{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","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":7921029,"sourceType":"competition"}],"dockerImageVersionId":30635,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Example Notebook\n\nWelcome to the example notebook for the Home Credit Kaggle competition. The goal of this competition is to determine how likely a customer is going to default on an issued loan. The main difference between the [first](https://www.kaggle.com/c/home-credit-default-risk) and this competition is that now your submission will be scored with a custom metric that will take into account how well the model performs in future. A decline in performance will be penalized. The goal is to create a model that is stable and performs well in the future.\n\nIn this notebook you will see how to:\n* Load the data\n* Join tables with Polars - a DataFrame library implemented in Rust language, designed to be blazingy fast and memory efficient.  \n* Create simple aggregation features\n* Train a LightGBM model\n* Create a submission table\n\n## Load the data","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_auc_score \n\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:04:21.837508Z","iopub.execute_input":"2024-03-18T20:04:21.839664Z","iopub.status.idle":"2024-03-18T20:04:21.848799Z","shell.execute_reply.started":"2024-03-18T20:04:21.839601Z","shell.execute_reply":"2024-03-18T20:04:21.847270Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def set_table_dtypes(df: pl.DataFrame) -> pl.DataFrame:\n    # implement here all desired dtypes for tables\n    # the following is just an example\n    for col in df.columns:\n        # last letter of column name will help you determine the type\n        if col[-1] in (\"P\", \"A\"):\n            df = df.with_columns(pl.col(col).cast(pl.Float64).alias(col))\n\n    return df\n\ndef convert_strings(df: pd.DataFrame) -> pd.DataFrame:\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":"2024-03-18T20:04:23.082854Z","iopub.execute_input":"2024-03-18T20:04:23.084169Z","iopub.status.idle":"2024-03-18T20:04:23.094524Z","shell.execute_reply.started":"2024-03-18T20:04:23.084126Z","shell.execute_reply":"2024-03-18T20:04:23.093145Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_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)\ntrain_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)\ntrain_prev = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/train/train_applprev_1_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/train/train_applprev_1_1.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:04:24.888066Z","iopub.execute_input":"2024-03-18T20:04:24.888486Z","iopub.status.idle":"2024-03-18T20:04:55.908903Z","shell.execute_reply.started":"2024-03-18T20:04:24.888454Z","shell.execute_reply":"2024-03-18T20:04:55.904307Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_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)\ntest_prev = pl.concat(\n    [\n        pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_0.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_1.csv\").pipe(set_table_dtypes),\n        pl.read_csv(dataPath + \"csv_files/test/test_applprev_1_2.csv\").pipe(set_table_dtypes),\n    ],\n    how=\"vertical_relaxed\",\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:05:05.704741Z","iopub.execute_input":"2024-03-18T20:05:05.705237Z","iopub.status.idle":"2024-03-18T20:05:05.796620Z","shell.execute_reply.started":"2024-03-18T20:05:05.705199Z","shell.execute_reply":"2024-03-18T20:05:05.795363Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\n\nIn this part, we can see a simple example of joining tables via `case_id`. Here the loading and joining is done with polars library. Polars library is blazingly fast and has much smaller memory footprint than pandas. ","metadata":{}},{"cell_type":"code","source":"from datetime import date\n\ntrain_basetable = train_basetable.with_columns((pl.col(\"date_decision\").str.to_date() < date(2020, 3, 1)).cast(pl.Int32).alias(\"pre_covid\"))\ntrain_basetable = train_basetable.with_columns(pl.col(\"date_decision\").str.to_date().dt.weekday().cast(pl.Int32).alias(\"weekday\"))","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:05:09.042359Z","iopub.execute_input":"2024-03-18T20:05:09.043688Z","iopub.status.idle":"2024-03-18T20:05:10.238510Z","shell.execute_reply.started":"2024-03-18T20:05:09.043631Z","shell.execute_reply":"2024-03-18T20:05:10.235304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_basetable = test_basetable.with_columns((pl.col(\"date_decision\").str.to_date() < date(2020, 3, 1)).cast(pl.Int32).alias(\"pre_covid\"))\ntest_basetable = test_basetable.with_columns(pl.col(\"date_decision\").str.to_date().dt.weekday().cast(pl.Int32).alias(\"weekday\"))","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:05:11.304362Z","iopub.execute_input":"2024-03-18T20:05:11.304861Z","iopub.status.idle":"2024-03-18T20:05:11.313783Z","shell.execute_reply.started":"2024-03-18T20:05:11.304826Z","shell.execute_reply":"2024-03-18T20:05:11.312185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\n\ncols = [\"case_id\", \"birth_259D\", \"num_group1\", \"education_927M\", \"familystate_447L\", \"incometype_1044T\", \"mainoccupationinc_384A\", \"sex_738L\"]\ntrain_person_1 = train_person_1.select(cols).