <td id=\"T_71f02_row0_col7\" class=\"data row0 col7\" >0.5980</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row1\" class=\"row_heading level0 row1\" >lasso</th>\n      <td id=\"T_71f02_row1_col0\" class=\"data row1 col0\" >Lasso Regression</td>\n      <td id=\"T_71f02_row1_col1\" class=\"data row1 col1\" >73.7573</td>\n      <td id=\"T_71f02_row1_col2\" class=\"data row1 col2\" >21737.5682</td>\n      <td id=\"T_71f02_row1_col3\" class=\"data row1 col3\" >147.0068</td>\n      <td id=\"T_71f02_row1_col4\" class=\"data row1 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row1_col5\" class=\"data row1 col5\" >1.9453</td>\n      <td id=\"T_71f02_row1_col6\" class=\"data row1 col6\" >102.5627</td>\n      <td id=\"T_71f02_row1_col7\" class=\"data row1 col7\" >0.2930</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row2\" class=\"row_heading level0 row2\" >ridge</th>\n      <td id=\"T_71f02_row2_col0\" class=\"data row2 col0\" >Ridge Regression</td>\n      <td id=\"T_71f02_row2_col1\" class=\"data row2 col1\" >73.7573</td>\n      <td id=\"T_71f02_row2_col2\" class=\"data row2 col2\" >21737.5816</td>\n      <td id=\"T_71f02_row2_col3\" class=\"data row2 col3\" >147.0069</td>\n      <td id=\"T_71f02_row2_col4\" class=\"data row2 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row2_col5\" class=\"data row2 col5\" >1.9453</td>\n      <td id=\"T_71f02_row2_col6\" class=\"data row2 col6\" >102.5632</td>\n      <td id=\"T_71f02_row2_col7\" class=\"data row2 col7\" >0.2930</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row3\" class=\"row_heading level0 row3\" >en</th>\n      <td id=\"T_71f02_row3_col0\" class=\"data row3 col0\" >Elastic Net</td>\n      <td id=\"T_71f02_row3_col1\" class=\"data row3 col1\" >73.7563</td>\n      <td id=\"T_71f02_row3_col2\" class=\"data row3 col2\" >21737.3654</td>\n      <td id=\"T_71f02_row3_col3\" class=\"data row3 col3\" >147.0061</td>\n      <td id=\"T_71f02_row3_col4\" class=\"data row3 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row3_col5\" class=\"data row3 col5\" >1.9453</td>\n      <td id=\"T_71f02_row3_col6\" class=\"data row3 col6\" >102.5550</td>\n      <td id=\"T_71f02_row3_col7\" class=\"data row3 col7\" >0.3530</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row4\" class=\"row_heading level0 row4\" >lar</th>\n      <td id=\"T_71f02_row4_col0\" class=\"data row4 col0\" >Least Angle Regression</td>\n      <td id=\"T_71f02_row4_col1\" class=\"data row4 col1\" >73.7573</td>\n      <td id=\"T_71f02_row4_col2\" class=\"data row4 col2\" >21737.5817</td>\n      <td id=\"T_71f02_row4_col3\" class=\"data row4 col3\" >147.0069</td>\n      <td id=\"T_71f02_row4_col4\" class=\"data row4 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row4_col5\" class=\"data row4 col5\" >1.9453</td>\n      <td id=\"T_71f02_row4_col6\" class=\"data row4 col6\" >102.5632</td>\n      <td id=\"T_71f02_row4_col7\" class=\"data row4 col7\" >0.2900</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row5\" class=\"row_heading level0 row5\" >llar</th>\n      <td id=\"T_71f02_row5_col0\" class=\"data row5 col0\" >Lasso Least Angle Regression</td>\n      <td id=\"T_71f02_row5_col1\" class=\"data row5 col1\" >73.7573</td>\n      <td id=\"T_71f02_row5_col2\" class=\"data row5 col2\" >21737.5675</td>\n      <td id=\"T_71f02_row5_col3\" class=\"data row5 col3\" >147.0068</td>\n      <td id=\"T_71f02_row5_col4\" class=\"data row5 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row5_col5\" class=\"data row5 col5\" >1.9453</td>\n      <td id=\"T_71f02_row5_col6\" class=\"data row5 col6\" >102.5627</td>\n      <td id=\"T_71f02_row5_col7\" class=\"data row5 col7\" >0.2870</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row6\" class=\"row_heading level0 row6\" >omp</th>\n      <td id=\"T_71f02_row6_col0\" class=\"data row6 col0\" >Orthogonal Matching Pursuit</td>\n      <td id=\"T_71f02_row6_col1\" class=\"data row6 col1\" >73.7573</td>\n      <td id=\"T_71f02_row6_col2\" class=\"data row6 col2\" >21737.5817</td>\n      <td id=\"T_71f02_row6_col3\" class=\"data row6 col3\" >147.0069</td>\n      <td id=\"T_71f02_row6_col4\" class=\"data row6 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row6_col5\" class=\"data row6 col5\" >1.9453</td>\n      <td id=\"T_71f02_row6_col6\" class=\"data row6 col6\" >102.5632</td>\n      <td id=\"T_71f02_row6_col7\" class=\"data row6 col7\" >0.2960</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row7\" class=\"row_heading level0 row7\" >br</th>\n      <td id=\"T_71f02_row7_col0\" class=\"data row7 col0\" >Bayesian Ridge</td>\n      <td id=\"T_71f02_row7_col1\" class=\"data row7 col1\" >73.7573</td>\n      <td id=\"T_71f02_row7_col2\" class=\"data row7 col2\" >21737.5817</td>\n      <td id=\"T_71f02_row7_col3\" class=\"data row7 