{"metadata":{"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true},"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.10.13"},"papermill":{"default_parameters":{},"duration":1155.898649,"end_time":"2024-05-26T00:54:40.070283","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2024-05-26T00:35:24.171634","version":"2.5.0"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"#! pip install MonthDelta\nimport 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\nimport lightgbm as lgb\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer\n\n#from monthdelta import monthmod","metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","execution":{"iopub.execute_input":"2024-05-26T00:35:27.006845Z","iopub.status.busy":"2024-05-26T00:35:27.00646Z","iopub.status.idle":"2024-05-26T00:35:33.682141Z","shell.execute_reply":"2024-05-26T00:35:33.681299Z"},"papermill":{"duration":6.689037,"end_time":"2024-05-26T00:35:33.684539","exception":false,"start_time":"2024-05-26T00:35:26.995502","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"def n_of_month(yr,mon,kjn):\n    tgt = datetime(yr.cast(pl.Int64),mon.cast(pl.Int64),1)   \n    delta = monthmod(tgt,kjn)\n    return delta[0].months\n    \n#kjn = datetime(2024,12,1)\n#n_of_month(2024,1,kjn)\n    ","metadata":{"execution":{"iopub.execute_input":"2024-05-21T20:16:26.012725Z","iopub.status.busy":"2024-05-21T20:16:26.011955Z","iopub.status.idle":"2024-05-21T20:16:26.019711Z","shell.execute_reply":"2024-05-21T20:16:26.018621Z","shell.execute_reply.started":"2024-05-21T20:16:26.01266Z"},"papermill":{"duration":0.008365,"end_time":"2024-05-26T00:35:33.702089","exception":false,"start_time":"2024-05-26T00:35:33.693724","status":"completed"},"tags":[]}},{"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\",\"riskassesment_302T_rng\",\"riskassesment_302T_mean\"]:\n                isnull = df[col].is_null().mean()\n                if isnull > 0.975:\n                    df = df.drop(col)\n        \n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\",\"riskassesment_302T\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n                if (freq == 1) | (freq > 200):\n                    print(col)\n                    df = df.drop(col)\n        \n        return df\n\n\nclass Aggregator:\n    #Please add or subtract features yourself, be aware that too many features will take up too much space.\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        \n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        \n        #--------------------------------\n        expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        expr_var = [pl.var(col).alias(f\"var_{col}\") for col in cols]\n\n#         expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n#        expr_median = [pl.median(col).alias(f\"median_{col}\") for col in cols]\n        #--------------------------------\n        \n        \n        return expr_max +expr_last+expr_mean+expr_var+expr_count#+expr_median\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        #--------------------------------\n#         expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n#         expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        #--------------------------------\n        \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\n        return  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        \n        #--------------------------------\n        expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        #--------------------------------\n        \n        return  expr_max +expr_last+expr_count\n    \n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n\n        return exprs\n\ndef read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1,2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    \n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        if depth in [1,2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df\n\n\ndef transform_cols(df: pl.DataFrame) -> pl.DataFrame:\n    \"\"\"\n    Transforms columns in the DataFrame according to predefined rules.\n\n    Args:\n    - df (pl.DataFrame): Input DataFrame.\n\n    Returns:\n    - pl.DataFrame: DataFrame with transformed columns.