{"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":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"\n# 详情请看我的另一个公开笔记本 https://www.kaggle.com/code/zivanwan/remove-features-based-on-relevance-0-002?kernelSessionId=168996843\n# 如果对您有帮助请给点赞谢谢。","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:14:56.334701Z","iopub.execute_input":"2024-03-30T16:14:56.335078Z","iopub.status.idle":"2024-03-30T16:14:56.370288Z","shell.execute_reply.started":"2024-03-30T16:14:56.335043Z","shell.execute_reply":"2024-03-30T16:14:56.368992Z"}}},{"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":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-30T16:14:56.372086Z","iopub.execute_input":"2024-03-30T16:14:56.372402Z","iopub.status.idle":"2024-03-30T16:14:59.704965Z","shell.execute_reply.started":"2024-03-30T16:14:56.372375Z","shell.execute_reply":"2024-03-30T16:14:59.703713Z"},"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":"2024-03-30T16:14:59.711170Z","iopub.execute_input":"2024-03-30T16:14:59.712806Z","iopub.status.idle":"2024-03-30T16:15:01.665777Z","shell.execute_reply.started":"2024-03-30T16:14:59.712765Z","shell.execute_reply":"2024-03-30T16:15:01.664421Z"},"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":"2024-03-30T16:15:01.668487Z","iopub.execute_input":"2024-03-30T16:15:01.669067Z","iopub.status.idle":"2024-03-30T16:15:01.682365Z","shell.execute_reply.started":"2024-03-30T16:15:01.669031Z","shell.execute_reply":"2024-03-30T16:15:01.681099Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nclass Aggregator:\n    #Please add or subtract features yourself, be aware that too many features will take up too much space.\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        \n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return expr_max +expr_last+expr_mean\n    \n    def date_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"D\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return  expr_max +expr_last+expr_mean\n    \n    def str_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        #expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        return  expr_max +expr_last#+expr_count\n    \n    def other_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\n    \n    def count_expr(df):\n        cols = [col for col in df.columns if \"num_group\" in col]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols] \n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\n    \n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:15:01.687932Z","iopub.execute_input":"2024-03-30T16:15:01.688896Z","iopub.status.idle":"2024-03-30T16:15:01.706025Z","shell.execute_reply.started":"2024-03-30T16:15:01.688856Z","shell.execute_reply":"2024-03-30T16:15:01.704380Z"},"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":"2024-03-30T16:15:01.707355Z","iopub.execute_input":"2024-03-30T16:15:01.708353Z","iopub.status.idle":"2024-03-30T16:15:01.731730Z","shell.execute_reply.started":"2024-03-30T16:15:01.708319Z","shell.execute_reply":"2024-03-30T16:15:01.730856Z"},"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":"2024-03-30T16:15:01.733322Z","iopub.execute_input":"2024-03-30T16:15:01.734329Z","iopub.status.idle":"2024-03-30T16:15:01.751666Z","shell.execute_reply.started":"2024-03-30T16:15:01.734287Z","shell.execute_reply":"2024-03-30T16:15:01.750230Z"},"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":"2024-03-30T16:15:01.753270Z","iopub.execute_input":"2024-03-30T16:15:01.753619Z","iopub.status.idle":"2024-03-30T16:15:01.765547Z","shell.execute_reply.started":"2024-03-30T16:15:01.753590Z","shell.execute_reply":"2024-03-30T16:15:01.764126Z"},"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":{"execution":{"iopub.status.busy":"2024-03-30T16:15:01.771754Z","iopub.execute_input":"2024-03-30T16:15:01.773104Z","iopub.status.idle":"2024-03-30T16:15:01.787954Z","shell.execute_reply.started":"2024-03-30T16:15:01.773057Z","shell.execute_reply":"2024