{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"},{"sourceId":8070650,"sourceType":"datasetVersion","datasetId":4755062,"isSourceIdPinned":true},{"sourceId":8122314,"sourceType":"datasetVersion","datasetId":4761515,"isSourceIdPinned":true}],"dockerImageVersionId":30683,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Home Credit Ensemble Model","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:03:35.030948Z","iopub.execute_input":"2024-05-11T01:03:35.031523Z","iopub.status.idle":"2024-05-11T01:03:35.036626Z","shell.execute_reply.started":"2024-05-11T01:03:35.031487Z","shell.execute_reply":"2024-05-11T01:03:35.035730Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import sys\nfrom pathlib import Path\nimport subprocess\nimport os\nimport gc\nfrom glob import glob\nfrom tqdm import tqdm_notebook\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\nimport pickle as pkl\nfrom sklearn.model_selection import 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\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-11T01:03:35.038192Z","iopub.execute_input":"2024-05-11T01:03:35.038471Z","iopub.status.idle":"2024-05-11T01:03:41.034789Z","shell.execute_reply.started":"2024-05-11T01:03:35.038448Z","shell.execute_reply":"2024-05-11T01:03:41.033909Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Pipeline:\n\n    def set_table_dtypes(df):\n        for col in df.columns:\n            if col in [\"case_id\", \"WEEK_NUM\", \"num_group1\", \"num_group2\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Int64))\n            elif col in [\"date_decision\"]:\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n            elif col[-1] in (\"P\", \"A\"):\n                df = df.with_columns(pl.col(col).cast(pl.Float64))\n            elif col[-1] in (\"M\",):\n                df = df.with_columns(pl.col(col).cast(pl.String))\n            elif col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col).cast(pl.Date))\n        return df\n\n    def handle_dates(df):\n        for col in df.columns:\n            if col[-1] in (\"D\",):\n                df = df.with_columns(pl.col(col) - pl.col(\"date_decision\"))  #!!?\n                df = df.with_columns(pl.col(col).dt.total_days()) # t - t-1\n        df = df.drop(\"date_decision\", \"MONTH\")\n        return df\n\n    def filter_cols(df):\n        for col in df.columns:\n            if col not in [\"target\", \"case_id\", \"WEEK_NUM\"]:\n                isnull = df[col].is_null().mean()\n                if isnull > 0.7:\n                    df = df.drop(col)\n        \n        for col in df.columns:\n            if (col not in [\"target\", \"case_id\", \"WEEK_NUM\"]) & (df[col].dtype == pl.String):\n                freq = df[col].n_unique()\n                if (freq == 1) | (freq > 200):\n                    df = df.drop(col)\n        \n        return df\n\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        expr_median = [pl.median(col).alias(f\"median_{col}\") for col in cols]\n        expr_var = [pl.var(col).alias(f\"var_{col}\") for col in cols]\n\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        expr_median = [pl.median(col).alias(f\"median_{col}\") for col in cols]\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        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":"2024-05-11T01:03:41.036523Z","iopub.execute_input":"2024-05-11T01:03:41.037289Z","iopub.status.idle":"2024-05-11T01:03:41.061118Z","shell.execute_reply.started":"2024-05-11T01:03:41.037253Z","shell.execute_reply":"2024-05-11T01:03:41.060132Z"},"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\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    df_base = df_base.pipe(Pipeline.handle_dates)\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\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\":\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":"2024-05-11T01:03:41.063448Z","iopub.execute_input":"2024-05-11T01:03:41.063714Z","iopub.status.idle":"2024-05-11T01:03:41.083691Z","shell.execute_reply.started":"2024-05-11T01:03:41.063692Z","shell.execute_reply":"2024-05-11T01:03:41.082771Z"},"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\"\n\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.status.busy":"2024-05-11T01:03:41.084723Z","iopub.execute_input":"2024-05-11T01:03:41.085014Z","iopub.status.idle":"2024-05-11T01:05:56.530853Z","shell.execute_reply.started":"2024-05-11T01:03:41.084992Z","shell.execute_reply":"2024-05-11T01:05:56.529789Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\ndel data_store\ndf_train = df_train.pipe(Pipeline.filter_cols)\nprint(\"train data shape:\\t\", df_train.shape)\ngc.collect()\n","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:05:56.532439Z","iopub.execute_input":"2024-05-11T01:05:56.532884Z","iopub.status.idle":"2024-05-11T01:06:17.781626Z","shell.execute_reply.started":"2024-05-11T01:05:56.532845Z","shell.execute_reply":"2024-05-11T01:06:17.780783Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_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\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;\nx = gc.collect()\n\n\ndef reduce_group(grps):\n    use = []\n    for g in grps:\n        mx = 0;\n        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\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\n\nuses = []\nfor k, v in nans_groups.items():\n    if len(v) > 1:\n        Vs = nans_groups[k]\n        # cross_features=list(combinations(Vs, 2))\n        # make_corr(Vs)\n        grps = group_columns_by_correlation(df_train[Vs], threshold=0.8)\n        use = reduce_group(grps)\n        uses = uses + use\n        # make_corr(use)\n    else:\n        uses = uses + v\n    print('####### NAN count =', k)\nprint(uses)\nprint(len(uses))\nuses = uses + list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\ndf_train = df_train[uses]","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:06:17.782641Z","iopub.execute_input":"2024-05-11T01:06:17.782948Z","iopub.status.idle":"2024-05-11T01:07:35.387340Z","shell.execute_reply.started":"2024-05-11T01:06:17.782924Z","shell.execute_reply":"2024-05-11T01:07:35.386483Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"\n\ndata_store = {\n    \"df_base\": read_file(TEST_DIR / \"test_base.parquet\"),\n    \"depth_0\": [\n        read_file(TEST_DIR / \"test_static_cb_0.parquet\"),\n        read_files(TEST_DIR / \"test_static_0_*.parquet\"),\n    ],\n    \"depth_1\": [\n        read_files(TEST_DIR / \"test_applprev_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_a_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_tax_registry_c_1.parquet\", 1),\n        read_files(TEST_DIR / \"test_credit_bureau_a_1_*.parquet\", 1),\n        read_file(TEST_DIR / \"test_credit_bureau_b_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_other_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_person_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_deposit_1.parquet\", 1),\n        read_file(TEST_DIR / \"test_debitcard_1.parquet\", 1),\n    ],\n    \"depth_2\": [\n        read_file(TEST_DIR / \"test_credit_bureau_b_2.parquet\", 2),\n        read_files(TEST_DIR / \"test_credit_bureau_a_2_*.parquet\", 2),\n        read_file(TEST_DIR / \"test_applprev_2.parquet\", 2),\n        read_file(TEST_DIR / \"test_person_2.parquet\", 2)\n    ]\n}","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:35.388479Z","iopub.execute_input":"2024-05-11T01:07:35.388780Z","iopub.status.idle":"2024-05-11T01:07:35.744198Z","shell.execute_reply.started":"2024-05-11T01:07:35.388755Z","shell.execute_reply":"2024-05-11T01:07:35.743405Z"},"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()\n\ndf_test = df_test.select([col for col in df_train.columns if col not in [\"target\"]])\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\n\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:35.745237Z","iopub.execute_input":"2024-05-11T01:07:35.745487Z","iopub.status.idle":"2024-05-11T01:07:36.242034Z","shell.execute_reply.started":"2024-05-11T01:07:35.745465Z","shell.execute_reply":"2024-05-11T01:07:36.241167Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb_models = []\n# TODO load trained models\nn_fold = 5\nfor i in range(n_fold):\n    with open(f'/kaggle/input/home-credit-lgb/home-credit-lgb/model_{i}.pkl', 'rb') as fin:\n        lgb_models.append(pkl.load(fin))\nprint('load lgb done.')","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:36.244490Z","iopub.execute_input":"2024-05-11T01:07:36.244788Z","iopub.status.idle":"2024-05-11T01:07:36.810439Z","shell.execute_reply.started":"2024-05-11T01:07:36.244760Z","shell.execute_reply":"2024-05-11T01:07:36.809695Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_models = []\n\n# TODO load trained models\nn_fold = 5\nfor i in range(n_fold):\n    with open(f'/kaggle/input/home-credit-cab/home-credit-cab/model_{i}.pkl', 'rb') as fin:\n        cat_models.append(pkl.load(fin))\nprint('load cat done.')","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:36.811618Z","iopub.execute_input":"2024-05-11T01:07:36.812531Z","iopub.status.idle":"2024-05-11T01:07:38.456095Z","shell.execute_reply.started":"2024-05-11T01:07:36.812503Z","shell.execute_reply":"2024-05-11T01:07:38.455142Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class VotingModel(BaseEstimator, RegressorMixin):\n    def __init__(self, estimators):\n        super().__init__()\n        self.estimators = estimators\n        \n    def fit(self, X, y=None):\n        return self\n    \n    def predict(self, X):\n        y_preds = [estimator.predict(X) for estimator in self.estimators]\n        return np.mean(y_preds, axis=0)\n    \n#     def predict_proba(self, X):\n#         y_preds = [estimator.predict_proba(X) for estimator in self.estimators]\n#         return np.mean(y_preds, axis=0)\n\n    def predict_proba(self, X):\n#         weights = [0.6] * 5 + [0.4] * 5\n        X[cat_cols] = X[cat_cols].astype(str)\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) + 0.01 for estimator in self.estimators[5:]]\n        \n#         y_preds = [item * weights[i] for i, item in enumerate(y_preds)]\n        return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(cat_models + lgb_models)","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:38.457417Z","iopub.execute_input":"2024-05-11T01:07:38.457801Z","iopub.status.idle":"2024-05-11T01:07:38.466659Z","shell.execute_reply.started":"2024-05-11T01:07:38.457761Z","shell.execute_reply":"2024-05-11T01:07:38.465491Z"},"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\")\n\ny_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\n\ncondition=y_pred<0.98\n\ndf_subm = pd.read_csv(ROOT / \"sample_submission.csv\")\ndf_subm = df_subm.set_index(\"case_id\")\n\n# df_subm[\"score\"] = y_pred\ndf_subm.loc[condition, 'score'] = (df_subm.loc[condition, 'score'] - 0.073).clip(0)\ndf_subm.to_csv(\"submission.csv\")\ndf_subm","metadata":{"execution":{"iopub.status.busy":"2024-05-11T01:07:38.467709Z","iopub.execute_input":"2024-05-11T01:07:38.468002Z","iopub.status.idle":"2024-05-11T01:07:39.160864Z","shell.execute_reply.started":"2024-05-11T01:07:38.467979Z","shell.execute_reply":"2024-05-11T01:07:39.159949Z"},"trusted":true},"execution_count":null,"outputs":[]}]}