{"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"kernelspec":{"display_name":"Python 3 (ipykernel)","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.8.10"},"papermill":{"default_parameters":{},"duration":1221.035913,"end_time":"2024-03-11T20:40:31.474791","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-03-11T20:20:10.438878","version":"2.5.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Note: I'm looking for a job in Europe, if you like my work don't hesitate to reach =)\n\nimport os\nimport gc\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\n\nfrom datetime import datetime\n\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, ClassifierMixin\n\nimport lightgbm as lgb\n\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2024-03-11T20:20:13.177936Z","iopub.status.busy":"2024-03-11T20:20:13.177674Z","iopub.status.idle":"2024-03-11T20:20:19.340830Z","shell.execute_reply":"2024-03-11T20:20:19.340062Z"},"papermill":{"duration":6.175783,"end_time":"2024-03-11T20:20:19.343026","exception":false,"start_time":"2024-03-11T20:20:13.167243","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pre-Fitted Voting Model","metadata":{"papermill":{"duration":0.008777,"end_time":"2024-03-11T20:20:19.361579","exception":false,"start_time":"2024-03-11T20:20:19.352802","status":"completed"},"tags":[]}},{"cell_type":"code","source":"class VotingModel(BaseEstimator, ClassifierMixin):\n    def __init__(self, estimators):\n        super().__init__()\n        self.estimators = estimators\n        \n    def fit(self, X, y=None):\n        return self\n    \n    def predict(self, X):\n        y_preds = [estimator.predict(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)\n    \n    def predict_proba(self, X):\n        y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.381759Z","iopub.status.busy":"2024-03-11T20:20:19.381081Z","iopub.status.idle":"2024-03-11T20:20:19.387550Z","shell.execute_reply":"2024-03-11T20:20:19.386761Z"},"papermill":{"duration":0.018278,"end_time":"2024-03-11T20:20:19.389382","exception":false,"start_time":"2024-03-11T20:20:19.371104","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pipeline","metadata":{"papermill":{"duration":0.008615,"end_time":"2024-03-11T20:20:19.406942","exception":false,"start_time":"2024-03-11T20:20:19.398327","status":"completed"},"tags":[]}},{"cell_type":"code","source":"some_date = datetime(2024, 3, 16)\n\nclass Pipeline:\n    @staticmethod\n    def set_table_dtypes(df):\n        for col in df.columns:\n            if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Int32))\n            elif col in [\"date_decision\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n            elif col[-1] in (\"P\", \"A\"):\n                df = df.with_columns(pl.col(col).cast(pl.Float64))\n            elif col[-1] in (\"M\",):\n                df = df.with_columns(pl.col(col).cast(pl.String))\n            elif col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col).cast(pl.Date))            \n\n        return df\n    \n    @staticmethod\n    def handle_dates1(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",):\n                df = df.with_columns((pl.col(col) - some_date).alias(col))\n                \n        df = df.drop(\"date_decision\", \"MONTH\")\n\n        return df\n    \n    @staticmethod\n    def handle_dates2(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",) or col[-2:] in (\"D#\",):\n                df = df.with_columns(pl.col(col) + (some_date - pl.col(\"date_decision\")))\n                df = df.with_columns(pl.col(col).dt.total_days())\n                df = df.with_columns(pl.col(col).cast(pl.Float32))\n                \n        df = df.drop(\"date_decision\", \"MONTH\")\n\n        return df\n    \n    @staticmethod\n    def filter_cols(df):\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n\n                