{"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"},{"sourceId":162470947,"sourceType":"kernelVersion"},{"sourceId":177580815,"sourceType":"kernelVersion"}],"dockerImageVersionId":30665,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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\nimport joblib\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\nfrom sklearn.model_selection import StratifiedGroupKFold\nimport warnings\nwarnings.filterwarnings('ignore')","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-23T15:45:45.456883Z","iopub.execute_input":"2024-05-23T15:45:45.457308Z","iopub.status.idle":"2024-05-23T15:45:49.115446Z","shell.execute_reply.started":"2024-05-23T15:45:45.457275Z","shell.execute_reply":"2024-05-23T15:45:49.113851Z"},"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 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\n                avg: pl.Series = ((pct_low + pct_high) / 2).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    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_940T\",\n                           \"riskassesment_302T_rng\", \"riskassesment_302T_mean\"]:\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\", \"riskassesment_940T\",\n                            \"riskassesment_302T_rng\", \"riskassesment_302T_mean\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n                    \n        for col in df.columns:\n            if col[-1] == \"C\":\n                if (df[col] == 0).mean() > 0.9:\n                    df = df.drop(col)\n        \n        return df\n\ncategories = {}\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_min+expr_median\n    \n    def cat_expr(df, test=False):\n        agg_cols = []\n        if test:\n            cat_cols = categories.keys()\n            for col in df.columns:\n                if col in cat_cols:\n                    for value in categories[col]:\n                        agg_cols += [pl.col(col).filter(pl.col(col) == value).count().alias(f\"{col}_{value}_C\")]\n        else:\n            for col in df.select([pl.col(pl.String), pl.col(pl.Boolean)]).columns:\n                values = df[col].unique().to_list()\n                if len(values) <= 10 and df[col].is_null().mean() < 0.9:\n                    try:\n                        categories[col] = list(set(categories[col] + values))\n                    except:\n                        categories[col] = values\n                    for value in values:\n                        agg_cols += [pl.col(col).filter(pl.col(col) == value).count().alias(f\"{col}_{value}_C\")]\n\n        return agg_cols\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_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        \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, test=False, cat_cols=False):\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        if cat_cols:\n            exprs += Aggregator.cat_expr(df, test)\n\n        return exprs\n\ndef read_file(path, depth=None, test=False, cat_cols=False):\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, test, cat_cols)) \n    return df\n\ndef read_files(regex_path, depth=None, test=False, cat_cols=False):\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, test, cat_cols))\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"diagonal_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df\n\ndef feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base\n\ndef to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols\n\ndef reduce_mem_usage(df):\n    \"\"\" 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\" or col == \"date_decision\":\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":"2024-05-23T15:45:49.118148Z","iopub.execute_input":"2024-05-23T15:45:49.118863Z","iopub.status.idle":"2024-05-23T15:45:49.199430Z","shell.execute_reply.started":"2024-05-23T15:45:49.118814Z","shell.execute_reply":"2024-05-23T15:45:49.197896Z"},"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":"2024-05-23T15:45:49.201501Z","iopub.execute_input":"2024-05-23T15:45:49.202015Z","iopub.status.idle":"2024-05-23T15:45:49.222220Z","shell.execute_reply.started":"2024-05-23T15:45:49.201966Z","shell.execute_reply":"2024-05-23T15:45:49.220696Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"chunks = []\n\nfor path in glob(str(TRAIN_DIR / \"train_credit_bureau_a_2_*.parquet\")):\n    print(path)\n    df = pl.read_parquet(path, columns=[\"case_id\", \"num_group1\", \"pmts_month_158T\", \"pmts_month_706T\"])\n    df = df.group_by([\"case_id\", \"num_group1\"]).agg(\n        pl.count(\"pmts_month_158T\").alias(\"count_pmts_month_158T\"),\n        pl.count(\"pmts_month_706T\").alias(\"count_pmts_month_706T\"),\n    ).group_by(\"case_id\").agg(\n        pl.when(pl.col(\"count_pmts_month_158T\") > 0).then(pl.col(\"count_pmts_month_158T\")).otherwise(None).min().alias(\"min_count_pmts_month_158T\"),\n        pl.when(pl.col(\"count_pmts_month_158T\") > 0).then(pl.col(\"count_pmts_month_158T\")).otherwise(None).max().alias(\"max_count_pmts_month_158T\"),\n        pl.when(pl.col(\"count_pmts_month_158T\") > 0).then(pl.col(\"count_pmts_month_158T\")).otherwise(None).mean().alias(\"mean_count_pmts_month_158T\"),\n        pl.when(pl.col(\"count_pmts_month_158T\") > 