{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":50160,"databundleVersionId":7602123,"sourceType":"competition"}],"dockerImageVersionId":30646,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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# Import necessary libraries\nimport polars as pl\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import roc_auc_score\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\n# import os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-02-20T22:31:15.713943Z","iopub.execute_input":"2024-02-20T22:31:15.714468Z","iopub.status.idle":"2024-02-20T22:31:15.722712Z","shell.execute_reply.started":"2024-02-20T22:31:15.714430Z","shell.execute_reply":"2024-02-20T22:31:15.721313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define the path to the data\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:14.763154Z","iopub.execute_input":"2024-02-20T22:08:14.764522Z","iopub.status.idle":"2024-02-20T22:08:14.769918Z","shell.execute_reply.started":"2024-02-20T22:08:14.764466Z","shell.execute_reply":"2024-02-20T22:08:14.768681Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Define functions for setting data types and converting strings\ndef set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # Set desired data types for columns\n    for col in df.columns:\n        if col[-1] in (\"P\", \"A\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:14.772000Z","iopub.execute_input":"2024-02-20T22:08:14.772393Z","iopub.status.idle":"2024-02-20T22:08:14.786744Z","shell.execute_reply.started":"2024-02-20T22:08:14.772357Z","shell.execute_reply":"2024-02-20T22:08:14.785360Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Load train and test datasets using Polars\ntrain_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\ntrain_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_static_0_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:14.789972Z","iopub.execute_input":"2024-02-20T22:08:14.790453Z","iopub.status.idle":"2024-02-20T22:08:25.097868Z","shell.execute_reply.started":"2024-02-20T22:08:14.790416Z","shell.execute_reply":"2024-02-20T22:08:25.096041Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_static.head(3)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:25.099478Z","iopub.execute_input":"2024-02-20T22:08:25.100764Z","iopub.status.idle":"2024-02-20T22:08:25.125226Z","shell.execute_reply.started":"2024-02-20T22:08:25.100724Z","shell.execute_reply":"2024-02-20T22:08:25.123710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_static_cb = pl.read_csv(dataPath + \"csv_files/train/train_static_cb_0.csv\").pipe(set_table_dtypes)\ntrain_person_1 = pl.read_csv(dataPath + \"csv_files/train/train_person_1.csv\").pipe(set_table_dtypes) \ntrain_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/train/train_credit_bureau_b_2.csv\").pipe(set_table_dtypes) \ntest_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\ntest_static = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_static_0_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\ntest_person_1 = pl.read_csv(dataPath + \"csv_files/test/test_person_1.csv\").pipe(set_table_dtypes) \ntest_credit_bureau_b_2 = pl.read_csv(dataPath + \"csv_files/test/test_credit_bureau_b_2.csv\").pipe(set_table_dtypes) \n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:25.126821Z","iopub.execute_input":"2024-02-20T22:08:25.127246Z","iopub.status.idle":"2024-02-20T22:08:30.616252Z","shell.execute_reply.started":"2024-02-20T22:08:25.127203Z","shell.execute_reply":"2024-02-20T22:08:30.614965Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature engineering - Grouping and aggregating features","metadata":{}},{"cell_type":"code","source":"train_person_1_feats_1 = train_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\ntrain_person_1_feats_2 = train_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\ntrain_credit_bureau_b_2_feats = train_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:30.617861Z","iopub.execute_input":"2024-02-20T22:08:30.618678Z","iopub.status.idle":"2024-02-20T22:08:31.656127Z","shell.execute_reply.started":"2024-02-20T22:08:30.618642Z","shell.execute_reply":"2024-02-20T22:08:31.655163Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Select relevant static columns","metadata":{}},{"cell_type":"code","source":"\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\n\nselected_static_cb_cols = []\nfor col in train_static_cb.