{"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":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"This notebook is priamrily based on https://www.kaggle.com/code/pshikk/lgbm-hyperopt\n\nI used more features from the dataset and added some new features based on the existing ones. Hyperopt is used for fine-tuning","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":"2024-03-15T13:30:29.976102Z","iopub.execute_input":"2024-03-15T13:30:29.976911Z","iopub.status.idle":"2024-03-15T13:30:33.366672Z","shell.execute_reply.started":"2024-03-15T13:30:29.976840Z","shell.execute_reply":"2024-03-15T13:30:33.364826Z"},"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":"2024-03-15T13:30:33.369275Z","iopub.execute_input":"2024-03-15T13:30:33.369759Z","iopub.status.idle":"2024-03-15T13:30:33.381408Z","shell.execute_reply.started":"2024-03-15T13:30:33.369717Z","shell.execute_reply":"2024-03-15T13:30:33.379654Z"},"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":"2024-03-15T13:30:33.383456Z","iopub.execute_input":"2024-03-15T13:30:33.384094Z","iopub.status.idle":"2024-03-15T13:30:55.832890Z","shell.execute_reply.started":"2024-03-15T13:30:33.384039Z","shell.execute_reply":"2024-03-15T13:30:55.831459Z"},"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":"2024-03-15T13:30:55.836938Z","iopub.execute_input":"2024-03-15T13:30:55.838021Z","iopub.status.idle":"2024-03-15T13:30:55.909466Z","shell.execute_reply.started":"2024-03-15T13:30:55.837960Z","shell.execute_reply":"2024-03-15T13:30:55.908027Z"},"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\", \"P\", \"M\", \"D\", \"T\", \"L\"):\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\", \"P\", \"M\", \"D\", \"T\", \"L\"):\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)\n\ndel train_basetable\ndel train_static\ndel train_static_cb\ndel train_person_1_feats_1\ndel train_person_1_feats_2\ndel train_credit_bureau_b_2_feats","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:30:55.911034Z","iopub.execute_input":"2024-03-15T13:30:55.911466Z","iopub.status.idle":"2024-03-15T13:31:01.285686Z","shell.execute_reply.started":"2024-03-15T13:30:55.911430Z","shell.execute_reply":"2024-03-15T13:31:01.284184Z"},"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)\n\ndel test_basetable\ndel test_static\ndel test_static_cb\ndel test_person_1_feats_1\ndel test_person_1_feats_2\ndel test_credit_bureau_b_2_feats","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:31:01.286933Z","iopub.execute_input":"2024-03-15T13:31:01.287317Z","iopub.status.idle":"2024-03-15T13:31:01.314508Z","shell.execute_reply.started":"2024-03-15T13:31:01.287285Z","shell.execute_reply":"2024-03-15T13:31:01.313469Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def add_custom_columns(df):\n    df = df.with_columns([\n        ((pl.col(\"totalsettled_863A\") - pl.col(\"currdebt_22A\")) / pl.col(\"maininc_215A\")).alias(\"custom_credit_minus_debt_over_income\"),\n        (pl.col(\"totalsettled_863A\") / pl.col(\"maininc_215A\")).alias(\"custom_credit_over_income\"),\n        (pl.col(\"currdebt_22A\") / pl.col(\"maininc_215A\")).alias(\"custom_debt_over_income\"),\n        (pl.col(\"annuity_780A\") / pl.col(\"maininc_215A\")).alias(\"custom_annuity_over_income\"),\n        (pl.col(\"maxdbddpdtollast12m_3658940P\") + pl.col(\"maxdbddpdtollast6m_4187119P\")).alias(\"custom_maxdpdtoll_ultimate_sum\"),\n        (pl.col(\"maxdbddpdtollast12m_3658940P\") * pl.col(\"maxdbddpdtollast6m_4187119P\")).alias(\"custom_maxdpdtoll_ultimate_mul\"),\n        (pl.col(\"maxdpdlast12m_727P\") + pl.col(\"maxdpdlast24m_143P\") + pl.col(\"maxdpdlast3m_392P\") + pl.col(\"maxdpdlast6m_474P\") + pl.col(\"maxdpdlast9m_1059P\")).alias(\"custom_maxdpdlast_ultimate_sum\"),\n        (pl.col(\"maxdpdlast12m_727P\") * pl.col(\"maxdpdlast24m_143P\") * pl.col(\"maxdpdlast3m_392P\") * pl.col(\"maxdpdlast6m_474P\") * pl.col(\"maxdpdlast9m_1059P\")).alias(\"custom_maxdpdlast_ultimate_mul\"),\n        (pl.col(\"avgdbddpdlast24m_3658932P\") + pl.col(\"avgdbddpdlast3m_4187120P\")).alias(\"custom_avgdbddpdlast_ultimate_sum\"),\n        (pl.col(\"avgdbddpdlast24m_3658932P\") * pl.col(\"avgdbddpdlast3m_4187120P\")).alias(\"custom_avgdbddpdlast_ultimate_mul\"),\n    ])\n    return df\n\ndata = add_custom_columns(data)\ndata_submission = add_custom_columns(data_submission)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:31:01.316633Z","iopub.execute_input":"2024-03-15T13:31:01.317525Z","iopub.status.idle":"2024-03-15T13:31:01.439398Z","shell.execute_reply.started":"2024-03-15T13:31:01.317475Z","shell.execute_reply":"2024-03-15T13:31:01.438327Z"},"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)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\nexclude_cols = [\"opencred_647L\"]\n\ncols_pred = []\nfor col in data.columns:\n    if ((col[-1].isupper() and col[:-1].islower()) or col.find(\"custom\") == 0) and data[col].dtype == data_submission[col].dtype and col not in exclude_cols:\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\ndel data\n\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:31:01.441243Z","iopub.execute_input":"2024-03-15T13:31:01.441667Z","iopub.status.idle":"2024-03-15T13:31:39.879651Z","shell.execute_reply.started":"2024-03-15T13:31:01.441626Z","shell.execute_reply":"2024-03-15T13:31:39.878372Z"},"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":"2024-03-15T13:31:39.881611Z","iopub.execute_input":"2024-03-15T13:31:39.882362Z","iopub.status.idle":"2024-03-15T13:31:39.889753Z","shell.execute_reply.started":"2024-03-15T13:31:39.882310Z","shell.execute_reply":"2024-03-15T13:31:39.888295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# desc = pd.read_csv(dataPath + \"feature_definitions.csv\")\n# desc[desc[\"Variable\"].isin()]","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:31:39.894219Z","iopub.execute_input":"2024-03-15T13:31:39.894768Z","iopub.status.idle":"2024-03-15T13:31:39.909428Z","shell.execute_reply.started":"2024-03-15T13:31:39.894729Z","shell.execute_reply":"2024-03-15T13:31:39.907627Z"},"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":"from hyperopt import hp, fmin, tpe, Trials, STATUS_OK\nfrom sklearn.model_selection import cross_val_score\n\nlgb_cls_params = {\n    'learning_rate':    hp.uniform('learning_rate', 0.1, 1),\n    'max_depth':        hp.choice('max_depth', np.arange(2, 100, 1, dtype=int)),\n    'min_child_weight': hp.choice('min_child_weight', np.arange(1, 50, 1, dtype=int)),\n    'colsample_bytree': hp.uniform('colsample_bytree', 0.4, 1),\n    'subsample':        hp.uniform('subsample', 0.6, 1),\n    'num_leaves':       hp.choice('num_leaves', np.arange(2, 200, 1, dtype=int)),\n    'min_split_gain':   hp.uniform('min_split_gain', 0, 1),\n    'reg_alpha':        hp.uniform('reg_alpha', 0, 1),\n    'reg_lambda':       hp.uniform('reg_lambda', 0, 1),\n    'n_estimators':     10,\n    'objective':        'binary',  # or 'multiclass' for multiclass classification\n    'metric':           'auc',  # or 'multi_logloss' for multiclass classification\n    'boosting_type':    'gbdt'  # Gradient Boosting Decision Tree\n}\n\n\ndef f(params):\n    lgbm = lgb.LGBMClassifier(n_jobs=-1,early_stopping_rounds=None,**params)\n    score = cross_val_score(lgbm, X_train, y_train, cv=2,n_jobs=-1).mean()\n    return score\n\ntrials = Trials()\nresult = fmin(\n    fn=f,                           # objective