{"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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"## HW info\n\n**Original notebook:** https://www.kaggle.com/code/jetakow/home-credit-2024-starter-notebook (version 4)\n\n**Original score:** 0.361\n\n**My name:** Andrew Ishutin\n\n**Improvements**:\n- 3 features related to debts (current_debt / total_debt, overdue / total_debt, totalsettled / maxdebt)\n- optuna hyperparams tuning\n\n## Load the data\n","metadata":{}},{"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":"2024-03-15T19:19:02.474162Z","iopub.execute_input":"2024-03-15T19:19:02.474689Z","iopub.status.idle":"2024-03-15T19:19:02.482134Z","shell.execute_reply.started":"2024-03-15T19:19:02.474653Z","shell.execute_reply":"2024-03-15T19:19:02.480774Z"},"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":"2024-03-15T19:19:02.484493Z","iopub.execute_input":"2024-03-15T19:19:02.485756Z","iopub.status.idle":"2024-03-15T19:19:02.498832Z","shell.execute_reply.started":"2024-03-15T19:19:02.485694Z","shell.execute_reply":"2024-03-15T19:19:02.497212Z"},"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) ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:02.500743Z","iopub.execute_input":"2024-03-15T19:19:02.501730Z","iopub.status.idle":"2024-03-15T19:19:27.699374Z","shell.execute_reply.started":"2024-03-15T19:19:02.501673Z","shell.execute_reply":"2024-03-15T19:19:27.696448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# My Code\ntrain_tax_registry_a_1 = pl.read_csv(dataPath + \"csv_files/train/train_tax_registry_a_1.csv\")\ntrain_tax_registry_b_1 = pl.read_csv(dataPath + \"csv_files/train/train_tax_registry_b_1.csv\")\ntrain_tax_registry_c_1 = pl.read_csv(dataPath + \"csv_files/train/train_tax_registry_c_1.csv\")\nprint(train_tax_registry_a_1.columns, train_tax_registry_b_1.columns, train_tax_registry_c_1.columns)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:27.711669Z","iopub.execute_input":"2024-03-15T19:19:27.713631Z","iopub.status.idle":"2024-03-15T19:19:30.790316Z","shell.execute_reply.started":"2024-03-15T19:19:27.713444Z","shell.execute_reply":"2024-03-15T19:19:30.786308Z"},"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) ","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:30.794042Z","iopub.execute_input":"2024-03-15T19:19:30.794986Z","iopub.status.idle":"2024-03-15T19:19:30.883222Z","shell.execute_reply.started":"2024-03-15T19:19:30.794951Z","shell.execute_reply":"2024-03-15T19:19:30.879861Z"},"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#train_tax_registry_a_1_feats = train_tax_registry_a_1.select([\"case_id\", \"num_group1\", \"amount_4527230A\"]).filter(pl.col(\"num_group1\") == 0)\n#train_tax_registry_a_1_feats = train_tax_registry_1.select([\"case_id\", \"num_group1\", \"amount_4527230A\"]).filter(pl.col(\"num_group1\") == 0)\n#train_tax_registry_a_1_feats = train_tax_registry_a_1.select([\"case_id\", \"num_group1\", \"amount_4527230A\"]).filter(pl.col(\"num_group1\") == 0)\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":"2024-03-15T19:19:30.890488Z","iopub.execute_input":"2024-03-15T19:19:30.893287Z","iopub.status.idle":"2024-03-15T19:19:35.916185Z","shell.execute_reply.started":"2024-03-15T19:19:30.893182Z","shell.execute_reply":"2024-03-15T19:19:35.910445Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_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\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)\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":"2024-03-15T19:19:35.921827Z","iopub.execute_input":"2024-03-15T19:19:35.923270Z","iopub.status.idle":"2024-03-15T19:19:35.989366Z","shell.execute_reply.started":"2024-03-15T19:19:35.923220Z","shell.execute_reply":"2024-03-15T19:19:35.985513Z"},"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":"2024-03-15T19:19:35.994952Z","iopub.execute_input":"2024-03-15T19:19:35.998439Z","iopub.status.idle":"2024-03-15T19:19:54.397888Z","shell.execute_reply.started":"2024-03-15T19:19:35.998187Z","shell.execute_reply":"2024-03-15T19:19:54.396292Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# MyFeatures\ndef