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cb_cols.append(col)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:31.660760Z","iopub.execute_input":"2024-02-20T22:08:31.663022Z","iopub.status.idle":"2024-02-20T22:08:31.671263Z","shell.execute_reply.started":"2024-02-20T22:08:31.662972Z","shell.execute_reply":"2024-02-20T22:08:31.669922Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Join all tables together","metadata":{}},{"cell_type":"code","source":"\ndata = train_basetable.join(\n    train_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    train_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:31.672958Z","iopub.execute_input":"2024-02-20T22:08:31.673643Z","iopub.status.idle":"2024-02-20T22:08:33.085607Z","shell.execute_reply.started":"2024-02-20T22:08:31.673610Z","shell.execute_reply":"2024-02-20T22:08:33.084510Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Repeat the feature engineering process for the test dataset","metadata":{}},{"cell_type":"code","source":"\ntest_person_1_feats_1 = test_person_1.group_by(\"case_id\").agg(\n    pl.col(\"mainoccupationinc_384A\").max().alias(\"mainoccupationinc_384A_max\"),\n    (pl.col(\"incometype_1044T\") == \"SELFEMPLOYED\").max().alias(\"mainoccupationinc_384A_any_selfemployed\")\n)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.091174Z","iopub.execute_input":"2024-02-20T22:08:33.091901Z","iopub.status.idle":"2024-02-20T22:08:33.100035Z","shell.execute_reply.started":"2024-02-20T22:08:33.091859Z","shell.execute_reply":"2024-02-20T22:08:33.098806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Continue feature engineering for the test dataset","metadata":{}},{"cell_type":"code","source":"\ntest_person_1_feats_2 = test_person_1.select([\"case_id\", \"num_group1\", \"housetype_905L\"]).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\").rename({\"housetype_905L\": \"person_housetype\"})\n\ntest_credit_bureau_b_2_feats = test_credit_bureau_b_2.group_by(\"case_id\").agg(\n    pl.col(\"pmts_pmtsoverdue_635A\").max().alias(\"pmts_pmtsoverdue_635A_max\"),\n    (pl.col(\"pmts_dpdvalue_108P\") > 31).max().alias(\"pmts_dpdvalue_108P_over31\")\n)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.101711Z","iopub.execute_input":"2024-02-20T22:08:33.102750Z","iopub.status.idle":"2024-02-20T22:08:33.112266Z","shell.execute_reply.started":"2024-02-20T22:08:33.102701Z","shell.execute_reply":"2024-02-20T22:08:33.110982Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Join all tables together for the test dataset","metadata":{}},{"cell_type":"code","source":"\n\ndata_submission = test_basetable.join(\n    test_static.select([\"case_id\"]+selected_static_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_static_cb.select([\"case_id\"]+selected_static_cb_cols), how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_1, how=\"left\", on=\"case_id\"\n).join(\n    test_person_1_feats_2, how=\"left\", on=\"case_id\"\n).join(\n    test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n)\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.114381Z","iopub.execute_input":"2024-02-20T22:08:33.115249Z","iopub.status.idle":"2024-02-20T22:08:33.127287Z","shell.execute_reply.started":"2024-02-20T22:08:33.115205Z","shell.execute_reply":"2024-02-20T22:08:33.125919Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Split the data into train, validation, and test sets\ncase_ids = data[\"case_id\"].unique().shuffle(seed=1)\ncase_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)\ncase_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)\n\n# Define columns for prediction\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.129559Z","iopub.execute_input":"2024-02-20T22:08:33.131208Z","iopub.status.idle":"2024-02-20T22:08:33.348956Z","shell.execute_reply.started":"2024-02-20T22:08:33.131159Z","shell.execute_reply":"2024-02-20T22:08:33.347669Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Function to convert Polars DataFrame to Pandas DataFrame\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.350261Z","iopub.execute_input":"2024-02-20T22:08:33.350586Z","iopub.status.idle":"2024-02-20T22:08:33.357660Z","shell.execute_reply.started":"2024-02-20T22:08:33.350558Z","shell.execute_reply":"2024-02-20T22:08:33.356400Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Extract train, validation, and test sets","metadata":{}},{"cell_type":"code","source":"def convert_strings(df: pd.DataFrame) -> pd.DataFrame:\n    # Convert string columns to categorical\n    for col in df.columns:  \n        if df[col].dtype.name in ['object', 'string']:\n            df[col] = df[col].astype(\"string\").astype('category')\n            current_categories = df[col].cat.categories\n            new_categories = current_categories.to_list() + [\"Unknown\"]\n            new_dtype = pd.CategoricalDtype(categories=new_categories, ordered=True)\n            df[col] = df[col].astype(new_dtype)\n    return df","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.359747Z","iopub.execute_input":"2024-02-20T22:08:33.360372Z","iopub.status.idle":"2024-02-20T22:08:33.368608Z","shell.execute_reply.started":"2024-02-20T22:08:33.360338Z","shell.execute_reply":"2024-02-20T22:08:33.367714Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\nbase_train, X_train, y_train = from_polars_to_pandas(case_ids_train)\nbase_valid, X_valid, y_valid = from_polars_to_pandas(case_ids_valid)\nbase_test, X_test, y_test = from_polars_to_pandas(case_ids_test)\n\n# Convert string columns to