if isnull > 0.95:\n                    df = df.drop(col)\n\n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n\n        return df","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.425745Z","iopub.status.busy":"2024-03-11T20:20:19.425481Z","iopub.status.idle":"2024-03-11T20:20:19.437672Z","shell.execute_reply":"2024-03-11T20:20:19.436838Z"},"papermill":{"duration":0.023479,"end_time":"2024-03-11T20:20:19.439407","exception":false,"start_time":"2024-03-11T20:20:19.415928","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Automatic Aggregation","metadata":{"papermill":{"duration":0.008664,"end_time":"2024-03-11T20:20:19.457100","exception":false,"start_time":"2024-03-11T20:20:19.448436","status":"completed"},"tags":[]}},{"cell_type":"code","source":"class Aggregator:\n    @staticmethod\n    def num_expr(df, agg):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n\n        expr_max = [agg(col).alias(f\"{agg.__name__}_{col}#\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def date_expr(df, agg):\n        cols = [col for col in df.columns if col[-1] in (\"D\",)]\n\n        expr_max = [agg(col).alias(f\"{agg.__name__}_{col}#\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def str_expr(df, agg):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        \n        expr_max = [agg(col).alias(f\"{agg.__name__}_{col}#\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def other_expr(df, agg):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        \n        expr_max = [agg(col).alias(f\"{agg.__name__}_{col}#\") for col in cols]\n\n        return expr_max\n    \n    @staticmethod\n    def count_expr(df, agg):\n        cols = [col for col in df.columns if \"num_group\" in col]\n\n        expr_max = [agg(col).alias(f\"{agg.__name__}_{col}#\") for col in cols]\n\n        return expr_max\n\n    @staticmethod\n    def get_exprs(df, agg):\n        exprs = Aggregator.num_expr(df, agg) + \\\n                Aggregator.date_expr(df, agg) + \\\n                Aggregator.other_expr(df, agg) + \\\n                Aggregator.count_expr(df, agg)\n        #                 Aggregator.str_expr(df, agg) + \\\n\n        return exprs","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.476571Z","iopub.status.busy":"2024-03-11T20:20:19.476292Z","iopub.status.idle":"2024-03-11T20:20:19.486434Z","shell.execute_reply":"2024-03-11T20:20:19.485637Z"},"papermill":{"duration":0.021569,"end_time":"2024-03-11T20:20:19.488325","exception":false,"start_time":"2024-03-11T20:20:19.466756","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### File I/O","metadata":{"papermill":{"duration":0.009719,"end_time":"2024-03-11T20:20:19.506836","exception":false,"start_time":"2024-03-11T20:20:19.497117","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def read_file(path, is_train, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth is not None:\n        df = df.pipe(Pipeline.handle_dates1)\n    \n    if depth in [1, 2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df, pl.max) + Aggregator.get_exprs(df, pl.min) + \\\n                               Aggregator.get_exprs(df, pl.mean) + Aggregator.get_exprs(df, pl.median))\n    if is_train:\n        df = df.pipe(Pipeline.filter_cols)\n    return df\n\ndef read_files(regex_path, is_train, depth=None):\n    chunks = []\n    for path in glob(str(regex_path)):\n        df = read_file(path, False, depth)\n#         print(df.shape)\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    if is_train:\n        df = df.pipe(Pipeline.filter_cols)\n\n    return