\n    \"\"\"\n    if \"riskassesment_302T\" in df.columns:\n        if df[\"riskassesment_302T\"].dtype == pl.Null:\n            df = df.with_columns(\n                [\n                    pl.Series(\n                        \"riskassesment_302T_rng\", df[\"riskassesment_302T\"], pl.UInt8\n                    ),\n                    pl.Series(\n                        \"riskassesment_302T_mean\", df[\"riskassesment_302T\"], pl.UInt8\n                    ),\n                ]\n            )\n        else:\n            pct_low: pl.Series = (\n                df[\"riskassesment_302T\"]\n                .str.split(\" - \")\n                .apply(lambda x: x[0].replace(\"%\", \"\"))\n                .cast(pl.UInt8)\n            )\n            pct_high: pl.Series = (\n                df[\"riskassesment_302T\"]\n                .str.split(\" - \")\n                .apply(lambda x: x[1].replace(\"%\", \"\"))\n                .cast(pl.UInt8)\n            )\n\n            diff: pl.Series = (( pct_high - pct_low ) / ((pct_low + pct_high) / 2)).cast(pl.Float32)\n            avg: pl.Series = (pct_high).cast(pl.Float32)\n\n            del pct_high, pct_low\n            gc.collect()\n\n            df = df.with_columns(\n                [\n                    diff.alias(\"riskassesment_302T_rng\"),\n                    avg.alias(\"riskassesment_302T_mean\"),\n                ]\n            )\n\n        df.drop(\"riskassesment_302T\")\n\n    return df\n\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    \n    print(df_base.shape)\n    df_base = df_base.pipe(Pipeline.handle_dates)\n\n    df_base = transform_cols(df_base)\n   \n    new_column3 = pl.when(pl.col(\"maxdbddpdtollast12m_3658940P\") == 0.0).then(-10e30).otherwise(np.log(pl.col(\"maxdbddpdtollast12m_3658940P\")+1e-30)).alias(\"maxdbddpdtollast12m_3658940P_log\")   \n    new_column4 = pl.when(pl.col(\"max_numberofoverdueinstlmax_1151L\") == 0.0).then(-10e30).otherwise(np.log(pl.col(\"max_numberofoverdueinstlmax_1151L\")+1e-30)).alias(\"max_numberofoverdueinstlmax_1151L_log\")  \n\n    df_base = df_base.with_columns([new_column3,new_column4])\n\n    df_base = df_base.drop([\"clientscnt_100L\",\n                            \"clientscnt_257L\",\n                            \"clientscnt_360L\",\n                            \"clientscnt_304L\",\n                            \"clientscnt_493L\",\n                            \"clientscnt_1071L\",\n                           ])\n    return df_base\n\n\ndef to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols\n\ndef reduce_mem_usage(df):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        col_type = df[col].dtype\n        #print(col_type)\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.execute_input":"2024-05-26T00:35:33.721753Z","iopub.status.busy":"2024-05-26T00:35:33.721122Z","iopub.status.idle":"2024-05-26T00:35:33.773762Z","shell.execute_reply":"2024-05-26T00:35:33.772887Z"},"papermill":{"duration":0.065131,"end_time":"2024-05-26T00:35:33.775798","exception":false,"start_time":"2024-05-26T00:35:33.710667","status":"completed"},"tags":[]},"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.execute_input":"2024-05-26T00:35:33.796571Z","iopub.status.busy":"2024-05-26T00:35:33.795684Z","iopub.status.idle":"2024-05-26T00:35:33.800728Z","shell.execute_reply":"2024-05-26T00:35:33.799731Z"},"papermill":{"duration":0.017468,"end_time":"2024-05-26T00:35:33.802677","exception":false,"start_time":"2024-05-26T00:35:33.785209","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndata_store = {\n    \"df_base\": read_file(TRAIN_DIR / \"train_base.parquet\"),\n    \"depth_0\": [\n        read_file(TRAIN_DIR / \"train_static_cb_0.parquet\"),\n        read_files(TRAIN_DIR / \"train_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_a_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_tax_registry_c_1.parquet\", 1),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_other_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_person_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_deposit_1.parquet\", 1),\n        read_file(TRAIN_DIR / \"train_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TRAIN_DIR / \"train_credit_bureau_b_2.parquet\", 2),\n        read_files(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_applprev_2.parquet\", 2),\n        read_file(TRAIN_DIR / \"train_person_2.parquet\", 2)\n    ]\n}","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:35:33.822141Z","iopub.status.busy":"2024-05-26T00:35:33.821794Z","iopub.status.idle":"2024-05-26T00:37:48.524852Z","shell.execute_reply":"2024-05-26T00:37:48.523918Z"},"papermill":{"duration":134.725104,"end_time":"2024-05-26T00:37:48.536909","exception":false,"start_time":"2024-05-26T00:35:33.811805","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"data_store","metadata":{"execution":{"iopub.execute_input":"2024-04-27T15:16:29.109488Z","iopub.status.busy":"2024-04-27T15:16:29.10897Z","iopub.status.idle":"2024-04-27T15:16:29.151541Z","shell.execute_reply":"2024-04-27T15:16:29.150513Z","shell.execute_reply.started":"2024-04-27T15:16:29.109447Z"},"papermill":{"duration":0.008456,"end_time":"2024-05-26T00:37:48.554072","exception":false,"start_time":"2024-05-26T00:37:48.545616","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"import pickle \nwith open('datas.pkl','wb') as f:\n    pickle.dump(data_store,f)","metadata":{"execution":{"iopub.execute_input":"2024-04-27T15:25:06.995417Z","iopub.status.busy":"2024-04-27T15:25:06.994332Z","iopub.status.idle":"2024-04-27T15:25:08.482812Z","shell.execute_reply":"2024-04-27T15:25:08.481016Z","shell.execute_reply.started":"2024-04-27T15:25:06.995366Z"},"papermill":{"duration":0.008627,"end_time":"2024-05-26T00:37:48.57128","exception":false,"start_time":"2024-05-26T00:37:48.562653","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"# Reduce Memory usage ","metadata":{"papermill":{"duration":0.00845,"end_time":"2024-05-26T00:37:48.588259","exception":false,"start_time":"2024-05-26T00:37:48.579809","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"[](http://)","metadata":{"papermill":{"duration":0.008346,"end_time":"2024-05-26T00:37:48.605098","exception":false,"start_time":"2024-05-26T00:37:48.596752","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.00833,"end_time":"2024-05-26T00:37:48.621923","exception":false,"start_time":"2024-05-26T00:37:48.613593","status":"completed"},"tags":[]}},{"cell_type":"markdown","source":"%%time\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\n\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"papermill":{"duration":0.008298,"end_time":"2024-05-26T00:37:48.638925","exception":false,"start_time":"2024-05-26T00:37:48.630627","status":"completed"},"tags":[]}},{"cell_type":"code","source":"%%time\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\n\nprint(\"train data shape:\\t\", df_train.shape)","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:37:48.65832Z","iopub.status.busy":"2024-05-26T00:37:48.657692Z","iopub.status.idle":"2024-05-26T00:38:08.420415Z","shell.execute_reply":"2024-05-26T00:38:08.419111Z"},"papermill":{"duration":19.774932,"end_time":"2024-05-26T00:38:08.422553","exception":false,"start_time":"2024-05-26T00:37:48.647621","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"df_tarin = df_train.to_pandas()\n\ncat_list = list(df_train.select_dtypes(include='category').columns)\n\ncat_list","metadata":{"execution":{"iopub.execute_input":"2024-04-27T16:07:24.390013Z","iopub.status.busy":"2024-04-27T16:07:24.389522Z","iopub.status.idle":"2024-04-27T16:07:42.104163Z","shell.execute_reply":"2024-04-27T16:07:42.103019Z","shell.execute_reply.started":"2024-04-27T16:07:24.389977Z"},"papermill":{"duration":0.008812,"end_time":"2024-05-26T00:38:08.44053","exception":false,"start_time":"2024-05-26T00:38:08.431718","status":"completed"},"tags":[]}},{"cell_type":"code","source":"#import pickle \n#with open('datas.pkl','wb') as f:\n#    pickle.dump(df_train,f)\n\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\nprint(uses)\nprint(len(uses))\nuses=uses+list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\nprint(list(df_train.select_dtypes(include='category').columns))\ndf_train=df_train[uses]","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:38:08.459687Z","iopub.status.busy":"2024-05-26T00:38:08.459198Z","iopub.status.idle":"2024-05-26T00:39:45.766012Z","shell.execute_reply":"2024-05-26T00:39:45.765161Z"},"papermill":{"duration":97.319061,"end_time":"2024-05-26T00:39:45.768332","exception":false,"start_time":"2024-05-26T00:38:08.449271","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"/kaggle/input/home-credit-credit-risk-model-stability/sample_submission.csv\")\ndevice='gpu'\n#n_samples=200000\nn_est=6000\nDRY_RUN = True if sample.shape[0] == 10 else False   \nif DRY_RUN:\n    device='cpu'\n    df_train = df_train[:50000]\n    #n_samples=10000\n    