{"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":7602123,"sourceType":"competition"},{"sourceId":7584174,"sourceType":"datasetVersion","datasetId":4414761}],"dockerImageVersionId":30648,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"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":"2024-02-18T07:40:58.941531Z","iopub.execute_input":"2024-02-18T07:40:58.941981Z","iopub.status.idle":"2024-02-18T07:41:01.956577Z","shell.execute_reply.started":"2024-02-18T07:40:58.941942Z","shell.execute_reply":"2024-02-18T07:41:01.955442Z"},"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":"2024-02-18T07:41:01.958781Z","iopub.execute_input":"2024-02-18T07:41:01.959205Z","iopub.status.idle":"2024-02-18T07:41:01.980192Z","shell.execute_reply.started":"2024-02-18T07:41:01.95917Z","shell.execute_reply":"2024-02-18T07:41:01.976797Z"},"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":"2024-02-18T07:41:01.982298Z","iopub.execute_input":"2024-02-18T07:41:01.982653Z","iopub.status.idle":"2024-02-18T07:41:02.001913Z","shell.execute_reply.started":"2024-02-18T07:41:01.982623Z","shell.execute_reply":"2024-02-18T07:41:02.000542Z"},"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    \n    if depth in [1, 2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n    \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        \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    \n    return df\n","metadata":{"execution":{"iopub.status.busy":"2024-02-18T07:41:02.004908Z","iopub.execute_input":"2024-02-18T07:41:02.005545Z","iopub.status.idle":"2024-02-18T07:41:02.0144Z","shell.execute_reply.started":"2024-02-18T07:41:02.005513Z","shell.execute_reply":"2024-02-18T07:41:02.013512Z"},"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":"2024-02-18T07:41:02.015475Z","iopub.execute_input":"2024-02-18T07:41:02.015784Z","iopub.status.idle":"2024-02-18T07:41:02.025006Z","shell.execute_reply.started":"2024-02-18T07:41:02.015761Z","shell.execute_reply":"2024-02-18T07:41:02.024033Z"},"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":"2024-02-18T07:41:02.026212Z","iopub.execute_input":"2024-02-18T07:41:02.026478Z","iopub.status.idle":"2024-02-18T07:41:02.038612Z","shell.execute_reply.started":"2024-02-18T07:41:02.026455Z","shell.execute_reply":"2024-02-18T07:41:02.037727Z"},"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":"2024-02-18T07:41:02.039715Z","iopub.execute_input":"2024-02-18T07:41:02.04006Z","iopub.status.idle":"2024-02-18T07:41:02.047959Z","shell.execute_reply.started":"2024-02-18T07:41:02.040028Z","shell.execute_reply":"2024-02-18T07:41:02.047075Z"},"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_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":"2024-02-18T07:41:02.04893Z","iopub.execute_input":"2024-02-18T07:41:02.04919Z","iopub.status.idle":"2024-02-18T07:41:31.210225Z","shell.execute_reply.started":"2024-02-18T07:41:02.049168Z","shell.execute_reply":"2024-02-18T07:41:31.209383Z"},"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":"2024-02-18T07:41:31.21135Z","iopub.execute_input":"2024-02-18T07:41:31.211665Z","iopub.status.idle":"2024-02-18T07:41:38.265768Z","shell.execute_reply.started":"2024-02-18T07:41:31.211638Z","shell.execute_reply":"2024-02-18T07:41:38.264787Z"},"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_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":"2024-02-18T07:41:38.269438Z","iopub.execute_input":"2024-02-18T07:41:38.269735Z","iopub.status.idle":"2024-02-18T07:41:38.658915Z","shell.execute_reply.started":"2024-02-18T07:41:38.26971Z","shell.execute_reply":"2024-02-18T07:41:38.658046Z"},"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":"2024-02-18T07:41:38.660227Z","iopub.execute_input":"2024-02-18T07:41:38.660621Z","iopub.status.idle":"2024-02-18T07:41:38.690824Z","shell.execute_reply.started":"2024-02-18T07:41:38.660584Z","shell.execute_reply":"2024-02-18T07:41:38.689879Z"},"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":"2024-02-18T07:41:38.692001Z","iopub.execute_input":"2024-02-18T07:41:38.692635Z","iopub.status.idle":"2024-02-18T07:41:40.852136Z","shell.execute_reply.started":"2024-02-18T07:41:38.692603Z","shell.execute_reply":"2024-02-18T07:41:40.851119Z"},"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":"2024-02-18T07:41:40.85342Z","iopub.execute_input":"2024-02-18T07:41:40.854195Z","iopub.status.idle":"2024-02-18T07:41:54.855677Z","shell.execute_reply.started":"2024-02-18T07:41:40.854159Z","shell.execute_reply":"2024-02-18T07:41:54.85472Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del