categorical\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)\n\n# Display the shape of the datasets\nprint(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:33.369817Z","iopub.execute_input":"2024-02-20T22:08:33.370260Z","iopub.status.idle":"2024-02-20T22:08:42.109699Z","shell.execute_reply.started":"2024-02-20T22:08:33.370216Z","shell.execute_reply":"2024-02-20T22:08:42.108500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Training LightGBM model","metadata":{}},{"cell_type":"code","source":"\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n# Define LightGBM parameters\nparams = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"max_depth\": 5,\n    \"num_leaves\": 50,\n    \"learning_rate\": 0.1,\n    \"feature_fraction\": 0.8,\n    \"bagging_fraction\": 0.9,\n    \"bagging_freq\": 10,\n    \"n_estimators\": 1500,\n    \"verbose\": -1,\n}\n\n# Train the LightGBM model\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)\n\n# Evaluate the AUC scores on train, validation, and test sets\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = gbm.predict(X, num_iteration=gbm.best_iteration)\n    base[\"score\"] = y_pred\n\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:08:42.111110Z","iopub.execute_input":"2024-02-20T22:08:42.111463Z","iopub.status.idle":"2024-02-20T22:09:34.956028Z","shell.execute_reply.started":"2024-02-20T22:08:42.111431Z","shell.execute_reply":"2024-02-20T22:09:34.954655Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Train the XGBoost model","metadata":{}},{"cell_type":"code","source":"import xgboost as xgb\nfrom sklearn.metrics import roc_auc_score\n\n# Train the XGBoost model\nxgb_model = xgb.XGBClassifier(\n    objective=\"binary:logistic\",\n    max_depth=3,\n    learning_rate=0.1,\n    n_estimators=1000,\n    subsample=0.8,\n    colsample_bytree=0.8,\n    random_state=42\n)\n\n# Set eval_metric and enable_categorical in the constructor or using set_params\nxgb_model.set_params(eval_metric=[\"auc\"], enable_categorical=True)\n\nxgb_model.fit(X_train, y_train, eval_set=[(X_valid, y_valid)], early_stopping_rounds=10, verbose=50)\n\n# Evaluate the AUC scores on train, validation, and test sets for XGBoost\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred_xgb = xgb_model.predict_proba(X)[:, 1]\n    base[\"score_xgb\"] = y_pred_xgb\n\nprint(f'The AUC score on the train set (XGBoost) is: {roc_auc_score(base_train[\"target\"], base_train[\"score_xgb\"])}') \nprint(f'The AUC score on the valid set (XGBoost) is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score_xgb\"])}') \nprint(f'The AUC score on the test set (XGBoost) is: {roc_auc_score(base_test[\"target\"], base_test[\"score_xgb\"])}')\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:20:58.475553Z","iopub.execute_input":"2024-02-20T22:20:58.476128Z","iopub.status.idle":"2024-02-20T22:23:17.962831Z","shell.execute_reply.started":"2024-02-20T22:20:58.476087Z","shell.execute_reply":"2024-02-20T22:23:17.961320Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Stability metric function","metadata":{}},{"cell_type":"code","source":"\ndef gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\n# Calculate stability scores for train, validation, and test sets\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}')\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:09:34.964872Z","iopub.execute_input":"2024-02-20T22:09:34.965222Z","iopub.status.idle":"2024-02-20T22:09:36.147081Z","shell.execute_reply.started":"2024-02-20T22:09:34.965191Z","shell.execute_reply":"2024-02-20T22:09:36.145823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Submission - Scoring the submission dataset\nX_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\n# Handle new categories in the submission dataset\nfor col in categorical_cols:\n    train_categories = set(X_train[col].cat.categories)\n    submission_categories = set(X_submission[col].cat.categories)\n    new_categories = submission_categories - train_categories\n    X_submission.loc[X_submission[col].isin(new_categories), col] = \"Unknown\"\n    new_dtype = pd.CategoricalDtype(categories=train_categories, ordered=True)\n    X_train[col] = X_train[col].astype(new_dtype)\n    X_submission[col] = X_submission[col].astype(new_dtype)\n\n# Predict on the submission dataset\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)\n\n# Create submission DataFrame\nsubmission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\n\n# Save the submission to a CSV file\nsubmission.to_csv(\"./submission.csv\")\n\n# Print a closing message\nprint(\"Best of luck, and most importantly, enjoy the process of learning and discovery!\")","metadata":{"execution":{"iopub.status.busy":"2024-02-20T22:09:36.148486Z","iopub.execute_input":"2024-02-20T22:09:36.148826Z","iopub.status.idle":"2024-02-20T22:09:36.269704Z","shell.execute_reply.started":"2024-02-20T22:09:36.148797Z","shell.execute_reply":"2024-02-20T22:09:36.268374Z"},"trusted":true},"execution_count":null,"outputs":[]}]}