{"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"}],"dockerImageVersionId":30699,"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'\n\nfrom sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nfrom lightgbm import LGBMClassifier, early_stopping, log_evaluation\nimport lightgbm as lgb\nfrom xgboost import XGBClassifier\nfrom catboost import CatBoostClassifier, Pool\nfrom sklearn.ensemble import GradientBoostingClassifier\nimport optuna\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":7.704866,"end_time":"2024-04-12T04:59:59.042174","exception":false,"start_time":"2024-04-12T04:59:51.337308","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T12:23:28.555048Z","iopub.execute_input":"2024-05-27T12:23:28.555317Z","iopub.status.idle":"2024-05-27T12:23:34.746576Z","shell.execute_reply.started":"2024-05-27T12:23:28.555292Z","shell.execute_reply":"2024-05-27T12:23:34.745806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Preprocessing","metadata":{}},{"cell_type":"code","source":"class Pipeline:\n    \"\"\"\n    Pipeline Class have \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()) \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        return df\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        #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 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    \n    df = df.drop([\n        'lastapprcommoditytypec_5251766M',\n         'previouscontdistrict_112M',\n         'district_544M',\n         'profession_152M',\n         'name_4527232M',\n         'name_4917606M',\n         'employername_160M',\n         'classificationofcontr_400M',\n         'financialinstitution_382M',\n         'contaddr_district_15M',\n         'contaddr_zipcode_807M',\n         'empladdr_district_926M',\n         'empladdr_zipcode_114M',\n         'registaddr_district_1083M',\n         'registaddr_zipcode_184M',\n         'addres_district_368M',\n         'addres_zip_823M'])\n    \n    df = df.drop([\n        'birthdate_87D',\n        'birthdate_574D', \n        'dateofbirth_337D',\n        'dateofbirth_342D'\n    ])\n    \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 = df.drop([\n        'lastapprcommoditytypec_5251766M',\n         'previouscontdistrict_112M',\n         'district_544M',\n         'profession_152M',\n         'name_4527232M',\n         'name_4917606M',\n         'employername_160M',\n         'classificationofcontr_400M',\n         'financialinstitution_382M',\n         'contaddr_district_15M',\n         'contaddr_zipcode_807M',\n         'empladdr_district_926M',\n         'empladdr_zipcode_114M',\n         'registaddr_district_1083M',\n         'registaddr_zipcode_184M',\n         'addres_district_368M',\n         'addres_zip_823M'])\n    \n    df = df.drop([\n        'birthdate_87D',\n        'birthdate_574D', \n        'dateofbirth_337D',\n        'dateofbirth_342D'\n    ])\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    \"\"\" \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":{"papermill":{"duration":0.04765,"end_time":"2024-04-12T04:59:59.095877","exception":false,"start_time":"2024-04-12T04:59:59.048227","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:31:51.070051Z","iopub.execute_input":"2024-05-27T10:31:51.070649Z","iopub.status.idle":"2024-05-27T10:31:51.124194Z","shell.execute_reply.started":"2024-05-27T10:31:51.070615Z","shell.execute_reply":"2024-05-27T10:31:51.122968Z"},"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":{"papermill":{"duration":0.011907,"end_time":"2024-04-12T04:59:59.1133","exception":false,"start_time":"2024-04-12T04:59:59.101393","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:31:51.125570Z","iopub.execute_input":"2024-05-27T10:31:51.125913Z","iopub.status.idle":"2024-05-27T10:31:51.144864Z","shell.execute_reply.started":"2024-05-27T10:31:51.125869Z","shell.execute_reply":"2024-05-27T10:31:51.143256Z"},"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":{"papermill":{"duration":138.440655,"end_time":"2024-04-12T