{"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":"nvidiaTeslaT4","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 os\nimport gc\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom glob import glob\nfrom pathlib import Path\nfrom datetime import datetime\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-10T14:55:58.416516Z","iopub.execute_input":"2024-05-10T14:55:58.417227Z","iopub.status.idle":"2024-05-10T14:56:04.002012Z","shell.execute_reply.started":"2024-05-10T14:55:58.417194Z","shell.execute_reply":"2024-05-10T14:56:04.000789Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class 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.Int64))\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        return df\n    @staticmethod\n    def handle_dates(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col) - pl.col(\"date_decision\"))\n                df = df.with_columns(pl.col(col).dt.total_days())\n        df = df.drop(\"date_decision\", \"MONTH\")\n        return df\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.status.busy":"2024-05-10T14:56:04.004510Z","iopub.execute_input":"2024-05-10T14:56:04.004902Z","iopub.status.idle":"2024-05-10T14:56:04.018865Z","shell.execute_reply.started":"2024-05-10T14:56:04.004868Z","shell.execute_reply":"2024-05-10T14:56:04.017747Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Aggregator:\n    @staticmethod\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        return expr_max\n    @staticmethod\n    def date_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"D\",)]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        return expr_max\n    @staticmethod\n    def str_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        return expr_max\n    @staticmethod\n    def other_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        return expr_max\n    @staticmethod\n    def count_expr(df):\n        cols = [col for col in df.columns if \"num_group\" in col]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        return expr_max\n    @staticmethod\n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.020397Z","iopub.execute_input":"2024-05-10T14:56:04.021031Z","iopub.status.idle":"2024-05-10T14:56:04.039410Z","shell.execute_reply.started":"2024-05-10T14:56:04.020985Z","shell.execute_reply":"2024-05-10T14:56:04.038228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1, 2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n    return df\ndef read_files(regex_path, depth=None):\n    chunks = []\n    for path in glob(str(regex_path)):\n        chunks.append(pl.read_parquet(path).pipe(Pipeline.set_table_dtypes))\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    if depth in [1, 2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.042644Z","iopub.execute_input":"2024-05-10T14:56:04.043002Z","iopub.status.idle":"2024-05-10T14:56:04.051887Z","shell.execute_reply.started":"2024-05-10T14:56:04.042972Z","shell.execute_reply":"2024-05-10T14:56:04.050713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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    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    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.053303Z","iopub.execute_input":"2024-05-10T14:56:04.053980Z","iopub.status.idle":"2024-05-10T14:56:04.060833Z","shell.execute_reply.started":"2024-05-10T14:56:04.053929Z","shell.execute_reply":"2024-05-10T14:56:04.059985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.062072Z","iopub.execute_input":"2024-05-10T14:56:04.062358Z","iopub.status.idle":"2024-05-10T14:56:04.073921Z","shell.execute_reply.started":"2024-05-10T14:56:04.062334Z","shell.execute_reply":"2024-05-10T14:56:04.072677Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.075590Z","iopub.execute_input":"2024-05-10T14:56:04.076271Z","iopub.status.idle":"2024-05-10T14:56:04.086997Z","shell.execute_reply.started":"2024-05-10T14:56:04.076237Z","shell.execute_reply":"2024-05-10T14:56:04.085376Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\"),\n    \"depth_0\": [\n        read_file(TRAIN_DIR / \"train_static_cb_0.parquet\"),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:04.089485Z","iopub.execute_input":"2024-05-10T14:56:04.090293Z","iopub.status.idle":"2024-05-10T14:56:36.942127Z","shell.execute_reply.started":"2024-05-10T14:56:04.090257Z","shell.execute_reply":"2024-05-10T14:56:36.941027Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:36.943665Z","iopub.execute_input":"2024-05-10T14:56:36.944430Z","iopub.status.idle":"2024-05-10T14:56:42.473964Z","shell.execute_reply.started":"2024-05-10T14:56:36.944401Z","shell.execute_reply":"2024-05-10T14:56:42.472732Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_store = {\n    \"df_base\": read_file(TEST_DIR / \"test_base.parquet\"),\n    \"depth_0\": [\n        read_file(TEST_DIR / \"test_static_cb_0.parquet\"),\n        read_files(TEST_DIR / \"test_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TEST_DIR / \"test_applprev_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_other_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_deposit_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:42.478646Z","iopub.execute_input":"2024-05-10T14:56:42.479003Z","iopub.status.idle":"2024-05-10T14:56:42.891654Z","shell.execute_reply.started":"2024-05-10T14:56:42.478973Z","shell.execute_reply":"2024-05-10T14:56:42.890718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:42.892756Z","iopub.execute_input":"2024-05-10T14:56:42.893051Z","iopub.status.idle":"2024-05-10T14:56:42.923438Z","shell.execute_reply.started":"2024-05-10T14:56:42.893026Z","shell.execute_reply":"2024-05-10T14:56:42.922609Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.filter_cols)\ndf_test = df_test.select([col for col in df_train.columns if col != \"target\"])\n\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:42.924442Z","iopub.execute_input":"2024-05-10T14:56:42.924754Z","iopub.status.idle":"2024-05-10T14:56:45.003829Z","shell.execute_reply.started":"2024-05-10T14:56:42.924728Z","shell.execute_reply":"2024-05-10T14:56:45.002895Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train, cat_cols = to_pandas(df_train)\ndf_test, cat_cols = to_pandas(df_test, cat_cols)","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:56:45.005185Z","iopub.execute_input":"2024-05-10T14:56:45.005577Z","iopub.status.idle":"2024-05-10T14:57:00.802780Z","shell.execute_reply.started":"2024-05-10T14:56:45.005544Z","shell.execute_reply":"2024-05-10T14:57:00.801900Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:57:00.803807Z","iopub.execute_input":"2024-05-10T14:57:00.804111Z","iopub.status.idle":"2024-05-10T14:57:00.912934Z","shell.execute_reply.started":"2024-05-10T14:57:00.804085Z","shell.execute_reply":"2024-05-10T14:57:00.911765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class VotingModel(BaseEstimator, RegressorMixin):\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.status.busy":"2024-05-10T14:57:00.914504Z","iopub.execute_input":"2024-05-10T14:57:00.914784Z","iopub.status.idle":"2024-05-10T14:57:00.922540Z","shell.execute_reply.started":"2024-05-10T14:57:00.914761Z","shell.execute_reply":"2024-05-10T14:57:00.921500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = df_train.drop(columns=[\"target\", \"case_id\",\"WEEK_NUM\"])\ny = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 10,\n    \"learning_rate\": 0.05,\n    \"max_bin\": 255,\n    \"n_estimators\": 1200,\n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"reg_alpha\": 0.1,\n    \"reg_lambda\": 10,\n    \"extra_trees\":True,\n    'num_leaves':64,\n    \"device\": \"gpu\", \n}\n\nfitted_models = []\ncv_scores = []\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    print(\"Valid week range: \", (weeks.iloc[idx_valid].min(), weeks.iloc[idx_valid].max()))\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(50), lgb.early_stopping(50)]\n    )\n\n    fitted_models.append(model)\n\n    y_pred_valid = model.predict_proba(X_valid)[:, 1]\n    auc_score = roc_auc_score(y_valid, y_pred_valid)\n    cv_scores.append(auc_score)\n\nmodel = VotingModel(fitted_models)\nprint(\"CV AUC scores: \", cv_scores)\nprint(\"Average CV AUC score: \", sum(cv_scores) / len(cv_scores))","metadata":{"execution":{"iopub.status.busy":"2024-05-10T14:57:00.923641Z","iopub.execute_input":"2024-05-10T14:57:00.923933Z","iopub.status.idle":"2024-05-10T15:18:47.791833Z","shell.execute_reply.started":"2024-05-10T14:57:00.923908Z","shell.execute_reply":"2024-05-10T15:18:47.790797Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = df_test.drop(columns=[\"WEEK_NUM\"])\nX_test = X_test.set_index(\"case_id\")\n\nlgb_pred = pd.Series(model.predict_proba(X_test)[:, 1], index=X_test.index)","metadata":{"execution":{"iopub.status.busy":"2024-05-10T15:18:47.793080Z","iopub.execute_input":"2024-05-10T15:18:47.793358Z","iopub.status.idle":"2024-05-10T15:18:48.016608Z","shell.execute_reply.started":"2024-05-10T15:18:47.793334Z","shell.execute_reply":"2024-05-10T15:18:48.015775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\"] = lgb_pred","metadata":{"execution":{"iopub.status.busy":"2024-05-10T15:18:48.017913Z","iopub.execute_input":"2024-05-10T15:18:48.018295Z","iopub.status.idle":"2024-05-10T15:18:48.030715Z","shell.execute_reply.started":"2024-05-10T15:18:48.018260Z","shell.execute_reply":"2024-05-10T15:18:48.029770Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())","metadata":{"execution":{"iopub.status.busy":"2024-05-10T15:18:48.031966Z","iopub.execute_input":"2024-05-10T15:18:48.032687Z","iopub.status.idle":"2024-05-10T15:18:48.038325Z","shell.execute_reply.started":"2024-05-10T15:18:48.032660Z","shell.execute_reply":"2024-05-10T15:18:48.037238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-05-10T15:18:48.039581Z","iopub.execute_input":"2024-05-10T15:18:48.039840Z","iopub.status.idle":"2024-05-10T15:18:48.052710Z","shell.execute_reply.started":"2024-05-10T15:18:48.039818Z","shell.execute_reply":"2024-05-10T15:18:48.051789Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-10T15:29:45.615444Z","iopub.execute_input":"2024-05-10T15:29:45.616372Z","iopub.status.idle":"2024-05-10T15:29:45.622205Z","shell.execute_reply.started":"2024-05-10T15:29:45.616340Z","shell.execute_reply":"2024-05-10T15:29:45.621165Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}