{"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":"## Cargando los datos","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":{"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":{"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":{"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Feature engineering\nUnión de tablas a través de case_id con la librería Polars","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":{"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids = data[\"case_id\"].unique().shuffle(seed=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids_train, case_ids_test = train_test_split(case_ids, train_size=0.6, random_state=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"case_ids_valid, case_ids_test = train_test_split(case_ids_test, train_size=0.5, random_state=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols_pred = []\nfor col in data.columns:\n    if col[-1].isupper() and col[:-1].islower():\n        cols_pred.append(col)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols_pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Función para transformar a df de pandas\ndef from_polars_to_pandas(case_ids: pl.DataFrame) -> pl.DataFrame:\n    return (\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[[\"case_id\", \"WEEK_NUM\", \"target\"]].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[cols_pred].to_pandas(),\n        data.filter(pl.col(\"case_id\").is_in(case_ids))[\"target\"].to_pandas()\n    )","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"base_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":{"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Métodos correctivos de datos y tratamiento de nulos","metadata":{}},{"cell_type":"code","source":"# Graficamente analizamos los nulos\nimport missingno as msno\nmsno.matrix(X_train)\n# observamos que hay bastantes valores nulos en varias columnas","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Graficamos las variables numéricas\ncolumnas_numericas = X_train.select_dtypes(include=['number'])\nfor columna in columnas_numericas.columns:\n    plt.hist(X_train[columna])  # Por ejemplo, un histograma para cada columna numérica\n    plt.title(columna)\n    plt.show()\n\nfor data in [X_train, X_valid, X_test]:\n    data.drop(['avginstallast24m_3658937A', 'downpmt_116A', 'maxannuity_159A', 'totalsettled_863A'], axis = 1, inplace = True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Luego de analizar las gráficas y la información de los nulos eliminamos algunas variables redundantes\nfor data in [X_train, X_valid, X_test]:\n    data.drop(['avglnamtstart24m_4525187A', 'avglnamtstart24m_4525187A', 'lastotherinc_902A', \n               'lastotherlnsexpense_631A', 'maxannuity_4075009A', 'pmtaverage_4955615A', \n               'pmtaverage_4527227A', 'pmtaverage_3A'], axis = 1, inplace = True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Para el caso de las variables numéricas que no tienen demasiados nulos \n# Se reemplaza cada nulo por el valor medio\nfor data in [X_train, X_valid, X_test]:\n    # Obtener las columnas numéricas\n    numeric_columns = data.select_dtypes(include=['number']).columns\n\n    # Reemplazar los valores nulos en las columnas numéricas con la media\n    for column in numeric_columns:\n        data[column].fillna(data[column].mean(), inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# De la misma manera se analizan las variables categóricas\nfor data in [X_train, X_valid, X_test]:\n    # Obtener las columnas categóricas\n    categorical_columns = data.select_dtypes(include=['category']).columns\n\n    # Convertir las columnas categóricas de tipo category a object\n    for column in categorical_columns:\n        data[column] = data[column].astype('object')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Se reemplazan los datos nulos con una nueva categoría \"Desconocido\"\nfor data in [X_train, X_valid, X_test]:\n    # Obtener las columnas de tipo objeto\n    object_columns = data.select_dtypes(include=['object']).columns\n\n    # Reemplazar los valores nulos en las columnas de tipo objeto con un valor específico (por ejemplo, \"Desconocido\")\n    for column in object_columns:\n        data[column].fillna(\"Desconocido\", inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.hist(y_train)\nplt.title(\"target\")\nplt.show()\n# Observamos que la variable dependiente esta muy desbalanceada ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Escalamiento","metadata":{}},{"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\n\n# Obtener las características numéricas\nnumeric_columns_train = X_train.select_dtypes(include=['number']).columns\nnumeric_columns_valid = X_valid.select_dtypes(include=['number']).columns\nnumeric_columns_test = X_test.select_dtypes(include=['number']).columns\n\n# Inicializar el objeto StandardScaler\nscaler = StandardScaler()\n\n# Estandarizar las características numéricas en X_train\nX_train_scaled = X_train.copy()\nX_train_scaled[numeric_columns_train] = scaler.fit_transform(X_train[numeric_columns_train])\n\n# Estandarizar las características numéricas en X_valid\nX_valid_scaled = X_valid.copy()\nX_valid_scaled[numeric_columns_valid] = scaler.transform(X_valid[numeric_columns_valid])\n\n# Estandarizar las características numéricas en X_test\nX_test_scaled = X_test.copy()\nX_test_scaled[numeric_columns_test] = scaler.transform(X_test[numeric_columns_test])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# **Training CatBoost**\nSe emplea el modelo CatBoost para manejar más facilmente las variables categóricas","metadata":{}},{"cell_type":"code","source":"categorical_columns = X_train.select_dtypes(include=['object']).columns.tolist()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from catboost import CatBoostClassifier, Pool\n\n# Crear el conjunto de datos Pool para el entrenamiento\ntrain_pool = Pool(data=X_train, label=y_train, cat_features=categorical_columns)\n\n# Crear el conjunto de datos Pool para la validación\nvalid_pool = Pool(data=X_valid, label=y_valid, cat_features=categorical_columns)\n\n# Inicializar y entrenar el modelo CatBoost\nmodel = CatBoostClassifier(iterations=1000, learning_rate=0.05, depth=3)\nmodel.fit(train_pool, eval_set=valid_pool, verbose=False)\n\n# Evaluar el rendimiento del modelo en el conjunto de validación\neval_results = model.eval_metrics(valid_pool, metrics=['Accuracy'])\naccuracy = eval_results['Accuracy'][0]\nprint(f\"Precisión en el conjunto de validación: {accuracy:.4f}\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"categorical_columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import roc_auc_score\n\n# Crear una lista para almacenar los resultados de las predicciones en los tres conjuntos de datos\npredictions = []\n\n# Hacer predicciones en los conjuntos de datos de entrenamiento, validación y prueba\nfor base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    # Hacer predicciones con el modelo CatBoost\n    y_pred = (model.predict_proba(X)[:, 1] >= 0.5).astype(int)  # Seleccionar las probabilidades de clase positiva\n    base[\"score\"] = y_pred  # Añadir las predicciones al DataFrame base\n    predictions.append(y_pred)  # Almacenar las predicciones\n\n# Calcular y mostrar el AUC para cada conjunto de datos\nprint(f'The AUC score on the train set is: {roc_auc_score(base_train[\"target\"], predictions[0])}') \nprint(f'The AUC score on the valid set is: {roc_auc_score(base_valid[\"target\"], predictions[1])}') \nprint(f'The AUC score on the test set is: {roc_auc_score(base_test[\"target\"], predictions[2])}') ","metadata":{"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generación de archivo ","metadata":{}},{"cell_type":"code","source":"X_submission = data_submission[cols_pred].to_pandas()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission = convert_strings(X_submission)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"numeric_columns = X_submission.select_dtypes(include=['number']).columns\n\n    # Reemplazar los valores nulos en las columnas numéricas con la media\nfor column in numeric_columns:\n    X_submission[column].fillna(X_submission[column].mean(), inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"numeric_columns = X_submission.select_dtypes(include=['number']).columns\n\n    # Reemplazar los valores nulos en las columnas numéricas con la media\nfor column in numeric_columns:\n    X_submission[column].fillna(0, inplace=True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"float_columns = X_submission.select_dtypes(include=['float']).columns\n\n# Convertir las columnas seleccionadas de tipo float a tipo int\nX_submission[float_columns] = X_submission[float_columns].astype(int)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission.drop(['avglnamtstart24m_4525187A', 'avglnamtstart24m_4525187A', 'lastotherinc_902A', \n               'lastotherlnsexpense_631A', 'maxannuity_4075009A', 'pmtaverage_4955615A', \n               'pmtaverage_4527227A', 'pmtaverage_3A'], axis = 1, inplace = True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission.drop(['avginstallast24m_3658937A'], axis = 1, inplace = True)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission[categorical_columns] = X_submission[categorical_columns].astype('object')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cols_train = set(X_train.columns)\ncols_submission = set(X_submission.columns)\nextra_columns = cols_submission - cols_train\nX_submission = X_submission.drop(columns=extra_columns)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"extra_columns","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_submission.info()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Realizar las predicciones con CatBoost en el conjunto de datos de presentación\ny_submission_pred = (model.predict_proba(X_submission)[:, 1] >= 0.5).astype(int)","metadata":{"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":{"trusted":true},"execution_count":null,"outputs":[]}]}