{"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"},{"sourceId":167406483,"sourceType":"kernelVersion"}],"dockerImageVersionId":30683,"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\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport joblib\nimport lightgbm as lgb\n\nfrom sklearn.model_selection import StratifiedGroupKFold\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.ensemble import VotingClassifier\nfrom sklearn.preprocessing import LabelEncoder\n\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'\n\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\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:14:15.772826Z","iopub.execute_input":"2024-04-13T08:14:15.773178Z","iopub.status.idle":"2024-04-13T08:14:19.040342Z","shell.execute_reply.started":"2024-04-13T08:14:15.773147Z","shell.execute_reply":"2024-04-13T08:14:19.039336Z"},"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 > 0.7:\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\n\n\nclass Aggregator:\n    #Please add or subtract features yourself, be aware that too many features will take up too much space.\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        \n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return expr_max +expr_last+expr_mean\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        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return  expr_max +expr_last+expr_mean\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        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        #expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        return  expr_max +expr_last#+expr_count\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        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\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] \n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\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\n\ndef 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\n\ndef 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\n\ndef 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\n\ndef reduce_mem_usage(df):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        col_type = df[col].dtype\n        if str(col_type)==\"category\":\n            continue\n        \n        if col_type != object:\n            c_min = df[col].min()\n            c_max = df[col].max()\n            if str(col_type)[:3] == 'int':\n                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n                    df[col] = df[col].astype(np.int8)\n                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n                    df[col] = df[col].astype(np.int16)\n                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n                    df[col] = df[col].astype(np.int32)\n                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n                    df[col] = df[col].astype(np.int64)  \n            else:\n                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n                    df[col] = df[col].astype(np.float16)\n                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n                    df[col] = df[col].astype(np.float32)\n                else:\n                    df[col] = df[col].astype(np.float64)\n        else:\n            continue\n    end_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))\n    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))\n    \n    return df","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:14:19.045547Z","iopub.execute_input":"2024-04-13T08:14:19.045831Z","iopub.status.idle":"2024-04-13T08:14:19.087739Z","shell.execute_reply.started":"2024-04-13T08:14:19.045806Z","shell.execute_reply":"2024-04-13T08:14:19.086782Z"},"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":"2024-04-13T08:14:19.088908Z","iopub.execute_input":"2024-04-13T08:14:19.089209Z","iopub.status.idle":"2024-04-13T08:14:19.102357Z","shell.execute_reply.started":"2024-04-13T08:14:19.089184Z","shell.execute_reply":"2024-04-13T08:14:19.101309Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndata_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":"2024-04-13T08:14:19.106231Z","iopub.execute_input":"2024-04-13T08:14:19.106629Z","iopub.status.idle":"2024-04-13T08:16:47.407698Z","shell.execute_reply.started":"2024-04-13T08:14:19.106601Z","shell.execute_reply":"2024-04-13T08:16:47.406607Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()\ndf_train = df_train.pipe(Pipeline.filter_cols)\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\nnums=df_train.select_dtypes(exclude='category').columns\nfrom itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()\nnans_groups={}\nfor col in nums:\n    cur_group = nans_df[col].sum()\n    try:\n        nans_groups[cur_group].append(col)\n    except:\n        nans_groups[cur_group]=[col]\ndel nans_df; x=gc.collect()\n\ndef reduce_group(grps):\n    use = []\n    for g in grps:\n        mx = 0; vx = g[0]\n        for gg in g:\n            n = df_train[gg].nunique()\n            if n>mx:\n                mx = n\n                