df","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.525391Z","iopub.status.busy":"2024-03-11T20:20:19.525145Z","iopub.status.idle":"2024-03-11T20:20:19.531829Z","shell.execute_reply":"2024-03-11T20:20:19.531102Z"},"papermill":{"duration":0.018108,"end_time":"2024-03-11T20:20:19.533703","exception":false,"start_time":"2024-03-11T20:20:19.515595","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Engineering","metadata":{"papermill":{"duration":0.00854,"end_time":"2024-03-11T20:20:19.550995","exception":false,"start_time":"2024-03-11T20:20:19.542455","status":"completed"},"tags":[]}},{"cell_type":"code","source":"def feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n        \n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n        \n    df_base = df_base.pipe(Pipeline.handle_dates2)\n    \n    return df_base","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.570143Z","iopub.status.busy":"2024-03-11T20:20:19.569547Z","iopub.status.idle":"2024-03-11T20:20:19.574976Z","shell.execute_reply":"2024-03-11T20:20:19.574273Z"},"papermill":{"duration":0.01688,"end_time":"2024-03-11T20:20:19.576796","exception":false,"start_time":"2024-03-11T20:20:19.559916","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    \n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    \n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    \n    return df_data, cat_cols","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.595389Z","iopub.status.busy":"2024-03-11T20:20:19.595137Z","iopub.status.idle":"2024-03-11T20:20:19.599640Z","shell.execute_reply":"2024-03-11T20:20:19.598867Z"},"papermill":{"duration":0.015752,"end_time":"2024-03-11T20:20:19.601370","exception":false,"start_time":"2024-03-11T20:20:19.585618","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Configuration","metadata":{"papermill":{"duration":0.00861,"end_time":"2024-03-11T20:20:19.619092","exception":false,"start_time":"2024-03-11T20:20:19.610482","status":"completed"},"tags":[]}},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n# ROOT = Path(\".\")\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.637746Z","iopub.status.busy":"2024-03-11T20:20:19.637467Z","iopub.status.idle":"2024-03-11T20:20:19.641419Z","shell.execute_reply":"2024-03-11T20:20:19.640728Z"},"papermill":{"duration":0.015255,"end_time":"2024-03-11T20:20:19.643247","exception":false,"start_time":"2024-03-11T20:20:19.627992","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Train Files Read & Feature Engineering","metadata":{"papermill":{"duration":0.008715,"end_time":"2024-03-11T20:20:19.660605","exception":false,"start_time":"2024-03-11T20:20:19.651890","status":"completed"},"tags":[]}},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\", True),\n    \"depth_0\": [\n        read_file(TRAIN_DIR / \"train_static_cb_0.parquet\", True, 0),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\", True, 0),\n    ],\n    \"depth_1\": [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", True, 1),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_1_*.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", True, 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", True, 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", True, 2),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", True, 2),\n    ]\n}","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:20:19.678920Z","iopub.status.busy":"2024-03-11T20:20:19.678686Z","iopub.status.idle":"2024-03-11T20:22:26.542632Z","shell.execute_reply":"2024-03-11T20:22:26.541531Z"},"papermill":{"duration":126.876005,"end_time":"2024-03-11T20:22:26.545249","exception":false,"start_time":"2024-03-11T20:20:19.669244","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\n\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:22:26.565337Z","iopub.status.busy":"2024-03-11T20:22:26.564999Z","iopub.status.idle":"2024-03-11T20:22:38.552398Z","shell.execute_reply":"2024-03-11T20:22:38.551267Z"},"papermill":{"duration":11.999532,"end_time":"2024-03-11T20:22:38.554478","exception":false,"start_time":"2024-03-11T20:22:26.554946","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\n\ngc.collect()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Files