{"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30699,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"kernelspec":{"display_name":"Python 3","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":"3.10.13"},"papermill":{"default_parameters":{},"duration":9468.936222,"end_time":"2024-02-18T04:41:03.134316","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-02-18T02:03:14.198094","version":"2.5.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Home Credit - Credit Risk Model Stability\n\nref：https://www.kaggle.com/code/finlay/home-credit-02-lightgbm","metadata":{}},{"cell_type":"markdown","source":"# Import library","metadata":{}},{"cell_type":"code","source":"import warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)\nimport os\nimport gc\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nprint(pl.__version__)\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":{"execution":{"iopub.status.busy":"2024-05-05T12:19:48.507804Z","iopub.execute_input":"2024-05-05T12:19:48.508468Z","iopub.status.idle":"2024-05-05T12:19:48.515237Z","shell.execute_reply.started":"2024-05-05T12:19:48.508433Z","shell.execute_reply":"2024-05-05T12:19:48.514365Z"},"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\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\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.status.busy":"2024-05-05T12:21:30.752907Z","iopub.execute_input":"2024-05-05T12:21:30.753653Z","iopub.status.idle":"2024-05-05T12:21:30.765556Z","shell.execute_reply.started":"2024-05-05T12:21:30.753618Z","shell.execute_reply":"2024-05-05T12:21:30.764513Z"},"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\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\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\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\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\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":"2024-05-05T12:24:23.634049Z","iopub.execute_input":"2024-05-05T12:24:23.634861Z","iopub.status.idle":"2024-05-05T12:24:23.645377Z","shell.execute_reply.started":"2024-05-05T12:24:23.634831Z","shell.execute_reply":"2024-05-05T12:24:23.644483Z"},"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\n\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":"2024-05-05T12:24:31.686908Z","iopub.execute_input":"2024-05-05T12:24:31.687239Z","iopub.status.idle":"2024-05-05T12:24:31.694770Z","shell.execute_reply.started":"2024-05-05T12:24:31.687214Z","shell.execute_reply":"2024-05-05T12:24:31.693730Z"},"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":"2024-05-05T12:25:12.193303Z","iopub.execute_input":"2024-05-05T12:25:12.194004Z","iopub.status.idle":"2024-05-05T12:25:12.200069Z","shell.execute_reply.started":"2024-05-05T12:25:12.193976Z","shell.execute_reply":"2024-05-05T12:25:12.199114Z"},"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":"2024-05-05T12:32:08.515615Z","iopub.execute_input":"2024-05-05T12:32:08.515995Z","iopub.status.idle":"2024-05-05T12:32:08.521344Z","shell.execute_reply.started":"2024-05-05T12:32:08.515963Z","shell.execute_reply":"2024-05-05T12:32:08.520364Z"},"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":"2024-05-05T12:32:55.296690Z","iopub.execute_input":"2024-05-05T12:32:55.297604Z","iopub.status.idle":"2024-05-05T12:32:55.301812Z","shell.execute_reply.started":"2024-05-05T12:32:55.297572Z","shell.execute_reply":"2024-05-05T12:32:55.300875Z"},"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":"2024-05-05T12:34:01.120020Z","iopub.execute_input":"2024-05-05T12:34:01.120407Z","iopub.status.idle":"2024-05-05T12:34:31.495621Z","shell.execute_reply.started":"2024-05-05T12:34:01.120378Z","shell.execute_reply":"2024-05-05T12:34:31.494786Z"},"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":"2024-05-05T12:34:45.322326Z","iopub.execute_input":"2024-05-05T12:34:45.322683Z","iopub.status.idle":"2024-05-05T12:34:50.986267Z","shell.execute_reply.started":"2024-05-05T12:34:45.322655Z","shell.execute_reply":"2024-05-05T12:34:50.985355Z"},"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":"2024-05-05T12:35:37.509086Z","iopub.execute_input":"2024-05-05T12:35:37.509914Z","iopub.status.idle":"2024-05-05T12:35:37.832133Z","shell.execute_reply.started":"2024-05-05T12:35:37.509881Z","shell.execute_reply":"2024-05-05T12:35:37.831299