col3\" >147.0069</td>\n      <td id=\"T_71f02_row7_col4\" class=\"data row7 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row7_col5\" class=\"data row7 col5\" >1.9453</td>\n      <td id=\"T_71f02_row7_col6\" class=\"data row7 col6\" >102.5632</td>\n      <td id=\"T_71f02_row7_col7\" class=\"data row7 col7\" >0.2880</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row8\" class=\"row_heading level0 row8\" >dt</th>\n      <td id=\"T_71f02_row8_col0\" class=\"data row8 col0\" >Decision Tree Regressor</td>\n      <td id=\"T_71f02_row8_col1\" class=\"data row8 col1\" >73.7575</td>\n      <td id=\"T_71f02_row8_col2\" class=\"data row8 col2\" >21737.6067</td>\n      <td id=\"T_71f02_row8_col3\" class=\"data row8 col3\" >147.0069</td>\n      <td id=\"T_71f02_row8_col4\" class=\"data row8 col4\" >-0.0002</td>\n      <td id=\"T_71f02_row8_col5\" class=\"data row8 col5\" >1.9453</td>\n      <td id=\"T_71f02_row8_col6\" class=\"data row8 col6\" >102.5643</td>\n      <td id=\"T_71f02_row8_col7\" class=\"data row8 col7\" >0.3100</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row9\" class=\"row_heading level0 row9\" >huber</th>\n      <td id=\"T_71f02_row9_col0\" class=\"data row9 col0\" >Huber Regressor</td>\n      <td id=\"T_71f02_row9_col1\" class=\"data row9 col1\" >67.0249</td>\n      <td id=\"T_71f02_row9_col2\" class=\"data row9 col2\" >22958.4471</td>\n      <td id=\"T_71f02_row9_col3\" class=\"data row9 col3\" >151.0971</td>\n      <td id=\"T_71f02_row9_col4\" class=\"data row9 col4\" >-0.0569</td>\n      <td id=\"T_71f02_row9_col5\" class=\"data row9 col5\" >1.7247</td>\n      <td id=\"T_71f02_row9_col6\" class=\"data row9 col6\" >52.2872</td>\n      <td id=\"T_71f02_row9_col7\" class=\"data row9 col7\" >0.2810</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row10\" class=\"row_heading level0 row10\" >knn</th>\n      <td id=\"T_71f02_row10_col0\" class=\"data row10 col0\" >K Neighbors Regressor</td>\n      <td id=\"T_71f02_row10_col1\" class=\"data row10 col1\" >78.8543</td>\n      <td id=\"T_71f02_row10_col2\" class=\"data row10 col2\" >24291.6324</td>\n      <td id=\"T_71f02_row10_col3\" class=\"data row10 col3\" >155.4688</td>\n      <td id=\"T_71f02_row10_col4\" class=\"data row10 col4\" >-0.1198</td>\n      <td id=\"T_71f02_row10_col5\" class=\"data row10 col5\" >1.9217</td>\n      <td id=\"T_71f02_row10_col6\" class=\"data row10 col6\" >98.4152</td>\n      <td id=\"T_71f02_row10_col7\" class=\"data row10 col7\" >1.0460</td>\n    </tr>\n    <tr>\n      <th id=\"T_71f02_level0_row11\" class=\"row_heading level0 row11\" >par</th>\n      <td id=\"T_71f02_row11_col0\" class=\"data row11 col0\" >Passive Aggressive Regressor</td>\n      <td id=\"T_71f02_row11_col1\" class=\"data row11 col1\" >84.5908</td>\n      <td id=\"T_71f02_row11_col2\" class=\"data row11 col2\" >25693.6761</td>\n      <td id=\"T_71f02_row11_col3\" class=\"data row11 col3\" >159.7577</td>\n      <td id=\"T_71f02_row11_col4\" class=\"data row11 col4\" >-0.1864</td>\n      <td id=\"T_71f02_row11_col5\" class=\"data row11 col5\" >2.4928</td>\n      <td id=\"T_71f02_row11_col6\" class=\"data row11 col6\" >73.8704</td>\n      <td id=\"T_71f02_row11_col7\" class=\"data row11 col7\" >0.2880</td>\n    </tr>\n  </tbody>\n</table>\n"},"metadata":{}},{"output_type":"display_data","data":{"text/plain":"Processing:   0%|          | 0/85 [00:00<?, ?it/s]","application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"681fdfb4811f44519d5f8ef7a223f988"}},"metadata":{}}]},{"cell_type":"code","source":"# plot residuals\nplot_model(best, plot = 'residuals')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# plot error\nplot_model(best, plot = 'error')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# plot feature importance\nplot_model(best, plot = 'feature')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# predict on test set\nholdout_pred = predict_model(best)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# predict model on new_data\npredictions = predict_model(best, data = test_df)\npredictions.head()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Submit:\n    \n    def submit_predictions(self):        \n        df_submit = pd.DataFrame(data={'ID_LAT_LON_YEAR_WEEK': test_df['ID_LAT_LON_YEAR_WEEK'],'emission':predictions['prediction_label']})\n        df_submit.to_csv('submission.csv',index=False)\n        print('Submission Completed!!')\n        return df_submit\n        \n        \nsubmit = Submit()\ndf_submit=submit.submit_predictions()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# save pipeline\nsave_model(best, 'emission_pipeline')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# load pipeline\nloaded_best_pipeline = load_model('my_first_pipeline')\nloaded_best_pipeline","metadata":{},"execution_count":null,"outputs":[]}]}