{"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":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30699,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"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 ","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:19:31.993644Z","iopub.execute_input":"2024-05-07T03:19:31.994022Z","iopub.status.idle":"2024-05-07T03:19:37.727573Z","shell.execute_reply.started":"2024-05-07T03:19:31.993992Z","shell.execute_reply":"2024-05-07T03:19:37.726565Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:19:39.364769Z","iopub.execute_input":"2024-05-07T03:19:39.365141Z","iopub.status.idle":"2024-05-07T03:19:39.369791Z","shell.execute_reply.started":"2024-05-07T03:19:39.365113Z","shell.execute_reply":"2024-05-07T03:19:39.368721Z"},"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    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":"2024-05-07T03:19:41.904842Z","iopub.execute_input":"2024-05-07T03:19:41.905493Z","iopub.status.idle":"2024-05-07T03:19:41.914142Z","shell.execute_reply.started":"2024-05-07T03:19:41.905460Z","shell.execute_reply":"2024-05-07T03:19:41.913144Z"},"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":"2024-05-07T03:19:42.192994Z","iopub.execute_input":"2024-05-07T03:19:42.193390Z","iopub.status.idle":"2024-05-07T03:19:58.648372Z","shell.execute_reply.started":"2024-05-07T03:19:42.193358Z","shell.execute_reply":"2024-05-07T03:19:58.647389Z"},"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":"2024-05-07T03:19:58.649948Z","iopub.execute_input":"2024-05-07T03:19:58.650316Z","iopub.status.idle":"2024-05-07T03:19:58.737389Z","shell.execute_reply.started":"2024-05-07T03:19:58.650269Z","shell.execute_reply":"2024-05-07T03:19:58.735950Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering","metadata":{}},{"cell_type":"code","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. \n# 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)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:19:58.738904Z","iopub.execute_input":"2024-05-07T03:19:58.739292Z","iopub.status.idle":"2024-05-07T03:19:59.622682Z","shell.execute_reply.started":"2024-05-07T03:19:58.739260Z","shell.execute_reply":"2024-05-07T03:19:59.621511Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 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\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":"2024-05-07T03:19:59.625445Z","iopub.execute_input":"2024-05-07T03:19:59.625756Z","iopub.status.idle":"2024-05-07T03:20:00.693255Z","shell.execute_reply.started":"2024-05-07T03:19:59.625731Z","shell.execute_reply":"2024-05-07T03:20:00.692393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_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\ntest_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\ntest_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\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":"2024-05-07T03:20:00.694504Z","iopub.execute_input":"2024-05-07T03:20:00.694861Z","iopub.status.idle":"2024-05-07T03:20:01.726851Z","shell.execute_reply.started":"2024-05-07T03:20:00.694829Z","shell.execute_reply":"2024-05-07T03:20:01.725917Z"},"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\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)","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:20:01.728057Z","iopub.execute_input":"2024-05-07T03:20:01.728372Z","iopub.status.idle":"2024-05-07T03:20:01.905071Z","shell.execute_reply.started":"2024-05-07T03:20:01.728346Z","shell.execute_reply":"2024-05-07T03:20:01.904008Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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":"2024-05-07T03:20:01.906383Z","iopub.execute_input":"2024-05-07T03:20:01.906692Z","iopub.status.idle":"2024-05-07T03:20:09.715124Z","shell.execute_reply.started":"2024-05-07T03:20:01.906664Z","shell.execute_reply":"2024-05-07T03:20:09.714223Z"},"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":"2024-05-07T03:20:09.716583Z","iopub.execute_input":"2024-05-07T03:20:09.716977Z","iopub.status.idle":"2024-05-07T03:20:09.722758Z","shell.execute_reply.started":"2024-05-07T03:20:09.716939Z","shell.execute_reply":"2024-05-07T03:20:09.721760Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import lightgbm as lgb\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.metrics import roc_auc_score\n\n\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 5,\n    \"num_leaves\": 50, \n    \"learning_rate\": 0.01,\n    \"feature_fraction\": 0.8,\n    \"bagging_fraction\": 0.8,\n    \"bagging_freq\": 5,\n    \"n_estimators\": 3000,\n    \"verbose\": -1,\n    'device':'gpu'\n}\n\nn_splits = 5\nskf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)\n\nlgb_models = []\n\nfor train_index, valid_index in skf.split(X_train, y_train):\n    X_train_fold, X_valid_fold = X_train.iloc[train_index], X_train.iloc[valid_index]\n    y_train_fold, y_valid_fold = y_train.iloc[train_index], y_train.iloc[valid_index]\n\n    lgb_train = lgb.Dataset(X_train_fold, label=y_train_fold)\n    lgb_valid = lgb.Dataset(X_valid_fold, label=y_valid_fold, reference=lgb_train)\n\n    gbm = lgb.train(params, lgb_train, valid_sets=[lgb_valid],callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)])\n\n    lgb_models.append(gbm)\n\nlgb_models","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:20:09.724171Z","iopub.execute_input":"2024-05-07T03:20:09.724559Z","iopub.status.idle":"2024-05-07T03:33:22.701978Z","shell.execute_reply.started":"2024-05-07T03:20:09.724532Z","shell.execute_reply":"2024-05-07T03:33:22.701095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# %% [code] {\"papermill\":{\"duration\":2476.526221,\"end_time\":\"2024-02-06T08:14:50.939246\",\"exception\":false,\"start_time\":\"2024-02-06T07:33:34.413025\",\"status\":\"completed\"},\"tags\":[],\"execution\":{\"iopub.status.busy\":\"2024-02-07T01:17:46.753592Z\",\"iopub.execute_input\":\"2024-02-07T01:17:46.754472Z\",\"iopub.status.idle\":\"2024-02-07T01:17:52.237159Z\",\"shell.execute_reply.started\":\"2024-02-07T01:17:46.754414Z\",\"shell.execute_reply\":\"2024-02-07T01:17:52.236102Z\"}}\nimport xgboost as xgb\n\nxgb_model = xgb.XGBClassifier(\n    device=\"cuda\",\n    objective='binary:logistic',\n    tree_method=\"hist\",\n    enable_categorical=True,\n    eval_metric='auc',\n    subsample=1,\n    colsample_bytree=1,\n    min_child_weight=1,\n    max_depth=20,\n    #gamma=0.7,\n    #reg_alpha=0.7,\n    n_estimators=1200,\n    random_state=42,\n)\n\n# Training the model on the training data\nxgb_model.fit(\n    X_train, y_train,\n    eval_set=[(X_valid, y_valid)],\n    early_stopping_rounds=100,\n    verbose=True,\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:33:35.324765Z","iopub.execute_input":"2024-05-07T03:33:35.325385Z","iopub.status.idle":"2024-05-07T03:34:23.610631Z","shell.execute_reply.started":"2024-05-07T03:33:35.325331Z","shell.execute_reply":"2024-05-07T03:34:23.609704Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# %% [code] {\"papermill\":{\"duration\":2283.103416,\"end_time\":\"2024-02-06T08:52:54.076015\",\"exception\":false,\"start_time\":\"2024-02-06T08:14:50.972599\",\"status\":\"completed\"},\"tags\":[],\"execution\":{\"iopub.status.busy\":\"2024-02-07T01:17:52.238383Z\",\"iopub.execute_input\":\"2024-02-07T01:17:52.239026Z\",\"iopub.status.idle\":\"2024-02-07T01:18:30.093513Z\",\"shell.execute_reply.started\":\"2024-02-07T01:17:52.238991Z\",\"shell.execute_reply\":\"2024-02-07T01:18:30.092424Z\"}}\nimport pandas as pd\nfrom catboost import CatBoostClassifier\n\n# 找出分类特征\ncat_features = [col for col in X_train.columns if X_train[col].dtype.name == 'category' or X_train[col].dtype.name == 'object']\n\n# 为每个分类特征添加新类别 'Missing' 并替换 NaN 值\nfor col in cat_features:\n    X_train[col] = X_train[col].cat.add_categories('Missing').fillna('Missing')\n    X_valid[col] = X_valid[col].cat.add_categories('Missing').fillna('Missing')\n\ncat_model = CatBoostClassifier(\n    iterations=1200,                 \n    depth=12,                        \n    learning_rate=0.1,               \n    eval_metric='AUC',               \n    random_seed=42,                  \n    bootstrap_type='Bayesian',       \n    bagging_temperature=1,           \n    od_type='Iter',                  \n    od_wait=50,\n    task_type='GPU'\n)\n\n# 训练模型\ncat_model.fit(\n    X_train, y_train,\n    eval_set=(X_valid, y_valid),\n    cat_features=cat_features,  # 明确指定了分类特征\n    use_best_model=True,\n    verbose=True\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:34:29.494701Z","iopub.execute_input":"2024-05-07T03:34:29.495082Z","iopub.status.idle":"2024-05-07T03:37:51.738570Z","shell.execute_reply.started":"2024-05-07T03:34:29.495050Z","shell.execute_reply":"2024-05-07T03:37:51.737429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# %% [code] {\"papermill\":{\"duration\":0.204329,\"end_time\":\"2024-02-06T08:52:54.873928\",\"exception\":false,\"start_time\":\"2024-02-06T08:52:54.669599\",\"status\":\"completed\"},\"tags\":[],\"execution\":{\"iopub.status.busy\":\"2024-02-07T01:18:30.115381Z\",\"iopub.execute_input\":\"2024-02-07T01:18:30.115943Z\",\"iopub.status.idle\":\"2024-02-07T01:18:30.346644Z\",\"shell.execute_reply.started\":\"2024-02-07T01:18:30.115918Z\",\"shell.execute_reply\":\"2024-02-07T01:18:30.344387Z\"}}\nX_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\nX_submission_processed = X_submission.copy()\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\nfor col in cat_features:\n    X_submission_processed[col] = X_submission_processed[col].cat.add_categories('Missing').fillna('Missing')\n\n#Make prediction\ndef predict_with_fold_models(models, X):\n    predictions = [model.predict(X, num_iteration=model.best_iteration) for model in models]\n    return np.mean(predictions, axis=0)\n\nlgb_pred = predict_with_fold_models(lgb_models, X_submission) \n\nxgb_pred = xgb_model.predict(X_submission)\n\ncat_pred = cat_model.predict(X_submission_processed)\n\nweight_lgb = 0.5\nweight_xgb = 0.25 \nweight_cat = 0.25\n\nassert weight_lgb + weight_xgb + weight_cat == 1, \"The sum of weights must be 1.\"\n\ny_submission_pred = (weight_lgb * lgb_pred) + (weight_xgb * xgb_pred) + (weight_cat * cat_pred)\n\n# %% [code] {\"papermill\":{\"duration\":0.089784,\"end_time\":\"2024-02-06T08:52:55.026753\",\"exception\":false,\"start_time\":\"2024-02-06T08:52:54.936969\",\"status\":\"completed\"},\"tags\":[],\"execution\":{\"iopub.status.busy\":\"2024-02-07T01:18:30.34765Z\",\"iopub.execute_input\":\"2024-02-07T01:18:30.348282Z\",\"iopub.status.idle\":\"2024-02-07T01:18:30.357145Z\",\"shell.execute_reply.started\":\"2024-02-07T01:18:30.348256Z\",\"shell.execute_reply\":\"2024-02-07T01:18:30.356183Z\"}}\nsubmission = 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\")\n\n# %% [code] {\"papermill\":{\"duration\":0.086803,\"end_time\":\"2024-02-06T08:52:55.176296\",\"exception\":false,\"start_time\":\"2024-02-06T08:52:55.089493\",\"status\":\"completed\"},\"tags\":[],\"execution\":{\"iopub.status.busy\":\"2024-02-07T01:18:30.358299Z\",\"iopub.execute_input\":\"2024-02-07T01:18:30.358582Z\",\"iopub.status.idle\":\"2024-02-07T01:18:30.372662Z\",\"shell.execute_reply.started\":\"2024-02-07T01:18:30.358559Z\",\"shell.execute_reply\":\"2024-02-07T01:18:30.371674Z\"}}\nsubmission","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:46:57.580469Z","iopub.execute_input":"2024-05-07T03:46:57.580896Z","iopub.status.idle":"2024-05-07T03:46:57.820650Z","shell.execute_reply.started":"2024-05-07T03:46:57.580865Z","shell.execute_reply":"2024-05-07T03:46:57.819617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# from sklearn.metrics import roc_auc_score\n\n# for model, name in [(lgb_models[-1], \"lgb\"), (xgb_model, \"xgb\")]:\n#     for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n#         y_pred = model.predict(X, num_iteration=model.best_iteration) if name == \"lgb\" else model.predict(X)\n#         base[f\"{name}_score\"] = y_pred\n        \n# for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n#     X_processed = X.copy()\n#     cat_features = [col for col in X_processed.columns if X_processed[col].dtype.name == 'category' or X_processed[col].dtype.name == 'object']\n#     for col in cat_features:\n#         X_processed[col] = X_processed[col].cat.add_categories('Missing').fillna('Missing')\n\n#     y_pred = cat_model.predict(X_processed)\n#     base[\"cat_score\"] = y_pred\n\n# for base in [base_train, base_valid, base_test]:\n#     base['combined_score'] = base[['lgb_score', 'xgb_score', 'cat_score']].mean(axis=1)\n#     print(f'The AUC score of combined models on the {base.name} set is: {roc_auc_score(base[\"target\"], base[\"combined_score\"])}')\n    \n# 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\n# model_names = [\"lgb\", \"xgb\", \"cat\", \"combined\"]\n# for model_name in model_names:\n#     score_column = f\"{model_name}_score\" if model_name != \"combined\" else \"combined_score\"\n#     stability_score_train = gini_stability(base_train, score_column)\n#     stability_score_valid = gini_stability(base_valid, score_column)\n#     stability_score_test = gini_stability(base_test, score_column)\n\n#     print(f'The stability score of {model_name} on the train set is: {stability_score_train}') \n#     print(f'The stability score of {model_name} on the valid set is: {stability_score_valid}') \n#     print(f'The stability score of {model_name} on the test set is: {stability_score_test}')","metadata":{"execution":{"iopub.status.busy":"2024-05-07T03:42:36.583707Z","iopub.execute_input":"2024-05-07T03:42:36.584467Z","iopub.status.idle":"2024-05-07T03:44:32.278774Z","shell.execute_reply.started":"2024-05-07T03:42:36.584431Z","shell.execute_reply":"2024-05-07T03:44:32.277409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}