{"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":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7602123,"sourceType":"competition"},{"sourceId":7584174,"sourceType":"datasetVersion","datasetId":4414761}],"dockerImageVersionId":30646,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import 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\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\nfrom sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\n\nimport joblib\n\nimport lightgbm as lgb\n\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-03T08:53:01.412267Z","iopub.execute_input":"2024-04-03T08:53:01.412783Z","iopub.status.idle":"2024-04-03T08:53:05.422782Z","shell.execute_reply.started":"2024-04-03T08:53:01.412727Z","shell.execute_reply":"2024-04-03T08:53:05.421175Z"},"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\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                \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":"2024-04-03T08:53:05.425368Z","iopub.execute_input":"2024-04-03T08:53:05.425883Z","iopub.status.idle":"2024-04-03T08:53:05.446119Z","shell.execute_reply.started":"2024-04-03T08:53:05.425839Z","shell.execute_reply":"2024-04-03T08:53:05.444196Z"},"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\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\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\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\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        \n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\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        \n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\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\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n\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\n        return exprs\n","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:53:05.448021Z","iopub.execute_input":"2024-04-03T08:53:05.448516Z","iopub.status.idle":"2024-04-03T08:53:05.465620Z","shell.execute_reply.started":"2024-04-03T08:53:05.448474Z","shell.execute_reply":"2024-04-03T08:53:05.464102Z"},"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    \n    for path in glob(str(regex_path)):\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        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:53:05.469290Z","iopub.execute_input":"2024-04-03T08:53:05.469778Z","iopub.status.idle":"2024-04-03T08:53:05.483118Z","shell.execute_reply.started":"2024-04-03T08:53:05.469730Z","shell.execute_reply":"2024-04-03T08:53:05.482148Z"},"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        \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_dates)\n    \n    return df_base","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:53:05.484811Z","iopub.execute_input":"2024-04-03T08:53:05.485834Z","iopub.status.idle":"2024-04-03T08:53:05.497498Z","shell.execute_reply.started":"2024-04-03T08:53:05.485791Z","shell.execute_reply":"2024-04-03T08:53:05.496159Z"},"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    \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.status.busy":"2024-04-03T08:53:05.499476Z","iopub.execute_input":"2024-04-03T08:53:05.499879Z","iopub.status.idle":"2024-04-03T08:53:05.522177Z","shell.execute_reply.started":"2024-04-03T08:53:05.499831Z","shell.execute_reply":"2024-04-03T08:53:05.521026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Configuration","metadata":{}},{"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":"2024-04-03T08:53:05.524205Z","iopub.execute_input":"2024-04-03T08:53:05.525039Z","iopub.status.idle":"2024-04-03T08:53:05.537483Z","shell.execute_reply.started":"2024-04-03T08:53:05.524996Z","shell.execute_reply":"2024-04-03T08:53:05.536257Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Train Files Read & Feature Engineering","metadata":{}},{"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_files(TRAIN_DIR / \"train_credit_bureau_a_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        read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_applprev_2.