{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor 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":"2022-06-23T08:52:09.591413Z","iopub.execute_input":"2022-06-23T08:52:09.592901Z","iopub.status.idle":"2022-06-23T08:52:09.652778Z","shell.execute_reply.started":"2022-06-23T08:52:09.592744Z","shell.execute_reply":"2022-06-23T08:52:09.651314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Introduction\n\nThe objective of this competition is to predict the probability that a customer does not pay back their credit card balance amount in the future based on their monthly customer profile. The target binary variable is calculated by observing 18 months performance window after the latest credit card statement, and if the customer does not pay due amount in 120 days after their latest statement date it is considered a default event.\n\nThe dataset contains aggregated profile features for each customer at each statement date. Features are anonymized and normalized, and fall into the following general categories:\n\nD_* = Delinquency variables\nS_* = Spend variables\nP_* = Payment variables\nB_* = Balance variables\nR_* = Risk variables\nwith the following features being categorical:\n\n['B_30', 'B_38', 'D_114', 'D_116', 'D_117', 'D_120', 'D_126', 'D_63', 'D_64', 'D_66', 'D_68']\n\nYour task is to predict, for each customer_ID, the probability of a future payment default (target = 1).\n\nNote that the negative class has been subsampled for this dataset at 5%, and thus receives a 20x weighting in the scoring metric.","metadata":{}},{"cell_type":"markdown","source":"### Import Libraries","metadata":{}},{"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:09.703074Z","iopub.execute_input":"2022-06-23T08:52:09.704527Z","iopub.status.idle":"2022-06-23T08:52:10.934636Z","shell.execute_reply.started":"2022-06-23T08:52:09.704463Z","shell.execute_reply":"2022-06-23T08:52:10.933198Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Load the data","metadata":{}},{"cell_type":"code","source":"# Reading feather format data(memory efficient, available on kaggle: https://www.kaggle.com/datasets/munumbutt/amexfeather) \ntrain_df = pd.read_feather('../input/amexfeather/train_data.ftr')","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:10.937687Z","iopub.execute_input":"2022-06-23T08:52:10.938148Z","iopub.status.idle":"2022-06-23T08:52:33.813353Z","shell.execute_reply.started":"2022-06-23T08:52:10.938100Z","shell.execute_reply":"2022-06-23T08:52:33.810933Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:33.815575Z","iopub.execute_input":"2022-06-23T08:52:33.816324Z","iopub.status.idle":"2022-06-23T08:52:33.874211Z","shell.execute_reply.started":"2022-06-23T08:52:33.816277Z","shell.execute_reply":"2022-06-23T08:52:33.872825Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.info()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:33.878193Z","iopub.execute_input":"2022-06-23T08:52:33.878919Z","iopub.status.idle":"2022-06-23T08:52:33.936320Z","shell.execute_reply.started":"2022-06-23T08:52:33.878874Z","shell.execute_reply":"2022-06-23T08:52:33.933011Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#check for missing values\ntrain_df.isna().sum()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:33.938103Z","iopub.execute_input":"2022-06-23T08:52:33.938913Z","iopub.status.idle":"2022-06-23T08:52:39.206937Z","shell.execute_reply.started":"2022-06-23T08:52:33.938868Z","shell.execute_reply":"2022-06-23T08:52:39.205568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#shape of the dataset\ntrain_df.shape","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:39.209319Z","iopub.execute_input":"2022-06-23T08:52:39.210202Z","iopub.status.idle":"2022-06-23T08:52:39.219924Z","shell.execute_reply.started":"2022-06-23T08:52:39.210146Z","shell.execute_reply":"2022-06-23T08:52:39.218280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#target unique values\n\ntrain_df[\"customer_ID\"].