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\")\n\ntrain_prev = train_prev.filter(pl.col(\"num_group1\") == 0)[[\"case_id\", \"credamount_590A\"]]\n\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\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)\n\n\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in train_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\nprint(selected_static_cols)\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)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\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, how=\"left\", on=\"case_id\"\n).join(\n    train_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n).join(\n    train_prev, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:05:14.263047Z","iopub.execute_input":"2024-03-18T20:05:14.263499Z","iopub.status.idle":"2024-03-18T20:05:17.211747Z","shell.execute_reply.started":"2024-03-18T20:05:14.263465Z","shell.execute_reply":"2024-03-18T20:05:17.210612Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data = data.with_columns(((pl.col(\"date_decision\").str.to_date() - pl.col(\"birth_259D\").str.to_date()).dt.total_days() // 365).alias(\"diff\"))\ndata = data.drop(\"birth_259D\")","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:10:37.718195Z","iopub.execute_input":"2024-03-18T20:10:37.718759Z","iopub.status.idle":"2024-03-18T20:10:38.902388Z","shell.execute_reply.started":"2024-03-18T20:10:37.718719Z","shell.execute_reply":"2024-03-18T20:10:38.901026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or\n# also num_group2 column.\n\ncols = [\"case_id\", \"birth_259D\", \"num_group1\", \"education_927M\", \"familystate_447L\", \"incometype_1044T\", \"mainoccupationinc_384A\", \"sex_738L\"]\ntest_person_1 = test_person_1.select(cols).filter(\n    pl.col(\"num_group1\") == 0\n).drop(\"num_group1\")\n\ntest_prev = test_prev.filter(pl.col(\"num_group1\") == 0)[[\"case_id\", \"credamount_590A\"]]\n\n\n# Here we have num_goup1 and num_group2, so we need to aggregate again.\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)\n\n\n\n# We will process in this examples only A-type and M-type columns, so we need to select them.\nselected_static_cols = []\nfor col in test_static.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cols.append(col)\nprint(selected_static_cols)\n\nselected_static_cb_cols = []\nfor col in test_static_cb.columns:\n    if col[-1] in (\"A\", \"M\"):\n        selected_static_cb_cols.append(col)\nprint(selected_static_cb_cols)\n\n# Join all tables together.\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, how=\"left\", on=\"case_id\"\n).join(\n    test_credit_bureau_b_2_feats, how=\"left\", on=\"case_id\"\n).join(\n    test_prev, how=\"left\", on=\"case_id\"\n)\n\ndata_submission = data_submission.with_columns(((pl.col(\"date_decision\").str.to_date() - pl.col(\"birth_259D\").str.to_date()).dt.total_days() // 365).alias(\"diff\"))\ndata_submission = data_submission.drop(\"birth_259D\")","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:11:52.609580Z","iopub.execute_input":"2024-03-18T20:11:52.610405Z","iopub.status.idle":"2024-03-18T20:11:52.644004Z","shell.execute_reply.started":"2024-03-18T20:11:52.610349Z","shell.execute_reply":"2024-03-18T20:11:52.643047Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_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\ncols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)\n\ncols_pred += [\"diff\", \"pre_covid\", \"weekday\"]\n\nprint(cols_pred)\n\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    )\n\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\nfor df in [X_train, X_valid, X_test]:\n    df = convert_strings(df)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:13:21.488718Z","iopub.execute_input":"2024-03-18T20:13:21.489226Z","iopub.status.idle":"2024-03-18T20:13:33.541081Z","shell.execute_reply.started":"2024-03-18T20:13:21.489190Z","shell.execute_reply":"2024-03-18T20:13:33.539828Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(f\"Train: {X_train.shape}\")\nprint(f\"Valid: {X_valid.shape}\")\nprint(f\"Test: {X_test.shape}\")","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:13:38.850744Z","iopub.execute_input":"2024-03-18T20:13:38.852087Z","iopub.status.idle":"2024-03-18T20:13:38.860046Z","shell.execute_reply.started":"2024-03-18T20:13:38.852030Z","shell.execute_reply":"2024-03-18T20:13:38.858364Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Training LightGBM\n\nMinimal example of LightGBM training is shown below.","metadata":{}},{"cell_type":"code","source":"import