Read & Feature Engineering","metadata":{"papermill":{"duration":0.009104,"end_time":"2024-03-11T20:22:38.572989","exception":false,"start_time":"2024-03-11T20:22:38.563885","status":"completed"},"tags":[]}},{"cell_type":"code","source":"# data_store = {\n#     \"df_base\": read_file(TEST_DIR / \"test_base.parquet\", False,),\n#     \"depth_0\": [\n#         read_file(TEST_DIR / \"test_static_cb_0.parquet\", False, 0),\n#         read_files(TEST_DIR / \"test_static_0_*.parquet\", False, 0),\n#     ],\n#     \"depth_1\": [\n#         read_files(TEST_DIR / \"test_applprev_1_*.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", False, 1),\n#         read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_other_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_person_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_deposit_1.parquet\", False, 1),\n#         read_file(TEST_DIR / \"test_debitcard_1.parquet\", False, 1),\n#     ],\n#     \"depth_2\": [\n#         read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", False, 2),\n#         read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", False, 2),\n#     ]\n# }","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:22:38.592481Z","iopub.status.busy":"2024-03-11T20:22:38.591784Z","iopub.status.idle":"2024-03-11T20:22:39.168839Z","shell.execute_reply":"2024-03-11T20:22:39.167993Z"},"papermill":{"duration":0.589237,"end_time":"2024-03-11T20:22:39.171145","exception":false,"start_time":"2024-03-11T20:22:38.581908","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_test = feature_eng(**data_store)\n\n# print(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:22:39.190830Z","iopub.status.busy":"2024-03-11T20:22:39.190540Z","iopub.status.idle":"2024-03-11T20:22:39.230327Z","shell.execute_reply":"2024-03-11T20:22:39.229525Z"},"papermill":{"duration":0.051709,"end_time":"2024-03-11T20:22:39.232155","exception":false,"start_time":"2024-03-11T20:22:39.180446","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Elimination","metadata":{"papermill":{"duration":0.008776,"end_time":"2024-03-11T20:22:39.250093","exception":false,"start_time":"2024-03-11T20:22:39.241317","status":"completed"},"tags":[]}},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.filter_cols)\ndf_train_columns = df_train.columns\n# df_test = df_test.select([col for col in df_train.columns if col != \"target\"])\n\nprint(\"train data shape:\\t\", df_train.shape)\n# print(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:22:39.269947Z","iopub.status.busy":"2024-03-11T20:22:39.269394Z","iopub.status.idle":"2024-03-11T20:22:42.015546Z","shell.execute_reply":"2024-03-11T20:22:42.014587Z"},"papermill":{"duration":2.758307,"end_time":"2024-03-11T20:22:42.017667","exception":false,"start_time":"2024-03-11T20:22:39.259360","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Pandas Conversion","metadata":{"papermill":{"duration":0.009039,"end_time":"2024-03-11T20:22:42.036115","exception":false,"start_time":"2024-03-11T20:22:42.027076","status":"completed"},"tags":[]}},{"cell_type":"code","source":"df_train, cat_cols = to_pandas(df_train)\n# df_test, cat_cols = to_pandas(df_test, cat_cols)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:22:42.057274Z","iopub.status.busy":"2024-03-11T20:22:42.056714Z","iopub.status.idle":"2024-03-11T20:23:00.747089Z","shell.execute_reply":"2024-03-11T20:23:00.746301Z"},"papermill":{"duration":18.703961,"end_time":"2024-03-11T20:23:00.749238","exception":false,"start_time":"2024-03-11T20:22:42.045277","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### EDA","metadata":{"papermill":{"duration":0.009084,"end_time":"2024-03-11T20:23:00.932380","exception":false,"start_time":"2024-03-11T20:23:00.923296","status":"completed"},"tags":[]}},{"cell_type":"code","source":"print(\"Train