{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30673,"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'","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:17.944264Z","iopub.execute_input":"2024-04-09T15:55:17.944661Z","iopub.status.idle":"2024-04-09T15:55:20.301249Z","shell.execute_reply.started":"2024-04-09T15:55:17.944628Z","shell.execute_reply":"2024-04-09T15:55:20.300451Z"},"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":{"execution":{"iopub.status.busy":"2024-04-09T15:55:20.302646Z","iopub.execute_input":"2024-04-09T15:55:20.303013Z","iopub.status.idle":"2024-04-09T15:55:23.951348Z","shell.execute_reply.started":"2024-04-09T15:55:20.302988Z","shell.execute_reply":"2024-04-09T15:55:23.950504Z"},"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","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:23.952382Z","iopub.execute_input":"2024-04-09T15:55:23.952881Z","iopub.status.idle":"2024-04-09T15:55:23.964748Z","shell.execute_reply.started":"2024-04-09T15:55:23.952857Z","shell.execute_reply":"2024-04-09T15:55:23.963854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Aggregator:\n    \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","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:23.966916Z","iopub.execute_input":"2024-04-09T15:55:23.967212Z","iopub.status.idle":"2024-04-09T15:55:23.981659Z","shell.execute_reply.started":"2024-04-09T15:55:23.967188Z","shell.execute_reply":"2024-04-09T15:55:23.980864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth = None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1,2]:\n        df = df.group_by('case_id').agg(Aggregator.get_exprs(df))\n    return df\n\ndef read_files(regex_path,depth = None):\n    chunks = []\n    \n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        if depth in [1, 2]:\n            df = df.group_by('case_id').agg(Aggregator.get_exprs(df))\n        chunks.append(df)\n        \n    df = pl.concat(chunks,how = 'vertical_relaxed')\n    df = df.unique(subset = ['case_id'])\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:23.982725Z","iopub.execute_input":"2024-04-09T15:55:23.983035Z","iopub.status.idle":"2024-04-09T15:55:23.994436Z","shell.execute_reply.started":"2024-04-09T15:55:23.983006Z","shell.execute_reply":"2024-04-09T15:55:23.993638Z"},"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":{"execution":{"iopub.status.busy":"2024-04-09T15:55:23.995461Z","iopub.execute_input":"2024-04-09T15:55:23.995774Z","iopub.status.idle":"2024-04-09T15:55:24.005948Z","shell.execute_reply.started":"2024-04-09T15:55:23.995744Z","shell.execute_reply":"2024-04-09T15:55:24.005223Z"},"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":{"execution":{"iopub.status.busy":"2024-04-09T15:55:24.006807Z","iopub.execute_input":"2024-04-09T15:55:24.007053Z","iopub.status.idle":"2024-04-09T15:55:24.014387Z","shell.execute_reply.started":"2024-04-09T15:55:24.007031Z","shell.execute_reply":"2024-04-09T15:55:24.013658Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def reduce_mem_usage(df):\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('内存使用了 {:.2f} MB'.format(start_mem))  # 修正\n    for col in df.columns:\n        col_type = df[col].dtype\n        if str(col_type)==\"category\":\n            continue\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    \n    end_mem = df.memory_usage().sum() / 1024**2\n    print('内存现在使用 {:.2f} MB (减少了 {:.1f}% )'.format(end_mem, 100 * (start_mem - end_mem) / start_mem))  # 修正此行\n    return df\n","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:24.015450Z","iopub.execute_input":"2024-04-09T15:55:24.015757Z","iopub.status.idle":"2024-04-09T15:55:24.030100Z","shell.execute_reply.started":"2024-04-09T15:55:24.015724Z","shell.execute_reply":"2024-04-09T15:55:24.029330Z"},"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":"2024-04-09T15:55:24.031075Z","iopub.execute_input":"2024-04-09T15:55:24.031347Z","iopub.status.idle":"2024-04-09T15:55:24.040876Z","shell.execute_reply.started":"2024-04-09T15:55:24.031326Z","shell.execute_reply":"2024-04-09T15:55:24.039999Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_store = {\n    'df_base': read_file(TRAIN_DIR / 'train_base.parquet'),\n    'depth_0':[\n        read_file(TRAIN_DIR / 'train_static_cb_0.parquet'),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n    ],\n     'depth_1': [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),  \n     ],\n     'depth_2':[\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_applprev_2.