n_est=600\nprint(device)","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:39:45.796709Z","iopub.status.busy":"2024-05-26T00:39:45.79632Z","iopub.status.idle":"2024-05-26T00:39:45.811277Z","shell.execute_reply":"2024-05-26T00:39:45.810397Z"},"papermill":{"duration":0.03136,"end_time":"2024-05-26T00:39:45.813119","exception":false,"start_time":"2024-05-26T00:39:45.781759","status":"completed"},"tags":[]},"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.execute_input":"2024-05-26T00:39:45.840771Z","iopub.status.busy":"2024-05-26T00:39:45.840245Z","iopub.status.idle":"2024-05-26T00:39:46.182371Z","shell.execute_reply":"2024-05-26T00:39:46.181578Z"},"papermill":{"duration":0.358223,"end_time":"2024-05-26T00:39:46.184678","exception":false,"start_time":"2024-05-26T00:39:45.826455","status":"completed"},"tags":[]},"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()\n\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.execute_input":"2024-05-26T00:39:46.213373Z","iopub.status.busy":"2024-05-26T00:39:46.212583Z","iopub.status.idle":"2024-05-26T00:39:46.814316Z","shell.execute_reply":"2024-05-26T00:39:46.813394Z"},"papermill":{"duration":0.618131,"end_time":"2024-05-26T00:39:46.81639","exception":false,"start_time":"2024-05-26T00:39:46.198259","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Selection","metadata":{"papermill":{"duration":0.013312,"end_time":"2024-05-26T00:39:46.843553","exception":false,"start_time":"2024-05-26T00:39:46.830241","status":"completed"},"tags":[]}},{"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)\n","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:39:46.872415Z","iopub.status.busy":"2024-05-26T00:39:46.871592Z","iopub.status.idle":"2024-05-26T00:39:47.031641Z","shell.execute_reply":"2024-05-26T00:39:47.030828Z"},"papermill":{"duration":0.176828,"end_time":"2024-05-26T00:39:47.033869","exception":false,"start_time":"2024-05-26T00:39:46.857041","status":"completed"},"tags":[]},"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.execute_input":"2024-05-26T00:39:47.062891Z","iopub.status.busy":"2024-05-26T00:39:47.062529Z","iopub.status.idle":"2024-05-26T00:39:47.295312Z","shell.execute_reply":"2024-05-26T00:39:47.294549Z"},"papermill":{"duration":0.249551,"end_time":"2024-05-26T00:39:47.297505","exception":false,"start_time":"2024-05-26T00:39:47.047954","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"import pickle\nwith open('dat.pkl','wb') as f:\n    pickle.dump(df_train,f)","metadata":{"execution":{"iopub.execute_input":"2024-04-18T02:21:30.440683Z","iopub.status.busy":"2024-04-18T02:21:30.438821Z","iopub.status.idle":"2024-04-18T02:21:30.570303Z","shell.execute_reply":"2024-04-18T02:21:30.569433Z","shell.execute_reply.started":"2024-04-18T02:21:30.440636Z"},"papermill":{"duration":0.013514,"end_time":"2024-05-26T00:39:47.32475","exception":false,"start_time":"2024-05-26T00:39:47.311236","status":"completed"},"tags":[]}},{"cell_type":"code","source":"params = {\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\nparams2 = {\n    \"booster\": \"gbtree\",\n    \"objective\": \"binary:logistic\",\n    \"eval_metric\": \"auc\",\n    \"max_depth\": 10,\n    \"learning_rate\": 0.045,\n    \"n_estimators\": 2000,\n    \"colsample_bytree\": 0.78,\n    \"colsample_bynode\": 0.78,\n    \"alpha\": 0.1,  \n    \"lambda\": 10,  \n    \"tree_method\": 'gpu_hist' if device == 'gpu' else 'auto',\n    \"random_state\": 42,\n    \"verbosity\": 0,\n    \"enable_categorical\":True,\n}","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:39:47.353297Z","iopub.status.busy":"2024-05-26T00:39:47.352949Z","iopub.status.idle":"2024-05-26T00:39:47.359854Z","shell.execute_reply":"2024-05-26T00:39:47.359019Z"},"papermill":{"duration":0.023232,"end_time":"2024-05-26T00:39:47.361712","exception":false,"start_time":"2024-05-26T00:39:47.33848","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\nfrom catboost import CatBoostClassifier, Pool\nimport xgboost as xgb\n\nfitted_models_cat = []\nfitted_models_lgb = []\nfitted_models_xgb = []\n\ncv_scores_cat = []\ncv_scores_lgb = []\ncv_scores_xgb = []\n\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    clf = CatBoostClassifier(\n    eval_metric='AUC',\n    task_type='GPU',\n    learning_rate=0.045,\n    bagging_temperature=0.70,\n    l2_leaf_reg = 8,\n    border_count=256,\n    random_seed=42,\n    iterations=n_est)\n    clf.fit(train_pool, eval_set=val_pool,verbose=300)\n    fitted_models_cat.append(clf)\n    y_pred_valid = clf.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    \n    X_train[cat_cols] = X_train[cat_cols].astype(\"category\")\n    X_valid[cat_cols] = X_valid[cat_cols].astype(\"category\")\n    \n    model = lgb.LGBMClassifier(**params)\n    model.fit(\n        X_train, y_train,\n        eval_set = [(X_valid, y_valid)],\n        callbacks = [lgb.log_evaluation(200), lgb.early_stopping(100)] )\n    \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    \n    \n    model2 = xgb.XGBClassifier(**params2)\n    model2.