Z"},"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":"2024-05-05T12:36:31.488265Z","iopub.execute_input":"2024-05-05T12:36:31.488667Z","iopub.status.idle":"2024-05-05T12:36:31.519516Z","shell.execute_reply.started":"2024-05-05T12:36:31.488638Z","shell.execute_reply":"2024-05-05T12:36:31.518610Z"},"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":"2024-05-05T12:36:40.935046Z","iopub.execute_input":"2024-05-05T12:36:40.935415Z","iopub.status.idle":"2024-05-05T12:36:42.919245Z","shell.execute_reply.started":"2024-05-05T12:36:40.935386Z","shell.execute_reply":"2024-05-05T12:36:42.918263Z"},"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":"2024-05-05T12:36:55.607372Z","iopub.execute_input":"2024-05-05T12:36:55.608016Z","iopub.status.idle":"2024-05-05T12:37:11.057326Z","shell.execute_reply.started":"2024-05-05T12:36:55.607985Z","shell.execute_reply":"2024-05-05T12:37:11.056506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-05T12:37:48.279130Z","iopub.execute_input":"2024-05-05T12:37:48.279880Z","iopub.status.idle":"2024-05-05T12:37:48.471519Z","shell.execute_reply.started":"2024-05-05T12:37:48.279848Z","shell.execute_reply":"2024-05-05T12:37:48.470501Z"},"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":"2024-05-05T12:38:11.778276Z","iopub.execute_input":"2024-05-05T12:38:11.779088Z","iopub.status.idle":"2024-05-05T12:38:11.785920Z","shell.execute_reply.started":"2024-05-05T12:38:11.779059Z","shell.execute_reply":"2024-05-05T12:38:11.784913Z"},"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\"]\n\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2024-05-05T12:38:27.139504Z","iopub.execute_input":"2024-05-05T12:38:27.140109Z","iopub.status.idle":"2024-05-05T12:38:28.076141Z","shell.execute_reply.started":"2024-05-05T12:38:27.140073Z","shell.execute_reply":"2024-05-05T12:38:28.075087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"params = {\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}","metadata":{"execution":{"iopub.status.busy":"2024-05-05T12:39:33.065545Z","iopub.execute_input":"2024-05-05T12:39:33.066169Z","iopub.status.idle":"2024-05-05T12:39:33.071532Z","shell.execute_reply.started":"2024-05-05T12:39:33.066124Z","shell.execute_reply":"2024-05-05T12:39:33.070584Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fitted_models = []\ncv_scores = []\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    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":"2024-05-05T12:41:53.515004Z","iopub.execute_input":"2024-05-05T12:41:53.515390Z","iopub.status.idle":"2024-05-05T13:04:01.876668Z","shell.execute_reply.started":"2024-05-05T12:41:53.515362Z","shell.execute_reply":"2024-05-05T13:04:01.875715Z"},"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":"2024-05-05T13:04:01.878711Z","iopub.execute_input":"2024-05-05T13:04:01.879084Z","iopub.status.idle":"2024-05-05T13:04:02.092195Z","shell.execute_reply.started":"2024-05-05T13:04:01.879051Z","shell.execute_reply":"2024-05-05T13:04:02.091350Z"},"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":"2024-05-05T13:04:02.093515Z","iopub.execute_input":"2024-05-05T13:04:02.093891Z","iopub.status.idle":"2024-05-05T13:04:02.109143Z","shell.execute_reply.started":"2024-05-05T13:04:02.093857Z","shell.execute_reply":"2024-05-05T13:04:02.108459Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())","metadata":{"execution":{"iopub.status.busy":"2024-05-05T13:04:02.111210Z","iopub.execute_input":"2024-05-05T13:04:02.111477Z","iopub.status.idle":"2024-05-05T13:04:02.116708Z","shell.execute_reply.started":"2024-05-05T13:04:02.111455Z","shell.execute_reply":"2024-05-05T13:04:02.115730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.head()\n","metadata":{"execution":{"iopub.status.busy":"2024-05-05T13:04:02.117892Z","iopub.execute_input":"2024-05-05T13:04:02.118151Z","iopub.status.idle":"2024-05-05T13:04:02.133148Z","shell.execute_reply.started":"2024-05-05T13:04:02.118129Z","shell.execute_reply":"2024-05-05T13:04:02.132101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-05T13:04:02.134048Z","iopub.execute_input":"2024-05-05T13:04:02.134273Z","iopub.status.idle":"2024-05-05T13:04:02.140428Z","shell.execute_reply.started":"2024-05-05T13:04:02.134254Z","shell.execute_reply":"2024-05-05T13:04:02.139630Z"},"trusted":true},"execution_count":null,"outputs":[]}]}