{"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":"nvidiaTeslaT4","dataSources":[{"sourceId":50160,"databundleVersionId":7921029,"sourceType":"competition"}],"dockerImageVersionId":30684,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# COMMAND ----------\n\nimport sys\nfrom pathlib import Path\nimport subprocess\nimport os\nimport gc\nfrom glob import glob\nimport boto3\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\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\nimport xgboost as xgb\nfrom sklearn.ensemble import GradientBoostingClassifier\nfrom catboost import CatBoostClassifier, Pool\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer\nimport os\n\nKAGGLE = True\n\n# COMMAND ----------\n\nif not KAGGLE:\n    os.chdir('/Workspace/Users/Elliott.Sloate@nrg.com/Hackathon Q2 2024')\n\n# COMMAND ----------\n\nif KAGGLE:\n    ROOT            = \"/kaggle/input/home-credit-credit-risk-model-stability\"\n    TRAIN_DIR       = ROOT + \"/parquet_files\" + \"/train/\"\n    TEST_DIR        = ROOT + \"/parquet_files\" + \"/test/\"\nelse:\n    from module_nonspark.s3ops import fetch_pkl, store_pkl\n    from module_spark.dfops import env, conf\n    ROOT            = '/Workspace/Users/Elliott.Sloate@nrg.com/Hackathon Q2 2024'\n\n    TRAIN_DIR       = ROOT + \"/parquet_files/train/\"\n    TEST_DIR        = ROOT + \"/parquet_files/test/\"\n\n\n# COMMAND ----------\n\nclass 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 > 0.95:\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\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        #expr_sum = [pl.sum(col).alias(f\"sum_{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 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\n\ndef read_file(path, depth=None):\n    df = pl.read_parquet(path)\n    df = df.pipe(Pipeline.set_table_dtypes)\n    fill_cols = []\n    for col in fill_cols:\n        if col in df.columns:\n            df = df.with_column(\n                pl.col().fillna(0)\n            )\n\n    if depth in [1,2]:\n        df = df.group_by(\"case_id\").agg(Aggregator.get_exprs(df)) \n    return df\n\ndef list_all_parq_files(filepath):\n\n    s3_bucket = conf[env]['bucket_ads']\n\n    s3_client = boto3.client(\"s3\")\n    response = s3_client.list_objects_v2(Bucket=s3_bucket, Prefix=filepath)\n\n    if \"Contents\" in response:\n        files = [file[\"Key\"] for file in response[\"Contents\"]]\n        return files\n    else:\n        print(\"No files found in the specified path.\")\n\ndef get_files(regex_path):\n    rpath = regex_path.split('*')[0]\n    file_prefix = rpath.split('/')[-1]\n    if 'train' in regex_path:\n        files = [TRAIN_DIR + f for f in os.listdir(TRAIN_DIR) if file_prefix in f]\n    else:\n        files = [TEST_DIR + f for f in os.listdir(TEST_DIR) if file_prefix in f]\n    return files\n\ndef read_files(regex_path, depth=None):\n    chunks = []\n    \n    if KAGGLE:\n        files = glob(str(regex_path))\n    else:\n        files = get_files(regex_path)\n        print(files)\n    for fpath in files:\n        df = pl.read_parquet(fpath)\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\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    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\":\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\n\n# COMMAND ----------\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    ],\n    \"depth_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_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_file(TRAIN_DIR + \"train_applprev_2.parquet\", 2),\n        read_file(TRAIN_DIR + \"train_person_2.parquet\", 2)\n    ]\n}\n\nif KAGGLE:\n    data_store['depth_0'].append(read_files(TRAIN_DIR + \"train_static_0_*.parquet\"))\n    data_store['depth_1'].append(read_files(TRAIN_DIR + \"train_applprev_1_*.parquet\", 1))\n    data_store['depth_1'].append(read_files(TRAIN_DIR + \"train_credit_bureau_a_1_*.parquet\", 1))\n    data_store['depth_2'].append(read_files(TRAIN_DIR + \"train_credit_bureau_a_2_*.parquet\", 2))\nelse:\n\n    chunks = [read_file(TRAIN_DIR + \"train_static_0_0.parquet\"),read_file(TRAIN_DIR + \"train_static_0_1.parquet\")]\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_0'].append(df.unique(subset=[\"case_id\"]))\n    \n    chunks = [read_file(TRAIN_DIR + \"train_applprev_1_0.parquet\", 1),read_file(TRAIN_DIR + \"train_applprev_1_1.parquet\", 1)]\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_1'].append(df.unique(subset=[\"case_id\"]))\n    \n    chunks = [read_file(TRAIN_DIR + \"train_credit_bureau_a_1_0.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_1.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_2.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_3.parquet\", 1),]\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_1'].append(df.unique(subset=[\"case_id\"]))\n\n    chunks = [read_file(TRAIN_DIR + \"train_credit_bureau_a_2_0.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_1.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_2.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_3.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_4.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_5.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_6.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_7.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_8.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_9.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_10.parquet\", 2),\n    ]\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_2'].append(df.unique(subset=[\"case_id\"]))\n\n\n# COMMAND ----------\n\ndf_train = feature_eng(**data_store)\nprint(\"train data shape:\\t\", df_train.shape)\n\ndel data_store\ngc.collect()\ndf_train = df_train.pipe(Pipeline.filter_cols)\n\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\nif not KAGGLE:\n    store_pkl(df_train, bucket = conf[env]['bucket_ads'], s3Path = 'mine_rootile/loyalty/data/models/data/hthon_model_data.pkl')\n    store_pkl(cat_cols, bucket = conf[env]['bucket_ads'], s3Path = 'mine_rootile/loyalty/data/models/data/hthon_cat_cols.pkl')\n\n# COMMAND ----------\n\n\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    # Compute the correlation between columns.\n    correlation_matrix = matrix.corr()\n\n    # Grouping columns\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=0.95)\n            use=reduce_group(grps)\n            uses=uses+use\n            #make_corr(use)\n    else:\n        uses=uses+v\n    print('####### NAN count =',k)\n\nprint(uses)\nprint(len(uses))\nuses=uses+list(df_train.select_dtypes(include='category').columns)\nprint(len(uses))\ndf_train=df_train[uses]\n\n# COMMAND ----------\n\nif KAGGLE:\n    sample = pd.read_csv(\"/kaggle/input/home-credit-credit-risk-model-stability/sample_submission.csv\")\n    device = 'cpu'\nelse:\n    sample = pd.read_csv('s3://' + conf[env]['bucket_ads'] + '/mine_rootile/hackathon/hackathon_q2_2024_data/sample_submission.csv')\n    device = 'cpu'\n\n# COMMAND ----------\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    ],\n    \"depth_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_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_file(TEST_DIR + \"test_applprev_2.parquet\", 2),\n        read_file(TEST_DIR + \"test_person_2.parquet\", 2)\n    ]\n}\n\nif KAGGLE:\n    data_store['depth_0'].append(read_files(TEST_DIR + \"test_static_0_*.parquet\"))\n    data_store['depth_1'].append(read_files(TEST_DIR + \"test_applprev_1_*.parquet\", 1))\n    data_store['depth_1'].append(read_files(TEST_DIR + \"test_credit_bureau_a_1_*.parquet\", 1))\n    data_store['depth_2'].append(read_files(TEST_DIR + \"test_credit_bureau_a_2_*.parquet\", 2))\nelse:\n\n    chunks = [read_file(TRAIN_DIR + \"train_static_0_0.parquet\"),read_file(TRAIN_DIR + \"train_static_0_1.parquet\")]\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_0'].append(df.unique(subset=[\"case_id\"]))\n    \n    chunks = [read_file(TRAIN_DIR + \"train_applprev_1_0.parquet\", 1),read_file(TRAIN_DIR + \"train_applprev_1_1.parquet\", 1)]\n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_1'].append(df.unique(subset=[\"case_id\"]))\n    \n    chunks = [read_file(TRAIN_DIR + \"train_credit_bureau_a_1_0.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_1.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_2.parquet\", 1),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_1_3.parquet\", 1),]\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_1'].append(df.unique(subset=[\"case_id\"]))\n\n    chunks = [read_file(TRAIN_DIR + \"train_credit_bureau_a_2_0.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_1.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_2.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_3.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_4.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_5.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_6.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_7.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_8.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_9.parquet\", 2),\n              read_file(TRAIN_DIR + \"train_credit_bureau_a_2_10.parquet\", 2),\n    ]\n    \n    df = pl.concat(chunks, how=\"vertical_relaxed\")\n    data_store['depth_2'].append(df.unique(subset=[\"case_id\"]))\n\n# COMMAND ----------\n\ndf_test = feature_eng(**data_store)\nprint(\"test data shape:\\t\", df_test.shape)\ndel data_store\ngc.collect()\ndf_test = df_test.select([col for col in df_train.columns if col != \"target\"])\nprint(\"train data shape:\\t\", df_train.shape)\nprint(\"test data shape:\\t\", df_test.shape)\n\ndf_test, cat_cols = to_pandas(df_test, cat_cols)\ndf_test = reduce_mem_usage(df_test)\nweek_num = list(df_test[\"WEEK_NUM\"])\ngc.collect()\n\n#df_train = df_train.head(100000)\n\n\n\n\n\n\n\n\n    \n","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-19T18:01:29.006025Z","iopub.execute_input":"2024-04-19T18:01:29.006543Z","iopub.status.idle":"2024-04-19T18:05:56.225315Z","shell.execute_reply.started":"2024-04-19T18:01:29.006502Z","shell.execute_reply":"2024-04-19T18:05:56.224178Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.227205Z","iopub.execute_input":"2024-04-19T18:05:56.227518Z","iopub.status.idle":"2024-04-19T18:05:56.264343Z","shell.execute_reply.started":"2024-04-19T18:05:56.227491Z","shell.execute_reply":"2024-04-19T18:05:56.263409Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"### restrict to few months\nsample = 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.iloc[:50000]\n    #n_samples=10000\n    n_est=600\nprint(device)\n\ny = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\n\ndf_train = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.273455Z","iopub.execute_input":"2024-04-19T18:05:56.274097Z","iopub.status.idle":"2024-04-19T18:05:56.364427Z","shell.execute_reply.started":"2024-04-19T18:05:56.274061Z","shell.execute_reply":"2024-04-19T18:05:56.363382Z"},"trusted":true},"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.status.busy":"2024-04-19T18:05:56.365812Z","iopub.execute_input":"2024-04-19T18:05:56.366176Z","iopub.status.idle":"2024-04-19T18:05:56.707308Z","shell.execute_reply.started":"2024-04-19T18:05:56.366141Z","shell.execute_reply":"2024-04-19T18:05:56.705755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"imp_feats = ['price_1097A',\n 'pmtnum_254L',\n 'pmtssum_45A',\n 'mean_dateofcredstart_739D',\n 'mobilephncnt_593L',\n 'mean_pmts_dpd_1073P',\n 'isbidproduct_1095L',\n 'max_sex_738L',\n 'mean_residualamount_856A',\n 'interestrate_311L',\n 'max_incometype_1044T',\n 'birthdate_574D',\n 'mean_birth_259D',\n 'max_numberofcontrsvalue_358L',\n 'annuity_780A',\n 'max_numberofoverdueinstlmax_1039L',\n 'mean_pmts_dpd_303P',\n 'mean_pmts_overdue_1140A',\n 'mean_outstandingdebt_522A',\n 'max_numberofoverdueinstlmaxdat_148D',\n 'days90_310L',\n 'days120_123L',\n 'max_totalamount_6A',\n 'maxdbddpdtollast12m_3658940P',\n 'days30_165L',\n 'max_relationshiptoclient_415T',\n 'numinsttopaygr_769L',\n 'mean_maxdpdtolerance_577P',\n 'numinstunpaidmax_3546851L',\n 'mean_totalamount_996A',\n 'last_relationshiptoclient_642T',\n 'max_firstnonzeroinstldate_307D',\n 'mean_pmts_overdue_1152A',\n 'max_familystate_447L',\n 'numberofqueries_373L',\n 'max_employedfrom_700D',\n 'firstclxcampaign_1125D',\n 'max_overdueamountmax2date_1142D',\n 'lastdelinqdate_224D',\n 'mean_dateofcredstart_181D',\n 'applicationscnt_867L',\n 'education_1103M',\n 'max_dateofcredstart_739D',\n 'amtinstpaidbefduel24m_4187115A',\n 'weekday_decision',\n 'avgdpdtolclosure24_3658938P',\n 'mean_employedfrom_700D',\n 'days180_256L',\n 'mean_currdebt_94A',\n 'lastrejectdate_50D',\n 'max_pmtnum_8L',\n 'credamount_770A',\n 'max_collater_valueofguarantee_1124L',\n 'pmtscount_423L',\n 'last_num_group1_5',\n 'max_familystate_726L',\n 'numinstlsallpaid_934L',\n 'numrejects9m_859L',\n 'cntpmts24_3658933L',\n 'disbursedcredamount_1113A',\n 'last_education_1138M',\n 'max_dpdmaxdateyear_596T',\n 'max_empl_employedfrom_271D',\n 'pctinstlsallpaidlate1d_3546856L',\n 'numinstlswithdpd10_728L',\n 'mean_overdueamountmax2date_1142D',\n 'mean_dpdmax_139P',\n 'max_numberofoverdueinstlmaxdat_641D',\n 'mean_overdueamountmax2date_1002D',\n 'max_num_group2_13',\n 'mean_overdueamountmax2_14A',\n 'avgdbddpdlast24m_3658932P',\n 'dateofbirth_337D',\n 'mean_numberofoverdueinstlmaxdat_641D',\n 'currdebt_22A',\n 'maxdbddpdlast1m_3658939P',\n 'last_approvaldate_319D',\n 'max_totalamount_996A',\n 'last_birth_259D',\n 'mean_dpdmax_757P',\n 'numinstpaidearly3d_3546850L',\n 'numincomingpmts_3546848L',\n 'last_refreshdate_3813885D',\n 'mean_totalamount_6A',\n 'pctinstlsallpaidearl3d_427L',\n 'numinstlswithoutdpd_562L',\n 'numinstlallpaidearly3d_817L',\n 'numinstmatpaidtearly2d_4499204L',\n 'max_numberofoutstandinstls_59L',\n 'max_numberofinstls_320L',\n 'mean_numberofoverdueinstlmaxdat_148D',\n 'maxdpdinstldate_3546855D',\n 'mean_overdueamountmax2_398A',\n 'last_maxdpdtolerance_577P',\n 'max_residualamount_856A',\n 'lastst_736L',\n 'pctinstlsallpaidlat10d_839L',\n 'disbursementtype_67L',\n 'lastapprcommoditycat_1041M',\n 'max_financialinstitution_382M',\n 'downpmt_116A',\n 'max_pmtamount_36A',\n 'lastcancelreason_561M',\n 'avgdbddpdlast3m_4187120P',\n 'maxdpdlast3m_392P',\n 'max_num_group2_15',\n 'maxdpdlast12m_727P',\n 'numinsttopaygrest_4493213L',\n 'max_num_group1_6',\n 'maxdbddpdtollast6m_4187119P',\n 'max_overdueamountmax2date_1002D',\n 