{"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":7602123,"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\nDisclaim: huge credit to https://www.kaggle.com/code/jetakow/home-credit-2024-starter-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":"2024-02-08T20:23:31.116180Z","iopub.execute_input":"2024-02-08T20:23:31.118806Z","iopub.status.idle":"2024-02-08T20:23:31.128910Z","shell.execute_reply.started":"2024-02-08T20:23:31.118738Z","shell.execute_reply":"2024-02-08T20:23:31.127462Z"},"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":"2024-02-08T20:23:31.293573Z","iopub.execute_input":"2024-02-08T20:23:31.294807Z","iopub.status.idle":"2024-02-08T20:23:31.303980Z","shell.execute_reply.started":"2024-02-08T20:23:31.294754Z","shell.execute_reply":"2024-02-08T20:23:31.303037Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reading a base table for training data from a CSV file\ntrain_basetable = pl.read_csv(dataPath + \"csv_files/train/train_base.csv\")\n\n# Concatenating two training static data CSV files after setting their data types\n# The files are stacked vertically, accommodating for possible differences in column names\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)\n\n# Reading additional training data CSV files, each processed for data types\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) ","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:23:31.463740Z","iopub.execute_input":"2024-02-08T20:23:31.464185Z","iopub.status.idle":"2024-02-08T20:23:49.770866Z","shell.execute_reply.started":"2024-02-08T20:23:31.464154Z","shell.execute_reply":"2024-02-08T20:23:49.769803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_static.head(2)","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:23:49.774735Z","iopub.execute_input":"2024-02-08T20:23:49.775287Z","iopub.status.idle":"2024-02-08T20:23:49.791343Z","shell.execute_reply.started":"2024-02-08T20:23:49.775225Z","shell.execute_reply":"2024-02-08T20:23:49.789966Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_static_cb.head(2)","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:23:49.794626Z","iopub.execute_input":"2024-02-08T20:23:49.795009Z","iopub.status.idle":"2024-02-08T20:23:49.807215Z","shell.execute_reply.started":"2024-02-08T20:23:49.794973Z","shell.execute_reply":"2024-02-08T20:23:49.805509Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reading a CSV file into a Polars DataFrame named 'test_basetable'\n# 'dataPath' is a variable that contains the path to the data directory\ntest_basetable = pl.read_csv(dataPath + \"csv_files/test/test_base.csv\")\n\n# Reading multiple CSV files, each representing a part of the 'test_static' data\n# After reading each file, the 'set_table_dtypes' function is applied using the 'pipe' method\n# This function likely sets or adjusts the data types of the columns in the DataFrames\n# The individual DataFrames are then concatenated vertically (stacked on top of each other)\n# 'how=\"vertical_relaxed\"' indicates that the concatenation is vertical and allows for differing column names\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)\n\n# Reading another CSV file into a DataFrame 'test_static_cb'\n# Again, applying 'set_table_dtypes' to adjust the data types\ntest_static_cb = pl.read_csv(dataPath + \"csv_files/test/test_static_cb_0.csv\").pipe(set_table_dtypes)\n\n# Similarly, reading more CSV files into DataFrames 'test_person_1' and 'test_credit_bureau_b_2'\n# Each DataFrame is processed with the 'set_table_dtypes' function\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)","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:23:49.811861Z","iopub.execute_input":"2024-02-08T20:23:49.812497Z","iopub.status.idle":"2024-02-08T20:23:49.887757Z","shell.execute_reply.started":"2024-02-08T20:23:49.812453Z","shell.execute_reply":"2024-02-08T20:23:49.886456Z"},"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":"# We need to use aggregation functions in tables with depth > 1, so tables that contain num_group1 column or \n# also num_group2 column.\ntrain_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\n# Here num_group1=0 has special meaning, it is the person who applied for the loan.\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\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# 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_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":"2024-02-08T20:23:49.890717Z","iopub.execute_input":"2024-02-08T20:23:49.891308Z","iopub.status.idle":"2024-02-08T20:23:52.301752Z","shell.execute_reply.started":"2024-02-08T20:23:49.891270Z","shell.execute_reply":"2024-02-08T20:23:52.300427Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_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\ntest_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\ntest_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\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)","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:23:52.303390Z","iopub.execute_input":"2024-02-08T20:23:52.303751Z","iopub.status.idle":"2024-02-08T20:23:53.010187Z","shell.execute_reply.started":"2024-02-08T20:23:52.303722Z","shell.execute_reply":"2024-02-08T20:23:53.009089Z"},"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\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":"2024-02-08T20:23:53.012121Z","iopub.execute_input":"2024-02-08T20:23:53.012491Z","iopub.status.idle":"2024-02-08T20:24:00.370296Z","shell.execute_reply.started":"2024-02-08T20:23:53.012460Z","shell.execute_reply":"2024-02-08T20:24:00.369152Z"},"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":"2024-02-08T20:24:00.371864Z","iopub.execute_input":"2024-02-08T20:24:00.372214Z","iopub.status.idle":"2024-02-08T20:24:00.378715Z","shell.execute_reply.started":"2024-02-08T20:24:00.372181Z","shell.execute_reply":"2024-02-08T20:24:00.377429Z"},"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":"# lgb_train = lgb.Dataset(X_train, label=y_train)\n# lgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n# params = {\n#     \"boosting_type\": \"gbdt\",\n#     \"objective\": \"binary\",\n#     \"metric\": \"auc\",\n#     \"max_depth\": 3,\n#     \"num_leaves\": 31,\n#     \"learning_rate\": 0.05,\n#     \"feature_fraction\": 0.9,\n#     \"bagging_fraction\": 0.8,\n#     \"bagging_freq\": 5,\n#     \"n_estimators\": 1000,\n#     \"verbose\": -1,\n# }\n\n# gbm = 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":"2024-02-08T20:24:00.380220Z","iopub.execute_input":"2024-02-08T20:24:00.380637Z","iopub.status.idle":"2024-02-08T20:24:00.390122Z","shell.execute_reply.started":"2024-02-08T20:24:00.380592Z","shell.execute_reply":"2024-02-08T20:24:00.388823Z"},"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":"# 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\n# print(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], base_train[\"score\"])}') \n# print(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], base_valid[\"score\"])}') \n# print(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], base_test[\"score\"])}')  ","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:00.393450Z","iopub.execute_input":"2024-02-08T20:24:00.393850Z","iopub.status.idle":"2024-02-08T20:24:00.400880Z","shell.execute_reply.started":"2024-02-08T20:24:00.393816Z","shell.execute_reply":"2024-02-08T20:24:00.399619Z"},"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\n# stability_score_train = gini_stability(base_train)\n# stability_score_valid = gini_stability(base_valid)\n# stability_score_test = gini_stability(base_test)\n\n# print(f'The stability score on the train set is: {stability_score_train}') \n# print(f'The stability score on the valid set is: {stability_score_valid}') \n# print(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:00.402505Z","iopub.execute_input":"2024-02-08T20:24:00.403181Z","iopub.status.idle":"2024-02-08T20:24:00.413288Z","shell.execute_reply.started":"2024-02-08T20:24:00.403145Z","shell.execute_reply":"2024-02-08T20:24:00.411944Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Trying CatBoost","metadata":{}},{"cell_type":"code","source":"from catboost import CatBoostClassifier\nfrom sklearn.metrics import roc_auc_score\n\ncategorical_columns = [col for col in X_train.columns if X_train[col].dtype.name == 'category']\nfor col in categorical_columns:\n    X_train[col] = X_train[col].astype(str).fillna('missing')\n    X_valid[col] = X_valid[col].astype(str).fillna('missing')\n    X_test[col] = X_test[col].astype(str).fillna('missing')\n\n# Create a CatBoost classifier instance\ncatboost = CatBoostClassifier(\n    iterations=50, \n    learning_rate=0.1, \n    depth=6,\n    eval_metric='Accuracy',  # You can change this depending on your needs\n    random_seed=42,\n    cat_features=categorical_columns,  # Specify categorical features here\n    verbose=10  # It will print training progress every 100 iterations\n)\n# Train the CatBoost model (assuming y_train is your training target variable)\ncatboost.fit(X_train, y_train)\n\n# Now, use the trained model for predictions\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    y_pred = catboost.predict_proba(X)[:, 1]  # Get probabilities for the positive class\n    base[\"score\"] = y_pred\n\n# Print AUC scores\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\"])}') \n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:00.414978Z","iopub.execute_input":"2024-02-08T20:24:00.415331Z","iopub.status.idle":"2024-02-08T20:24:49.438638Z","shell.execute_reply.started":"2024-02-08T20:24:00.415301Z","shell.execute_reply":"2024-02-08T20:24:49.437406Z"},"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":"2024-02-08T20:24:49.440413Z","iopub.execute_input":"2024-02-08T20:24:49.441459Z","iopub.status.idle":"2024-02-08T20:24:50.416940Z","shell.execute_reply.started":"2024-02-08T20:24:49.441411Z","shell.execute_reply":"2024-02-08T20:24:50.415719Z"},"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\n#y_submission_pred = gbm.predict(X_submission, num_iteration=gbm.best_iteration)\n# Check if best_iteration_ is available and is an integer\nif hasattr(catboost, 'best_iteration_') and isinstance(catboost.best_iteration_, int):\n    ntree_end = catboost.best_iteration_\nelse:\n    # If best_iteration_ is not set or not an integer, use all trees\n    ntree_end = catboost.tree_count_\n\n# Predict probabilities\n# Predict probabilities\ny_submission_pred_proba = catboost.predict_proba(X_submission, ntree_end=ntree_end)\n\n# For binary classification, selecting the probability of the positive class (usually the second column)\ny_submission_pred = y_submission_pred_proba[:, 1]\n\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:50.418198Z","iopub.execute_input":"2024-02-08T20:24:50.418539Z","iopub.status.idle":"2024-02-08T20:24:50.464418Z","shell.execute_reply.started":"2024-02-08T20:24:50.418509Z","shell.execute_reply":"2024-02-08T20:24:50.463205Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_submission_pred","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:50.465829Z","iopub.execute_input":"2024-02-08T20:24:50.466157Z","iopub.status.idle":"2024-02-08T20:24:50.473052Z","shell.execute_reply.started":"2024-02-08T20:24:50.466128Z","shell.execute_reply":"2024-02-08T20:24:50.472270Z"},"trusted":true},"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":"2024-02-08T20:24:50.474458Z","iopub.execute_input":"2024-02-08T20:24:50.475081Z","iopub.status.idle":"2024-02-08T20:24:50.486072Z","shell.execute_reply.started":"2024-02-08T20:24:50.475018Z","shell.execute_reply":"2024-02-08T20:24:50.484761Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission","metadata":{"execution":{"iopub.status.busy":"2024-02-08T20:24:50.487527Z","iopub.execute_input":"2024-02-08T20:24:50.489542Z","iopub.status.idle":"2024-02-08T20:24:50.499856Z","shell.execute_reply.started":"2024-02-08T20:24:50.489317Z","shell.execute_reply":"2024-02-08T20:24:50.498858Z"},"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":{}}]}