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_person_2.parquet\", 2)\n         \n     ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:55:24.044631Z","iopub.execute_input":"2024-04-09T15:55:24.044883Z","iopub.status.idle":"2024-04-09T15:57:37.330795Z","shell.execute_reply.started":"2024-04-09T15:55:24.044862Z","shell.execute_reply":"2024-04-09T15:57:37.329692Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)#**传参，不需要提前知道字典中有哪些键，可以更加灵活地传递参数\nprint(\"train data shape:\\t\", df_train.shape)#获得DataFrame维度（行与列）\ndel data_store\ngc.collect()#内存回收\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)#优化后\n\nnums=df_train.select_dtypes(exclude='category').columns#排除分类变量，选择数值型\nfrom itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()#判断缺失值\nnans_groups={}\nfor col in nums:\n    cur_group = nans_df[col].sum()#缺失值相加\n    try:\n        nans_groups[cur_group].append(col)\n    except:\n        nans_groups[cur_group]=[col]\ndel nans_df; x=gc.collect()\n\n#从每个组中选择具有最多唯一值的列，然后返回所选列名的列表\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()#计算唯一值\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            grps= group_columns_by_correlation(df_train[Vs], threshold=0.8)\n            use=reduce_group(grps)\n            uses=uses+use\n            \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":"2024-04-09T15:57:37.332104Z","iopub.execute_input":"2024-04-09T15:57:37.332399Z","iopub.status.idle":"2024-04-09T15:59:16.447536Z","shell.execute_reply.started":"2024-04-09T15:57:37.332375Z","shell.execute_reply":"2024-04-09T15:59:16.446462Z"},"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=5000\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":"2024-04-09T15:59:16.448860Z","iopub.execute_input":"2024-04-09T15:59:16.449156Z","iopub.status.idle":"2024-04-09T15:59:16.463592Z","shell.execute_reply.started":"2024-04-09T15:59:16.449131Z","shell.execute_reply":"2024-04-09T15:59:16.462733Z"},"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":"2024-04-09T15:59:16.464677Z","iopub.execute_input":"2024-04-09T15:59:16.464938Z","iopub.status.idle":"2024-04-09T15:59:16.775566Z","shell.execute_reply.started":"2024-04-09T15:59:16.464917Z","shell.execute_reply":"2024-04-09T15:59:16.774841Z"},"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)\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:59:16.776686Z","iopub.execute_input":"2024-04-09T15:59:16.777364Z","iopub.status.idle":"2024-04-09T15:59:17.259232Z","shell.execute_reply.started":"2024-04-09T15:59:16.777331Z","shell.execute_reply":"2024-04-09T15:59:17.258368Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import seaborn as sns\nimport matplotlib.pyplot as plt\n'''\n#遍历键k-值v\nfor k, v in nans_groups.items():\n    if len(v) > 1:\n        # 检查列是否存在于DataFrame中\n        if all(col in df_train.columns for col in v):\n            # 计算相关性矩阵\n            correlation_matrix = df_train[v].corr()\n            \n            # 绘制热力图\n            plt.figure(figsize=(10, 8))\n            sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt=\".2f\")\n            plt.title(f'Correlation Matrix (NAN count = {k})')\n            plt.show()\n        else:\n            print(f\"Columns {v} not found in DataFrame.