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(model2)\n    \n    y_pred_valid = model2.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 clf, model, model2\n    gc.collect()\n    \n    \nprint(\"CV AUC scores: \", cv_scores_cat)\nprint(\"Maximum CV AUC score: \", max(cv_scores_cat))\n\n\nprint(\"CV AUC scores: \", cv_scores_lgb)\nprint(\"Maximum CV AUC score: \", max(cv_scores_lgb))\n\nprint(\"CV AUC scores: \", cv_scores_xgb)\nprint(\"Maximum CV AUC score: \", max(cv_scores_xgb))","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:39:47.391284Z","iopub.status.busy":"2024-05-26T00:39:47.390647Z","iopub.status.idle":"2024-05-26T00:54:37.379989Z","shell.execute_reply":"2024-05-26T00:54:37.379028Z"},"papermill":{"duration":890.022481,"end_time":"2024-05-26T00:54:37.397909","exception":false,"start_time":"2024-05-26T00:39:47.375428","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del y \ndel weeks\ndel df_train\n\ngc.collect()","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:54:37.431711Z","iopub.status.busy":"2024-05-26T00:54:37.430931Z","iopub.status.idle":"2024-05-26T00:54:37.594821Z","shell.execute_reply":"2024-05-26T00:54:37.593875Z"},"papermill":{"duration":0.182919,"end_time":"2024-05-26T00:54:37.596676","exception":false,"start_time":"2024-05-26T00:54:37.413757","status":"completed"},"tags":[]},"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[5:10]]\n        y_preds+=y_preds #tang trong so\n        y_preds += [estimator.predict_proba(X) for estimator in self.estimators[10:]]\n        print(len(y_preds))\n        return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models_cat+fitted_models_lgb+fitted_models_xgb)","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:54:37.674025Z","iopub.status.busy":"2024-05-26T00:54:37.673681Z","iopub.status.idle":"2024-05-26T00:54:37.682581Z","shell.execute_reply":"2024-05-26T00:54:37.681713Z"},"papermill":{"duration":0.028062,"end_time":"2024-05-26T00:54:37.684416","exception":false,"start_time":"2024-05-26T00:54:37.656354","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.015662,"end_time":"2024-05-26T00:54:37.71605","exception":false,"start_time":"2024-05-26T00:54:37.700388","status":"completed"},"tags":[]}},{"cell_type":"code","source":"del fitted_models_cat, fitted_models_lgb, fitted_models_xgb\ngc.collect()","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:54:37.749957Z","iopub.status.busy":"2024-05-26T00:54:37.749667Z","iopub.status.idle":"2024-05-26T00:54:37.878929Z","shell.execute_reply":"2024-05-26T00:54:37.878058Z"},"papermill":{"duration":0.149171,"end_time":"2024-05-26T00:54:37.881036","exception":false,"start_time":"2024-05-26T00:54:37.731865","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.016516,"end_time":"2024-05-26T00:54:37.914031","exception":false,"start_time":"2024-05-26T00:54:37.897515","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Submision","metadata":{"papermill":{"duration":0.015961,"end_time":"2024-05-26T00:54:37.945978","exception":false,"start_time":"2024-05-26T00:54:37.930017","status":"completed"},"tags":[]}},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")","metadata":{"execution":{"iopub.execute_input":"2024-05-26T00:54:37.979237Z","iopub.status.busy":"2024-05-26T00:54:37.978906Z","iopub.status.idle":"2024-05-26T00:54:38.007051Z","shell.execute_reply":"2024-05-26T00:54:38.006302Z"},"papermill":{"duration":0.047082,"end_time":"2024-05-26T00:54:38.008974","exception":false,"start_time":"2024-05-26T00:54:37.961892","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\n\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.execute_input":"2024-05-26T00:54:38.042445Z","iopub.status.busy":"2024-05-26T00:54:38.042149Z","iopub.status.idle":"2024-05-26T00:54:38.962075Z","shell.execute_reply":"2024-05-26T00:54:38.96105Z"},"papermill":{"duration":0.938973,"end_time":"2024-05-26T00:54:38.964134","exception":false,"start_time":"2024-05-26T00:54:38.025161","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"papermill":{"duration":0.016287,"end_time":"2024-05-26T00:54:38.997693","exception":false,"start_time":"2024-05-26T00:54:38.981406","status":"completed"},"tags":[]},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{"papermill":{"duration":0.016127,"end_time":"2024-05-26T00:54:39.030116","exception":false,"start_time":"2024-05-26T00:54:39.013989","status":"completed"},"tags":[]}}]}