is duplicated:\\t\", df_train[\"case_id\"].duplicated().any())\nprint(\"Train Week Range:\\t\", (df_train[\"WEEK_NUM\"].min(), df_train[\"WEEK_NUM\"].max()))\n\n# print()\n\n# print(\"Test is duplicated:\\t\", df_test[\"case_id\"].duplicated().any())\n# print(\"Test Week Range:\\t\", (df_test[\"WEEK_NUM\"].min(), df_test[\"WEEK_NUM\"].max()))","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:23:00.952356Z","iopub.status.busy":"2024-03-11T20:23:00.951810Z","iopub.status.idle":"2024-03-11T20:23:00.978038Z","shell.execute_reply":"2024-03-11T20:23:00.977167Z"},"papermill":{"duration":0.038139,"end_time":"2024-03-11T20:23:00.979829","exception":false,"start_time":"2024-03-11T20:23:00.941690","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Training","metadata":{"papermill":{"duration":0.01291,"end_time":"2024-03-11T20:23:17.567408","exception":false,"start_time":"2024-03-11T20:23:17.554498","status":"completed"},"tags":[]}},{"cell_type":"code","source":"best_features = ['annuity_780A',\n 'price_1097A',\n 'pmtnum_254L',\n 'pmtssum_45A',\n 'max_birth_259D#',\n 'max_numberofoverdueinstlmaxdat_148D#',\n 'validfrom_1069D',\n 'dateofbirth_337D',\n 'max_amount_4527230A#',\n 'lastrejectdate_50D',\n 'lastcancelreason_561M',\n 'min_refreshdate_3813885D#',\n 'min_dateofcredstart_739D#',\n 'credamount_770A',\n 'lastdelinqdate_224D',\n 'median_dateofcredstart_739D#',\n 'eir_270L',\n 'max_overdueamountmax2date_1002D#',\n 'max_employedfrom_700D#',\n 'inittransactionamount_650A',\n 'mobilephncnt_593L',\n 'max_dateofcredstart_739D#',\n 'mean_dateofcredstart_739D#',\n 'max_num_group1#_3',\n 'mean_amount_4527230A#',\n 'median_refreshdate_3813885D#',\n 'max_empl_employedfrom_271D#',\n 'mean_pmtnum_8L#',\n 'disbursedcredamount_1113A',\n 'lastrejectcredamount_222A',\n 'maxdpdinstldate_3546855D',\n 'max_mainoccupationinc_384A#',\n 'max_dtlastpmt_581D#',\n 'max_overdueamountmax2date_1142D#',\n 'max_totalamount_6A#',\n 'min_totalamount_6A#',\n 'min_amount_4527230A#',\n 'median_mainoccupationinc_437A#',\n 'datelastinstal40dpd_247D',\n 'mean_refreshdate_3813885D#',\n 'max_dateofrealrepmt_138D#',\n 'median_totalamount_6A#',\n 'min_mainoccupationinc_437A#',\n 'lastapprcommoditycat_1041M',\n 'mean_mainoccupationinc_437A#',\n 'min_employedfrom_700D#',\n 'max_dateofcredend_289D#',\n 'min_dateofcredend_289D#',\n 'pmtaverage_3A',\n 'birthdate_574D',\n 'max_firstnonzeroinstldate_307D#',\n 'max_dtlastpmtallstes_3545839D#',\n 'max_dateofcredend_353D#',\n 'days360_512L',\n 'maxdbddpdlast1m_3658939P',\n 'maxannuity_159A',\n 'mean_totalamount_6A#',\n 'pctinstlsallpaidearl3d_427L',\n 'median_credamount_590A#',\n 'cntpmts24_3658933L',\n 'max_annuity_853A#',\n 'max_incometype_1044T#',\n 'pmtaverage_4527227A',\n 'firstclxcampaign_1125D',\n 'applicationscnt_867L',\n 'maxdbddpdtollast12m_3658940P',\n 'mean_annuity_853A#',\n 'max_numberofoverdueinstlmaxdat_641D#',\n 'mean_credamount_590A#',\n 'median_residualamount_856A#',\n 'datelastunpaid_3546854D',\n 'mindbddpdlast24m_3658935P',\n 'mean_num_group2#_13',\n 'max_sex_738L#',\n 'median_amount_4527230A#',\n 'datefirstoffer_1144D',\n 'mean_pmts_dpd_1073P#',\n 'mean_employedfrom_700D#',\n 'maininc_215A',\n 'min_totaloutstanddebtvalue_39A#',\n 'pctinstlsallpaidlate1d_3546856L',\n 'maxinstallast24m_3658928A',\n 'max_dateofcredstart_181D#',\n 'median_annuity_853A#',\n 'max_lastupdate_388D#',\n 'min_pmtamount_36A#',\n 'mean_overdueamountmaxdatemonth_284T#',\n 'min_credamount_590A#',\n 'max_residualamount_856A#',\n 'lastrejectcommoditycat_161M',\n 'numincomingpmts_3546848L',\n 'median_monthlyinstlamount_674A#',\n 'median_employedfrom_700D#',\n 'numinstlswithdpd10_728L',\n 'mean_dpdmaxdatemonth_442T#',\n 'mean_monthlyinstlamount_674A#',\n 