\")\n\n    print('####### NAN count =', k)\n'''","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:59:17.260540Z","iopub.execute_input":"2024-04-09T15:59:17.260802Z","iopub.status.idle":"2024-04-09T15:59:17.267641Z","shell.execute_reply.started":"2024-04-09T15:59:17.260780Z","shell.execute_reply":"2024-04-09T15:59:17.266709Z"},"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'])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:59:17.268723Z","iopub.execute_input":"2024-04-09T15:59:17.269532Z","iopub.status.idle":"2024-04-09T15:59:17.400737Z","shell.execute_reply.started":"2024-04-09T15:59:17.269502Z","shell.execute_reply":"2024-04-09T15:59:17.399775Z"},"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":{"execution":{"iopub.status.busy":"2024-04-09T15:59:17.401849Z","iopub.execute_input":"2024-04-09T15:59:17.402146Z","iopub.status.idle":"2024-04-09T15:59:17.716071Z","shell.execute_reply.started":"2024-04-09T15:59:17.402122Z","shell.execute_reply":"2024-04-09T15:59:17.715128Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from catboost import CatBoostClassifier, Pool\nfrom sklearn.preprocessing import LabelEncoder\nfrom lightgbm import LGBMClassifier\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.ensemble import VotingClassifier\n\nfitted_models = []\ncv_scores = []\n\ndef encode_categorical_features(df, cat_cols):\n    for col in cat_cols:\n        le = LabelEncoder()\n        df[col] = le.fit_transform(df[col])\n    return df\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\n    # 训练CatBoost模型\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    catboost_clf = CatBoostClassifier(\n        eval_metric='AUC',\n        task_type='GPU',\n        learning_rate=0.03,\n        iterations=n_est,\n        verbose=300\n    )\n    catboost_clf.fit(train_pool, eval_set=val_pool, verbose=False)\n\n    # 训练LightGBM模型,编码类别特征\n    X_train_encoded = encode_categorical_features(X_train.copy(), cat_cols)\n    X_valid_encoded = encode_categorical_features(X_valid.copy(), cat_cols)\n    lgbm_clf = LGBMClassifier(\n        objective='binary',\n        metric='auc',\n        learning_rate=0.05,\n        n_estimators=2000\n    )\n    lgbm_clf.fit(X_train_encoded, y_train)\n\n    # 融合模型\n    voting_model = VotingClassifier(estimators=[('catboost', catboost_clf), ('lgbm', lgbm_clf)], voting='soft')\n    voting_model.fit(X_train_encoded, y_train)  \n\n    # 在验证集上评估融合模型\n    y_pred_valid = voting_model.predict_proba(X_valid_encoded)[:, 1]  # 使用编码后的验证集数据\n\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))\n","metadata":{"execution":{"iopub.status.busy":"2024-04-09T15:59:17.717572Z","iopub.execute_input":"2024-04-09T15:59:17.717869Z","iopub.status.idle":"2024-04-09T16:22:20.476269Z","shell.execute_reply.started":"2024-04-09T15:59:17.717844Z","shell.execute_reply":"2024-04-09T16:22:20.475279Z"},"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\")","metadata":{"execution":{"iopub.status.busy":"2024-04-09T16:23:46.906859Z","iopub.execute_input":"2024-04-09T16:23:46.907675Z","iopub.status.idle":"2024-04-09T16:23:46.935585Z","shell.execute_reply.started":"2024-04-09T16:23:46.907640Z","shell.execute_reply":"2024-04-09T16:23:46.934811Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 处理测试数据\n\ndf_test_encoded = encode_categorical_features(df_test.copy(), cat_cols)  # 编码类别特征\n\n# 使用融合模型进行预测\ny_pred = pd.Series(voting_model.predict_proba(df_test_encoded)[:, 1], index=df_test.index)\n\n# 创建提交文件\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm[\"score\"] = y_pred.values  # 确保预测结果与提交格式对应\ndf_subm.to_csv(\"submission.csv\", index=False) \ndf_subm\n","metadata":{"execution":{"iopub.status.busy":"2024-04-09T16:23:55.780449Z","iopub.execute_input":"2024-04-09T16:23:55.781377Z","iopub.status.idle":"2024-04-09T16:23:55.869794Z","shell.execute_reply.started":"2024-04-09T16:23:55.781346Z","shell.execute_reply":"2024-04-09T16:23:55.868923Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"execution":{"iopub.status.busy":"2024-04-09T16:35:49.424552Z","iopub.execute_input":"2024-04-09T16:35:49.424827Z","iopub.status.idle":"2024-04-09T16:35:49.746590Z","shell.execute_reply.started":"2024-04-09T16:35:49.424800Z","shell.execute_reply":"2024-04-09T16:35:49.745399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}