05:02:17.559186","exception":false,"start_time":"2024-04-12T04:59:59.118531","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:31:51.148252Z","iopub.execute_input":"2024-05-27T10:31:51.148750Z","iopub.status.idle":"2024-05-27T10:35:05.842430Z","shell.execute_reply.started":"2024-05-27T10:31:51.148706Z","shell.execute_reply":"2024-05-27T10:35:05.840194Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()","metadata":{"papermill":{"duration":101.102321,"end_time":"2024-04-12T05:03:58.666792","exception":false,"start_time":"2024-04-12T05:02:17.564471","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:35:05.844814Z","iopub.execute_input":"2024-05-27T10:35:05.845377Z","iopub.status.idle":"2024-05-27T10:35:27.673937Z","shell.execute_reply.started":"2024-05-27T10:35:05.845326Z","shell.execute_reply":"2024-05-27T10:35:27.672548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.filter_cols)","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:35:27.675379Z","iopub.execute_input":"2024-05-27T10:35:27.675706Z","iopub.status.idle":"2024-05-27T10:35:32.765902Z","shell.execute_reply.started":"2024-05-27T10:35:27.675679Z","shell.execute_reply":"2024-05-27T10:35:32.764707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"encoding_cols = df_train.select(pl.selectors.by_dtype([pl.String, pl.Boolean, pl.Categorical])).columns\n# encoding_cols","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:35:32.767506Z","iopub.execute_input":"2024-05-27T10:35:32.767982Z","iopub.status.idle":"2024-05-27T10:35:32.781009Z","shell.execute_reply.started":"2024-05-27T10:35:32.767938Z","shell.execute_reply":"2024-05-27T10:35:32.779708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"mappings = {}\nfor col in encoding_cols:\n    mappings[col] = df_train.group_by(col).len()\nmappings\n\ndf_train_lazy = df_train.select(mappings.keys()).lazy()\n# df_train_lazy = pl.LazyFrame(df_train.select('case_id'))\n\nfor col, mapping in mappings.items():\n    remapping = {category: count for category, count in mapping.rows()}\n# #     print(remapping)\n    remapping[None] = -2\n    expr = pl.col(col).replace(\n                remapping,\n                default=-1,\n            )\n    \n    df_train_lazy = df_train_lazy.with_columns(expr.alias(col + '_cnt')) # make new col with ending = '_cnt' contains expr\n    del col, mapping\n    gc.collect()\n\ntransformed_train = df_train_lazy.collect()\ndel df_train_lazy","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:35:32.782330Z","iopub.execute_input":"2024-05-27T10:35:32.782776Z","iopub.status.idle":"2024-05-27T10:35:56.275945Z","shell.execute_reply.started":"2024-05-27T10:35:32.782736Z","shell.execute_reply":"2024-05-27T10:35:56.274615Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = pl.concat([df_train, transformed_train.select(\"^*cnt$\")], how='horizontal')\ndel transformed_train\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:35:56.277517Z","iopub.execute_input":"2024-05-27T10:35:56.277854Z","iopub.status.idle":"2024-05-27T10:35:56.412063Z","shell.execute_reply.started":"2024-05-27T10:35:56.277828Z","shell.execute_reply":"2024-05-27T10:35:56.410745Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_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","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:35:56.416443Z","iopub.execute_input":"2024-05-27T10:35:56.416854Z","iopub.status.idle":"2024-05-27T10:36:52.377384Z","shell.execute_reply.started":"2024-05-27T10:35:56.416823Z","shell.execute_reply":"2024-05-27T10:36:52.375926Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()\nnans_groups={}\n\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('Use these',use)\n    return use\n\ndef group_columns_by_correlation(matrix, threshold=0.8):\n    correlation_matrix = matrix.corr()\n\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)\n\n# print(uses)\n# print(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":"2024-05-27T10:36:52.378659Z","iopub.execute_input":"2024-05-27T10:36:52.379008Z","iopub.status.idle":"2024-05-27T10:39:14.168650Z","shell.execute_reply.started":"2024-05-27T10:36:52.378977Z","shell.execute_reply":"2024-05-27T10:39:14.167002Z"},"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":{"papermill":{"duration":0.416482,"end_time":"2024-04-12T05:03:59.130015","exception":false,"start_time":"2024-04-12T05:03:58.713533","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:39:14.170409Z","iopub.execute_input":"2024-05-27T10:39:14.170788Z","iopub.status.idle":"2024-05-27T10:39:14.532775Z","shell.execute_reply.started":"2024-05-27T10:39:14.170755Z","shell.execute_reply":"2024-05-27T10:39:14.531328Z"},"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()","metadata":{"papermill":{"duration":0.524809,"end_time":"2024-04-12T05:03:59.665322","exception":false,"start_time":"2024-04-12T05:03:59.140513","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:39:14.534455Z","iopub.execute_input":"2024-05-27T10:39:14.534844Z","iopub.status.idle":"2024-05-27T10:39:14.760898Z","shell.execute_reply.started":"2024-05-27T10:39:14.534812Z","shell.execute_reply":"2024-05-27T10:39:14.759766Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test_lazy = df_test.select(mappings.keys()).lazy()\nfor col, mapping in mappings.items():\n    df_test_lazy = df_test_lazy.with_columns(expr.alias(col + '_cnt'))\n    del col, mapping","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:39:14.762471Z","iopub.execute_input":"2024-05-27T10:39:14.762923Z","iopub.status.idle":"2024-05-27T10:39:14.776995Z","shell.execute_reply.started":"2024-05-27T10:39:14.762863Z","shell.execute_reply":"2024-05-27T10:39:14.775483Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del mappings\ntransformed_test = df_test_lazy.collect()\n\ndf_test = pl.concat([df_test, transformed_test.select(\"^*cnt$\")], how='horizontal')\ndel transformed_test, encoding_cols, df_test_lazy","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:39:14.778451Z","iopub.execute_input":"2024-05-27T10:39:14.779000Z","iopub.status.idle":"2024-05-27T10:39:14.817413Z","shell.execute_reply.started":"2024-05-27T10:39:14.778958Z","shell.execute_reply":"2024-05-27T10:39:14.816218Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = df_test.select([col for col in df_train.columns if col != \"target\"])\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:47:11.688593Z","iopub.execute_input":"2024-05-27T10:47:11.689139Z","iopub.status.idle":"2024-05-27T10:47:12.100205Z","shell.execute_reply.started":"2024-05-27T10:47:11.689102Z","shell.execute_reply":"2024-05-27T10:47:12.098967Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_test","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:47:13.051581Z","iopub.execute_input":"2024-05-27T10:47:13.052002Z","iopub.status.idle":"2024-05-27T10:47:13.098729Z","shell.execute_reply.started":"2024-05-27T10:47:13.051970Z","shell.execute_reply":"2024-05-27T10:47:13.097609Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:47:15.303269Z","iopub.execute_input":"2024-05-27T10:47:15.303682Z","iopub.status.idle":"2024-05-27T10:47:15.310184Z","shell.execute_reply.started":"2024-05-27T10:47:15.303649Z","shell.execute_reply":"2024-05-27T10:47:15.308953Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Modeling","metadata":{"papermill":{"duration":0.008967,"end_time":"2024-04-12T05:03:59.683371","exception":false,"start_time":"2024-04-12T05:03:59.674404","status":"completed"},"tags":[]}},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ndf_train_opt = df_train.drop(columns=[\"target\", \"case_id\"])\ndf_train = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)","metadata":{"papermill":{"duration":0.139261,"end_time":"2024-04-12T05:03:59.831504","exception":false,"start_time":"2024-04-12T05:03:59.692243","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:50:52.944531Z","iopub.execute_input":"2024-05-27T10:50:52.945015Z","iopub.status.idle":"2024-05-27T10:50:57.876672Z","shell.execute_reply.started":"2024-05-27T10:50:52.944979Z","shell.execute_reply":"2024-05-27T10:50:57.875647Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.shape","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:50:57.878765Z","iopub.execute_input":"2024-05-27T10:50:57.879257Z","iopub.status.idle":"2024-05-27T10:50:57.887516Z","shell.execute_reply.started":"2024-05-27T10:50:57.879206Z","shell.execute_reply":"2024-05-27T10:50:57.886138Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train[cat_cols] = df_train[cat_cols].astype(str)\ndf_test[cat_cols] = df_test[cat_cols].astype(str)","metadata":{"papermill":{"duration":0.306032,"end_time":"2024-04-12T05:04:00.146706","exception":false,"start_time":"2024-04-12T05:03:59.840674","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:50:57.889298Z","iopub.execute_input":"2024-05-27T10:50:57.889755Z","iopub.status.idle":"2024-05-27T10:51:07.622076Z","shell.execute_reply.started":"2024-05-27T10:50:57.889715Z","shell.execute_reply":"2024-05-27T10:51:07.620896Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train[cat_cols] ","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:51:07.625314Z","iopub.execute_input":"2024-05-27T10:51:07.625817Z","iopub.status.idle":"2024-05-27T10:51:14.942814Z","shell.execute_reply.started":"2024-05-27T10:51:07.625774Z","shell.execute_reply":"2024-05-27T10:51:14.941434Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_pool = Pool(df_train, y, cat_features=cat_cols)","metadata":{"execution":{"iopub.status.busy":"2024-05-27T10:51:14.944538Z","iopub.execute_input":"2024-05-27T10:51:14.945036Z","iopub.status.idle":"2024-05-27T10:54:33.003816Z","shell.execute_reply.started":"2024-05-27T10:51:14.944992Z","shell.execute_reply":"2024-05-27T10:54:33.002362Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Hyperparameter Tuning","metadata":{}},{"cell_type":"code","source":"# from sklearn.model_selection import train_test_split\n# X_train, X_val, y_train, y_val = train_test_split(df_train_opt, y, test_size=0.2, random_state=42)","metadata":{"execution":{"iopub.status.busy":"2024-05-26T18:54:28.469529Z","iopub.execute_input":"2024-05-26T18:54:28.469829Z","iopub.status.idle":"2024-05-26T18:54:32.479855Z","shell.execute_reply.started":"2024-05-26T18:54:28.469805Z","shell.execute_reply":"2024-05-26T18:54:32.478943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def stability_metric(y_true, y_pred):\n    \"\"\"\n    Custom metric for model optimization during training\n    \"\"\"\n    weeks_to_score = X_val['WEEK_NUM'].reset_index(drop=True)\n    gini_in_time = []\n    \n    for week in weeks_to_score.unique():\n        week_idx = weeks_to_score.eq(week)\n        gini = np.array(2 * roc_auc_score(y_true[week_idx], y_pred[week_idx]) - 1)\n        gini_in_time.append(gini)\n\n    w_fallingrate = 88.0\n    w_resstd = -0.5\n    x = np.arange(len(gini_in_time))\n    y = np.array(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(y)\n    stability_score = avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n    is_higher_better = True\n\n    return 'stability_score', stability_score, is_higher_better\n\ndef lgbm_objective(trial):\n    \"\"\"\n    LGBMClassifier parameters search\n    \"\"\"\n    # Target ratio for unbalanced data\n    y_ratio = np.sum(y_train == 0) / np.sum(y_train == 1)\n    \n    params = {\n        'n_estimators': 5000,\n        'num_leaves': trial.suggest_int('num_leaves', 2, 300),\n        'max_depth': trial.suggest_int('max_depth', 3, 15),\n        'min_child_samples': trial.suggest_int('min_data_in_leaf', 20, 2000),\n        'learning_rate': trial.suggest_uniform('learning_rate', 0.005, 0.5),\n        'reg_alpha': trial.suggest_loguniform('lambda_l1', 1e-8, 10),\n        'reg_lambda': trial.suggest_loguniform('lambda_l2', 1e-8, 10),\n        'colsample_bytree': trial.suggest_uniform('feature_fraction', 0.5, 1),\n        'subsample': trial.suggest_uniform('bagging_fraction', 0.5, 1),\n        'subsample_freq': trial.suggest_int('bagging_freq', 0, 10),    \n        'scale_pos_weight': y_ratio,\n        'objective': 'binary',\n        'metric': 'AUC',\n        'verbosity': -1,\n        