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:39.222095Z","iopub.execute_input":"2022-06-23T08:52:39.222718Z","iopub.status.idle":"2022-06-23T08:52:40.164340Z","shell.execute_reply.started":"2022-06-23T08:52:39.222670Z","shell.execute_reply":"2022-06-23T08:52:40.162864Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Target values distribution\ntrain_df[\"target\"].value_counts(\"%\")","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:40.166704Z","iopub.execute_input":"2022-06-23T08:52:40.167308Z","iopub.status.idle":"2022-06-23T08:52:40.207035Z","shell.execute_reply.started":"2022-06-23T08:52:40.167230Z","shell.execute_reply":"2022-06-23T08:52:40.205538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### EDA","metadata":{}},{"cell_type":"code","source":"# Handing missing values\n#Dropping columns with missing values greater than 70%\n\nmissing_cols = train_df.isna().sum().mul(100).div(len(train_df)).sort_values(ascending=False)\nmissing_cols_df = pd.DataFrame(missing_cols).reset_index()\ndrop_cols = missing_cols_df[missing_cols_df[0]>70]['index'].values\nprint(drop_cols)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:40.209138Z","iopub.execute_input":"2022-06-23T08:52:40.209992Z","iopub.status.idle":"2022-06-23T08:52:45.931658Z","shell.execute_reply.started":"2022-06-23T08:52:40.209939Z","shell.execute_reply":"2022-06-23T08:52:45.929992Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:45.938358Z","iopub.execute_input":"2022-06-23T08:52:45.938711Z","iopub.status.idle":"2022-06-23T08:52:45.978187Z","shell.execute_reply.started":"2022-06-23T08:52:45.938663Z","shell.execute_reply":"2022-06-23T08:52:45.976952Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.drop(columns = drop_cols,axis=1, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:45.979921Z","iopub.execute_input":"2022-06-23T08:52:45.980686Z","iopub.status.idle":"2022-06-23T08:52:48.954635Z","shell.execute_reply.started":"2022-06-23T08:52:45.980638Z","shell.execute_reply":"2022-06-23T08:52:48.953281Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# For categorical column\n\ncols = train_df.columns\nnum_cols = train_df._get_numeric_data().columns\n\ncategorical_columns = list(set(cols) - set(num_cols))\nfiltered_categorical_columns = list(set(train_df[categorical_columns])-{\"S_2\",\"customer_ID\"})","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:48.956642Z","iopub.execute_input":"2022-06-23T08:52:48.957402Z","iopub.status.idle":"2022-06-23T08:52:49.065776Z","shell.execute_reply.started":"2022-06-23T08:52:48.957351Z","shell.execute_reply":"2022-06-23T08:52:49.064448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df[filtered_categorical_columns].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:49.067684Z","iopub.execute_input":"2022-06-23T08:52:49.068419Z","iopub.status.idle":"2022-06-23T08:52:49.390768Z","shell.execute_reply.started":"2022-06-23T08:52:49.068370Z","shell.execute_reply":"2022-06-23T08:52:49.389135Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df[filtered_categorical_columns].isna().sum().mul(100).div(len(train_df))","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:49.392617Z","iopub.execute_input":"2022-06-23T08:52:49.393357Z","iopub.status.idle":"2022-06-23T08:52:49.497332Z","shell.execute_reply.started":"2022-06-23T08:52:49.393311Z","shell.execute_reply":"2022-06-23T08:52:49.495850Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for i in filtered_categorical_columns:\n    print(train_df[i].value_counts())","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:49.499499Z","iopub.execute_input":"2022-06-23T08:52:49.500305Z","iopub.status.idle":"2022-06-23T08:52:49.858384Z","shell.execute_reply.started":"2022-06-23T08:52:49.500256Z","shell.execute_reply":"2022-06-23T08:52:49.856919Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.impute import SimpleImputer\nimputer=SimpleImputer(strategy=\"most_frequent\")\ntransformed_df = pd.DataFrame(imputer.fit_transform(train_df[filtered_categorical_columns]),columns = filtered_categorical_columns)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:52:49.860524Z","iopub.execute_input":"2022-06-23T08:52:49.861740Z","iopub.status.idle":"2022-06-23T08:53:21.914525Z","shell.execute_reply.started":"2022-06-23T08:52:49.861691Z","shell.execute_reply":"2022-06-23T08:53:21.913104Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df[filtered_categorical_columns] = transformed_df[filtered_categorical_columns]","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:21.916342Z","iopub.execute_input":"2022-06-23T08:53:21.916779Z","iopub.status.idle":"2022-06-23T08:53:23.611121Z","shell.execute_reply.started":"2022-06-23T08:53:21.916731Z","shell.execute_reply":"2022-06-23T08:53:23.609741Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# For numeric columns\nnumeric_columns = train_df.select_dtypes(np.number).columns\ntrain_df[numeric_columns] = train_df[numeric_columns].fillna(train_df[numeric_columns].mean())","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:23.613299Z","iopub.execute_input":"2022-06-23T08:53:23.613753Z","iopub.status.idle":"2022-06-23T08:53:50.822141Z","shell.execute_reply.started":"2022-06-23T08:53:23.613707Z","shell.execute_reply":"2022-06-23T08:53:50.819866Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:50.830013Z","iopub.execute_input":"2022-06-23T08:53:50.831183Z","iopub.status.idle":"2022-06-23T08:53:50.883335Z","shell.execute_reply.started":"2022-06-23T08:53:50.831115Z","shell.execute_reply":"2022-06-23T08:53:50.882080Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Handling date column\n\ntrain_df[\"S_2_day\"] = train_df[\"S_2\"].dt.day\ntrain_df[\"S_2_month\"] = train_df[\"S_2\"].dt.month\ntrain_df[\"S_2_year\"] = train_df[\"S_2\"].dt.year","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:50.888637Z","iopub.execute_input":"2022-06-23T08:53:50.891649Z","iopub.status.idle":"2022-06-23T08:53:52.642199Z","shell.execute_reply.started":"2022-06-23T08:53:50.891604Z","shell.execute_reply":"2022-06-23T08:53:52.640708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# considering only one data point per customer\ntrain_df = train_df.groupby(['customer_ID']).nth(-1).reset_index(drop=True)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:52.644461Z","iopub.execute_input":"2022-06-23T08:53:52.644940Z","iopub.status.idle":"2022-06-23T08:53:59.974693Z","shell.execute_reply.started":"2022-06-23T08:53:52.644892Z","shell.execute_reply":"2022-06-23T08:53:59.973163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# drop S_2\ntrain_df.drop(columns=[\"S_2\"], axis=1, inplace=True)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:53:59.977198Z","iopub.execute_input":"2022-06-23T08:53:59.977711Z","iopub.status.idle":"2022-06-23T08:54:00.390877Z","shell.execute_reply.started":"2022-06-23T08:53:59.977631Z","shell.execute_reply":"2022-06-23T08:54:00.389533Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# converting pandas \"categorical\" dtype to numeric\ncols = [\"D_63\", \"D_64\", \"D_68\", \"B_30\", \"B_38\", \"D_114\", \"D_116\", \"D_117\", \"D_120\", \"D_126\"]\ntrain_df[cols] = train_df[cols].apply(pd.to_numeric, errors='coerce')","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:00.393326Z","iopub.execute_input":"2022-06-23T08:54:00.393773Z","iopub.status.idle":"2022-06-23T08:54:03.081453Z","shell.execute_reply.started":"2022-06-23T08:54:00.393727Z","shell.execute_reply":"2022-06-23T08:54:03.080070Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Modelling","metadata":{}},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn import metrics\nfrom xgboost import XGBClassifier\nimport xgboost as xgb\nfrom datetime import datetime, timedelta","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:03.083814Z","iopub.execute_input":"2022-06-23T08:54:03.084347Z","iopub.status.idle":"2022-06-23T08:54:03.195171Z","shell.execute_reply.started":"2022-06-23T08:54:03.084299Z","shell.execute_reply":"2022-06-23T08:54:03.193855Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# https://www.kaggle.com/code/inversion/amex-competition-metric-python\n\ndef amex_metric_official(y_true: pd.DataFrame, y_pred: pd.DataFrame) -> float:\n\n    def top_four_percent_captured(y_true: pd.DataFrame, y_pred: pd.DataFrame) -> float:\n        df = (pd.concat([y_true, y_pred], axis='columns')\n              .sort_values('prediction', ascending=False))\n        df['weight'] = df['target'].apply(lambda x: 20 if x==0 else 1)\n        four_pct_cutoff = int(0.04 * df['weight'].sum())\n        df['weight_cumsum'] = df['weight'].cumsum()\n        df_cutoff = df.loc[df['weight_cumsum'] <= four_pct_cutoff]\n        return (df_cutoff['target'] == 1).sum() / (df['target'] == 1).sum()\n\n    def weighted_gini(y_true: pd.DataFrame, y_pred: pd.DataFrame) -> float:\n        df = (pd.concat([y_true, y_pred], axis='columns')\n              .sort_values('prediction', ascending=False))\n        df['weight'] = df['target'].apply(lambda x: 20 if x==0 else 1)\n        df['random'] = (df['weight'] / df['weight'].sum()).cumsum()\n        total_pos = (df['target'] * df['weight']).sum()\n        df['cum_pos_found'] = (df['target'] * df['weight']).cumsum()\n        df['lorentz'] = df['cum_pos_found'] / total_pos\n        df['gini'] = (df['lorentz'] - df['random']) * df['weight']\n        return df['gini'].sum()\n\n    def normalized_weighted_gini(y_true: pd.DataFrame, y_pred: pd.DataFrame) -> float:\n        y_true_pred = y_true.rename(columns={'target': 'prediction'})\n        return