data_store\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-18T07:41:54.856841Z","iopub.execute_input":"2024-02-18T07:41:54.85719Z","iopub.status.idle":"2024-02-18T07:41:54.982658Z","shell.execute_reply.started":"2024-02-18T07:41:54.857161Z","shell.execute_reply":"2024-02-18T07:41:54.98174Z"},"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":"2024-02-18T07:41:54.98404Z","iopub.execute_input":"2024-02-18T07:41:54.984467Z","iopub.status.idle":"2024-02-18T07:41:55.028076Z","shell.execute_reply.started":"2024-02-18T07:41:54.984434Z","shell.execute_reply":"2024-02-18T07:41:55.026898Z"},"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":"2024-02-18T07:41:55.029072Z","iopub.execute_input":"2024-02-18T07:41:55.029332Z","iopub.status.idle":"2024-02-18T07:42:11.822423Z","shell.execute_reply.started":"2024-02-18T07:41:55.029309Z","shell.execute_reply":"2024-02-18T07:42:11.821477Z"},"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":"2024-02-18T07:42:11.823835Z","iopub.execute_input":"2024-02-18T07:42:11.824513Z","iopub.status.idle":"2024-02-18T07:42:11.831718Z","shell.execute_reply.started":"2024-02-18T07:42:11.824477Z","shell.execute_reply":"2024-02-18T07:42:11.830659Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\n\nX = 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\": 1000,\n    \"colsample_bytree\": 0.9, \n    \"colsample_bynode\": 0.9,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"reg_alpha\": 0.1, \n    \"reg_lambda\": 3.25, \n    \"extra_trees\":True,\n    \"device\": \"gpu\",\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    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(100), lgb.early_stopping(100)]\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":"2024-02-18T07:42:11.832795Z","iopub.execute_input":"2024-02-18T07:42:11.833077Z","iopub.status.idle":"2024-02-18T07:59:09.981179Z","shell.execute_reply.started":"2024-02-18T07:42:11.833054Z","shell.execute_reply":"2024-02-18T07:59:09.980009Z"},"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":"2024-02-18T07:59:09.982508Z","iopub.execute_input":"2024-02-18T07:59:09.982785Z","iopub.status.idle":"2024-02-18T07:59:10.201045Z","shell.execute_reply.started":"2024-02-18T07:59:09.98276Z","shell.execute_reply":"2024-02-18T07:59:10.200194Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del model\ndel X_test\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-02-18T07:59:10.202204Z","iopub.execute_input":"2024-02-18T07:59:10.20249Z","iopub.status.idle":"2024-02-18T07:59:10.333811Z","shell.execute_reply.started":"2024-02-18T07:59:10.202465Z","shell.execute_reply":"2024-02-18T07:59:10.332922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import xgboost as xgb\n\nfitted_models = []\ncv_scores = []  \n\nparams = {\n    \"device\":\"cuda\",\n    \"objective\":'binary:logistic',\n    \"tree_method\":\"hist\",\n    \"enable_categorical\":True,\n    \"eval_metric\":'auc',\n    \"subsample\":1,\n    \"colsample_bytree\":1,\n    \"min_child_weight\":1,\n    \"max_depth\":20,\n    #gamma=0.7,\n    #reg_alpha=0.7,\n    \"n_estimators\":1200,\n    \"random_state\":42,\n}\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    xgb_model = xgb.XGBClassifier(**params)\n\n    # Training the model on the training data\n    xgb_model.fit(\n        X_train, y_train,\n        eval_set=[(X_valid, y_valid)],\n        early_stopping_rounds=100,\n        verbose=True,\n    )\n    fitted_models.append(xgb_model)\n\n    y_pred_valid = xgb_model.predict_proba(X_valid)[:, 1]\n    auc_score = roc_auc_score(y_valid, y_pred_valid)\n    cv_scores.append(auc_score)\n    break\n\nxgb_fitted_model = 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":"2024-02-18T08:10:48.391675Z","iopub.execute_input":"2024-02-18T08:10:48.392077Z","iopub.status.idle":"2024-02-18T08:16:05.701744Z","shell.execute_reply.started":"2024-02-18T08:10:48.392046Z","shell.execute_reply":"2024-02-18T08:16:05.700625Z"},"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\nxgb_pred = pd.Series(xgb_fitted_model.predict_proba(X_test)[:, 1], index=X_test.index)","metadata":{"execution":{"iopub.status.busy":"2024-02-18T08:16:05.703772Z","iopub.execute_input":"2024-02-18T08:16:05.704111Z","iopub.status.idle":"2024-02-18T08:16:05.879808Z","shell.execute_reply.started":"2024-02-18T08:16:05.704084Z","shell.execute_reply":"2024-02-18T08:16:05.878658Z"},"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 + xgb_pred)*0.5","metadata":{"execution":{"iopub.status.busy":"2024-02-18T08:16:05.881087Z","iopub.execute_input":"2024-02-18T08:16:05.881384Z","iopub.status.idle":"2024-02-18T08:16:05.895219Z","shell.execute_reply.started":"2024-02-18T08:16:05.881359Z","shell.execute_reply":"2024-02-18T08:16:05.894157Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", df_subm[\"score\"].isnull().any())","metadata":{"execution":{"iopub.status.busy":"2024-02-18T08:16:05.897078Z","iopub.execute_input":"2024-02-18T08:16:05.897349Z","iopub.status.idle":"2024-02-18T08:16:05.902794Z","shell.execute_reply.started":"2024-02-18T08:16:05.897325Z","shell.execute_reply":"2024-02-18T08:16:05.901701Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.head()","metadata":{"execution":{"iopub.status.busy":"2024-02-18T08:16:05.904074Z","iopub.execute_input":"2024-02-18T08:16:05.904323Z","iopub.status.idle":"2024-02-18T08:16:05.921782Z","shell.execute_reply.started":"2024-02-18T08:16:05.904302Z","shell.execute_reply":"2024-02-18T08:16:05.920903Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-02-18T08:16:05.923039Z","iopub.execute_input":"2024-02-18T08:16:05.923297Z","iopub.status.idle":"2024-02-18T08:16:05.929676Z","shell.execute_reply.started":"2024-02-18T08:16:05.923274Z","shell.execute_reply":"2024-02-18T08:16:05.928833Z"},"trusted":true},"execution_count":null,"outputs":[]}]}