'extra_trees': True,\n        'boosting_type': 'gbdt',\n        'device': 'gpu',\n        'max_bin': 255,\n        'n_jobs': -1,\n    }\n    model = LGBMClassifier(**params)  \n    model.fit(X_train, y_train,\n              eval_set=[(X_val, y_val)],\n              eval_metric=stability_metric,\n              callbacks=[log_evaluation(100), early_stopping(100)],\n              )\n    y_pred = model.predict_proba(X_val)[:, 1]\n    _, stability_score, _ = stability_metric(np.array(y_val), np.array(y_pred))\n\n    return stability_score","metadata":{"execution":{"iopub.status.busy":"2024-05-26T19:43:33.781197Z","iopub.execute_input":"2024-05-26T19:43:33.781551Z","iopub.status.idle":"2024-05-26T19:43:33.795399Z","shell.execute_reply.started":"2024-05-26T19:43:33.781525Z","shell.execute_reply":"2024-05-26T19:43:33.794382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# X_train[cat_cols] = X_train[cat_cols].astype('category')\n# X_val[cat_cols] = X_val[cat_cols].astype('category')\n        \n# # Optuna study\n# objective = lgbm_objective\n# sampler = optuna.samplers.TPESampler(multivariate=True)\n# study = optuna.create_study(direction='maximize')\n# study.optimize(objective, n_trials=100)\n\n# # Show best results\n# trial = study.best_trial\n\n# print('Number of finished trials: ', len(study.trials))\n# print('Best trial:')\n# print('Value:', trial.value)\n# print('Params:')\n\n# for key, value in trial.params.items():\n#     print('{}: {}'.format(key, value))","metadata":{"execution":{"iopub.status.busy":"2024-05-26T19:43:34.517483Z","iopub.execute_input":"2024-05-26T19:43:34.517842Z","iopub.status.idle":"2024-05-26T21:01:00.688456Z","shell.execute_reply.started":"2024-05-26T19:43:34.517813Z","shell.execute_reply":"2024-05-26T21:01:00.686887Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb_params = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n     'num_leaves': 87, \n    \"max_depth\": 10,  \n    'min_data_in_leaf': 1507, \n    \"learning_rate\": 0.11309594007889878,\n    \"n_estimators\": 2000,  \n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\n     'lambda_l1': 2.1761191901733277, \n     'lambda_l2': 7.620040584063105e-05, \n     'feature_fraction': 0.7012592071041297, \n     'bagging_fraction': 0.7084234811527836, \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}\n\ncb_params = {\n    'eval_metric' : 'AUC',\n    'task_type' : 'GPU',\n    'learning_rate' : 0.03,\n    'iterations' : 1000\n}\n\nxgb_params = {\n    \"booster\": \"gbtree\",\n    \"objective\": \"binary:logistic\",\n    \"eval_metric\": \"auc\",\n    \"max_depth\": 10,\n    \"learning_rate\": 0.05,\n    \"n_estimators\": 1000,\n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\n    \"alpha\": 0.1,  \n    \"lambda\": 10,  \n    \"tree_method\": 'gpu_hist',\n    \"random_state\": 42,\n    \"verbosity\": 0,\n    \"enable_categorical\":True,\n}\n\ngb_params = {\n    'n_estimators': 12,\n    'learning_rate': 0.1,\n    'max_depth': 3,\n    'min_samples_split': 3,\n    'min_samples_leaf': 1\n}","metadata":{"papermill":{"duration":0.017152,"end_time":"2024-04-12T05:04:00.172842","exception":false,"start_time":"2024-04-12T05:04:00.15569","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:54:33.005659Z","iopub.execute_input":"2024-05-27T10:54:33.006129Z","iopub.status.idle":"2024-05-27T10:54:33.018794Z","shell.execute_reply.started":"2024-05-27T10:54:33.006090Z","shell.execute_reply":"2024-05-27T10:54:33.017812Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Voting Classifier","metadata":{}},{"cell_type":"code","source":"%%time\n\nfitted_models_cat, fitted_models_lgb, fitted_models_xgb  = [], [], []\ncv_scores_cat, cv_scores_lgb, cv_scores_xgb = [], [], []\n\nfor idx_train, idx_valid in cv.split(df_train, y, groups=weeks):\n    X_train, y_train = df_train.iloc[idx_train], y.iloc[idx_train]\n    X_valid, y_valid = df_train.iloc[idx_valid], y.iloc[idx_valid]\n    train_pool = Pool(X_train, y_train,cat_features=cat_cols)\n    val_pool = Pool(X_valid, y_valid,cat_features=cat_cols)\n    