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_person_2.parquet\", 2)\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:53:05.539174Z","iopub.execute_input":"2024-04-03T08:53:05.540206Z","iopub.status.idle":"2024-04-03T08:56:08.154994Z","shell.execute_reply.started":"2024-04-03T08:53:05.540168Z","shell.execute_reply":"2024-04-03T08:56:08.153705Z"},"trusted":true},"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.status.busy":"2024-04-03T08:56:08.156536Z","iopub.execute_input":"2024-04-03T08:56:08.157223Z","iopub.status.idle":"2024-04-03T08:56:28.196403Z","shell.execute_reply.started":"2024-04-03T08:56:08.157187Z","shell.execute_reply":"2024-04-03T08:56:28.195101Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Test Files Read & Feature Engineering","metadata":{}},{"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_files(TEST_DIR / \"test_credit_bureau_a_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        read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TEST_DIR / \"test_applprev_2.parquet\", 2),\n        read_file(TEST_DIR / \"test_person_2.parquet\", 2)\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:56:28.200806Z","iopub.execute_input":"2024-04-03T08:56:28.201202Z","iopub.status.idle":"2024-04-03T08:56:28.966537Z","shell.execute_reply.started":"2024-04-03T08:56:28.201168Z","shell.execute_reply":"2024-04-03T08:56:28.964845Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\n\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:56:28.968368Z","iopub.execute_input":"2024-04-03T08:56:28.968882Z","iopub.status.idle":"2024-04-03T08:56:29.039101Z","shell.execute_reply.started":"2024-04-03T08:56:28.968832Z","shell.execute_reply":"2024-04-03T08:56:29.037685Z"},"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":"2024-04-03T08:56:29.040997Z","iopub.execute_input":"2024-04-03T08:56:29.041565Z","iopub.status.idle":"2024-04-03T08:56:32.663966Z","shell.execute_reply.started":"2024-04-03T08:56:29.041526Z","shell.execute_reply":"2024-04-03T08:56:32.661961Z"},"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":"2024-04-03T08:56:32.666143Z","iopub.execute_input":"2024-04-03T08:56:32.666648Z","iopub.status.idle":"2024-04-03T08:56:57.707474Z","shell.execute_reply.started":"2024-04-03T08:56:32.666604Z","shell.execute_reply":"2024-04-03T08:56:57.706089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:56:57.710175Z","iopub.execute_input":"2024-04-03T08:56:57.710646Z","iopub.status.idle":"2024-04-03T08:56:57.966500Z","shell.execute_reply.started":"2024-04-03T08:56:57.710612Z","shell.execute_reply":"2024-04-03T08:56:57.964695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### EDA","metadata":{}},{"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\nprint()\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":{"iopub.status.busy":"2024-04-03T08:56:57.968256Z","iopub.execute_input":"2024-04-03T08:56:57.968735Z","iopub.status.idle":"2024-04-03T08:56:58.022157Z","shell.execute_reply.started":"2024-04-03T08:56:57.968677Z","shell.execute_reply":"2024-04-03T08:56:58.020411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.lineplot(\n    data=df_train,\n    x=\"WEEK_NUM\",\n    y=\"target\",\n)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:56:58.024911Z","iopub.execute_input":"2024-04-03T08:56:58.025573Z","iopub.status.idle":"2024-04-03T08:57:17.496625Z","shell.execute_reply.started":"2024-04-03T08:56:58.025524Z","shell.execute_reply":"2024-04-03T08:57:17.494799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Training","metadata":{}},{"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":"2024-04-03T08:57:17.498257Z","iopub.execute_input":"2024-04-03T08:57:17.498822Z","iopub.status.idle":"2024-04-03T08:57:17.511220Z","shell.execute_reply.started":"2024-04-03T08:57:17.498749Z","shell.execute_reply":"2024-04-03T08:57:17.509495Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:57:17.514172Z","iopub.execute_input":"2024-04-03T08:57:17.515316Z","iopub.status.idle":"2024-04-03T08:57:17.842366Z","shell.execute_reply.started":"2024-04-03T08:57:17.515259Z","shell.execute_reply":"2024-04-03T08:57:17.841014Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"week_threshold = 70\n\n# train_indices = df_train[df_train.WEEK_NUM < week_threshold].index\n# valid_indices = df_train[df_train.WEEK_NUM >= week_threshold].index\n\nX = df_train.drop(columns=[\"target\", \"case_id\",\"WEEK_NUM\"])\ny = df_train[\"target\"]\n\nX_valid = df_train.iloc[df_train[df_train.WEEK_NUM >= week_threshold].index]\ny_valid = y[df_train[df_train.WEEK_NUM >= week_threshold].index]\n\nX_train = df_train.iloc[df_train[df_train.WEEK_NUM < week_threshold].index]\ny_train = y[df_train[df_train.WEEK_NUM < week_threshold].index]","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:14:45.340165Z","iopub.execute_input":"2024-04-03T09:14:45.340898Z","iopub.status.idle":"2024-04-03T09:14:57.782544Z","shell.execute_reply.started":"2024-04-03T09:14:45.340835Z","shell.execute_reply":"2024-04-03T09:14:57.781149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:15:04.817772Z","iopub.execute_input":"2024-04-03T09:15:04.818269Z","iopub.status.idle":"2024-04-03T09:15:05.107049Z","shell.execute_reply.started":"2024-04-03T09:15:04.818232Z","shell.execute_reply":"2024-04-03T09:15:05.105316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:15:10.114778Z","iopub.execute_input":"2024-04-03T09:15:10.115320Z","iopub.status.idle":"2024-04-03T09:15:10.126570Z","shell.execute_reply.started":"2024-04-03T09:15:10.115279Z","shell.execute_reply":"2024-04-03T09:15:10.124531Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\n\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\": 2000,\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    #\"device\": \"gpu\",  # Uncomment if you want to use GPU for training\n}\n\nfitted_models = []\ncv_scores = []  \n\n\nmodel = lgb.LGBMClassifier(**params)\nmodel.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\ny_pred_valid = model.predict_proba(X_valid)[:, 1]\nauc_score = roc_auc_score(y_valid, y_pred_valid)\n\nprint(\"AUC scores: \", auc_score)","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:16:55.664685Z","iopub.execute_input":"2024-04-03T09:16:55.665706Z","iopub.status.idle":"2024-04-03T09:18:28.862837Z","shell.execute_reply.started":"2024-04-03T09:16:55.665658Z","shell.execute_reply":"2024-04-03T09:18:28.861487Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Refit model\nX = df_train.drop(columns=[\"target\", \"case_id\",\"WEEK_NUM\"])\ny = df_train[\"target\"]\nprint(\"Infer Model Trainning.\")\ninfer_params = params.copy()\ninfer_params[\"n_estimators\"] = int(1.2 * model.best_iteration_)\ninfer_model = lgb.LGBMClassifier(**infer_params)\ninfer_model.fit(X, y)","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:24:52.749510Z","iopub.execute_input":"2024-04-03T09:24:52.750078Z","iopub.status.idle":"2024-04-03T09:26:04.553935Z","shell.execute_reply.started":"2024-04-03T09:24:52.750041Z","shell.execute_reply":"2024-04-03T09:26:04.552568Z"},"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(infer_model.predict_proba(X_test)[:, 1], index=X_test.index)","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:26:12.698912Z","iopub.execute_input":"2024-04-03T09:26:12.699472Z","iopub.status.idle":"2024-04-03T09:26:12.798076Z","shell.execute_reply.started":"2024-04-03T09:26:12.699422Z","shell.execute_reply":"2024-04-03T09:26:12.796569Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#### Submission","metadata":{}},{"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":"2024-04-03T09:26:15.162289Z","iopub.execute_input":"2024-04-03T09:26:15.162864Z","iopub.status.idle":"2024-04-03T09:26:15.194727Z","shell.execute_reply.started":"2024-04-03T09:26:15.162818Z","shell.execute_reply":"2024-04-03T09:26:15.193063Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:26:16.586248Z","iopub.execute_input":"2024-04-03T09:26:16.586813Z","iopub.status.idle":"2024-04-03T09:26:16.600052Z","shell.execute_reply.started":"2024-04-03T09:26:16.586771Z","shell.execute_reply":"2024-04-03T09:26:16.598219Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-03T09:26:19.417835Z","iopub.execute_input":"2024-04-03T09:26:19.418387Z","iopub.status.idle":"2024-04-03T09:26:19.438552Z","shell.execute_reply.started":"2024-04-03T09:26:19.418344Z","shell.execute_reply":"2024-04-03T09:26:19.436844Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-04-03T08:57:27.942959Z","iopub.status.idle":"2024-04-03T08:57:27.943403Z","shell.execute_reply.started":"2024-04-03T08:57:27.943197Z","shell.execute_reply":"2024-04-03T08:57:27.943214Z"},"trusted":true},"execution_count":null,"outputs":[]}]}