-03-30T16:15:01.786436Z"},"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":"2024-03-30T16:15:01.792112Z","iopub.execute_input":"2024-03-30T16:15:01.793603Z","iopub.status.idle":"2024-03-30T16:15:01.804300Z","shell.execute_reply.started":"2024-03-30T16:15:01.793554Z","shell.execute_reply":"2024-03-30T16:15:01.803136Z"},"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}","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:15:01.805775Z","iopub.execute_input":"2024-03-30T16:15:01.806423Z","iopub.status.idle":"2024-03-30T16:18:03.061000Z","shell.execute_reply.started":"2024-03-30T16:15:01.806384Z","shell.execute_reply":"2024-03-30T16:18:03.059791Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()\ndf_train = df_train.pipe(Pipeline.filter_cols)\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\nnums=df_train.select_dtypes(exclude='category').columns\nfrom itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()\nnans_groups={}\nfor col in nums:\n    cur_group = nans_df[col].sum()\n    try:\n        nans_groups[cur_group].append(col)\n    except:\n        nans_groups[cur_group]=[col]\ndel nans_df; x=gc.collect()\n\ndef reduce_group(grps):\n    use = []\n    for g in grps:\n        mx = 0; vx = g[0]\n        for gg in g:\n            n = df_train[gg].nunique()\n            if n>mx:\n                mx = n\n                vx = gg\n            #print(str(gg)+'-'+str(n),', ',end='')\n        use.append(vx)\n        #print()\n    print('Use these',use)\n    return use\n\ndef group_columns_by_correlation(matrix, threshold=0.8):\n    # 计算列之间的相关性\n    correlation_matrix = matrix.corr()\n\n    # 分组列\n    groups = []\n    remaining_cols = list(matrix.columns)\n    while remaining_cols:\n        col = remaining_cols.pop(0)\n        group = [col]\n        correlated_cols = [col]\n        for c in remaining_cols:\n            if correlation_matrix.loc[col, c] >= threshold:\n                group.append(c)\n                correlated_cols.append(c)\n        groups.append(group)\n        remaining_cols = [c for c in remaining_cols if c not in correlated_cols]\n    \n    return groups\n\nuses=[]\nfor k,v in nans_groups.items():\n    if len(v)>1:\n            Vs = nans_groups[k]\n            #cross_features=list(combinations(Vs, 2))\n            #make_corr(Vs)\n            grps= group_columns_by_correlation(df_train[Vs], threshold=0.8)\n            use=reduce_group(grps)\n            uses=uses+use\n            #make_corr(use)\n    else:\n        uses=uses+v\n    print('####### NAN count =',k)\nprint(uses)\nprint(len(uses))\nuses=uses+list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\ndf_train=df_train[uses]","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:18:03.062497Z","iopub.execute_input":"2024-03-30T16:18:03.063164Z","iopub.status.idle":"2024-03-30T16:19:52.757155Z","shell.execute_reply.started":"2024-03-30T16:18:03.063129Z","shell.execute_reply":"2024-03-30T16:19:52.755703Z"},"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\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\nprint(device)","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:52.758558Z","iopub.execute_input":"2024-03-30T16:19:52.758898Z","iopub.status.idle":"2024-03-30T16:19:52.774816Z","shell.execute_reply.started":"2024-03-30T16:19:52.758870Z","shell.execute_reply":"2024-03-30T16:19:52.773664Z"},"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":"2024-03-30T16:19:52.776550Z","iopub.execute_input":"2024-03-30T16:19:52.776880Z","iopub.status.idle":"2024-03-30T16:19:53.120039Z","shell.execute_reply.started":"2024-03-30T16:19:52.776852Z","shell.execute_reply":"2024-03-30T16:19:53.118940Z"},"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":"2024-03-30T16:19:53.121493Z","iopub.execute_input":"2024-03-30T16:19:53.121873Z","iopub.status.idle":"2024-03-30T16:19:53.697635Z","shell.execute_reply.started":"2024-03-30T16:19:53.121814Z","shell.execute_reply":"2024-03-30T16:19:53.696429Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Selection","metadata":{}},{"cell_type":"code","source":"# drop_list = ['max_empl_employedtotal_800L', 'monthsannuity_845L', 'lastactivateddate_801D', \n#              'max_numberofoverdueinstls_725L', 'requesttype_4525192L', 'max_pmts_year_507T', \n#              'lastrejectcommodtypec_5251769M', 'numinstpaidlate1d_3546852L', 'numinstmatpaidtearly2d_4499204L', \n#              'max_overdueamountmaxdateyear_2T', 'max_overdueamountmaxdateyear_994T', 'twobodfilling_608L', \n#              'maxdpdlast12m_727P', 'numinsttopaygrest_4493213L', 'currdebtcredtyperange_828A', 'maxdpdlast9m_1059P', \n#              'numinstpaid_4499208L', 'applicationscnt_867L', 'numinstlswithoutdpd_562L', 'fourthquarter_440L', \n#              'max_num_group1_6', 'max_safeguarantyflag_411L', 'max_dpdmaxdateyear_896T', 'numinstregularpaid_973L', \n#              'avgdbdtollast24m_4525197P', 'numinstpaidearly5dest_4493211L', 'numinstpaidearly5dobd_4499205L', \n#              'homephncnt_628L', 'max_role_1084L', 'max_remitter_829L', 'numrejects9m_859L', \n#              'numinstlallpaidearly3d_817L', 'numinstpaidearly3dest_4493216L', 'annuitynextmonth_57A', \n#              'numinstregularpaidest_4493210L', 'firstquarter_103L', 'clientscnt_533L', 'maxdpdlast3m_392P', \n#              'sellerplacescnt_216L', 'secondquarter_766L', 'max_periodicityofpmts_1102L', 'numinstlsallpaid_934L', \n#              'opencred_647L', 'numinstls_657L', 'numactivecredschannel_414L', 'numinstpaidearly3d_3546850L', \n#              'numinstpaidearlyest_4493214L', 'max_totaldebtoverduevalue_718A', 'paytype1st_925L', \n#              'max_inittransactioncode_279L', 'max_contractst_545M', 'max_cancelreason_3545846M', \n#              'max_rejectreason_755M', 'max_personindex_1023L', 'max_subjectroles_name_838M', 'maxdpdlast6m_474P', \n#              'max_subjectrole_182M', 'actualdpdtolerance_344P', 'max_num_group1_9', 'max_collaterals_typeofguarante_669M', \n#              'numinstpaidearly_338L', 'clientscnt_887L', 'maritalst_893M', 'max_subjectrole_93M', 'max_type_25L', \n#              'max_refreshdate_3813885D', 'numinstpaidearly5d_1087L', 'max_actualdpd_943P', 'max_description_351M', \n#              'education_88M', 'clientscnt_946L', 'clientscnt12m_3712952L', 'numactiverelcontr_750L', \n#              'max_education_927M', 'applicationscnt_1086L', 'sellerplacecnt_915L', 'max_purposeofcred_426M', \n#              'max_subjectroles_name_541M', 'clientscnt_1022L', 'clientscnt_360L', 'max_totaloutstanddebtvalue_668A', \n#              'applicationscnt_629L', 'max_outstandingamount_354A', 'clientscnt_1071L', 'numactivecreds_622L', \n#              'clientscnt_493L', 'paytype_783L', 'clientscnt6m_3712949L', 'clientscnt_304L', 'max_classificationofcontr_13M', \n#              'numnotactivated_1143L', 'commnoinclast6m_3546845L', 'max_numberofoutstandinstls_520L', \n#              'applicationscnt_464L', 'clientscnt_1130L', 'max_numberofoverdueinstls_834L', 'clientscnt3m_3712950L', \n#              'max_rejectreasonclient_4145042M', 'max_contaddr_smempladdr_334L', 'numpmtchanneldd_318L', \n#              'numcontrs3months_479L', 'max_overdueamount_31A', 'max_collaterals_typeofguarante_359M', \n#              'clientscnt_257L', 'clientscnt_157L', 'applications30d_658L', 'clientscnt_100L', \n#              'max_collater_typofvalofguarant_298M', 'max_pmts_month_706T', 'max_pmts_month_158T', \n#              'mastercontrexist_109L', 'max_collater_typofvalofguarant_407M', 'mastercontrelectronic_519L', \n#              'applicationcnt_361L', 'max_persontype_1072L', 'max_empladdr_district_926M', 'deferredmnthsnum_166L', \n#              'max_empladdr_zipcode_114M', 'max_persontype_792L', 'max_contaddr_matchlist_1032L']\n\n# df_train = df_train.drop(drop_list)\n# df_test = df_test.drop(drop_list)\n\n\n\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.699273Z","iopub.execute_input":"2024-03-30T16:19:53.699608Z","iopub.status.idle":"2024-03-30T16:19:53.705775Z","shell.execute_reply.started":"2024-03-30T16:19:53.699579Z","shell.execute_reply":"2024-03-30T16:19:53.704664Z"},"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":"markdown","source":"### Handle categorical features (Ordinal encoding)","metadata":{}},{"cell_type":"code","source":"# cat_list = [col for col in df_train.columns if df_train[col].dtype.name == 'category']\n\n# catfreq_dict = {}\n# catcatfreq_dict = {}\n\n# for col in cat_list:\n#     catfreq_dict[col] = len(list(df_train[col].value_counts()))\n#     catcatfreq_dict[col] = {}\n#     for d in dict(df_train[col].value_counts()).items():\n#         catcatfreq_dict[col][d[0]] = d[1]\n\n# catfreq_df = pd.DataFrame.from_dict(catfreq_dict, orient='index', columns=['Categories'])\n# display(catfreq_df.sort_values(by=\"Categories\", ascending=False).head())\n# display(catfreq_df.sort_values(by=\"Categories\", ascending=True).head())","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.725294Z","iopub.execute_input":"2024-03-30T16:19:53.726141Z","iopub.status.idle":"2024-03-30T16:19:53.734651Z","shell.execute_reply.started":"2024-03-30T16:19:53.726105Z","shell.execute_reply":"2024-03-30T16:19:53.733593Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ordinal_enc = OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=np.nan)\n# df_train[cat_list] = ordinal_enc.fit_transform(df_train[cat_list])\n# df_test[cat_list] = ordinal_enc.transform(df_test[cat_list])\n# df_train[cat_list].head()","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.735715Z","iopub.execute_input":"2024-03-30T16:19:53.736041Z","iopub.status.idle":"2024-03-30T16:19:53.750027Z","shell.execute_reply.started":"2024-03-30T16:19:53.736014Z","shell.execute_reply":"2024-03-30T16:19:53.748722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Handle NaN","metadata":{}},{"cell_type":"code","source":"# nan_list = []\n# for col, boo in df_train.isnull().any().items():\n#     if boo == True:\n#         nan_list.append(col)\n\n# print(f\"Number of col contains Nan value: {len(nan_list)}\")\n# for i, v in df_train.isna().sum().items():\n#     if v/len(df_train)>0.6:\n#         print(f\"{i} : \\t {round((v/len(df_train))*100)}% Nan \")","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.751130Z","iopub.execute_input":"2024-03-30T16:19:53.751810Z","iopub.status.idle":"2024-03-30T16:19:53.762009Z","shell.execute_reply.started":"2024-03-30T16:19:53.751781Z","shell.execute_reply":"2024-03-30T16:19:53.760813Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ### trial\n# from sklearn.impute import SimpleImputer\n# imp = SimpleImputer(missing_values=np.nan, strategy='mean')\n# df_train[nan_list] = imp.fit_transform(df_train[nan_list])\n# df_test[nan_list] = imp.transform(df_test[nan_list])","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.766290Z","iopub.execute_input":"2024-03-30T16:19:53.766645Z","iopub.status.idle":"2024-03-30T16:19:53.774030Z","shell.execute_reply.started":"2024-03-30T16:19:53.766614Z","shell.execute_reply":"2024-03-30T16:19:53.772761Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# ## no work (too slow..) \n# ## require dimensionality reduction first & features with high feature impor. \n# imputer = KNNImputer()\n# df_train = imputer.fit_transform(df_train)","metadata":{"execution":{"iopub.status.busy":"2024-03-30T16:19:53.776084Z","iopub.execute_input":"2024-03-30T16:19:53.776414Z","iopub.status.idle":"2024-03-30T16:19:53.785300Z","shell.execute_reply.started":"2024-03-30T16:19:53.776386Z","shell.execute_reply":"2024-03-30T16:19:53.784300Z"},"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_count":null,"outputs":[]},{"cell_type":"code","source":"\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 10,  \n    \"learning_rate\": 0.05,\n    \"n_estimators\": 2000,  \n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\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\": device, \n    \"verbose\": -1,\n}\n\nfitted_models = []\ncv_scores = []\n\n\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    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    model = lgb.LGBMClassifier(**params)\n    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    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":{"execution":{"iopub.status.busy":"2024-03-30T17:30:58.471764Z","iopub.execute_input":"2024-03-30T17:30:58.472172Z"},"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        y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models)","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.054024Z","iopub.status.idle":"2024-03-30T17:25:14.054446Z","shell.execute_reply.started":"2024-03-30T17:25:14.054253Z","shell.execute_reply":"2024-03-30T17:25:14.054269Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb.plot_importance(fitted_models[2], importance_type=\"split\", figsize=(10,50))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.056419Z","iopub.status.idle":"2024-03-30T17:25:14.056864Z","shell.execute_reply.started":"2024-03-30T17:25:14.056653Z","shell.execute_reply":"2024-03-30T17:25:14.056673Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features = X_train.columns\nimportances = fitted_models[2].feature_importances_\nfeature_importance = pd.DataFrame({'importance':importances,'features':features}).sort_values('importance', ascending=False).reset_index(drop=True)\nfeature_importance\n\ndrop_list = []\nfor i, f in feature_importance.iterrows():\n    if f['importance']<80:\n        drop_list.append(f['features'])\nprint(f\"Number of features which are not important: {len(drop_list)} \")\n\nprint(drop_list)","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.058353Z","iopub.status.idle":"2024-03-30T17:25:14.058746Z","shell.execute_reply.started":"2024-03-30T17:25:14.058571Z","shell.execute_reply":"2024-03-30T17:25:14.058586Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{}},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")\n","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.059970Z","iopub.status.idle":"2024-03-30T17:25:14.060341Z","shell.execute_reply.started":"2024-03-30T17:25:14.060170Z","shell.execute_reply":"2024-03-30T17:25:14.060185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_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":{"iopub.status.busy":"2024-03-30T17:25:14.061655Z","iopub.status.idle":"2024-03-30T17:25:14.062061Z","shell.execute_reply.started":"2024-03-30T17:25:14.061881Z","shell.execute_reply":"2024-03-30T17:25:14.061897Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#X_test = df_test.drop(columns=[\"WEEK_NUM\"])\n#X_test = X_test.set_index(\"case_id\")\n\n#lgb_pred = pd.Series(model.predict_proba(X_test)[:, 1], index=X_test.index)\n\n#df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\n#df_subm = df_subm.set_index(\"case_id\")\n\n#df_subm[\"score\"] = lgb_pred\n\n#df_subm.head()\n\n#df_subm.to_csv(\"submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.063693Z","iopub.status.idle":"2024-03-30T17:25:14.064114Z","shell.execute_reply.started":"2024-03-30T17:25:14.063931Z","shell.execute_reply":"2024-03-30T17:25:14.063947Z"},"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":"markdown","source":"* handle nan value (both numeric & categorical)\n* preprocess the minority categorical value (drop / keep)\n* float to int after ordinal encode\n* oversampling (smote? (considering date feature)\n* high dimension (pca) \n* create new features based on high fea_imp features\n...\n...","metadata":{}},{"cell_type":"code","source":"# X_resampled, y_resampled = SMOTE().fit_resample(X, y)","metadata":{"execution":{"iopub.status.busy":"2024-03-30T17:25:14.066022Z","iopub.status.idle":"2024-03-30T17:25:14.067083Z","shell.execute_reply.started":"2024-03-30T17:25:14.066853Z","shell.execute_reply":"2024-03-30T17:25:14.066874Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}