{"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":30673,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Home Credit Competition","metadata":{}},{"cell_type":"markdown","source":"### Import Libs","metadata":{}},{"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","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:40.629225Z","iopub.execute_input":"2024-04-01T22:38:40.629883Z","iopub.status.idle":"2024-04-01T22:38:43.812108Z","shell.execute_reply.started":"2024-04-01T22:38:40.629836Z","shell.execute_reply":"2024-04-01T22:38:43.810550Z"},"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, SimpleImputer","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:43.814318Z","iopub.execute_input":"2024-04-01T22:38:43.814856Z","iopub.status.idle":"2024-04-01T22:38:45.895873Z","shell.execute_reply.started":"2024-04-01T22:38:43.814823Z","shell.execute_reply":"2024-04-01T22:38:45.894394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-01T22:38:45.897635Z","iopub.execute_input":"2024-04-01T22:38:45.898695Z","iopub.status.idle":"2024-04-01T22:38:45.935864Z","shell.execute_reply.started":"2024-04-01T22:38:45.898650Z","shell.execute_reply":"2024-04-01T22:38:45.934517Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Options","metadata":{}},{"cell_type":"code","source":"warnings.filterwarnings('ignore')","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:45.939015Z","iopub.execute_input":"2024-04-01T22:38:45.939516Z","iopub.status.idle":"2024-04-01T22:38:45.944654Z","shell.execute_reply.started":"2024-04-01T22:38:45.939474Z","shell.execute_reply":"2024-04-01T22:38:45.943683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%matplotlib inline","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:45.945840Z","iopub.execute_input":"2024-04-01T22:38:45.946361Z","iopub.status.idle":"2024-04-01T22:38:45.958568Z","shell.execute_reply.started":"2024-04-01T22:38:45.946323Z","shell.execute_reply":"2024-04-01T22:38:45.957653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Code","metadata":{"execution":{"iopub.status.busy":"2024-04-01T17:06:45.017106Z","iopub.execute_input":"2024-04-01T17:06:45.017531Z","iopub.status.idle":"2024-04-01T17:06:45.023113Z","shell.execute_reply.started":"2024-04-01T17:06:45.017502Z","shell.execute_reply":"2024-04-01T17:06:45.021754Z"}}},{"cell_type":"code","source":"class Pipeline:\n\n    def set_table_dtypes(df):\n        for col in df.columns:\n            if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Int64))\n            elif col in [\"date_decision\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n            elif col[-1] in (\"P\", \"A\"):\n                df = df.with_columns(pl.col(col).cast(pl.Float64))\n            elif col[-1] in (\"M\",):\n                df = df.with_columns(pl.col(col).cast(pl.String))\n            elif col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n        return df\n\n    def handle_dates(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col) - pl.col(\"date_decision\"))  #!!?\n                df = df.with_columns(pl.col(col).dt.total_days()) # t - t-1\n        df = df.drop(\"date_decision\", \"MONTH\")\n        return df\n\n    def filter_cols(df):\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n                if isnull > 0.7:\n                    df = df.drop(col)\n        \n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n        \n        return df","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:45.960168Z","iopub.execute_input":"2024-04-01T22:38:45.960629Z","iopub.status.idle":"2024-04-01T22:38:45.975938Z","shell.execute_reply.started":"2024-04-01T22:38:45.960586Z","shell.execute_reply":"2024-04-01T22:38:45.974698Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Aggregator:\n    #Please add or subtract features yourself, be aware that too many features will take up too much space.\n    def num_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"P\", \"A\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        \n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return expr_max +expr_last+expr_mean\n    \n    def date_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"D\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        expr_mean = [pl.mean(col).alias(f\"mean_{col}\") for col in cols]\n        return  expr_max +expr_last+expr_mean\n    \n    def str_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"M\",)]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        #expr_count = [pl.count(col).alias(f\"count_{col}\") for col in cols]\n        return  expr_max +expr_last#+expr_count\n    \n    def other_expr(df):\n        cols = [col for col in df.columns if col[-1] in (\"T\", \"L\")]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols]\n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\n    \n    def count_expr(df):\n        cols = [col for col in df.columns if \"num_group\" in col]\n        expr_max = [pl.max(col).alias(f\"max_{col}\") for col in cols] \n        #expr_min = [pl.min(col).alias(f\"min_{col}\") for col in cols]\n        expr_last = [pl.last(col).alias(f\"last_{col}\") for