function\n    space=lgb_cls_params,           # parameter space\n    algo=tpe.suggest,               # surrogate algorithm\n    max_evals=10,                   # no. of evaluations\n    trials=trials,                  # trials object that keeps track of the sample results (optional),\n    rstate=np.random.default_rng(42)\n)\nprint(result)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:31:39.911371Z","iopub.execute_input":"2024-03-15T13:31:39.911875Z","iopub.status.idle":"2024-03-15T13:48:05.096511Z","shell.execute_reply.started":"2024-03-15T13:31:39.911831Z","shell.execute_reply":"2024-03-15T13:48:05.094669Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"best_params = result","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:48:05.099376Z","iopub.execute_input":"2024-03-15T13:48:05.100574Z","iopub.status.idle":"2024-03-15T13:48:05.109984Z","shell.execute_reply.started":"2024-03-15T13:48:05.100478Z","shell.execute_reply":"2024-03-15T13:48:05.107787Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"gbm = lgb.train(\n    best_params,  \n    lgb.Dataset(X_train, label=y_train),  \n    valid_sets=[lgb.Dataset(X_valid, label=y_valid)], \n    valid_names=['valid'],\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]  \n)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:54:54.333517Z","iopub.execute_input":"2024-03-15T13:54:54.334145Z","iopub.status.idle":"2024-03-15T13:55:50.243833Z","shell.execute_reply.started":"2024-03-15T13:54:54.334092Z","shell.execute_reply":"2024-03-15T13:55:50.242419Z"},"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":"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":"2024-03-15T13:55:50.246351Z","iopub.execute_input":"2024-03-15T13:55:50.246801Z","iopub.status.idle":"2024-03-15T13:56:45.457534Z","shell.execute_reply.started":"2024-03-15T13:55:50.246763Z","shell.execute_reply":"2024-03-15T13:56:45.456188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-03-15T13:56:45.459052Z","iopub.execute_input":"2024-03-15T13:56:45.460372Z","iopub.status.idle":"2024-03-15T13:56:46.731913Z","shell.execute_reply.started":"2024-03-15T13:56:45.460328Z","shell.execute_reply":"2024-03-15T13:56:46.730853Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"The stability score on the train set is: 0.5610296300684563\n\nThe stability score on the valid set is: 0.5192647420998157\n\nThe stability score on the test set is: 0.5143880892968283","metadata":{}},{"cell_type":"code","source":"# sorted(list(zip(gbm.feature_importance(), gbm.feature_name(),\n#                 desc[desc[\"Variable\"].isin(gbm.feature_name())].sort_values(by=[\"Variable\"])[\"Description\"].to_numpy())), reverse=True)\n# sorted(list(zip(gbm.feature_importance(), gbm.feature_name())), reverse=True)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T13:58:05.836743Z","iopub.execute_input":"2024-03-15T13:58:05.839434Z","iopub.status.idle":"2024-03-15T13:58:05.852611Z","shell.execute_reply.started":"2024-03-15T13:58:05.839334Z","shell.execute_reply":"2024-03-15T13:58:05.850867Z"},"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":"2024-03-15T13:58:06.347473Z","iopub.execute_input":"2024-03-15T13:58:06.348615Z","iopub.status.idle":"2024-03-15T13:58:07.032636Z","shell.execute_reply.started":"2024-03-15T13:58:06.348546Z","shell.execute_reply":"2024-03-15T13:58:07.031438Z"},"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":"2024-03-15T13:58:08.088941Z","iopub.execute_input":"2024-03-15T13:58:08.090346Z","iopub.status.idle":"2024-03-15T13:58:08.101499Z","shell.execute_reply.started":"2024-03-15T13:58:08.090292Z","shell.execute_reply":"2024-03-15T13:58:08.099824Z"},"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":{}}]}