{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30673,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Example Notebook","metadata":{}},{"cell_type":"markdown","source":"### Welcome to the example notebook for the Home Credit Kaggle competition. The goal of this competition is to determine how likely a customer is going to default on an issued loan. The main difference between the first and this competition is that now your submission will be scored with a custom metric that will take into account how well the model performs in future. A decline in performance will be penalized. The goal is to create a model that is stable and performs well in the future.","metadata":{}},{"cell_type":"markdown","source":"### In this notebook you will see how to:\n","metadata":{}},{"cell_type":"markdown","source":"### Load the data\n### Join tables with Polars - a DataFrame library implemented in Rust language, designed to be blazingy fast and memory efficient.\n### Create simple aggregation features\n### Train a LightGBM model\n### Create a submission table","metadata":{}},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Load the data","metadata":{}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score \n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:09:10.61345Z","iopub.execute_input":"2024-03-31T04:09:10.613947Z","iopub.status.idle":"2024-03-31T04:09:15.235009Z","shell.execute_reply.started":"2024-03-31T04:09:10.613908Z","shell.execute_reply":"2024-03-31T04:09:15.23365Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # implement here all desired dtypes for tables\n    # the following is just an example\n    for col in df.columns:\n        # last letter of column name will help you determine the type\n        if col[-1] in (\"P\", \"A\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\n    return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n    for col in df.columns:  \n        if df[col].dtype.name in ['object', 'string']:\n            df[col] = df[col].astype(\"string\").astype('category')\n            current_categories = df[col].cat.categories\n            new_categories = current_categories.to_list() + [\"Unknown\"]\n            new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n            df[col] = df[col].astype(new_dtype)\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:09:34.664682Z","iopub.execute_input":"2024-03-31T04:09:34.665797Z","iopub.status.idle":"2024-03-31T04:09:34.675982Z","shell.execute_reply.started":"2024-03-31T04:09:34.665756Z","shell.execute_reply":"2024-03-31T04:09:34.675068Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"train_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntrain_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes) \ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:09:48.181365Z","iopub.execute_input":"2024-03-31T04:09:48.182635Z","iopub.status.idle":"2024-03-31T04:10:05.603526Z","shell.execute_reply.started":"2024-03-31T04:09:48.182588Z","shell.execute_reply":"2024-03-31T04:10:05.602413Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"test_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes) \ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes) ","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:10:07.93241Z","iopub.execute_input":"2024-03-31T04:10:07.932864Z","iopub.status.idle":"2024-03-31T04:10:07.996779Z","shell.execute_reply.started":"2024-03-31T04:10:07.932831Z","shell.execute_reply":"2024-03-31T04:10:07.995626Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"markdown","source":"### Feature engineering","metadata":{}},{"cell_type":"markdown","source":"#### In this part, we can see a simple example of joining tables via case_id. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas.","metadata":{}},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\ntrain_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\ntrain_person_1_feats_2 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\ntrain_credit_bureau_b_2_feats = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:11:44.728714Z","iopub.execute_input":"2024-03-31T04:11:44.729611Z","iopub.status.idle":"2024-03-31T04:11:47.165703Z","shell.execute_reply.started":"2024-03-31T04:11:44.729562Z","shell.execute_reply":"2024-03-31T04:11:47.164629Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"['amtinstpaidbefduel24m_4187115A', 'annuity_780A', 'annuitynextmonth_57A', 'avginstallast24m_3658937A', 'avglnamtstart24m_4525187A', 'avgoutstandbalancel6m_4187114A', 'avgpmtlast12m_4525200A', 'credamount_770A', 'currdebt_22A', 'currdebtcredtyperange_828A', 'disbursedcredamount_1113A', 'downpmt_116A', 'inittransactionamount_650A', 'lastapprcommoditycat_1041M', 'lastapprcommoditytypec_5251766M', 'lastapprcredamount_781A', 'lastcancelreason_561M', 'lastotherinc_902A', 'lastotherlnsexpense_631A', 'lastrejectcommoditycat_161M', 'lastrejectcommodtypec_5251769M', 'lastrejectcredamount_222A', 'lastrejectreason_759M', 'lastrejectreasonclient_4145040M', 'maininc_215A', 'maxannuity_159A', 'maxannuity_4075009A', 'maxdebt4_972A', 'maxinstallast24m_3658928A', 'maxlnamtstart6m_4525199A', 'maxoutstandbalancel12m_4187113A', 'maxpmtlast3m_4525190A', 'previouscontdistrict_112M', 'price_1097A', 'sumoutstandtotal_3546847A', 'sumoutstandtotalest_4493215A', 'totaldebt_9A', 'totalsettled_863A', 'totinstallast1m_4525188A']\n['description_5085714M', 'education_1103M', 'education_88M', 'maritalst_385M', 'maritalst_893M', 'pmtaverage_3A', 'pmtaverage_4527227A', 'pmtaverage_4955615A', 'pmtssum_45A']\n","output_type":"stream"}]},{"cell_type":"code","source":"test_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntest_person_1_feats_2 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\ntest_credit_bureau_b_2_feats = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)\n\ndata_submission = test_basetable.join(\n    test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:12:50.09791Z","iopub.execute_input":"2024-03-31T04:12:50.09837Z","iopub.status.idle":"2024-03-31T04:12:50.11641Z","shell.execute_reply.started":"2024-03-31T04:12:50.098336Z","shell.execute_reply":"2024-03-31T04:12:50.115201Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\nprint(cols_pred)\n\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )\n\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:13:14.21545Z","iopub.execute_input":"2024-03-31T04:13:14.216266Z","iopub.status.idle":"2024-03-31T04:13:22.639887Z","shell.execute_reply.started":"2024-03-31T04:13:14.216217Z","shell.execute_reply":"2024-03-31T04:13:22.638639Z"},"trusted":true},"execution_count":9,"outputs":[{"name":"stdout","text":"['amtinstpaidbefduel24m_4187115A', 'annuity_780A', 'annuitynextmonth_57A', 'avginstallast24m_3658937A', 'avglnamtstart24m_4525187A', 'avgoutstandbalancel6m_4187114A', 'avgpmtlast12m_4525200A', 'credamount_770A', 'currdebt_22A', 'currdebtcredtyperange_828A', 'disbursedcredamount_1113A', 'downpmt_116A', 'inittransactionamount_650A', 'lastapprcommoditycat_1041M', 'lastapprcommoditytypec_5251766M', 'lastapprcredamount_781A', 'lastcancelreason_561M', 'lastotherinc_902A', 'lastotherlnsexpense_631A', 'lastrejectcommoditycat_161M', 'lastrejectcommodtypec_5251769M', 'lastrejectcredamount_222A', 'lastrejectreason_759M', 'lastrejectreasonclient_4145040M', 'maininc_215A', 'maxannuity_159A', 'maxannuity_4075009A', 'maxdebt4_972A', 'maxinstallast24m_3658928A', 'maxlnamtstart6m_4525199A', 'maxoutstandbalancel12m_4187113A', 'maxpmtlast3m_4525190A', 'previouscontdistrict_112M', 'price_1097A', 'sumoutstandtotal_3546847A', 'sumoutstandtotalest_4493215A', 'totaldebt_9A', 'totalsettled_863A', 'totinstallast1m_4525188A', 'description_5085714M', 'education_1103M', 'education_88M', 'maritalst_385M', 'maritalst_893M', 'pmtaverage_3A', 'pmtaverage_4527227A', 'pmtaverage_4955615A', 'pmtssum_45A']\n","output_type":"stream"}]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:13:22.641599Z","iopub.execute_input":"2024-03-31T04:13:22.641943Z","iopub.status.idle":"2024-03-31T04:13:22.648484Z","shell.execute_reply.started":"2024-03-31T04:13:22.641906Z","shell.execute_reply":"2024-03-31T04:13:22.647256Z"},"trusted":true},"execution_count":10,"outputs":[{"name":"stdout","text":"Train: (915995, 48)\nValid: (305332, 48)\nTest: (305332, 48)\n","output_type":"stream"}]},{"cell_type":"markdown","source":"### Training LightGBM","metadata":{}},{"cell_type":"markdown","source":"#### Minimal example of LightGBM training is shown below.","metadata":{}},{"cell_type":"code","source":"lgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 3,\n    \"num_leaves\": 31,\n    \"learning_rate\": 0.05,\n    \"feature_fraction\": 0.9,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 1000,\n    \"verbose\": -1,\n}\n\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:14:10.705359Z","iopub.execute_input":"2024-03-31T04:14:10.706751Z","iopub.status.idle":"2024-03-31T04:15:33.655717Z","shell.execute_reply.started":"2024-03-31T04:14:10.706704Z","shell.execute_reply":"2024-03-31T04:15:33.654509Z"},"trusted":true},"execution_count":11,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/lightgbm/engine.py:172: UserWarning: Found `n_estimators` in params. Will use it instead of argument\n  _log_warning(f\"Found `{alias}` in params. Will use it instead of argument\")\n","output_type":"stream"},{"name":"stdout","text":"Training until validation scores don't improve for 10 rounds\n[50]\tvalid_0's auc: 0.705963\n[100]\tvalid_0's auc: 0.724362\n[150]\tvalid_0's auc: 0.731423\n[200]\tvalid_0's auc: 0.735874\n[250]\tvalid_0's auc: 0.739009\n[300]\tvalid_0's auc: 0.740965\n[350]\tvalid_0's auc: 0.742924\n[400]\tvalid_0's auc: 0.744582\n[450]\tvalid_0's auc: 0.745977\n[500]\tvalid_0's auc: 0.747033\n[550]\tvalid_0's auc: 0.747877\n[600]\tvalid_0's auc: 0.749039\n[650]\tvalid_0's auc: 0.750087\n[700]\tvalid_0's auc: 0.750863\nEarly stopping, best iteration is:\n[739]\tvalid_0's auc: 0.751216\n","output_type":"stream"}]},{"cell_type":"markdown","source":"#### Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = gbm.predict(X, num_iteration=gbm.best_iteration)\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:15:55.916689Z","iopub.execute_input":"2024-03-31T04:15:55.91714Z","iopub.status.idle":"2024-03-31T04:16:14.717748Z","shell.execute_reply.started":"2024-03-31T04:15:55.917108Z","shell.execute_reply":"2024-03-31T04:16:14.716106Z"},"trusted":true},"execution_count":12,"outputs":[{"name":"stdout","text":"The AUC score on the train set is: 0.764122917660593\nThe AUC score on the valid set is: 0.7512157223309048\nThe AUC score on the test set is: 0.7483072129459662\n","output_type":"stream"}]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}') ","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:16:19.394069Z","iopub.execute_input":"2024-03-31T04:16:19.394833Z","iopub.status.idle":"2024-03-31T04:16:20.476636Z","shell.execute_reply.started":"2024-03-31T04:16:19.394795Z","shell.execute_reply":"2024-03-31T04:16:20.475645Z"},"trusted":true},"execution_count":13,"outputs":[{"name":"stdout","text":"The stability score on the train set is: 0.4976648127691175\nThe stability score on the valid set is: 0.4726726686264489\nThe stability score on the test set is: 0.4583643686935092\n","output_type":"stream"}]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"markdown","source":"#### Scoring the submission dataset is below, we need to take care of new categories. Then we save the score as a last step.","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_train[col] = X_train[col].astype(new_dtype)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:17:07.075236Z","iopub.execute_input":"2024-03-31T04:17:07.076138Z","iopub.status.idle":"2024-03-31T04:17:07.180572Z","shell.execute_reply.started":"2024-03-31T04:17:07.076099Z","shell.execute_reply":"2024-03-31T04:17:07.17961Z"},"trusted":true},"execution_count":14,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-31T04:17:17.315141Z","iopub.execute_input":"2024-03-31T04:17:17.315989Z","iopub.status.idle":"2024-03-31T04:17:17.328416Z","shell.execute_reply.started":"2024-03-31T04:17:17.315942Z","shell.execute_reply":"2024-03-31T04:17:17.326807Z"},"trusted":true},"execution_count":15,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}