optuna\nimport lightgbm as lgb\n\n\ndef objective(trial):\n    lgb_train = lgb.Dataset(X_train, label=y_train)\n    lgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n    param = {\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"verbosity\": -1,\n        \"boosting_type\": \"gbdt\",\n        \"lambda_l1\": trial.suggest_float(\"lambda_l1\", 1e-8, 10.0, log=True),\n        \"lambda_l2\": trial.suggest_float(\"lambda_l2\", 1e-8, 10.0, log=True),\n        \"num_leaves\": trial.suggest_int(\"num_leaves\", 2, 128),\n        \"feature_fraction\": trial.suggest_float(\"feature_fraction\", 0.4, 1.0),\n        \"bagging_fraction\": trial.suggest_float(\"bagging_fraction\", 0.4, 1.0),\n        \"bagging_freq\": trial.suggest_int(\"bagging_freq\", 1, 7),\n        \"min_child_samples\": trial.suggest_int(\"min_child_samples\", 5, 100),\n    }\n\n    gbm = lgb.train(\n        param,\n        lgb_train,\n        valid_sets=lgb_valid,\n        callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n    )\n    y_pred = gbm.predict(X_valid, num_iteration=gbm.best_iteration)\n    base_valid[\"score\"] = y_pred\n    return roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])\n\nstudy = optuna.create_study(direction=\"maximize\")\nstudy.optimize(objective, n_trials=50)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:23:37.568072Z","iopub.execute_input":"2024-03-18T20:23:37.568587Z","iopub.status.idle":"2024-03-18T20:50:01.698444Z","shell.execute_reply.started":"2024-03-18T20:23:37.568547Z","shell.execute_reply":"2024-03-18T20:50:01.697142Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Evaluation with AUC and then comparison with the stability metric is shown below.","metadata":{}},{"cell_type":"code","source":"params = {\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"verbosity\": -1,\n    \"boosting_type\": \"gbdt\"\n}\n\nparams.update(study.best_trial.params)\n\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n\ngbm = lgb.train(\n    params,\n    lgb_train,\n    valid_sets=lgb_valid,\n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)]\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:52:24.538170Z","iopub.execute_input":"2024-03-18T20:52:24.538596Z","iopub.status.idle":"2024-03-18T20:53:07.788876Z","shell.execute_reply.started":"2024-03-18T20:52:24.538564Z","shell.execute_reply":"2024-03-18T20:53:07.787396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for 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":"2024-03-18T20:53:07.790925Z","iopub.execute_input":"2024-03-18T20:53:07.792223Z","iopub.status.idle":"2024-03-18T20:53:18.962731Z","shell.execute_reply.started":"2024-03-18T20:53:07.792172Z","shell.execute_reply":"2024-03-18T20:53:18.961581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def 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\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}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:53:28.960845Z","iopub.execute_input":"2024-03-18T20:53:28.961359Z","iopub.status.idle":"2024-03-18T20:53:30.108049Z","shell.execute_reply.started":"2024-03-18T20:53:28.961319Z","shell.execute_reply":"2024-03-18T20:53:30.106739Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Submission\n\nScoring the submission dataset is below, we need to take care of new categories. Then we save the score as a last step. ","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()\nX_submission = convert_strings(X_submission)\ncategorical_cols = X_train.select_dtypes(include=['category']).columns\n\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\ny_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:53:52.565133Z","iopub.execute_input":"2024-03-18T20:53:52.565605Z","iopub.status.idle":"2024-03-18T20:53:52.743247Z","shell.execute_reply.started":"2024-03-18T20:53:52.565567Z","shell.execute_reply":"2024-03-18T20:53:52.741917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_submission_pred","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:54:06.954432Z","iopub.execute_input":"2024-03-18T20:54:06.954882Z","iopub.status.idle":"2024-03-18T20:54:06.962986Z","shell.execute_reply.started":"2024-03-18T20:54:06.954845Z","shell.execute_reply":"2024-03-18T20:54:06.961777Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"case_id\": data_submission[\"case_id\"].to_numpy(),\n    \"score\": y_submission_pred\n}).set_index('case_id')\nsubmission.to_csv(\"./submission.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-18T20:54:10.125327Z","iopub.execute_input":"2024-03-18T20:54:10.125823Z","iopub.status.idle":"2024-03-18T20:54:10.142956Z","shell.execute_reply.started":"2024-03-18T20:54:10.125744Z","shell.execute_reply":"2024-03-18T20:54:10.141805Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Best of luck, and most importantly, enjoy the process of learning and discovery! \n\n<img src=\"https://i.imgur.com/obVWIBh.png\" alt=\"Image\" width=\"700\"/>","metadata":{}}]}