'max_monthlyinstlamount_674A#',\n 'max_mainoccupationinc_437A#',\n 'min_annuity_853A#',\n 'min_amount_4917619A#',\n 'min_dateofcredstart_181D#',\n 'max_monthlyinstlamount_332A#',\n 'min_residualamount_856A#',\n 'dtlastpmtallstes_4499206D',\n 'avgdbddpdlast3m_4187120P',\n 'mean_residualamount_856A#',\n 'max_credamount_590A#',\n 'days180_256L',\n 'max_totalamount_996A#',\n 'mean_outstandingdebt_522A#',\n 'min_numberofoverdueinstlmaxdat_148D#',\n 'min_overdueamountmax2date_1002D#',\n 'avgdbddpdlast24m_3658932P',\n 'amtinstpaidbefduel24m_4187115A',\n 'maxdpdinstlnum_3546846P',\n 'max_numberofoverdueinstlmax_1039L#',\n 'mean_pmts_dpd_303P#',\n 'min_birth_259D#',\n 'min_annualeffectiverate_199L#',\n 'median_numberofoverdueinstlmaxdat_148D#',\n 'min_outstandingamount_362A#',\n 'max_numberofoutstandinstls_59L#',\n 'median_overdueamountmax2date_1002D#',\n 'min_relationshiptoclient_415T#',\n 'min_monthlyinstlamount_332A#',\n 'avglnamtstart24m_4525187A',\n 'cntincpaycont9m_3716944L',\n 'median_firstnonzeroinstldate_307D#',\n 'mean_numberofinstls_229L#',\n 'max_instlamount_768A#',\n 'mean_pmts_overdue_1152A#',\n 'weekday_decision',\n 'lastapprcredamount_781A',\n 'max_lastupdate_1112D#',\n 'mean_dateofcredend_289D#',\n 'min_dtlastpmt_581D#',\n 'median_processingdate_168D#',\n 'min_totalamount_996A#',\n 'days120_123L',\n 'median_dateofcredend_289D#',\n 'max_pmtamount_36A#',\n 'mean_numberofoverdueinstlmaxdat_148D#',\n 'mean_monthlyinstlamount_332A#',\n 'median_pmtamount_36A#',\n 'mean_nominalrate_498L#',\n 'lastapplicationdate_877D',\n 'min_familystate_726L#',\n 'max_relationshiptoclient_415T#',\n 'min_numberofoverdueinstlmaxdat_641D#',\n 'median_lastupdate_388D#',\n 'days90_310L',\n 'max_credlmt_935A#',\n 'maxoutstandbalancel12m_4187113A',\n 'median_dtlastpmtallstes_3545839D#',\n 'median_dateofcredstart_181D#',\n 'max_amount_4917619A#',\n 'avgdpdtolclosure24_3658938P',\n 'median_creationdate_885D#',\n 'pmtscount_423L',\n 'days30_165L',\n 'mean_overdueamountmax2date_1002D#',\n 'mean_numberofoverdueinstlmax_1039L#',\n 'avginstallast24m_3658937A',\n 'max_processingdate_168D#',\n 'mean_pmts_overdue_1140A#',\n 'median_numberofoverdueinstlmax_1039L#',\n 'mean_maxdpdtolerance_577P#',\n 'max_numberofinstls_229L#',\n 'min_numberofoutstandinstls_59L#',\n 'max_credlmt_230A#',\n 'median_monthlyinstlamount_332A#',\n 'pctinstlsallpaidlat10d_839L',\n 'maxdebt4_972A',\n 'median_overdueamountmax2date_1142D#',\n 'totalsettled_863A',\n 'maxlnamtstart6m_4525199A',\n 'min_overdueamountmax2date_1142D#',\n 'clientscnt_887L',\n 'monthsannuity_845L',\n 'min_nominalrate_498L#',\n 'max_numberofoverdueinstlmax_1151L#',\n 'avgpmtlast12m_4525200A',\n 'median_nominalrate_498L#',\n 'min_pmtnum_8L#',\n 'avgoutstandbalancel6m_4187114A',\n 'median_dateofcredend_353D#',\n 'median_dpdmax_757P#',\n 'totinstallast1m_4525188A',\n 'min_numberofinstls_320L#',\n 'median_dateofrealrepmt_138D#',\n 'min_creationdate_885D#',\n 'isbidproduct_1095L',\n 'mean_firstnonzeroinstldate_307D#',\n 'numinstpaidlate1d_3546852L',\n 'min_dtlastpmtallstes_3545839D#',\n 'downpmt_116A',\n 'mean_numberofoverdueinstlmax_1151L#',\n 'mean_dateofcredstart_181D#',\n 'min_firstnonzeroinstldate_307D#',\n 'mean_overdueamountmaxdatemonth_365T#',\n 'mean_num_group1#_13',\n 'max_overdueamountmax_35A#',\n 'max_empl_industry_691L#',\n 'max_familystate_447L#',\n 'mean_numberofoutstandinstls_59L#',\n 'numrejects9m_859L',\n 'mean_pmtamount_36A#',\n 'median_numberofoutstandinstls_59L#',\n 'min_lastupdate_1112D#',\n 'min_numberofinstls_229L#',\n 'median_numberofinstls_229L#',\n 'median_lastupdate_1112D#',\n 'max_nominalrate_281L#',\n 'mean_totalamount_996A#',\n 'mean_childnum_21L#',\n 'mean_overdueamountmax_35A#',\n 'min_processingdate_168D#',\n 'min_lastupdate_388D#',\n 'numinstpaidlastcontr_4325080L',\n 'numinsttopaygr_769L',\n 'mindbdtollast24m_4525191P',\n 