0).then(pl.col(\"count_pmts_month_158T\")).otherwise(None).std().alias(\"std_count_pmts_month_158T\"),\n        pl.when(pl.col(\"count_pmts_month_706T\") > 0).then(pl.col(\"count_pmts_month_706T\")).otherwise(None).min().alias(\"min_count_pmts_month_706T\"),\n        pl.when(pl.col(\"count_pmts_month_706T\") > 0).then(pl.col(\"count_pmts_month_706T\")).otherwise(None).max().alias(\"max_count_pmts_month_706T\"),\n        pl.when(pl.col(\"count_pmts_month_706T\") > 0).then(pl.col(\"count_pmts_month_706T\")).otherwise(None).mean().alias(\"mean_count_pmts_month_706T\"),\n        pl.when(pl.col(\"count_pmts_month_706T\") > 0).then(pl.col(\"count_pmts_month_706T\")).otherwise(None).std().alias(\"std_count_pmts_month_706T\"),\n#         [f(pl.when(pl.col(col) > 0).then(pl.col(col)).otherwise(None)).alias(f\"{agg}_{col}\") for f, agg in [(pl.max, \"max\"), (pl.min, \"min\"), (pl.mean, \"mean\")] for col in [\"count_pmts_month_158T\", \"count_pmts_month_706T\"]]\n    )\n    chunks.append(df)\n\ncredit_bureau_a_2_feats = pl.concat(chunks, how=\"diagonal_relaxed\")\ncredit_bureau_a_2_feats = credit_bureau_a_2_feats.unique(subset=[\"case_id\"])\n\ndel df\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:45:49.230159Z","iopub.execute_input":"2024-05-23T15:45:49.231111Z","iopub.status.idle":"2024-05-23T15:46:46.441514Z","shell.execute_reply.started":"2024-05-23T15:45:49.231072Z","shell.execute_reply":"2024-05-23T15:46:46.440037Z"},"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, False, True),\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":"2024-05-23T15:54:36.650639Z","iopub.execute_input":"2024-05-23T15:54:36.651095Z","iopub.status.idle":"2024-05-23T15:57:29.295323Z","shell.execute_reply.started":"2024-05-23T15:54:36.651060Z","shell.execute_reply":"2024-05-23T15:57:29.293994Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:57:29.297869Z","iopub.execute_input":"2024-05-23T15:57:29.298380Z","iopub.status.idle":"2024-05-23T15:57:52.108275Z","shell.execute_reply.started":"2024-05-23T15:57:29.298340Z","shell.execute_reply":"2024-05-23T15:57:52.107042Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = df_train.join(credit_bureau_a_2_feats, how=\"left\", on=\"case_id\")","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:57:52.110012Z","iopub.execute_input":"2024-05-23T15:57:52.110400Z","iopub.status.idle":"2024-05-23T15:57:52.748719Z","shell.execute_reply.started":"2024-05-23T15:57:52.110369Z","shell.execute_reply":"2024-05-23T15:57:52.746942Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = df_train.pipe(Pipeline.transform_cols).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)","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:57:52.752802Z","iopub.execute_input":"2024-05-23T15:57:52.754540Z","iopub.status.idle":"2024-05-23T15:58:54.074862Z","shell.execute_reply.started":"2024-05-23T15:57:52.754437Z","shell.execute_reply":"2024-05-23T15:58:54.073528Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:58:54.076688Z","iopub.execute_input":"2024-05-23T15:58:54.077178Z","iopub.status.idle":"2024-05-23T15:58:54.562674Z","shell.execute_reply.started":"2024-05-23T15:58:54.077138Z","shell.execute_reply":"2024-05-23T15:58:54.561490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"nums=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))","metadata":{"execution":{"iopub.status.busy":"2024-05-23T15:58:54.564264Z","iopub.execute_input":"2024-05-23T15:58:54.564696Z","iopub.status.idle":"2024-05-23T15:59:39.369041Z","shell.execute_reply.started":"2024-05-23T15:58:54.564652Z","shell.execute_reply":"2024-05-23T15:59:39.367749Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"uses=uses+list(df_train.select_dtypes(include=['category']).columns) + [\"riskassesment_302T_rng\"]\nprint(len(uses))\ndf_train=df_train[uses]","metadata":{"execution":{"iopub.status.busy":"2024-05-23T16:00:43.164040Z","iopub.execute_input":"2024-05-23T16:00:43.164510Z","iopub.status.idle":"2024-05-23T16:00:47.201920Z","shell.execute_reply.started":"2024-05-23T16:00:43.164473Z","shell.execute_reply":"2024-05-23T16:00:47.200582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"joblib.dump(df_train, \"df_train.pkl\")","metadata":{"execution":{"iopub.status.busy":"2024-05-23T16:00:47.449154Z","iopub.execute_input":"2024-05-23T16:00:47.449545Z","iopub.status.idle":"2024-05-23T16:00:50.545369Z","shell.execute_reply.started":"2024-05-23T16:00:47.449515Z","shell.execute_reply":"2024-05-23T16:00:50.544037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"joblib.dump(cat_cols, \"cat_columns.pkl\")","metadata":{"execution":{"iopub.status.busy":"2024-05-23T16:00:50.547458Z","iopub.execute_input":"2024-05-23T16:00:50.547861Z","iopub.status.idle":"2024-05-23T16:00:50.557438Z","shell.execute_reply.started":"2024-05-23T16:00:50.547829Z","shell.execute_reply":"2024-05-23T16:00:50.556106Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"joblib.dump(categories, \"categories.pkl\")","metadata":{"execution":{"iopub.status.busy":"2024-05-23T16:00:50.559392Z","iopub.execute_input":"2024-05-23T16:00:50.559793Z","iopub.status.idle":"2024-05-23T16:00:50.584282Z","shell.execute_reply.started":"2024-05-23T16:00:50.559761Z","shell.execute_reply":"2024-05-23T16:00:50.583037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}