{"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":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import sys\nfrom pathlib import Path\nimport subprocess\nimport os\nimport gc\nfrom glob import glob\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom datetime import datetime\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-19T21:10:55.577087Z","iopub.execute_input":"2024-03-19T21:10:55.577741Z","iopub.status.idle":"2024-03-19T21:10:56.810832Z","shell.execute_reply.started":"2024-03-19T21:10:55.57769Z","shell.execute_reply":"2024-03-19T21:10:56.810055Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from 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":"2024-03-19T21:10:56.812087Z","iopub.execute_input":"2024-03-19T21:10:56.812417Z","iopub.status.idle":"2024-03-19T21:11:00.904378Z","shell.execute_reply.started":"2024-03-19T21:10:56.812395Z","shell.execute_reply":"2024-03-19T21:11:00.903565Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Pipeline:\n\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    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()) # t - t-1\n        df = df.drop(\"date_decision\", \"MONTH\")\n        return df\n\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                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                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n        \n        return df","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:00.905979Z","iopub.execute_input":"2024-03-19T21:11:00.906262Z","iopub.status.idle":"2024-03-19T21:11:00.918468Z","shell.execute_reply.started":"2024-03-19T21:11:00.906238Z","shell.execute_reply":"2024-03-19T21:11:00.917332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Aggregator:\n    \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    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    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    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    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]  # max & replace col name\n        return expr_max\n    \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\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:00.919443Z","iopub.execute_input":"2024-03-19T21:11:00.91967Z","iopub.status.idle":"2024-03-19T21:11:00.940954Z","shell.execute_reply.started":"2024-03-19T21:11:00.91965Z","shell.execute_reply":"2024-03-19T21:11:00.940103Z"},"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":"2024-03-19T21:11:00.943332Z","iopub.execute_input":"2024-03-19T21:11:00.944138Z","iopub.status.idle":"2024-03-19T21:11:00.954077Z","shell.execute_reply.started":"2024-03-19T21:11:00.944106Z","shell.execute_reply":"2024-03-19T21:11:00.953345Z"},"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":"2024-03-19T21:11:00.955076Z","iopub.execute_input":"2024-03-19T21:11:00.955435Z","iopub.status.idle":"2024-03-19T21:11:00.963416Z","shell.execute_reply.started":"2024-03-19T21:11:00.955404Z","shell.execute_reply":"2024-03-19T21:11:00.962539Z"},"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":"2024-03-19T21:11:00.964629Z","iopub.execute_input":"2024-03-19T21:11:00.96491Z","iopub.status.idle":"2024-03-19T21:11:00.976995Z","shell.execute_reply.started":"2024-03-19T21:11:00.964879Z","shell.execute_reply":"2024-03-19T21:11:00.976094Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:00.978007Z","iopub.execute_input":"2024-03-19T21:11:00.978281Z","iopub.status.idle":"2024-03-19T21:11:00.986838Z","shell.execute_reply.started":"2024-03-19T21:11:00.978259Z","shell.execute_reply":"2024-03-19T21:11:00.986095Z"},"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":"2024-03-19T21:11:00.98787Z","iopub.execute_input":"2024-03-19T21:11:00.988122Z","iopub.status.idle":"2024-03-19T21:11:32.41797Z","shell.execute_reply.started":"2024-03-19T21:11:00.9881Z","shell.execute_reply":"2024-03-19T21:11:32.417181Z"},"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":"2024-03-19T21:11:32.419158Z","iopub.execute_input":"2024-03-19T21:11:32.419515Z","iopub.status.idle":"2024-03-19T21:11:38.012374Z","shell.execute_reply.started":"2024-03-19T21:11:32.419485Z","shell.execute_reply":"2024-03-19T21:11:38.011439Z"},"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":"2024-03-19T21:11:38.015359Z","iopub.execute_input":"2024-03-19T21:11:38.015639Z","iopub.status.idle":"2024-03-19T21:11:38.405986Z","shell.execute_reply.started":"2024-03-19T21:11:38.015609Z","shell.execute_reply":"2024-03-19T21:11:38.404974Z"},"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":"2024-03-19T21:11:38.407167Z","iopub.execute_input":"2024-03-19T21:11:38.407463Z","iopub.status.idle":"2024-03-19T21:11:38.434974Z","shell.execute_reply.started":"2024-03-19T21:11:38.407439Z","shell.execute_reply":"2024-03-19T21:11:38.434146Z"},"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":"2024-03-19T21:11:38.43761Z","iopub.execute_input":"2024-03-19T21:11:38.437969Z","iopub.status.idle":"2024-03-19T21:11:40.622009Z","shell.execute_reply.started":"2024-03-19T21:11:38.437939Z","shell.execute_reply":"2024-03-19T21:11:40.621116Z"},"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":"2024-03-19T21:11:40.623161Z","iopub.execute_input":"2024-03-19T21:11:40.623464Z","iopub.status.idle":"2024-03-19T21:11:55.447608Z","shell.execute_reply.started":"2024-03-19T21:11:40.623438Z","shell.execute_reply":"2024-03-19T21:11:55.44647Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:55.448916Z","iopub.execute_input":"2024-03-19T21:11:55.449311Z","iopub.status.idle":"2024-03-19T21:11:55.56255Z","shell.execute_reply.started":"2024-03-19T21:11:55.449256Z","shell.execute_reply":"2024-03-19T21:11:55.561672Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(df_train.head())\ndisplay(df_test.head())","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:55.563758Z","iopub.execute_input":"2024-03-19T21:11:55.564021Z","iopub.status.idle":"2024-03-19T21:11:55.61323Z","shell.execute_reply.started":"2024-03-19T21:11:55.563998Z","shell.execute_reply":"2024-03-19T21:11:55.612446Z"},"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)\n\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    \"verbose\": -1,\n    \"lambda_l1\":0.1,\n}\n\nfitted_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    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(50)] )\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    \nprint(\"CV AUC scores: \", cv_scores)\nprint(\"Average CV AUC score: \", sum(cv_scores) / len(cv_scores))","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:11:55.614151Z","iopub.execute_input":"2024-03-19T21:11:55.614407Z","iopub.status.idle":"2024-03-19T21:33:29.108637Z","shell.execute_reply.started":"2024-03-19T21:11:55.614384Z","shell.execute_reply":"2024-03-19T21:33:29.107646Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"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":"2024-03-19T21:33:29.10988Z","iopub.execute_input":"2024-03-19T21:33:29.110161Z","iopub.status.idle":"2024-03-19T21:33:29.166748Z","shell.execute_reply.started":"2024-03-19T21:33:29.110136Z","shell.execute_reply":"2024-03-19T21:33:29.166014Z"},"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":"2024-03-19T21:33:29.167979Z","iopub.execute_input":"2024-03-19T21:33:29.168242Z","iopub.status.idle":"2024-03-19T21:33:29.22903Z","shell.execute_reply.started":"2024-03-19T21:33:29.168218Z","shell.execute_reply":"2024-03-19T21:33:29.228148Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:33:29.230223Z","iopub.execute_input":"2024-03-19T21:33:29.230812Z","iopub.status.idle":"2024-03-19T21:33:29.239126Z","shell.execute_reply.started":"2024-03-19T21:33:29.230779Z","shell.execute_reply":"2024-03-19T21:33:29.238238Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-19T21:33:29.240571Z","iopub.execute_input":"2024-03-19T21:33:29.241019Z","iopub.status.idle":"2024-03-19T21:33:29.24967Z","shell.execute_reply.started":"2024-03-19T21:33:29.240982Z","shell.execute_reply":"2024-03-19T21:33:29.248856Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}