{"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":7921029,"sourceType":"competition"}],"dockerImageVersionId":30664,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Introduction:\nSubmisions of references:**\n\nhttps://www.kaggle.com/code/brantcoral/home-credit-2024-starter-notebook-v1\n\nhttps://www.kaggle.com/code/maverickss26/lb-0-572-home-credit-risk\n\nhttps://www.kaggle.com/code/andreynesterov/home-credit-baseline-inference\n\nhttps://www.kaggle.com/code/anelyakurakinaa/anelya-kurakina-hse-cdm/notebook\n\nLOADING MODULES:","metadata":{}},{"cell_type":"code","source":"import polars as pl\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport lightgbm as lgb\nfrom sklearn.model_selection import train_test_split\nfrom sklearn import metrics\nfrom sklearn.metrics import roc_auc_score, log_loss\nimport lightgbm as lgb\nimport os, glob\nimport gc\ndataPath = \"/kaggle/input/home-credit-credit-risk-model-stability/\"\n","metadata":{"execution":{"iopub.status.busy":"2024-03-19T16:10:49.963203Z","iopub.execute_input":"2024-03-19T16:10:49.964323Z","iopub.status.idle":"2024-03-19T16:10:49.972133Z","shell.execute_reply.started":"2024-03-19T16:10:49.964276Z","shell.execute_reply":"2024-03-19T16:10:49.970653Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"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":"2024-03-19T14:55:04.689819Z","iopub.execute_input":"2024-03-19T14:55:04.690241Z","iopub.status.idle":"2024-03-19T14:55:04.701498Z","shell.execute_reply.started":"2024-03-19T14:55:04.690207Z","shell.execute_reply":"2024-03-19T14:55:04.699957Z"},"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":"2024-03-19T14:55:10.675994Z","iopub.execute_input":"2024-03-19T14:55:10.676492Z","iopub.status.idle":"2024-03-19T14:55:31.451306Z","shell.execute_reply.started":"2024-03-19T14:55:10.676455Z","shell.execute_reply":"2024-03-19T14:55:31.450411Z"},"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":"2024-03-19T14:55:40.452468Z","iopub.execute_input":"2024-03-19T14:55:40.452889Z","iopub.status.idle":"2024-03-19T14:55:40.515084Z","shell.execute_reply.started":"2024-03-19T14:55:40.452857Z","shell.execute_reply":"2024-03-19T14:55:40.513894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Using Polars:**\nThis library is the lightest ones like Pandas and allows a minor use of memory, to deal with our Features.","metadata":{}},{"cell_type":"markdown","source":"Agregamos data test , train in our Data","metadata":{}},{"cell_type":"code","source":"train_debitcard_1 = pl.read_csv(dataPath + \"csv_files/train/train_debitcard_1.csv\").pipe(set_table_dtypes)\ntrain_deposit_1 = pl.read_csv(dataPath + \"csv_files/train/train_deposit_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T14:55:52.400240Z","iopub.execute_input":"2024-03-19T14:55:52.400918Z","iopub.status.idle":"2024-03-19T14:55:52.507543Z","shell.execute_reply.started":"2024-03-19T14:55:52.400884Z","shell.execute_reply":"2024-03-19T14:55:52.506459Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_debitcard_1 = pl.read_csv(dataPath + \"csv_files/test/test_debitcard_1.csv\").pipe(set_table_dtypes)\ntest_deposit_1 = pl.read_csv(dataPath + \"csv_files/test/test_deposit_1.csv\").pipe(set_table_dtypes)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T14:55:56.253724Z","iopub.execute_input":"2024-03-19T14:55:56.254175Z","iopub.status.idle":"2024-03-19T14:55:56.272696Z","shell.execute_reply.started":"2024-03-19T14:55:56.254137Z","shell.execute_reply":"2024-03-19T14:55:56.270932Z"},"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.\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\ntrain_debitcard_1_feats = train_debitcard_1.group_by(\"case_id\").agg(\n    pl.col(\"last180dayaveragebalance_704A\").mean().alias(\"last180dayaveragebalance_704A_mean\"),\n    pl.col(\"last30dayturnover_651A\").max().alias(\"maxlast30dayturnover_651A\"),\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).join(\n    train_debitcard_1_feats, how=\"left\", on=\"case_id\" \n)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T14:56:09.322632Z","iopub.execute_input":"2024-03-19T14:56:09.323083Z","iopub.status.idle":"2024-03-19T14:56:12.509333Z","shell.execute_reply.started":"2024-03-19T14:56:09.323049Z","shell.execute_reply":"2024-03-19T14:56:12.508109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"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\ntest_debitcard_1_feats = test_debitcard_1.group_by(\"case_id\").agg(\n    pl.col(\"last180dayaveragebalance_704A\").mean().alias(\"last180dayaveragebalance_704A_mean\"),\n    pl.col(\"last30dayturnover_651A\").max().alias(\"maxlast30dayturnover_651A\"),\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).join(\n    test_debitcard_1_feats, how=\"left\", on=\"case_id\"\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T14:56:28.852159Z","iopub.execute_input":"2024-03-19T14:56:28.852544Z","iopub.status.idle":"2024-03-19T14:56:28.871163Z","shell.execute_reply.started":"2024-03-19T14:56:28.852515Z","shell.execute_reply":"2024-03-19T14:56:28.869885Z"},"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)\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":"2024-03-19T14:56:36.589633Z","iopub.execute_input":"2024-03-19T14:56:36.590159Z","iopub.status.idle":"2024-03-19T14:56:46.084357Z","shell.execute_reply.started":"2024-03-19T14:56:36.590118Z","shell.execute_reply":"2024-03-19T14:56:46.082991Z"},"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":"2024-03-19T14:56:51.196519Z","iopub.execute_input":"2024-03-19T14:56:51.197002Z","iopub.status.idle":"2024-03-19T14:56:51.204579Z","shell.execute_reply.started":"2024-03-19T14:56:51.196964Z","shell.execute_reply":"2024-03-19T14:56:51.203153Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**LGBM BASELINE MODEL**","metadata":{}},{"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\nparams = {\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\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":"2024-03-19T14:56:57.307459Z","iopub.execute_input":"2024-03-19T14:56:57.307951Z","iopub.status.idle":"2024-03-19T14:58:10.019021Z","shell.execute_reply.started":"2024-03-19T14:56:57.307910Z","shell.execute_reply":"2024-03-19T14:58:10.018169Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Using OPTUNA library for found the best PARAMETERS**","metadata":{}},{"cell_type":"code","source":"import optuna\n\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\n\ndef objective(trial):\n    params = {\n        \"objective\": \"binary\",\n        \"metric\": \"auc\",\n        \"verbosity\": -1,\n        \"boosting_type\": \"gbdt\",\n        \"num_leaves\": trial.suggest_int(\"num_leaves\", 2, 128),\n        \"max_depth\": trial.suggest_int(\"max_depth\", -1, 32),\n        \"learning_rate\": trial.suggest_float(\"learning_rate\", 0.001, 0.3),\n        \"n_estimators\": trial.suggest_int(\"n_estimators\", 100, 1000),\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    }\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    \n    auc = gbm.best_score[\"valid_0\"][\"auc\"]\n    return auc\n\nstudy = optuna.create_study(direction=\"maximize\")\nstudy.optimize(objective, n_trials=10)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T15:09:42.165225Z","iopub.execute_input":"2024-03-19T15:09:42.165660Z","iopub.status.idle":"2024-03-19T15:16:07.637757Z","shell.execute_reply.started":"2024-03-19T15:09:42.165625Z","shell.execute_reply":"2024-03-19T15:16:07.636297Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"[I 2024-03-19 15:11:43,808] Trial 3 finished with value: 0.7569797738585807 and parameters: {'num_leaves': 58, 'max_depth': 23, 'learning_rate': 0.0304712671364661, 'n_estimators': 870, 'feature_fraction': 0.587265944790295, 'bagging_fraction': 0.7316203580788994, 'bagging_freq': 1}. Best is trial 3 with value: 0.7569797738585807.","metadata":{}},{"cell_type":"code","source":"best_params = {\n    \"boosting_type\": \"gbdt\",\n    \"objective\": \"binary\",\n    \"metric\": \"auc\",\n    \"num_leaves\": 58,\n    \"max_depth\": 23,\n    \"learning_rate\": 0.0304712671364661,\n    \"n_estimators\": 780,\n    \"feature_fraction\": 0.587265944790295,\n    \"bagging_fraction\": 0.7316203580788994,\n    \"bagging_freq\": 1,\n    \"verbose\": -1\n}\n##from trial 3 above\n\nlgb_train = lgb.Dataset(X_train, label=y_train)\nlgb_valid = lgb.Dataset(X_valid, label=y_valid, reference=lgb_train)\n\ngbm = lgb.train(\nbest_params,\nlgb_train,\nvalid_sets=lgb_valid,\ncallbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)])","metadata":{"execution":{"iopub.status.busy":"2024-03-19T15:57:42.723510Z","iopub.execute_input":"2024-03-19T15:57:42.724828Z","iopub.status.idle":"2024-03-19T15:59:07.143537Z","shell.execute_reply.started":"2024-03-19T15:57:42.724784Z","shell.execute_reply":"2024-03-19T15:59:07.142325Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Se