random_seed=42\n    \n    # Catboost\n    cb_model = CatBoostClassifier(**cb_params)\n    cb_model.fit(train_pool, eval_set=val_pool,verbose=300)\n    \n    fitted_models_cat.append(cb_model)\n    y_pred_valid = cb_model.predict_proba(X_valid)[:,1]\n    auc_score = roc_auc_score(y_valid, y_pred_valid)\n    cv_scores_cat.append(auc_score)\n       \n    # LGB\n    X_train[cat_cols] = X_train[cat_cols].astype(\"category\")\n    X_valid[cat_cols] = X_valid[cat_cols].astype(\"category\")\n    \n    lgb_model = lgb.LGBMClassifier(**lgb_params)\n    lgb_model.fit(\n        X_train, y_train,\n        eval_set = [(X_valid, y_valid)],\n        callbacks = [lgb.log_evaluation(200), lgb.early_stopping(100)] )\n    \n    fitted_models_lgb.append(lgb_model)\n    y_pred_valid = lgb_model.predict_proba(X_valid)[:,1]\n    auc_score = roc_auc_score(y_valid, y_pred_valid)\n    cv_scores_lgb.append(auc_score)\n    \n    # XGBoost\n#     xgb_model = xgb.XGBClassifier(**xgb_params)\n#     xgb_model.fit(\n#         X_train, y_train,\n#         eval_set=[(X_valid, y_valid)],\n#         early_stopping_rounds=100, verbose=False)\n    \n#     fitted_models_xgb.append(xgb_model)\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_xgb.append(auc_score)\n    \n    del cb_model, lgb_model\n    gc.collect()\n    \nprint(\"CV AUC scores: \", cv_scores_cat)\nprint(\"Maximum CV AUC score: \", max(cv_scores_cat))\n\nprint(\"CV AUC scores: \", cv_scores_lgb)\nprint(\"Maximum CV AUC score: \", max(cv_scores_lgb))\n\n# print(\"CV AUC scores: \", cv_scores_xgb)\n# print(\"Maximum CV AUC score: \", max(cv_scores_xgb))","metadata":{"papermill":{"duration":399.288009,"end_time":"2024-04-12T05:10:39.469766","exception":false,"start_time":"2024-04-12T05:04:00.181757","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-27T10:54:33.020571Z","iopub.execute_input":"2024-05-27T10:54:33.020965Z","iopub.status.idle":"2024-05-27T10:57:48.587728Z","shell.execute_reply.started":"2024-05-27T10:54:33.020931Z","shell.execute_reply":"2024-05-27T10:57:48.586397Z"},"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        \n        y_preds = [estimator.predict_proba(X) for estimator in self.estimators[:5]]\n        \n        X[cat_cols] = X[cat_cols].astype(\"category\")\n        y_preds += [estimator.predict_proba(X) for estimator in self.estimators[5:]]\n        y_preds += [estimator.predict_proba(X) for estimator in self.estimators[10:]]\n        \n        return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models_cat+fitted_models_lgb)","metadata":{"papermill":{"duration":0.022829,"end_time":"2024-04-12T05:10:39.505874","exception":false,"start_time":"2024-04-12T05:10:39.483045","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-25T10:46:53.137575Z","iopub.status.idle":"2024-05-25T10:46:53.137915Z","shell.execute_reply.started":"2024-05-25T10:46:53.137755Z","shell.execute_reply":"2024-05-25T10:46:53.137768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")\n\n\ny_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\ndf_subm[\"score\"] = y_pred\ndf_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Stacking","metadata":{}},{"cell_type":"code","source":"# %%time\n\n# base_models = [\n#     ('CatBoost', CatBoostClassifier(**cb_params)),\n#     ('LightGBM', LGBMClassifier(**lgb_params)),\n#     ('XGBoost', XGBClassifier(**xgb_params))\n# ]\n    \n# meta_model = GradientBoostingClassifier(**gb_params)\n\n# fitted_models_cb, fitted_models_lgb, fitted_models_xgb  = [], [], []\n# cv_scores_cb, cv_scores_lgb, cv_scores_xgb = [], [], []\n# meta_features = pd.DataFrame(index=df_train.index, columns=['CatBoost', 'LightGBM', 'XGBoost'])\n\n# for name, model in base_models:\n#     for idx_train, idx_valid in cv.split(df_train, y, groups=weeks):\n#         X_train, y_train = df_train.iloc[idx_train], y.iloc[idx_train]\n#         X_valid, y_valid = df_train.iloc[idx_valid], y.iloc[idx_valid]\n\n#         if name == 'CatBoost':\n#             X_train[cat_cols] = X_train[cat_cols].astype(str)\n#             