{"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":30699,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import sys\nfrom pathlib import Path\nimport subprocess\nimport os\nimport gc\nfrom glob import glob\n\nimport numpy as np\nimport pandas as pd\nimport polars as pl\nfrom datetime import datetime\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\nimport warnings\nwarnings.filterwarnings('ignore')\n\nROOT = '/kaggle/input/home-credit-credit-risk-model-stability'\n\nfrom sklearn.model_selection import TimeSeriesSplit, GroupKFold, StratifiedGroupKFold\nfrom sklearn.base import BaseEstimator, RegressorMixin\nfrom sklearn.metrics import roc_auc_score\nimport lightgbm as lgb\nimport xgboost as xgb\n\nfrom imblearn.over_sampling import SMOTE\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.impute import KNNImputer","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-04-21T14:35:20.600419Z","iopub.execute_input":"2024-04-21T14:35:20.601321Z","iopub.status.idle":"2024-04-21T14:35:31.185606Z","shell.execute_reply.started":"2024-04-21T14:35:20.601288Z","shell.execute_reply":"2024-04-21T14:35:31.184773Z"},"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 > 0.99:\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        \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+expr_first\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        expr_unique = [pl.n_unique(col).alias(f\"unique_{col}\") for col in cols]\n        return  expr_max +expr_last+expr_count+expr_unique\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#     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\ndef feature_eng(df_base):\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):\n#         df_base = df_base.join(df, how=\"right\", on=\"case_id\", suffix=f\"_{i}\")\n    df_base = df_base.pipe(Pipeline.handle_dates)\n    return df_base\n\ndef to_pandas(df_data, cat_cols=None):\n    df_data = df_data.to_pandas()\n    if cat_cols is None:\n        cat_cols = list(df_data.select_dtypes(\"object\").columns)\n    df_data[cat_cols] = df_data[cat_cols].astype(\"category\")\n    return df_data, cat_cols\n\ndef reduce_mem_usage(df):\n    \"\"\" iterate through all the columns of a dataframe and modify the data type\n        to reduce memory usage.        \n    \"\"\"\n    start_mem = df.memory_usage().sum() / 1024**2\n    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n    \n    for col in df.columns:\n        col_type = df[col].dtype\n        if str(col_type)==\"category\":\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":"2024-04-21T14:35:31.187528Z","iopub.execute_input":"2024-04-21T14:35:31.188099Z","iopub.status.idle":"2024-04-21T14:35:31.226725Z","shell.execute_reply.started":"2024-04-21T14:35:31.188073Z","shell.execute_reply":"2024-04-21T14:35:31.225812Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT            = Path(\"/kaggle/input/home-credit-credit-risk-model-stability\")\n\nTRAIN_DIR       = ROOT / \"parquet_files\" / \"train\"\nTEST_DIR        = ROOT / \"parquet_files\" / \"test\"","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:35:31.227892Z","iopub.execute_input":"2024-04-21T14:35:31.228169Z","iopub.status.idle":"2024-04-21T14:35:31.244696Z","shell.execute_reply.started":"2024-04-21T14:35:31.228146Z","shell.execute_reply":"2024-04-21T14:35:31.243962Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_base = read_file(TRAIN_DIR / \"train_base.parquet\")\ndf_static_0 = read_files(TRAIN_DIR / \"train_applprev_1_*.parquet\")\ndf_train = df_static_0.join(df_base,how = \"left\",on=\"case_id\")\ndel df_base,df_static_0","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:35:31.246351Z","iopub.execute_input":"2024-04-21T14:35:31.246645Z","iopub.status.idle":"2024-04-21T14:35:44.411682Z","shell.execute_reply.started":"2024-04-21T14:35:31.246623Z","shell.execute_reply":"2024-04-21T14:35:44.410768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_train = feature_eng(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\n# del data_store1\ngc.collect()\ndf_train = df_train.pipe(Pipeline.filter_cols)\ndf_train, cat_cols = to_pandas(df_train)\ndf_train = reduce_mem_usage(df_train)\nprint(\"train data shape:\\t\", df_train.shape)\nnums=df_train.select_dtypes(exclude='category').columns\nfrom itertools import combinations, permutations\n#df_train=df_train[nums]\nnans_df = df_train[nums].isna()\nnans_groups={}\nfor col in nums:\n    cur_group = nans_df[col].sum()\n    try:\n        nans_groups[cur_group].append(col)\n    except:\n        nans_groups[cur_group]=[col]\ndel nans_df; x=gc.collect()","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:35:44.413042Z","iopub.execute_input":"2024-04-21T14:35:44.413357Z","iopub.status.idle":"2024-04-21T14:36:07.076163Z","shell.execute_reply.started":"2024-04-21T14:35:44.413332Z","shell.execute_reply":"2024-04-21T14:36:07.075236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"device='gpu'\nn_est=3000","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:37:50.730592Z","iopub.execute_input":"2024-04-21T14:37:50.731254Z","iopub.status.idle":"2024-04-21T14:37:50.735397Z","shell.execute_reply.started":"2024-04-21T14:37:50.731223Z","shell.execute_reply":"2024-04-21T14:37:50.734506Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\ndf_base = read_file(TEST_DIR / \"test_base.parquet\")\ndf_static_0 = read_files(TEST_DIR / \"test_applprev_1_*.parquet\")\ndf_test = df_static_0.join(df_base,how = \"left\",on=\"case_id\")\ndel df_base,df_static_0","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:37:53.707819Z","iopub.execute_input":"2024-04-21T14:37:53.708166Z","iopub.status.idle":"2024-04-21T14:37:53.773011Z","shell.execute_reply.started":"2024-04-21T14:37:53.708129Z","shell.execute_reply":"2024-04-21T14:37:53.772166Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test = feature_eng(df_test)\nprint(\"test data shape:\\t\", df_test.shape)\n# del data_store1\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()","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:37:57.367748Z","iopub.execute_input":"2024-04-21T14:37:57.368123Z","iopub.status.idle":"2024-04-21T14:37:57.625894Z","shell.execute_reply.started":"2024-04-21T14:37:57.368096Z","shell.execute_reply":"2024-04-21T14:37:57.624934Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# df_train[\"is_inprevlist\"] = 1\n# df_test[\"is_inprevlist\"] = 1\n# df_train[df_train[\"month_decision\"]==None][\"is_inprevlist\"] = 0\n# df_test[df_test[\"month_decision\"]==None][\"is_inprevlist\"] = 0","metadata":{"execution":{"iopub.status.busy":"2024-04-21T11:53:40.075323Z","iopub.execute_input":"2024-04-21T11:53:40.075909Z","iopub.status.idle":"2024-04-21T11:53:40.098058Z","shell.execute_reply.started":"2024-04-21T11:53:40.075879Z","shell.execute_reply":"2024-04-21T11:53:40.097029Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y = df_train[\"target\"]\nweeks = df_train[\"WEEK_NUM\"]\ncase_id = pd.DataFrame(df_train[\"case_id\"],columns = [\"case_id\"])\ndf_train = df_train.drop(columns=[\"target\", \"case_id\", \"WEEK_NUM\"])\ncv = StratifiedGroupKFold(n_splits=5, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:38:00.742542Z","iopub.execute_input":"2024-04-21T14:38:00.742904Z","iopub.status.idle":"2024-04-21T14:38:02.018126Z","shell.execute_reply.started":"2024-04-21T14:38:00.742875Z","shell.execute_reply":"2024-04-21T14:38:02.017021Z"},"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":"2024-04-21T14:38:04.125990Z","iopub.execute_input":"2024-04-21T14:38:04.126752Z","iopub.status.idle":"2024-04-21T14:38:12.829713Z","shell.execute_reply.started":"2024-04-21T14:38:04.126714Z","shell.execute_reply":"2024-04-21T14:38:12.828815Z"},"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}","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:38:25.615777Z","iopub.execute_input":"2024-04-21T14:38:25.616128Z","iopub.status.idle":"2024-04-21T14:38:25.621562Z","shell.execute_reply.started":"2024-04-21T14:38:25.616100Z","shell.execute_reply":"2024-04-21T14:38:25.620539Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%time\n\nfitted_models_lgb = []\n\ncv_scores_lgb = []\n\nvalid_set_lgb = pd.Series(index = [i for i in range(len(df_train))])\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    \n    X_train[cat_cols] = X_train[cat_cols].astype(\"category\")\n    X_valid[cat_cols] = X_valid[cat_cols].astype(\"category\")\n    \n    model = lgb.LGBMClassifier(**params)\n    model.fit(\n        X_train, y_train,\n        eval_set = [(X_valid, y_valid)],\n        callbacks = [lgb.log_evaluation(200), lgb.early_stopping(100)] )\n    \n    fitted_models_lgb.append(model)\n    y_pred_valid = model.predict_proba(X_valid)[:,1]\n    valid_set_lgb[idx_valid] = y_pred_valid.values\n    auc_score = roc_auc_score(y_valid, y_pred_valid)\n    cv_scores_lgb.append(auc_score)\n    \n    del model\n    gc.collect()\n\nprint(\"CV AUC scores: \", cv_scores_lgb)\nprint(\"Maximum CV AUC score: \", max(cv_scores_lgb))\n\nprint('Pred probability:',valid_pred)","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:38:29.918473Z","iopub.execute_input":"2024-04-21T14:38:29.918855Z","iopub.status.idle":"2024-04-21T14:38:47.261071Z","shell.execute_reply.started":"2024-04-21T14:38:29.918825Z","shell.execute_reply":"2024-04-21T14:38:47.260129Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import joblib\nfor i,model in enumerate(fitted_models_lgb):\n    joblib.dump(model,f'data_model_{i}.pkl')\nclf = joblib.load('data_model.pkl') ","metadata":{"execution":{"iopub.status.busy":"2024-04-21T13:00:55.675575Z","iopub.execute_input":"2024-04-21T13:00:55.676340Z","iopub.status.idle":"2024-04-21T13:00:56.152513Z","shell.execute_reply.started":"2024-04-21T13:00:55.676307Z","shell.execute_reply":"2024-04-21T13:00:56.151729Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds = clf.predict_proba(df_train)\n#case_id = pd.DataFrame(case_id,columns = ['case_id'])\ncase_id[\"pred\"] = preds[:,1]\ncase_id[\"pred\"] -= case_id[\"pred\"].mean()","metadata":{"execution":{"iopub.status.busy":"2024-04-21T13:02:58.527973Z","iopub.execute_input":"2024-04-21T13:02:58.528853Z","iopub.status.idle":"2024-04-21T13:21:32.613763Z","shell.execute_reply.started":"2024-04-21T13:02:58.528818Z","shell.execute_reply":"2024-04-21T13:21:32.612896Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_id_score = case_id.groupby('case_id',group_keys=False,as_index=False)['pred'].agg({'max','mean','sum','var',\"last\"})\ncase_id_score[\"var\"] = case_id_score[\"var\"].fillna(0)","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:14:55.217076Z","iopub.execute_input":"2024-04-21T14:14:55.217630Z","iopub.status.idle":"2024-04-21T14:14:55.796253Z","shell.execute_reply.started":"2024-04-21T14:14:55.217596Z","shell.execute_reply":"2024-04-21T14:14:55.795123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_id_score","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:27:30.447281Z","iopub.execute_input":"2024-04-21T14:27:30.448029Z","iopub.status.idle":"2024-04-21T14:27:30.463269Z","shell.execute_reply.started":"2024-04-21T14:27:30.447996Z","shell.execute_reply":"2024-04-21T14:27:30.462308Z"},"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[cat_cols] = df_test[cat_cols].astype(\"category\")\ntest_pred = pd.Series(model.predict_proba(df_test)[:, 1], index=df_test.index)\ntest_pred = pd.DataFrame({\"case_id\":df_test.index.tolist(),\"pred\":test_pred})\ntest_pred = test_pred.reset_index(drop=True)\ntest_pred_score = test_pred.groupby('case_id',group_keys=False,as_index=False)['pred'].agg({'max','mean','sum','var',\"last\"})\ntest_pred_score[\"var\"] = test_pred_score[\"var\"].fillna(0)","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:18:52.427820Z","iopub.execute_input":"2024-04-21T14:18:52.428596Z","iopub.status.idle":"2024-04-21T14:18:52.609780Z","shell.execute_reply.started":"2024-04-21T14:18:52.428564Z","shell.execute_reply":"2024-04-21T14:18:52.608517Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_pred_score","metadata":{"execution":{"iopub.status.busy":"2024-04-21T14:24:17.360866Z","iopub.execute_input":"2024-04-21T14:24:17.361203Z","iopub.status.idle":"2024-04-21T14:24:17.372538Z","shell.execute_reply.started":"2024-04-21T14:24:17.361179Z","shell.execute_reply":"2024-04-21T14:24:17.371667Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}