'homephncnt_628L',\n 'monthsannuity_845L',\n 'last_actualdpd_943P',\n 'last_status_219L',\n 'mean_firstnonzeroinstldate_307D',\n 'lastrejectreason_759M',\n 'max_birth_259D',\n 'maxdpdlast6m_474P',\n 'numinstunpaidmaxest_4493212L',\n 'max_contractst_964M',\n 'credtype_322L',\n 'mean_instlamount_768A',\n 'numinstpaid_4499208L',\n 'max_monthlyinstlamount_332A',\n 'datefirstoffer_1144D',\n 'clientscnt_533L',\n 'last_pmtnum_8L',\n 'pctinstlsallpaidlate6d_3546844L',\n 'max_outstandingdebt_522A',\n 'sumoutstandtotalest_4493215A',\n 'lastrejectcredamount_222A',\n 'daysoverduetolerancedd_3976961L',\n 'mean_pmtamount_36A',\n 'max_dtlastpmt_581D',\n 'maxdpdlast24m_143P',\n 'datelastunpaid_3546854D',\n 'max_currdebt_94A',\n 'max_dateofcredstart_181D',\n 'last_creationdate_885D',\n 'avgmaxdpdlast9m_3716943P',\n 'last_outstandingdebt_522A',\n 'max_nominalrate_281L',\n 'max_dateofcredend_289D',\n 'mean_monthlyinstlamount_674A',\n 'maxdebt4_972A',\n 'last_cancelreason_3545846M',\n 'mean_dateofcredend_289D',\n 'mean_processingdate_168D',\n 'maxdpdlast9m_1059P',\n 'max_tenor_203L',\n 'mean_dateofrealrepmt_138D',\n 'totalsettled_863A',\n 'requesttype_4525192L',\n 'totaldebt_9A',\n 'avgoutstandbalancel6m_4187114A',\n 'last_processingdate_168D',\n 'max_relationshiptoclient_642T',\n 'numinstpaidlastcontr_4325080L',\n 'max_maxdpdtolerance_577P',\n 'mean_monthlyinstlamount_332A',\n 'clientscnt3m_3712950L',\n 'max_approvaldate_319D',\n 'max_num_group1_13',\n 'sumoutstandtotal_3546847A',\n 'maxdpdtolerance_374P',\n 'firstquarter_103L',\n 'max_numberofinstls_229L',\n 'max_financialinstitution_591M',\n 'max_totaldebtoverduevalue_718A',\n 'numinstls_657L',\n 'last_familystate_726L',\n 'mean_dtlastpmtallstes_3545839D',\n 'max_annuity_853A',\n 'last_num_group2_15',\n 'firstdatedue_489D',\n 'max_overdueamountmax2_14A',\n 'last_annuity_853A',\n 'mean_overdueamountmax_35A',\n 'lastapplicationdate_877D',\n 'max_childnum_21L',\n 'max_outstandingamount_362A',\n 'cntincpaycont9m_3716944L',\n 'max_totaloutstanddebtvalue_39A',\n 'mean_lastupdate_388D',\n 'last_mainoccupationinc_384A',\n 'max_classificationofcontr_400M',\n 'pctinstlsallpaidlate4d_3546849L',\n 'mean_dtlastpmt_581D',\n 'avginstallast24m_3658937A',\n 'avgdbdtollast24m_4525197P',\n 'month_decision',\n 'mean_totaloutstanddebtvalue_39A',\n 'dtlastpmtallstes_4499206D',\n 'numinstpaidearly3dest_4493216L',\n 'last_mainoccupationinc_437A',\n 'max_pmts_dpd_1073P',\n 'max_empl_industry_691L',\n 'max_education_1138M',\n 'mindbddpdlast24m_3658935P',\n 'mean_annuity_853A',\n 'max_nominalrate_498L',\n 'maxinstallast24m_3658928A',\n 'mean_approvaldate_319D',\n 'max_dateofrealrepmt_138D',\n 'mindbdtollast24m_4525191P',\n 'mean_empl_employedfrom_271D',\n 'last_pmtamount_36A',\n 'last_employedfrom_700D',\n 'mean_credacc_credlmt_575A']","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.710395Z","iopub.execute_input":"2024-04-19T18:05:56.710816Z","iopub.status.idle":"2024-04-19T18:05:56.728674Z","shell.execute_reply.started":"2024-04-19T18:05:56.710778Z","shell.execute_reply":"2024-04-19T18:05:56.727632Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_cols = set(imp_feats).intersection(cat_cols)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.730013Z","iopub.execute_input":"2024-04-19T18:05:56.730382Z","iopub.status.idle":"2024-04-19T18:05:56.743030Z","shell.execute_reply.started":"2024-04-19T18:05:56.730342Z","shell.execute_reply":"2024-04-19T18:05:56.742087Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_cols = list(cat_cols)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.744224Z","iopub.execute_input":"2024-04-19T18:05:56.744591Z","iopub.status.idle":"2024-04-19T18:05:56.752470Z","shell.execute_reply.started":"2024-04-19T18:05:56.744557Z","shell.execute_reply":"2024-04-19T18:05:56.751422Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"imp_feats = set(imp_feats).intersection(df_train.columns)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.756267Z","iopub.execute_input":"2024-04-19T18:05:56.756585Z","iopub.status.idle":"2024-04-19T18:05:56.762848Z","shell.execute_reply.started":"2024-04-19T18:05:56.756560Z","shell.execute_reply":"2024-04-19T18:05:56.761677Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"imp_feats = list(imp_feats)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.764394Z","iopub.execute_input":"2024-04-19T18:05:56.764850Z","iopub.status.idle":"2024-04-19T18:05:56.771606Z","shell.execute_reply.started":"2024-04-19T18:05:56.764824Z","shell.execute_reply":"2024-04-19T18:05:56.770349Z"},"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\")\n# device='gpu'\n# #n_samples=200000\n# n_est=6000\n# DRY_RUN = True if sample.shape[0] == 10 else False   \n# if DRY_RUN:\n#     device='cpu'\n#     df_train = df_train.iloc[:50000]\n#     #n_samples=10000\n#     n_est=600\n# print(device)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.772837Z","iopub.execute_input":"2024-04-19T18:05:56.773163Z","iopub.status.idle":"2024-04-19T18:05:56.779326Z","shell.execute_reply.started":"2024-04-19T18:05:56.773104Z","shell.execute_reply":"2024-04-19T18:05:56.778458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# COMMAND ----------\nparams_lgb = {\n        \"objective\": \"binary\",\n        \"boosting_type\":\"gbdt\",\n        \"n_estimators\": 1000,\n        \"verbosity\": -1,\n        \"bagging_freq\": 1,\n        \"max_depth\": 5,\n        \"learning_rate\": 0.0881405590600479,\n        \"reg_alpha\" : 26,\n        \"reg_lambda\" : 39,\n        \"num_leaves\": 20,\n        \"subsample\": 0.7718831982797116,\n        \"colsample_bytree\": 0.9704442853713775,\n        \"min_child_samples\": 100,\n        \"min_data_in_leaf\": 40,\n    }\n\n# params_lgb2 = {\n#         \"objective\": \"binary\",\n#         \"boosting_type\":\"gbdt\",\n#         \"n_estimators\": 1000,\n#         \"verbosity\": -1,\n#         \"bagging_freq\": 1,\n#         \"max_depth\": 10,\n#         \"learning_rate\": 0.0881405590600479,\n#         \"reg_alpha\" : 100,\n#         \"reg_lambda\" : 100,\n#         \"num_leaves\": 10,\n#         \"subsample\": 0.7718831982797116,\n#         \"colsample_bytree\": 0.9704442853713775,\n#         \"min_child_samples\": 200,\n#         #\"min_data_in_leaf\": 40,\n#     }\n\n\nparams_xgb = {\n    \"booster\": \"gbtree\",\n    \"objective\": \"binary:logistic\",\n    #\"eval_metric\": \"auc\",\n    \"max_depth\": 5,\n    \"learning_rate\": 0.05,\n    \"n_estimators\": 1000,\n    \"colsample_bytree\": 0.8,\n    \"colsample_bynode\": 0.8,\n    \"alpha\": 20,  \n    \"lambda\": 30,  \n    \"tree_method\": 'gpu_hist' if device == 'gpu' else 'auto',\n    \"random_state\": 42,\n    \"verbosity\": 0,\n    \"enable_categorical\":True,\n}\n\n\n\n\n# model1 = lgb.LGBMClassifier(**params_lgb1)\n# model1.fit(df_train,y)\n\n# model2 = lgb.LGBMClassifier(**params_lgb2)\n# model2.fit(df_train,y)\n\n# model3 = xgb.XGBClassifier(**params_xgb)\n# model3.fit(df_train,y)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.780821Z","iopub.execute_input":"2024-04-19T18:05:56.781217Z","iopub.status.idle":"2024-04-19T18:05:56.792610Z","shell.execute_reply.started":"2024-04-19T18:05:56.781168Z","shell.execute_reply":"2024-04-19T18:05:56.791614Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fitted_models_cat = []\nfitted_models_lgb = []\nfitted_models_xgb = []\n\ncv_scores_cat = []\ncv_scores_lgb = []\ncv_scores_xgb = []\n\n### Only important feats\ndf_train = df_train[imp_feats]\n#df_test = df_test[imp_feats]\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    learning_rate=0.03,\n    iterations=n_est)\n    random_seed=3107\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_lgb)\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    model2 = xgb.XGBClassifier(**params_xgb)\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))","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:05:56.793778Z","iopub.execute_input":"2024-04-19T18:05:56.794079Z","iopub.status.idle":"2024-04-19T18:17:51.648453Z","shell.execute_reply.started":"2024-04-19T18:05:56.794056Z","shell.execute_reply":"2024-04-19T18:17:51.647174Z"},"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        \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:]]\n        \n        return np.mean(y_preds, axis=0)\n\nmodel = VotingModel(fitted_models_cat+fitted_models_lgb+fitted_models_xgb)","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:17:51.649872Z","iopub.execute_input":"2024-04-19T18:17:51.650272Z","iopub.status.idle":"2024-04-19T18:17:51.659025Z","shell.execute_reply.started":"2024-04-19T18:17:51.650237Z","shell.execute_reply":"2024-04-19T18:17:51.658070Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test.head()","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:17:51.660279Z","iopub.execute_input":"2024-04-19T18:17:51.660606Z","iopub.status.idle":"2024-04-19T18:17:51.700435Z","shell.execute_reply.started":"2024-04-19T18:17:51.660567Z","shell.execute_reply":"2024-04-19T18:17:51.699183Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_cols","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:17:51.701667Z","iopub.execute_input":"2024-04-19T18:17:51.701943Z","iopub.status.idle":"2024-04-19T18:17:51.710452Z","shell.execute_reply.started":"2024-04-19T18:17:51.701919Z","shell.execute_reply":"2024-04-19T18:17:51.709531Z"},"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\")\ndf_test = df_test[imp_feats]\n\n\ny_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\nprint(\"Check null: \", df_subm[\"score\"].isnull().any())\ndf_subm.to_csv(\"submission.csv\")\n#df_subm","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:17:51.711722Z","iopub.execute_input":"2024-04-19T18:17:51.712005Z","iopub.status.idle":"2024-04-19T18:17:52.138499Z","shell.execute_reply.started":"2024-04-19T18:17:51.711981Z","shell.execute_reply":"2024-04-19T18:17:52.137432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# y_pred = pd.Series(meta_model.predict_proba(meta_feats_test)[:, 1], index=df_test.index)\n# subm_df = pd.read_csv(ROOT + \"/sample_submission.csv\")\n# subm_df = subm_df.set_index(\"case_id\")\n# subm_df[\"score\"] = y_pred\n# print(\"Check null: \", subm_df[\"score\"].isnull().any())\n\n# if KAGGLE:\n#     subm_df.to_csv(\"submission.csv\")\n# else:\n#     current_datetime = datetime.now().strftime(\"%Y%m%d%H%M\")\n#     subm_df.to_csv(f\"s3://{conf[env]['bucket_ads']}/mine_rootile/loyalty/data/models/data/hackathon_submissions/ensemble_submission_{current_datetime}.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-04-19T18:17:52.139850Z","iopub.execute_input":"2024-04-19T18:17:52.140216Z","iopub.status.idle":"2024-04-19T18:17:52.145199Z","shell.execute_reply.started":"2024-04-19T18:17:52.140189Z","shell.execute_reply":"2024-04-19T18:17:52.143980Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}