{"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30683,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"},"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"},"papermill":{"default_parameters":{},"duration":2159.116896,"end_time":"2024-04-07T10:19:38.712675","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-04-07T09:43:39.595779","version":"2.5.0"}},"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\nfrom tqdm import tqdm_notebook\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom datetime import datetime\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","papermill":{"duration":2.185049,"end_time":"2024-04-07T09:43:44.599573","exception":false,"start_time":"2024-04-07T09:43:42.414524","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:52.864205Z","iopub.execute_input":"2024-04-16T09:32:52.865257Z","iopub.status.idle":"2024-04-16T09:32:55.047317Z","shell.execute_reply.started":"2024-04-16T09:32:52.865218Z","shell.execute_reply":"2024-04-16T09:32:55.046350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!mkdir home-credit-cab","metadata":{"execution":{"iopub.status.busy":"2024-04-16T09:38:52.466363Z","iopub.execute_input":"2024-04-16T09:38:52.467203Z","iopub.status.idle":"2024-04-16T09:38:53.642677Z","shell.execute_reply.started":"2024-04-16T09:38:52.467170Z","shell.execute_reply":"2024-04-16T09:38:53.641529Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer","metadata":{"papermill":{"duration":4.282624,"end_time":"2024-04-07T09:43:48.893553","exception":false,"start_time":"2024-04-07T09:43:44.610929","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:55.997093Z","iopub.execute_input":"2024-04-16T09:32:55.997416Z","iopub.status.idle":"2024-04-16T09:32:59.392894Z","shell.execute_reply.started":"2024-04-16T09:32:55.997388Z","shell.execute_reply":"2024-04-16T09:32:59.392073Z"},"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\",) and 'cnt' not in col:\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\",) and 'cnt' not in col:\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","metadata":{"papermill":{"duration":0.025581,"end_time":"2024-04-07T09:43:48.930409","exception":false,"start_time":"2024-04-07T09:43:48.904828","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.395128Z","iopub.execute_input":"2024-04-16T09:32:59.395694Z","iopub.status.idle":"2024-04-16T09:32:59.408111Z","shell.execute_reply.started":"2024-04-16T09:32:59.395666Z","shell.execute_reply":"2024-04-16T09:32:59.407099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class 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        # expr_var = [pl.var(col).alias(f\"var_{col}\") for col in cols]\n\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\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","metadata":{"papermill":{"duration":0.025994,"end_time":"2024-04-07T09:43:48.967199","exception":false,"start_time":"2024-04-07T09:43:48.941205","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.409403Z","iopub.execute_input":"2024-04-16T09:32:59.409676Z","iopub.status.idle":"2024-04-16T09:32:59.426078Z","shell.execute_reply.started":"2024-04-16T09:32:59.409654Z","shell.execute_reply":"2024-04-16T09:32:59.425316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1,2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    \n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        if depth in [1, 2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df","metadata":{"papermill":{"duration":0.020401,"end_time":"2024-04-07T09:43:48.998353","exception":false,"start_time":"2024-04-07T09:43:48.977952","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.427326Z","iopub.execute_input":"2024-04-16T09:32:59.428075Z","iopub.status.idle":"2024-04-16T09:32:59.437569Z","shell.execute_reply.started":"2024-04-16T09:32:59.428042Z","shell.execute_reply":"2024-04-16T09:32:59.436843Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base","metadata":{"papermill":{"duration":0.019136,"end_time":"2024-04-07T09:43:49.028168","exception":false,"start_time":"2024-04-07T09:43:49.009032","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.438682Z","iopub.execute_input":"2024-04-16T09:32:59.438934Z","iopub.status.idle":"2024-04-16T09:32:59.446885Z","shell.execute_reply.started":"2024-04-16T09:32:59.438913Z","shell.execute_reply":"2024-04-16T09:32:59.446023Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols","metadata":{"papermill":{"duration":0.017783,"end_time":"2024-04-07T09:43:49.056634","exception":false,"start_time":"2024-04-07T09:43:49.038851","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.447869Z","iopub.execute_input":"2024-04-16T09:32:59.448103Z","iopub.status.idle":"2024-04-16T09:32:59.456081Z","shell.execute_reply.started":"2024-04-16T09:32:59.448082Z","shell.execute_reply":"2024-04-16T09:32:59.455222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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":{"papermill":{"duration":0.025318,"end_time":"2024-04-07T09:43:49.092539","exception":false,"start_time":"2024-04-07T09:43:49.067221","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.457169Z","iopub.execute_input":"2024-04-16T09:32:59.457451Z","iopub.status.idle":"2024-04-16T09:32:59.470923Z","shell.execute_reply.started":"2024-04-16T09:32:59.457429Z","shell.execute_reply":"2024-04-16T09:32:59.470064Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT            = Path(ROOT)\n\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"\n\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":0.017335,"end_time":"2024-04-07T09:43:49.120502","exception":false,"start_time":"2024-04-07T09:43:49.103167","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:32:59.473797Z","iopub.execute_input":"2024-04-16T09:32:59.474062Z","iopub.status.idle":"2024-04-16T09:35:14.561889Z","shell.execute_reply.started":"2024-04-16T09:32:59.474040Z","shell.execute_reply":"2024-04-16T09:35:14.560943Z"},"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\ndf_train = df_train.pipe(Pipeline.filter_cols)\ngc.collect()","metadata":{"papermill":{"duration":22.182494,"end_time":"2024-04-07T09:46:28.617717","exception":false,"start_time":"2024-04-07T09:46:06.435223","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:35:14.563321Z","iopub.execute_input":"2024-04-16T09:35:14.563754Z","iopub.status.idle":"2024-04-16T09:35:36.248834Z","shell.execute_reply.started":"2024-04-16T09:35:14.563714Z","shell.execute_reply":"2024-04-16T09:35:36.247835Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":20.42648,"end_time":"2024-04-07T09:46:49.055823","exception":false,"start_time":"2024-04-07T09:46:28.629343","status":"completed"},"tags":[]},"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)\n\nnums = df_train.select_dtypes(exclude='category').columns\n\nfrom itertools import combinations, permutations\n\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;\nx = gc.collect()\n\n\ndef reduce_group(grps):\n    use = []\n    for g in grps:\n        mx = 0;\n        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\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\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\nprint(f'Using columns(total: {len(uses)}): {uses}')\n\nuses = uses + list(df_train.select_dtypes(include='category').columns)\nprint(f'Total columns including category {len(uses)}')\n\ndf_train = df_train[uses]\nprint(f'Train dataset shape: {df_train.shape}')\n# df_train.drop(['requesttype_4525192L_cnt','max_empl_employedtotal_800L_cnt', 'max_empl_industry_691L_cnt'], axis=1, inplace=True)\n","metadata":{"papermill":{"duration":166.726205,"end_time":"2024-04-07T09:49:35.793659","exception":false,"start_time":"2024-04-07T09:46:49.067454","status":"completed"},"scrolled":true,"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:35:36.250361Z","iopub.execute_input":"2024-04-16T09:35:36.250736Z","iopub.status.idle":"2024-04-16T09:36:54.248949Z","shell.execute_reply.started":"2024-04-16T09:35:36.250703Z","shell.execute_reply":"2024-04-16T09:36:54.247934Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ndf_train= df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])","metadata":{"papermill":{"duration":1.183027,"end_time":"2024-04-07T09:49:38.596688","exception":false,"start_time":"2024-04-07T09:49:37.413661","status":"completed"},"tags":[],"execution":{"iopub.status.busy":"2024-04-16T09:36:54.250322Z","iopub.execute_input":"2024-04-16T09:36:54.250653Z","iopub.status.idle":"2024-04-16T09:36:55.449236Z","shell.execute_reply.started":"2024-04-16T09:36:54.250624Z","shell.execute_reply":"2024-04-16T09:36:55.448401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train[cat_cols] = df_train[cat_cols].astype(str)","metadata":{"execution":{"iopub.status.busy":"2024-04-16T09:36:55.450259Z","iopub.execute_input":"2024-04-16T09:36:55.450528Z","iopub.status.idle":"2024-04-16T09:37:05.214580Z","shell.execute_reply.started":"2024-04-16T09:36:55.450505Z","shell.execute_reply":"2024-04-16T09:37:05.213788Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# train_mask = weeks <= 80\n# valid_mask = weeks > 80\n\n# df_train_ = df_train[train_mask]\n# df_train_v = df_train[valid_mask]\n\n# # df_train_ = df_train_[selected_feats]\n# # df_train_v = df_train_v[selected_feats]\n\n# y_ = y[train_mask]\n# y_v = y[valid_mask]","metadata":{"execution":{"iopub.status.busy":"2024-04-16T09:37:05.215663Z","iopub.execute_input":"2024-04-16T09:37:05.215921Z","iopub.status.idle":"2024-04-16T09:37:05.220353Z","shell.execute_reply.started":"2024-04-16T09:37:05.215899Z","shell.execute_reply":"2024-04-16T09:37:05.219282Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from catboost import CatBoostClassifier, Pool\n\nparams = {\n    \"eval_metric\": \"AUC\",  # 相当于LightGBM中的metric参数\n    # \"depth\": 10,  # 相当于LightGBM中的max_depth参数\n    \"learning_rate\": 0.03,\n    \"iterations\": 6000,  # 相当于LightGBM中的n_estimators参数\n    # \"random_seed\": 3107,  # 相当于LightGBM中的random_state参数\n    # \"l2_leaf_reg\": 10,  # 相当于LightGBM中的reg_lambda参数\n    # \"border_count\": 254,  # 没有直接相当于LightGBM中的colsample_by*参数，但可以用来增加分箱数\n    \"verbose\": False,  # 控制输出信息\n    \"task_type\": \"GPU\",  # 使用GPU训练\n}\n\nn_splits = 5\nfitted_models = []\ncv_scores = []\n\ncv = StratifiedGroupKFold(n_splits=n_splits, shuffle=False)\n\nstep = 0\nfor idx_train, idx_valid in cv.split(df_train, y, groups=weeks):#   Because it takes a long time to divide the data set, \n    step += 1\n    print(f'current step: {step}')\n    \n    X_train, y_train = df_train.iloc[idx_train], y.iloc[idx_train]# each time the data set is divided, two models are trained to each other twice, which saves time.\n    X_valid, y_valid = df_train.iloc[idx_valid], y.iloc[idx_valid]\n\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\n    model = CatBoostClassifier(**params)\n    model.fit(train_pool, eval_set=val_pool, verbose=1000)\n\n    \n    fitted_models.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.append(auc_score)\n    \nprint(\"CV AUC scores: \", cv_scores)\nprint(\"Maximum CV AUC score: \", max(cv_scores))","metadata":{"scrolled":true,"execution":{"iopub.status.busy":"2024-04-16T09:39:07.844247Z","iopub.execute_input":"2024-04-16T09:39:07.844969Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import pickle as pkl\n\nfor i in range(n_splits):\n    with open(f'/kaggle/working/home-credit-cab/model_{i}.pkl', 'wb') as fout:\n       pkl.dump(fitted_models[i], fout)\n        \nprint('saved model done.')\n","metadata":{"trusted":true},"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":"code","source":"","metadata":{"papermill":{"duration":0.053751,"end_time":"2024-04-07T10:19:37.331666","exception":false,"start_time":"2024-04-07T10:19:37.277915","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]}]}