col in cols]\n        #expr_first = [pl.first(col).alias(f\"first_{col}\") for col in cols]\n        return  expr_max +expr_last\n    \n    def get_exprs(df):\n        exprs = Aggregator.num_expr(df) + \\\n                Aggregator.date_expr(df) + \\\n                Aggregator.str_expr(df) + \\\n                Aggregator.other_expr(df) + \\\n                Aggregator.count_expr(df)\n\n        return exprs","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:45.977682Z","iopub.execute_input":"2024-04-01T22:38:45.978452Z","iopub.status.idle":"2024-04-01T22:38:45.997315Z","shell.execute_reply.started":"2024-04-01T22:38:45.978419Z","shell.execute_reply":"2024-04-01T22:38:45.995785Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    if depth in [1,2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n    return df\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    \n    for path in glob(str(regex_path)):\n        df = pl.read_parquet(path)\n        df = df.pipe(Pipeline.set_table_dtypes)\n        if depth in [1, 2]:\n            df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df))\n        chunks.append(df)\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    df = df.unique(subset=[\"case_id\"])\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:45.998885Z","iopub.execute_input":"2024-04-01T22:38:45.999378Z","iopub.status.idle":"2024-04-01T22:38:46.013275Z","shell.execute_reply.started":"2024-04-01T22:38:45.999344Z","shell.execute_reply":"2024-04-01T22:38:46.011877Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def feature_eng(df_base, depth_0, depth_1, depth_2):\n    df_base = (\n        df_base\n        .with_columns(\n            month_decision = pl.col(\"date_decision\").dt.month(),\n            weekday_decision = pl.col(\"date_decision\").dt.weekday(),\n        )\n    )\n    for i, df in enumerate(depth_0 + depth_1 + depth_2):\n        df_base = df_base.join(df, how=\"left\", on=\"case_id\", suffix=f\"_{i}\")\n    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:46.015043Z","iopub.execute_input":"2024-04-01T22:38:46.016056Z","iopub.status.idle":"2024-04-01T22:38:46.028685Z","shell.execute_reply.started":"2024-04-01T22:38:46.016023Z","shell.execute_reply":"2024-04-01T22:38:46.027003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:46.032877Z","iopub.execute_input":"2024-04-01T22:38:46.033893Z","iopub.status.idle":"2024-04-01T22:38:46.040098Z","shell.execute_reply.started":"2024-04-01T22:38:46.033856Z","shell.execute_reply":"2024-04-01T22:38:46.039165Z"},"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":"2024-04-01T22:38:46.041479Z","iopub.execute_input":"2024-04-01T22:38:46.042018Z","iopub.status.idle":"2024-04-01T22:38:46.059545Z","shell.execute_reply.started":"2024-04-01T22:38:46.041987Z","shell.execute_reply":"2024-04-01T22:38:46.058407Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Data Processing","metadata":{}},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-04-01T22:38:46.061434Z","iopub.execute_input":"2024-04-01T22:38:46.061952Z","iopub.status.idle":"2024-04-01T22:38:46.075930Z","shell.execute_reply.started":"2024-04-01T22:38:46.061913Z","shell.execute_reply":"2024-04-01T22:38:46.074918Z"},"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":"2024-04-01T22:38:46.077890Z","iopub.execute_input":"2024-04-01T22:38:46.078340Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Train Dataset","metadata":{}},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ngc.collect()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_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)","metadata":{"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()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"uses=[]\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":{"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Dataset","metadata":{}},{"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":{"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()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Feature Selection","metadata":{}},{"cell_type":"code","source":"df_train['nan_cols'] = df_train.isnull().sum(axis = 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test['nan_cols'] = df_test.isnull().sum(axis = 1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['nan_cols'].plot(kind='hist', color='green', bins=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test['nan_cols'].plot(kind='hist', color='blue', bins=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### NaN Imputer","metadata":{}},{"cell_type":"code","source":"# ! pip install feature-engine","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# from feature_engine.imputation import CategoricalImputer","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# num_imputer = KNNImputer(n_neighbors=5).set_output(transform='pandas')\nnum_imputer = SimpleImputer(strategy='median').set_output(transform='pandas')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# cat_imputer = CategoricalImputer(imputation_method='frequent').set_output(transform='pandas')\n# cat_imputer = CategoricalImputer(imputation_method='missing').set_output(transform='pandas')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"to_drop = [\"target\", \"case_id\", \"WEEK_NUM\"]\ndf_train_y = df_train[to_drop]\ndf_train_o = df_train.drop(columns=to_drop)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"to_drop_test = [\"case_id\", \"WEEK_NUM\"]\ndf_test_y = df_test[to_drop_test]\ndf_test_o = df_test.drop(columns=to_drop_test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols = list(df_train_o.columns)\nlen(cols)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_cols = list(df_train_o._get_numeric_data().columns)\nlen(num_cols)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_cols = list(set(cols) - set(num_cols))\nlen(cat_cols)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"assert len(cols) == len(num_cols) + len(cat_cols)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_full_num = pd.concat([df_train_o[num_cols], df_test_o[num_cols]], axis=0)\nnum_imputer.fit(df_full_num)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_full_cat = pd.concat([df_train_o[cat_cols], df_test_o[cat_cols]], axis=0)\n# cat_imputer.fit(df_full_cat)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train = pd.concat([num_imputer.transform(df_train_o[num_cols]), \n#                       cat_imputer.transform(df_train_o[cat_cols]), \n#                       df_train_y], axis=1)\ndf_train = pd.concat([num_imputer.transform(df_train_o[num_cols]), \n                      df_train_o[cat_cols], \n                      df_train_y], axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_test = pd.concat([num_imputer.transform(df_test_o[num_cols]), \n#                      cat_imputer.transform(df_test_o[cat_cols]), \n#                      df_test_y], axis=1)\ndf_test = pd.concat([num_imputer.transform(df_test_o[num_cols]), \n                     df_test_o[cat_cols], \n                     df_test_y], axis=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Model","metadata":{}},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\nX = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"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\nfitted_models = []\ncv_scores = []\n\n\nfor idx_train, idx_valid in cv.split(X, y, groups=weeks):#   Because it takes a long time to divide the data set, \n    X_train, y_train = X.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 = X.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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Maximum CV AUC score:  0.786151858029422","metadata":{"execution":{"iopub.status.busy":"2024-04-01T18:41:08.062656Z","iopub.execute_input":"2024-04-01T18:41:08.063196Z","iopub.status.idle":"2024-04-01T18:41:08.071313Z","shell.execute_reply.started":"2024-04-01T18:41:08.063160Z","shell.execute_reply":"2024-04-01T18:41:08.069631Z"}}},{"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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = VotingModel(fitted_models)","metadata":{"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":{"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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"drop_list = []\nfor i, f in feature_importance.iterrows():\n    if f['importance']<40:\n        drop_list.append(f['features'])\nprint(f\"Number of features which are not important: {len(drop_list)} \")\n\nprint(drop_list)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = df_test.drop(columns=[\"WEEK_NUM\"])\ndf_test = df_test.set_index(\"case_id\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Test Model","metadata":{}},{"cell_type":"code","source":"# model_t = lgb.LGBMClassifier(**params)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# model_t.fit(X.drop(columns=drop_list), y)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred = pd.Series(model_t.predict_proba(df_test.drop(columns=drop_list))[:, 1], index=df_test.index)\n# df_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\n# df_subm = df_subm.set_index(\"case_id\")\n\n# df_subm[\"score\"] = y_pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_subm.to_csv(\"submission_03.csv\")\n# df_subm","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_subm[\"score\"].plot(kind='hist', bins=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Submission","metadata":{"execution":{"iopub.status.busy":"2024-04-01T17:42:02.592443Z","iopub.execute_input":"2024-04-01T17:42:02.594568Z","iopub.status.idle":"2024-04-01T17:42:02.603212Z","shell.execute_reply.started":"2024-04-01T17:42:02.594506Z","shell.execute_reply":"2024-04-01T17:42:02.601541Z"}}},{"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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train['target'].plot(kind='hist', bins=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm[\"score\"].plot(kind='hist', bins=20)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_subm.loc[df_subm['score'] <= 0.05, 'score'] = 0","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# TO DO\n- 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 ... ...","metadata":{}},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}