vx = gg\n            #print(str(gg)+'-'+str(n),', ',end='')\n        use.append(vx)\n        #print()\n    print('Use these',use)\n    return use\n\ndef group_columns_by_correlation(matrix, threshold=0.8):\n    # 计算列之间的相关性\n    correlation_matrix = matrix.corr()\n\n    # 分组列\n    groups = []\n    remaining_cols = list(matrix.columns)\n    while remaining_cols:\n        col = remaining_cols.pop(0)\n        group = [col]\n        correlated_cols = [col]\n        for c in remaining_cols:\n            if correlation_matrix.loc[col, c] >= threshold:\n                group.append(c)\n                correlated_cols.append(c)\n        groups.append(group)\n        remaining_cols = [c for c in remaining_cols if c not in correlated_cols]\n    \n    return groups\n\nuses=[]\nfor k,v in nans_groups.items():\n    if len(v)>1:\n            Vs = nans_groups[k]\n            #cross_features=list(combinations(Vs, 2))\n            #make_corr(Vs)\n            grps= group_columns_by_correlation(df_train[Vs], threshold=0.8)\n            use=reduce_group(grps)\n            uses=uses+use\n            #make_corr(use)\n    else:\n        uses=uses+v\n    print('####### NAN count =',k)\nprint(uses)\nprint(len(uses))\nuses=uses+list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\ndf_train=df_train[uses]","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:16:47.408903Z","iopub.execute_input":"2024-04-13T08:16:47.409198Z","iopub.status.idle":"2024-04-13T08:18:37.101293Z","shell.execute_reply.started":"2024-04-13T08:16:47.409172Z","shell.execute_reply":"2024-04-13T08:18:37.099907Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"/kaggle/input/home-credit-credit-risk-model-stability/sample_submission.csv\")\ndevice='gpu'\n#n_samples=200000\nn_est=6000\nDRY_RUN = True if sample.shape[0] == 10 else False   \nif DRY_RUN:\n    device='cpu'\n    df_train = df_train.iloc[:50000]\n    #n_samples=10000\n    n_est=600\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:18:37.102789Z","iopub.execute_input":"2024-04-13T08:18:37.103120Z","iopub.status.idle":"2024-04-13T08:18:37.116898Z","shell.execute_reply.started":"2024-04-13T08:18:37.103091Z","shell.execute_reply":"2024-04-13T08:18:37.115774Z"},"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_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":"2024-04-13T08:18:37.118255Z","iopub.execute_input":"2024-04-13T08:18:37.118644Z","iopub.status.idle":"2024-04-13T08:18:37.547229Z","shell.execute_reply.started":"2024-04-13T08:18:37.118613Z","shell.execute_reply":"2024-04-13T08:18:37.546349Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)\ndel data_store\ngc.collect()\ndf_test = df_test.select([col for col in df_train.columns if col != \"target\"])\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\ntrain_df = df_train\ntest_df = df_test\ndrop_cols = []\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:18:37.548501Z","iopub.execute_input":"2024-04-13T08:18:37.548790Z","iopub.status.idle":"2024-04-13T08:18:38.114200Z","shell.execute_reply.started":"2024-04-13T08:18:37.548766Z","shell.execute_reply":"2024-04-13T08:18:38.113237Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"### from https://www.kaggle.com/code/batprem/home-credit-risk-mode-utility-scripts\n\ndef gini_stability(base, score_col=\"score\", w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", score_col]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", score_col]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[score_col])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:18:38.115457Z","iopub.execute_input":"2024-04-13T08:18:38.115763Z","iopub.status.idle":"2024-04-13T08:18:38.122976Z","shell.execute_reply.started":"2024-04-13T08:18:38.115737Z","shell.execute_reply":"2024-04-13T08:18:38.122047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nX = train_df.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"] + drop_cols)\nprint(\"X shape: \", X.shape)\ny = train_df[\"target\"]\nweeks = train_df[\"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\": 8,\n    \"max_bin\": 255,\n    \"learning_rate\": 0.05,\n    \"n_estimators\": 1000,\n    \"colsample_bytree\": 0.8, \n    \"colsample_bynode\": 0.8,\n    \"verbose\": -1,\n    \"random_state\": 42,\n    \"device\": \"gpu\",\n    \"gpu_platform_id\": 0,\n    \"gpu_device_id\": 0,\n    \"num_thread\": 2,\n}\n\nfitted_models = []\noof_pred = np.zeros(X.shape[0])\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(100)]\n    )\n    fitted_models.append(model)\n    val_pred = model.predict_proba(X_valid)[:, 1]\n    oof_pred[idx_valid] = val_pred\n    gc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:18:38.124316Z","iopub.execute_input":"2024-04-13T08:18:38.124616Z","iopub.status.idle":"2024-04-13T08:19:14.877452Z","shell.execute_reply.started":"2024-04-13T08:18:38.124590Z","shell.execute_reply":"2024-04-13T08:19:14.876239Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"roc_auc_oof = roc_auc_score(y, oof_pred)\nprint(\"CV roc_auc_oof: \", roc_auc_oof)","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:14.879266Z","iopub.execute_input":"2024-04-13T08:19:14.879687Z","iopub.status.idle":"2024-04-13T08:19:14.908742Z","shell.execute_reply.started":"2024-04-13T08:19:14.879652Z","shell.execute_reply":"2024-04-13T08:19:14.907692Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"oof_df = train_df[[\"WEEK_NUM\", \"target\"]].copy()\noof_df[\"pred_oof\"] = oof_pred\ngini_score = gini_stability(oof_df, score_col=\"pred_oof\")\nprint(\"gini_score:\\t\", gini_score)","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:14.910237Z","iopub.execute_input":"2024-04-13T08:19:14.911085Z","iopub.status.idle":"2024-04-13T08:19:15.084455Z","shell.execute_reply.started":"2024-04-13T08:19:14.911017Z","shell.execute_reply":"2024-04-13T08:19:15.083356Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"oof_models_dict = [(str(i), model) for i, model in enumerate(fitted_models)]\n\nmodel = VotingClassifier(\n    estimators=oof_models_dict,\n    voting='soft',\n)\nmodel.estimators_ = fitted_models\nmodel.le_ = LabelEncoder().fit(y)\nmodel.classes_ = model.le_.classes_","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:15.088275Z","iopub.execute_input":"2024-04-13T08:19:15.088628Z","iopub.status.idle":"2024-04-13T08:19:15.095258Z","shell.execute_reply.started":"2024-04-13T08:19:15.088601Z","shell.execute_reply":"2024-04-13T08:19:15.094150Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"joblib.dump(model, \"oof_model_1.pkl\")\njoblib.dump((train_df.columns, cat_cols, drop_cols), \"train_cat_columns.pkl\")\njoblib.dump(oof_pred, \"oof_pred.pkl\")","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:15.096621Z","iopub.execute_input":"2024-04-13T08:19:15.096915Z","iopub.status.idle":"2024-04-13T08:19:15.262681Z","shell.execute_reply.started":"2024-04-13T08:19:15.096890Z","shell.execute_reply":"2024-04-13T08:19:15.261713Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del X\ndel train_df\ndel oof_pred\ndel oof_df\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:15.263966Z","iopub.execute_input":"2024-04-13T08:19:15.264379Z","iopub.status.idle":"2024-04-13T08:19:15.389894Z","shell.execute_reply.started":"2024-04-13T08:19:15.264349Z","shell.execute_reply":"2024-04-13T08:19:15.388775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prediction","metadata":{}},{"cell_type":"code","source":"def predict_proba_in_batches(model, data, batch_size=100000):\n    num_samples = len(data)\n    num_batches = int(np.ceil(num_samples / batch_size))\n    probabilities = np.zeros((num_samples,))\n\n    for batch_idx in range(num_batches):\n        print(f\"Processing batch: {batch_idx+1}/{num_batches}\")\n        start_idx = batch_idx * batch_size\n        end_idx = min((batch_idx + 1) * batch_size, num_samples)\n        X_batch = data.iloc[start_idx:end_idx]\n        batch_probs = model.predict_proba(X_batch)[:, 1]\n        probabilities[start_idx:end_idx] = batch_probs\n        gc.collect()\n\n    return probabilities","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:15.391336Z","iopub.execute_input":"2024-04-13T08:19:15.391903Z","iopub.status.idle":"2024-04-13T08:19:15.399491Z","shell.execute_reply.started":"2024-04-13T08:19:15.391874Z","shell.execute_reply":"2024-04-13T08:19:15.398509Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_test = test_df.drop(columns=[\"WEEK_NUM\"] + drop_cols)\nX_test = X_test.set_index(\"case_id\")\nprint(\"X_test shape: \", X_test.shape)\n\ny_pred = pd.Series(predict_proba_in_batches(model, X_test), index=X_test.index)\ny_pred[:10]","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:15.400629Z","iopub.execute_input":"2024-04-13T08:19:15.400942Z","iopub.status.idle":"2024-04-13T08:19:16.029844Z","shell.execute_reply.started":"2024-04-13T08:19:15.400917Z","shell.execute_reply":"2024-04-13T08:19:16.027816Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submision","metadata":{}},{"cell_type":"code","source":"subm_df = pd.read_csv(ROOT / \"sample_submission.csv\")\nsubm_df = subm_df.set_index(\"case_id\")\n\nsubm_df[\"score\"] = y_pred","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:16.031469Z","iopub.execute_input":"2024-04-13T08:19:16.032386Z","iopub.status.idle":"2024-04-13T08:19:16.042264Z","shell.execute_reply.started":"2024-04-13T08:19:16.032347Z","shell.execute_reply":"2024-04-13T08:19:16.041077Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Check null: \", subm_df[\"score\"].isnull().any())\n\nsubm_df.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:16.043796Z","iopub.execute_input":"2024-04-13T08:19:16.044137Z","iopub.status.idle":"2024-04-13T08:19:16.059680Z","shell.execute_reply.started":"2024-04-13T08:19:16.044108Z","shell.execute_reply":"2024-04-13T08:19:16.058551Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"subm_df.to_csv(\"submission.csv\")\nsubm_df","metadata":{"execution":{"iopub.status.busy":"2024-04-13T08:19:16.060868Z","iopub.execute_input":"2024-04-13T08:19:16.061174Z","iopub.status.idle":"2024-04-13T08:19:16.074888Z","shell.execute_reply.started":"2024-04-13T08:19:16.061149Z","shell.execute_reply":"2024-04-13T08:19:16.073810Z"},"trusted":true},"execution_count":null,"outputs":[]}]}