add_total_debt_to_total_debt(df):\n    # currdebt_22A is nearly the same s totaldebt_9A\n    df['current_debt_to_total_debt'] = df['currdebt_22A'] / (1e-6 + df['maxdebt4_972A']) # 'maxdebt4_972A'\n    return df\n\n#def add_overdue_to_total_debt(df):\n#    df['overdue_to_total_debt'] = df['totaloutstanddebtvalue_39A'] / (1e-6 + df['maxdebt4_972A'])\n#    return df\n\ndef add_totalsettled_to_total_debt(df):\n    df['totalsettled_to_total_debt'] = df['totalsettled_863A'] / (1e-6 + df['maxdebt4_972A'])\n    return df\n\ndef add_maxannuity_to_maxdebt(df):\n    df['maxannuity_to_maxdebt'] = df['maxannuity_159A'] / (1e-6 + df['maxdebt4_972A']) # approximates r\n    return df\n\n\nnew_feature_fs = [add_total_debt_to_total_debt, add_totalsettled_to_total_debt, add_maxannuity_to_maxdebt]\ndata_submission = data_submission.to_pandas()\nfor f in new_feature_fs:\n    X_train = f(X_train)\n    X_valid = f(X_valid)\n    X_test = f(X_test)\n    data_submission = f(data_submission)\n\ncols_pred = list(X_train.columns)\nprint(cols_pred) # .extend(['current_debt_to_total_debt', 'totalsettled_to_total_debt'])","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:54.399994Z","iopub.execute_input":"2024-03-15T19:19:54.400553Z","iopub.status.idle":"2024-03-15T19:19:54.522033Z","shell.execute_reply.started":"2024-03-15T19:19:54.400505Z","shell.execute_reply":"2024-03-15T19:19:54.520399Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"data_submission","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:54.527987Z","iopub.execute_input":"2024-03-15T19:19:54.528583Z","iopub.status.idle":"2024-03-15T19:19:54.575821Z","shell.execute_reply.started":"2024-03-15T19:19:54.528529Z","shell.execute_reply":"2024-03-15T19:19:54.574299Z"},"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":"2024-03-15T19:19:54.578125Z","iopub.execute_input":"2024-03-15T19:19:54.579151Z","iopub.status.idle":"2024-03-15T19:19:54.590715Z","shell.execute_reply.started":"2024-03-15T19:19:54.579099Z","shell.execute_reply":"2024-03-15T19:19:54.589451Z"},"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":"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","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:54.592970Z","iopub.execute_input":"2024-03-15T19:19:54.593927Z","iopub.status.idle":"2024-03-15T19:19:54.606217Z","shell.execute_reply.started":"2024-03-15T19:19:54.593877Z","shell.execute_reply":"2024-03-15T19:19:54.604746Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# modified from https://github.com/optuna/optuna-examples/blob/main/lightgbm/lightgbm_simple.py\n\nimport optuna\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        \"metric\": \"auc\",\n    #    'device': 'gpu',\n        \"learning_rate\": trial.suggest_float('learning_rate', 1e-3, 1e-1, log=True),\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"boosting_type\": \"gbdt\",\n        'verbose': -1,\n        \"max_depth\": trial.suggest_int(\"max_depth\", 2, 4),\n        \"n_estimators\": trial.suggest_int(\"n_estimators\", 500, 1500),\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, 256),\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\n    gbm = lgb.train(param, lgb_train)\n    preds = gbm.predict(X_valid)\n    base_valid[\"score\"] = gbm.predict(X_valid)\n    score = gini_stability(base_valid)\n    return score\n\n'''\nstudy = optuna.create_study(direction=\"maximize\")\nstudy.optimize(objective, n_trials=200)\n\nprint(\"Number of finished trials: {}\".format(len(study.trials)))\n\nprint(\"Best trial:\")\ntrial = study.best_trial\n\nprint(\"  Value: {}\".format(trial.value))\n\nprint(\"  Params: \")\nfor key, value in trial.params.items():\n    print(\"    {}: {}\".format(key, value))\n'''","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:54.613699Z","iopub.execute_input":"2024-03-15T19:19:54.614359Z","iopub.status.idle":"2024-03-15T19:19:54.638383Z","shell.execute_reply.started":"2024-03-15T19:19:54.614311Z","shell.execute_reply":"2024-03-15T19:19:54.637070Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"lgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\nparam = {\n    \"metric\": \"auc\",\n#    'device': 'gpu',\n    \"learning_rate\": 0.05935170848140834,\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"boosting_type\": \"gbdt\",\n    'verbose': -1,\n    \"max_depth\": 4,\n    \"n_estimators\": 1359,\n    \"lambda_l1\": 3.99387307534986e-06,\n    \"lambda_l2\": 4.807095652736764e-06,\n    \"num_leaves\": 83,\n    \"feature_fraction\": 0.47190800241941916,\n    \"bagging_fraction\": 0.7478174293912009,\n    \"bagging_freq\": 1,\n    \"min_child_samples\": 46,\n}\n\n#for key, value in trial.params.items():\n#    param[key] = value\n\nmodel = lgb.train(param, lgb_train)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:19:54.639985Z","iopub.execute_input":"2024-03-15T19:19:54.640791Z","iopub.status.idle":"2024-03-15T19:22:29.086037Z","shell.execute_reply.started":"2024-03-15T19:19:54.640737Z","shell.execute_reply":"2024-03-15T19:22:29.084918Z"},"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 = model.predict(X)\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":"2024-03-15T19:22:29.087679Z","iopub.execute_input":"2024-03-15T19:22:29.088324Z","iopub.status.idle":"2024-03-15T19:23:35.757413Z","shell.execute_reply.started":"2024-03-15T19:22:29.088289Z","shell.execute_reply":"2024-03-15T19:23:35.755863Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\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":"2024-03-15T19:23:35.760585Z","iopub.execute_input":"2024-03-15T19:23:35.761160Z","iopub.status.idle":"2024-03-15T19:23:36.946956Z","shell.execute_reply.started":"2024-03-15T19:23:35.761110Z","shell.execute_reply":"2024-03-15T19:23:36.945661Z"},"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":"len(cols_pred)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:23:36.949001Z","iopub.execute_input":"2024-03-15T19:23:36.949809Z","iopub.status.idle":"2024-03-15T19:23:36.957723Z","shell.execute_reply.started":"2024-03-15T19:23:36.949764Z","shell.execute_reply":"2024-03-15T19:23:36.956297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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 = model.predict(X_submission)","metadata":{"execution":{"iopub.status.busy":"2024-03-15T19:23:36.959588Z","iopub.execute_input":"2024-03-15T19:23:36.960117Z","iopub.status.idle":"2024-03-15T19:23:37.110206Z","shell.execute_reply.started":"2024-03-15T19:23:36.960071Z","shell.execute_reply":"2024-03-15T19:23:37.108835Z"},"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":"2024-03-15T19:23:37.112219Z","iopub.execute_input":"2024-03-15T19:23:37.112712Z","iopub.status.idle":"2024-03-15T19:23:37.128443Z","shell.execute_reply.started":"2024-03-15T19:23:37.112669Z","shell.execute_reply":"2024-03-15T19:23:37.126916Z"},"trusted":true},"execution_count":null,"outputs":[]}]}