'median_pmtnum_8L#',\n 'month_decision',\n 'avgdbdtollast24m_4525197P',\n 'avgmaxdpdlast9m_3716943P',\n 'numinstunpaidmax_3546851L',\n 'median_dtlastpmt_581D#',\n 'max_pmtnum_8L#',\n 'max_annualeffectiverate_63L#',\n 'mean_dpdmaxdatemonth_89T#',\n 'median_totalamount_996A#',\n 'maxdbddpdtollast6m_4187119P',\n 'daysoverduetolerancedd_3976961L',\n 'interestrate_311L',\n 'min_annualeffectiverate_63L#',\n 'max_overdueamountmax2_398A#',\n 'secondquarter_766L',\n 'maxdpdlast24m_143P',\n 'mean_overdueamountmax2_398A#',\n 'min_credlmt_935A#',\n 'maxpmtlast3m_4525190A',\n 'mean_byoccupationinc_3656910L#',\n 'max_downpmt_134A#',\n 'mean_prolongationcount_1120L#',\n 'currdebt_22A',\n 'maxdpdlast3m_392P',\n 'max_numberofinstls_320L#',\n 'mean_lastupdate_1112D#',\n 'median_credlmt_230A#',\n 'median_numberofoverdueinstlmax_1151L#',\n 'maxdpdtolerance_374P',\n 'mean_dpdmaxdateyear_596T#',\n 'mean_credlmt_230A#',\n 'median_pmts_overdue_1152A#',\n 'mean_amount_4917619A#',\n 'lastactivateddate_801D',\n 'min_instlamount_768A#',\n 'min_monthlyinstlamount_674A#',\n 'responsedate_4527233D',\n 'median_numberofoverdueinstlmaxdat_641D#',\n 'mean_overdueamountmax2date_1142D#',\n 'mean_dpdmax_757P#',\n 'median_overdueamountmaxdatemonth_284T#',\n 'mean_dtlastpmtallstes_3545839D#',\n 'mean_downpmt_134A#',\n 'median_dpdmax_139P#',\n 'min_dateofcredend_353D#',\n 'lastapprdate_640D',\n 'median_deductiondate_4917603D#',\n 'mean_creationdate_885D#',\n 'max_outstandingamount_362A#',\n 'numinstlsallpaid_934L',\n 'mean_currdebt_94A#',\n 'max_numberofcontrsvalue_358L#',\n 'max_debtoutstand_525A#',\n 'mean_dtlastpmt_581D#',\n 'mean_processingdate_168D#',\n 'mean_dateofcredend_353D#',\n 'mean_tenor_203L#',\n 'max_overdueamountmax2_14A#',\n 'sellerplacescnt_216L',\n 'mean_pmts_year_1139T#',\n 'mean_num_group1#_3',\n 'min_dateofrealrepmt_138D#',\n 'maxdpdfrom6mto36m_3546853P',\n 'thirdquarter_1082L',\n 'median_dpdmaxdatemonth_442T#',\n 'min_credlmt_230A#',\n 'firstdatedue_489D',\n 'median_overdueamountmax2_398A#',\n 'firstquarter_103L',\n 'mean_lastupdate_388D#',\n 'max_dpdmax_757P#',\n 'mean_nominalrate_281L#',\n 'median_nominalrate_281L#',\n 'mean_dpdmaxdateyear_896T#',\n 'median_overdueamountmax_35A#',\n 'mean_instlamount_768A#',\n 'pctinstlsallpaidlate6d_3546844L',\n 'numinstlswithoutdpd_562L']","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = df_train[best_features]\ny = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\n\ndel df_train\n\ngc.collect()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cv = StratifiedGroupKFold(n_splits=10, shuffle=False)\n\nparams = {\n    'n_estimators': 5000,\n    'learning_rate': 0.02253760303697913,\n    'num_leaves': 860,\n    'max_depth': 7,\n    'min_data_in_leaf': 200,\n    'lambda_l1': 15,\n    'lambda_l2': 10,\n    'min_gain_to_split': 1.1140289769354332,\n    'bagging_fraction': 0.7,\n    'bagging_freq': 1,\n    'feature_fraction': 0.30000000000000004,\n    \"objective\": \"binary\",\n    \"boosting_type\": \"gbdt\",\n    \"verbose\": -1,\n    \"device\": \"gpu\",\n    \"metric\": \"auc\",\n}\n\nfitted_models = []\n\nfor idx_train, idx_valid in cv.split(X, y, groups=weeks):\n    X_train, y_train = X.iloc[idx_train], y.iloc[idx_train]\n    X_valid, y_valid = X.iloc[idx_valid], y.iloc[idx_valid]\n\n    model = lgb.LGBMClassifier(**params)\n    model.fit(\n        X_train, y_train,\n        eval_set=[(X_valid, y_valid)],\n        callbacks=[lgb.log_evaluation(100), lgb.early_stopping(100)]\n    )\n\n    fitted_models.append(model)\n\nmodel = VotingModel(fitted_models)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:23:17.595206Z","iopub.status.busy":"2024-03-11T20:23:17.594787Z","iopub.status.idle":"2024-03-11T20:40:29.888472Z","shell.execute_reply":"2024-03-11T20:40:29.887312Z"},"papermill":{"duration":1032.311042,"end_time":"2024-03-11T20:40:29.890585","exception":false,"start_time":"2024-03-11T20:23:17.579543","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del