hace la evaluación con AUC y comparamos con la métrica de estabilidad.","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\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":"2024-03-19T16:06:28.895865Z","iopub.execute_input":"2024-03-19T16:06:28.897293Z","iopub.status.idle":"2024-03-19T16:06:59.858185Z","shell.execute_reply.started":"2024-03-19T16:06:28.897217Z","shell.execute_reply":"2024-03-19T16:06:59.856768Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"auc_values = []\n\ndef record_auc(preds, train_data):\n    labels = train_data.get_label()\n    auc = roc_auc_score(labels, preds)\n    auc_values.append(auc)\n    return 'auc', auc, True\ngbm_1 = lgb.train(\n    best_params,\n    lgb_train,\n    valid_sets=lgb_valid,  \n    callbacks=[lgb.log_evaluation(50), lgb.early_stopping(10)],\n    feval=record_auc\n)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T16:15:46.284782Z","iopub.execute_input":"2024-03-19T16:15:46.285247Z","iopub.status.idle":"2024-03-19T16:18:10.765788Z","shell.execute_reply.started":"2024-03-19T16:15:46.285215Z","shell.execute_reply":"2024-03-19T16:18:10.764421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n**# Guardamos la puntuación AUC de cada iteración**\n\nAsí se puede hacer un gráfico para ver cómo la iteración mejora la ROC (tasa de verdaderos positivos versus tasa de falsos positivos)","metadata":{}},{"cell_type":"code","source":"auc = metrics.roc_auc_score(y_valid, y_pred)\n\nplt.figure(figsize=(6, 4))\nplt.plot(range(1, len(auc_values) + 1), auc_values, color='b', linewidth=2, label='AUC values')\nplt.xlabel('Iteration', fontsize=12)\nplt.ylabel('AUC', fontsize=12)\nplt.title('AUC values over iterations', fontsize=14)\nplt.legend(fontsize=12)\nplt.grid(True)\nplt.xticks(fontsize=10)\nplt.yticks(fontsize=10)\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-03-19T16:21:50.617659Z","iopub.execute_input":"2024-03-19T16:21:50.618729Z","iopub.status.idle":"2024-03-19T16:21:51.169522Z","shell.execute_reply.started":"2024-03-19T16:21:50.618690Z","shell.execute_reply":"2024-03-19T16:21:51.167944Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = gbm.predict(X_valid)\nauc = metrics.roc_auc_score(y_valid, y_pred)\nprint(f\"AUC: {auc}\")\nfpr, tpr, thresholds = metrics.roc_curve(y_valid, y_pred)\nplt.plot(fpr, tpr, label='ROC curve (area = %0.2f)' % auc)\nplt.plot([0, 1], [0, 1], 'k--')\nplt.xlim([0.0, 1.0])\nplt.ylim([0.0, 1.05])\nplt.xlabel('False Positive Rate')\nplt.ylabel('True Positive Rate')\nplt.title('Receiver Operating Characteristic (ROC) Curve')\nplt.legend(loc=\"lower right\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-03-19T16:23:55.506244Z","iopub.execute_input":"2024-03-19T16:23:55.506746Z","iopub.status.idle":"2024-03-19T16:24:02.277674Z","shell.execute_reply.started":"2024-03-19T16:23:55.506708Z","shell.execute_reply":"2024-03-19T16:24:02.276468Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**CALCULANDO LA ESTABILIDAD**","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\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":"2024-03-19T16:25:52.116855Z","iopub.execute_input":"2024-03-19T16:25:52.118019Z","iopub.status.idle":"2024-03-19T16:25:53.246056Z","shell.execute_reply.started":"2024-03-19T16:25:52.117975Z","shell.execute_reply":"2024-03-19T16:25:53.244617Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Submission**","metadata":{}},{"cell_type":"code","source":"#submission \nX_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":"2024-03-19T16:26:03.273084Z","iopub.execute_input":"2024-03-19T16:26:03.273582Z","iopub.status.idle":"2024-03-19T16:26:03.412506Z","shell.execute_reply.started":"2024-03-19T16:26:03.273543Z","shell.execute_reply":"2024-03-19T16:26:03.411032Z"},"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":"2024-03-19T16:26:56.510571Z","iopub.execute_input":"2024-03-19T16:26:56.511041Z","iopub.status.idle":"2024-03-19T16:26:56.525610Z","shell.execute_reply.started":"2024-03-19T16:26:56.511007Z","shell.execute_reply":"2024-03-19T16:26:56.524418Z"},"trusted":true},"execution_count":null,"outputs":[]}]}