weighted_gini(y_true, y_pred) / weighted_gini(y_true, y_true_pred)\n\n    g = normalized_weighted_gini(y_true, y_pred)\n    d = top_four_percent_captured(y_true, y_pred)\n\n    return 0.5 * (g + d)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:03.197086Z","iopub.execute_input":"2022-06-23T08:54:03.197742Z","iopub.status.idle":"2022-06-23T08:54:03.216927Z","shell.execute_reply.started":"2022-06-23T08:54:03.197678Z","shell.execute_reply":"2022-06-23T08:54:03.214972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X = train_df.drop(columns=[\"target\"],axis=1)\ny = train_df[\"target\"]","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:03.218997Z","iopub.execute_input":"2022-06-23T08:54:03.220225Z","iopub.status.idle":"2022-06-23T08:54:03.518226Z","shell.execute_reply.started":"2022-06-23T08:54:03.220047Z","shell.execute_reply":"2022-06-23T08:54:03.516823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.33,random_state=100)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:03.520487Z","iopub.execute_input":"2022-06-23T08:54:03.521003Z","iopub.status.idle":"2022-06-23T08:54:04.626111Z","shell.execute_reply.started":"2022-06-23T08:54:03.520928Z","shell.execute_reply":"2022-06-23T08:54:04.624702Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"xgb_classifier = XGBClassifier(objective='binary:logistic', \n                      n_estimators=10,\n                      seed=123,\n                      use_label_encoder=False,\n                      eval_metric='aucpr',                      \n#                       early_stopping_rounds=10,tree_method='gpu_hist',enable_categorical=True\n                            )\nxgb_classifier.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:54:04.633716Z","iopub.execute_input":"2022-06-23T08:54:04.634072Z","iopub.status.idle":"2022-06-23T08:55:14.151719Z","shell.execute_reply.started":"2022-06-23T08:54:04.634040Z","shell.execute_reply":"2022-06-23T08:55:14.150381Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = xgb_classifier.predict(X_test)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:14.154147Z","iopub.execute_input":"2022-06-23T08:55:14.155104Z","iopub.status.idle":"2022-06-23T08:55:14.671649Z","shell.execute_reply.started":"2022-06-23T08:55:14.155055Z","shell.execute_reply":"2022-06-23T08:55:14.670228Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred_prob = xgb_classifier.predict_proba(X_test)[:,1]","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:14.674156Z","iopub.execute_input":"2022-06-23T08:55:14.675141Z","iopub.status.idle":"2022-06-23T08:55:15.196165Z","shell.execute_reply.started":"2022-06-23T08:55:14.675066Z","shell.execute_reply":"2022-06-23T08:55:15.194717Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_test = pd.DataFrame(y_test, columns=[\"target\"])\ny_pred = pd.DataFrame(y_pred, columns=[\"prediction\"])\ny_pred_prob = pd.DataFrame(y_pred_prob, columns=[\"prediction\"])","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:15.199003Z","iopub.execute_input":"2022-06-23T08:55:15.199983Z","iopub.status.idle":"2022-06-23T08:55:15.213743Z","shell.execute_reply.started":"2022-06-23T08:55:15.199931Z","shell.execute_reply":"2022-06-23T08:55:15.211878Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # computing metric score\namex_metric_official(y_test, y_pred_prob)","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:15.216092Z","iopub.execute_input":"2022-06-23T08:55:15.217521Z","iopub.status.idle":"2022-06-23T08:55:15.855358Z","shell.execute_reply.started":"2022-06-23T08:55:15.217456Z","shell.execute_reply":"2022-06-23T08:55:15.853720Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Compute accuracy\naccuracy = metrics.accuracy_score(y_test[\"target\"], y_pred[\"prediction\"])\nprint(f'accuracy: {accuracy: .2%}')","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:15.857325Z","iopub.execute_input":"2022-06-23T08:55:15.859181Z","iopub.status.idle":"2022-06-23T08:55:15.881086Z","shell.execute_reply.started":"2022-06-23T08:55:15.859133Z","shell.execute_reply":"2022-06-23T08:55:15.879738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import joblib\njoblib.dump(xgb_classifier, \"xgb_classifier_v1.h5\")","metadata":{"execution":{"iopub.status.busy":"2022-06-23T08:55:15.885032Z","iopub.execute_input":"2022-06-23T08:55:15.887752Z","iopub.status.idle":"2022-06-23T08:55:15.901368Z","shell.execute_reply.started":"2022-06-23T08:55:15.887717Z","shell.execute_reply":"2022-06-23T08:55:15.899981Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}