X_valid[cat_cols] = X_valid[cat_cols].astype(str)\n#             train_pool = Pool(X_train, y_train, cat_features=cat_cols)\n#             val_pool = Pool(X_valid, y_valid, cat_features=cat_cols)\n#             model.fit(train_pool, eval_set=val_pool, verbose=False)\n#             y_pred_valid = model.predict_proba(val_pool)[:, 1]\n#             fitted_models_cb.append(model)\n#             auc_score = roc_auc_score(y_valid, y_pred_valid)\n#             cv_scores_cb.append(auc_score)\n#         elif name == 'LightGBM':\n#             X_train[cat_cols] = X_train[cat_cols].astype('category')\n#             X_valid[cat_cols] = X_valid[cat_cols].astype('category')\n#             model.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], callbacks=[lgb.log_evaluation(200), lgb.early_stopping(100)])\n#             fitted_models_lgb.append(model)\n#             y_pred_valid = model.predict_proba(X_valid)[:, 1]\n#             auc_score = roc_auc_score(y_valid, y_pred_valid)\n#             cv_scores_lgb.append(auc_score)\n#         else:  # XGBoost\n#             X_train[cat_cols] = X_train[cat_cols].astype('category')\n#             X_valid[cat_cols] = X_valid[cat_cols].astype('category')\n#             model.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], early_stopping_rounds=100, verbose=False)\n#             fitted_models_xgb.append(model)\n#             y_pred_valid = model.predict_proba(X_valid)[:, 1]\n#             auc_score = roc_auc_score(y_valid, y_pred_valid)\n#             cv_scores_xgb.append(auc_score)\n\n#         meta_features.loc[X_valid.index, name] = y_pred_valid","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# meta_model.fit(meta_features, y)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_test = df_test.drop(columns=[\"WEEK_NUM\"])\n# df_test = df_test.set_index(\"case_id\")","metadata":{"papermill":{"duration":0.728037,"end_time":"2024-04-12T05:10:40.267135","exception":false,"start_time":"2024-04-12T05:10:39.539098","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-05-25T10:46:53.140026Z","iopub.status.idle":"2024-05-25T10:46:53.140359Z","shell.execute_reply.started":"2024-05-25T10:46:53.140196Z","shell.execute_reply":"2024-05-25T10:46:53.140210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test_meta_features = pd.DataFrame(index=df_test.index, columns=['CatBoost', 'LightGBM', 'XGBoost'])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # CatBoost\n# for model in fitted_models_cb:\n#     df_test[cat_cols] = df_test[cat_cols].astype(str)\n#     y_pred_test = model.predict_proba(df_test)[:, 1]\n#     test_meta_features['CatBoost'] = test_meta_features['CatBoost'].add(y_pred_test, fill_value=0)\n\n# test_meta_features['CatBoost'] /= len(fitted_models_cb)\n\n# # LightGBM\n# for model in fitted_models_lgb:\n#     df_test[cat_cols] = df_test[cat_cols].astype(\"category\")\n#     y_pred_test = model.predict_proba(df_test)[:, 1]\n#     test_meta_features['LightGBM'] = test_meta_features['LightGBM'].add(y_pred_test, fill_value=0)\n\n# test_meta_features['LightGBM'] /= len(fitted_models_lgb)\n\n# # XGBoost\n# for model in fitted_models_xgb:\n#     df_test[cat_cols] = df_test[cat_cols].astype(\"category\")\n#     y_pred_test = model.predict_proba(df_test)[:, 1]\n#     test_meta_features['XGBoost'] = test_meta_features['XGBoost'].add(y_pred_test, fill_value=0)\n\n# test_meta_features['XGBoost'] /= len(fitted_models_xgb)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# test_meta_features","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred = pd.Series(meta_model.predict_proba(test_meta_features)[:, 1], index=df_test.index)\n# df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\n# df_subm = df_subm.set_index(\"case_id\")\n\n# df_subm[\"score\"] = y_pred\n# df_subm.to_csv(\"submission.csv\")\n# df_subm","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submision","metadata":{"papermill":{"duration":0.011022,"end_time":"2024-04-12T05:10:39.528","exception":false,"start_time":"2024-04-12T05:10:39.516978","status":"completed"},"tags":[]}}]}