X\ndel y\ndel weeks\n\ngc.collect()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Prediction","metadata":{"papermill":{"duration":0.015335,"end_time":"2024-03-11T20:40:29.921663","exception":false,"start_time":"2024-03-11T20:40:29.906328","status":"completed"},"tags":[]}},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TEST_DIR / \"test_base.parquet\", False,),\n    \"depth_0\": [\n        read_file(TEST_DIR / \"test_static_cb_0.parquet\", False, 0),\n        read_files(TEST_DIR / \"test_static_0_*.parquet\", False, 0),\n    ],\n    \"depth_1\": [\n        read_files(TEST_DIR / \"test_applprev_1_*.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", False, 1),\n        read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_other_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_deposit_1.parquet\", False, 1),\n        read_file(TEST_DIR / \"test_debitcard_1.parquet\", False, 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", False, 2),\n        read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", False, 2),\n    ]\n}","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)\n\ndel data_store\ngc.collect()\n\ndf_test = df_test.select([col for col in df_train_columns if col != \"target\"])\nprint(\"test data shape:\\t\", df_test.shape)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\n\nprint(\"Test is duplicated:\\t\", df_test[\"case_id\"].duplicated().any())\nprint(\"Test Week Range:\\t\", (df_test[\"WEEK_NUM\"].min(), df_test[\"WEEK_NUM\"].max()))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = df_test[best_features + [\"case_id\"]]\nX_test = X_test.set_index(\"case_id\")\n\ny_pred = pd.Series(model.predict_proba(X_test)[:, 1], index=X_test.index)","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:40:29.953970Z","iopub.status.busy":"2024-03-11T20:40:29.953671Z","iopub.status.idle":"2024-03-11T20:40:30.231819Z","shell.execute_reply":"2024-03-11T20:40:30.230927Z"},"papermill":{"duration":0.29704,"end_time":"2024-03-11T20:40:30.234187","exception":false,"start_time":"2024-03-11T20:40:29.937147","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{"papermill":{"duration":0.015506,"end_time":"2024-03-11T20:40:30.266313","exception":false,"start_time":"2024-03-11T20:40:30.250807","status":"completed"},"tags":[]}},{"cell_type":"code","source":"df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:40:30.299204Z","iopub.status.busy":"2024-03-11T20:40:30.298476Z","iopub.status.idle":"2024-03-11T20:40:30.315227Z","shell.execute_reply":"2024-03-11T20:40:30.314249Z"},"papermill":{"duration":0.035461,"end_time":"2024-03-11T20:40:30.317145","exception":false,"start_time":"2024-03-11T20:40:30.281684","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())\n\ndf_subm.head()","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:40:30.349432Z","iopub.status.busy":"2024-03-11T20:40:30.349153Z","iopub.status.idle":"2024-03-11T20:40:30.362280Z","shell.execute_reply":"2024-03-11T20:40:30.361363Z"},"papermill":{"duration":0.031645,"end_time":"2024-03-11T20:40:30.364269","exception":false,"start_time":"2024-03-11T20:40:30.332624","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.execute_input":"2024-03-11T20:40:30.397489Z","iopub.status.busy":"2024-03-11T20:40:30.397241Z","iopub.status.idle":"2024-03-11T20:40:30.403177Z","shell.execute_reply":"2024-03-11T20:40:30.402519Z"},"papermill":{"duration":0.024175,"end_time":"2024-03-11T20:40:30.404950","exception":false,"start_time":"2024-03-11T20:40:30.380775","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.015608,"end_time":"2024-03-11T20:40:30.436155","exception":false,"start_time":"2024-03-11T20:40:30.420547","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]}]}