{"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"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Example Notebook\n\nWelcome 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](https://www.kaggle.com/c/home-credit-default-risk) 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.\n\nIn this notebook you will see how to:\n* 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\n\n## Load the data","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"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":"2024-04-28T06:04:17.814283Z","iopub.execute_input":"2024-04-28T06:04:17.815676Z","iopub.status.idle":"2024-04-28T06:04:17.822060Z","shell.execute_reply.started":"2024-04-28T06:04:17.815611Z","shell.execute_reply":"2024-04-28T06:04:17.821054Z"},"trusted":true},"execution_count":null,"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":"2024-04-28T06:04:17.824287Z","iopub.execute_input":"2024-04-28T06:04:17.824926Z","iopub.status.idle":"2024-04-28T06:04:17.838353Z","shell.execute_reply.started":"2024-04-28T06:04:17.824890Z","shell.execute_reply":"2024-04-28T06:04:17.837231Z"},"trusted":true},"execution_count":null,"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":"2024-04-28T06:04:17.841027Z","iopub.execute_input":"2024-04-28T06:04:17.841827Z","iopub.status.idle":"2024-04-28T06:04:31.093727Z","shell.execute_reply.started":"2024-04-28T06:04:17.841794Z","shell.execute_reply":"2024-04-28T06:04:31.092806Z"},"trusted":true},"execution_count":null,"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":"2024-04-28T06:04:31.094971Z","iopub.execute_input":"2024-04-28T06:04:31.095261Z","iopub.status.idle":"2024-04-28T06:04:31.143138Z","shell.execute_reply.started":"2024-04-28T06:04:31.095236Z","shell.execute_reply":"2024-04-28T06:04:31.142303Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_person_1.head()\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:04:31.145924Z","iopub.execute_input":"2024-04-28T06:04:31.146300Z","iopub.status.idle":"2024-04-28T06:04:31.159353Z","shell.execute_reply.started":"2024-04-28T06:04:31.146265Z","shell.execute_reply":"2024-04-28T06:04:31.158296Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\n\nIn 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":"2024-04-28T06:04:31.161001Z","iopub.execute_input":"2024-04-28T06:04:31.161370Z","iopub.status.idle":"2024-04-28T06:04:32.635921Z","shell.execute_reply.started":"2024-04-28T06:04:31.161331Z","shell.execute_reply":"2024-04-28T06:04:32.635058Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-04-28T06:04:32.636998Z","iopub.execute_input":"2024-04-28T06:04:32.637283Z","iopub.status.idle":"2024-04-28T06:04:32.649327Z","shell.execute_reply.started":"2024-04-28T06:04:32.637258Z","shell.execute_reply":"2024-04-28T06:04:32.648347Z"},"trusted":true},"execution_count":null,"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 ) ##random_state=1\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1) ##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)\n8\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:04:32.650526Z","iopub.execute_input":"2024-04-28T06:04:32.650841Z","iopub.status.idle":"2024-04-28T06:04:40.380764Z","shell.execute_reply.started":"2024-04-28T06:04:32.650815Z","shell.execute_reply":"2024-04-28T06:04:40.379941Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# # Assuming 'data' is a Polars DataFrame and 'case_id' is a column in it\n# case_ids = np.random.default_rng(seed=1).permutation(data[\"case_id\"].unique().to_numpy())\n# train_size = int(len(case_ids) * 0.6)\n# valid_size = int(len(case_ids) * 0.2)\n\n# case_ids_train = case_ids[:train_size]\n# case_ids_test = case_ids[train_size:]\n# case_ids_valid = case_ids_test[:valid_size]\n# case_ids_test = case_ids_test[valid_size:]\n\n# # Select columns following a specific naming convention\n# cols_pred = [col for col in data.columns if col[-1].isupper() and col[:-1].islower()]\n\n# def from_polars_to_pandas(case_ids):\n#     filtered_data = data.filter(pl.col(\"case_id\").is_in(case_ids))\n#     base = filtered_data.select([\"case_id\", \"WEEK_NUM\", \"target\"]).to_pandas()\n#     X = filtered_data.select(cols_pred).to_pandas()\n#     y = filtered_data.select(\"target\").to_pandas()\n#     return base, X, y\n\n# base_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\n# base_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\n# base_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\n# def convert_strings(df):\n#     for col in df.columns:\n#         if df[col].dtype == 'object':\n#             df[col] = df[col].astype(str)\n#     return df\n\n# X_train.fillna(0, inplace=True) \n# X_valid.fillna(0, inplace=True) \n# X_test.fillna(0, inplace=True) \n\n# X_train = convert_strings(X_train)\n# X_valid = convert_strings(X_valid)\n# X_test = convert_strings(X_test)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:04:40.381896Z","iopub.execute_input":"2024-04-28T06:04:40.382188Z","iopub.status.idle":"2024-04-28T06:04:40.387475Z","shell.execute_reply.started":"2024-04-28T06:04:40.382162Z","shell.execute_reply":"2024-04-28T06:04:40.386590Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-04-28T06:04:40.388756Z","iopub.execute_input":"2024-04-28T06:04:40.389103Z","iopub.status.idle":"2024-04-28T06:04:40.405508Z","shell.execute_reply.started":"2024-04-28T06:04:40.389068Z","shell.execute_reply":"2024-04-28T06:04:40.404568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM\n\nMinimal 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\n\n##OLD\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\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)] ##.early_stopping(10)\n)","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:04:40.406936Z","iopub.execute_input":"2024-04-28T06:04:40.407574Z","iopub.status.idle":"2024-04-28T06:05:55.830094Z","shell.execute_reply.started":"2024-04-28T06:04:40.407521Z","shell.execute_reply":"2024-04-28T06:05:55.829219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"from lightgbm import LGBMClassifier\nfrom sklearn.model_selection import GridSearchCV\nfrom sklearn.metrics import roc_auc_score, make_scorer\n\n# Define the classifier with initial parameters\nparams = LGBMClassifier(\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\n# Define the parameter grid to search\nparam_grid = {\n    'max_depth': [3, 5, 7],\n    'num_leaves': [31, 50, 70],\n    'learning_rate': [0.01, 0.05, 0.1]\n}\n\n# Set up the AUC scorer\nauc_scorer = make_scorer(roc_auc_score, needs_proba=True)\n\n# Initialize GridSearchCV with the estimator and parameter grid\ngrid_search = GridSearchCV(\n    estimator=params,\n    param_grid=param_grid,\n    scoring=auc_scorer,\n    cv=5,  # Number of folds in cross-validation\n    verbose=1,\n    n_jobs=-1\n)\n\n# Fit GridSearchCV\ngrid_search.fit(X_train, y_train)\n\n# Get the best model from grid search\nbest_model = grid_search.best_estimator_\n\n# Prediction and evaluation on training, validation, and test sets\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = best_model.predict_proba(X)[:, 1]  # get probabilities for the positive class\n    base[\"score\"] = y_pred\n\n# Calculate AUC scores\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\"])}')\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:05:55.835308Z","iopub.execute_input":"2024-04-28T06:05:55.837384Z","iopub.status.idle":"2024-04-28T06:05:55.848392Z","shell.execute_reply.started":"2024-04-28T06:05:55.837351Z","shell.execute_reply":"2024-04-28T06:05:55.847421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"##OLD\nfor 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\"])}')  \n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:05:55.849150Z","iopub.status.idle":"2024-04-28T06:05:55.850046Z","shell.execute_reply.started":"2024-04-28T06:05:55.849846Z","shell.execute_reply":"2024-04-28T06:05:55.849867Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"##OLD\ndef 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":"2024-04-28T06:05:55.851264Z","iopub.status.idle":"2024-04-28T06:05:55.851701Z","shell.execute_reply.started":"2024-04-28T06:05:55.851472Z","shell.execute_reply":"2024-04-28T06:05:55.851498Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"###NEW\ndef predict_and_score(base, model, X, best_iteration):\n    base[\"score\"] = model.predict(X, num_iteration=best_iteration)\n    return roc_auc_score(base[\"target\"], base[\"score\"])\n\nauc_train = predict_and_score(base_train, gbm, X_train, gbm.best_iteration)\nauc_valid = predict_and_score(base_valid, gbm, X_valid, gbm.best_iteration)\nauc_test = predict_and_score(base_test, gbm, X_test, gbm.best_iteration)\n\nprint(f'The AUC score on the train set is: {auc_train}') \nprint(f'The AUC score on the valid set is: {auc_valid}') \nprint(f'The AUC score on the test set is: {auc_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-04-28T06:05:55.853308Z","iopub.status.idle":"2024-04-28T06:05:55.853700Z","shell.execute_reply.started":"2024-04-28T06:05:55.853490Z","shell.execute_reply":"2024-04-28T06:05:55.853507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission\n\nScoring 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":"2024-04-28T06:05:55.854940Z","iopub.status.idle":"2024-04-28T06:05:55.855391Z","shell.execute_reply.started":"2024-04-28T06:05:55.855123Z","shell.execute_reply":"2024-04-28T06:05:55.855141Z"},"trusted":true},"execution_count":null,"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":"2024-04-28T06:05:55.857716Z","iopub.status.idle":"2024-04-28T06:05:55.858152Z","shell.execute_reply.started":"2024-04-28T06:05:55.857957Z","shell.execute_reply":"2024-04-28T06:05:55.857981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Best of luck, and most importantly, enjoy the process of learning and discovery! \n\n<img src=\"https://i.imgur.com/obVWIBh.png\" alt=\"Image\" width=\"700\"/>","metadata":{}}]}