{"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"},{"sourceId":7879565,"sourceType":"datasetVersion","datasetId":4624594}],"dockerImageVersionId":30664,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-19T05:40:19.203973Z","iopub.execute_input":"2024-03-19T05:40:19.204489Z","iopub.status.idle":"2024-03-19T05:40:19.279156Z","shell.execute_reply.started":"2024-03-19T05:40:19.204424Z","shell.execute_reply":"2024-03-19T05:40:19.277082Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Importando Librerías a utilizar ( Empezando con el Starter Notebook )","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-risk-model-stability/LAB001/\"","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:40:25.673426Z","iopub.execute_input":"2024-03-19T05:40:25.673849Z","iopub.status.idle":"2024-03-19T05:40:25.681461Z","shell.execute_reply.started":"2024-03-19T05:40:25.673817Z","shell.execute_reply":"2024-03-19T05:40:25.679856Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Rutinas Utilizadas ( Suministradas en el Starter Notebook )","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":"2024-03-19T05:40:29.905948Z","iopub.execute_input":"2024-03-19T05:40:29.908379Z","iopub.status.idle":"2024-03-19T05:40:29.922881Z","shell.execute_reply.started":"2024-03-19T05:40:29.908325Z","shell.execute_reply":"2024-03-19T05:40:29.921144Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Importación de Datos de TRAIN y TEST ( Empezaremos tomando la misma data del Starter Notebook )","metadata":{}},{"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":"2024-03-19T05:40:34.249160Z","iopub.execute_input":"2024-03-19T05:40:34.249622Z","iopub.status.idle":"2024-03-19T05:40:54.544516Z","shell.execute_reply.started":"2024-03-19T05:40:34.249585Z","shell.execute_reply":"2024-03-19T05:40:54.543153Z"},"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":"2024-03-19T05:40:57.763562Z","iopub.execute_input":"2024-03-19T05:40:57.764474Z","iopub.status.idle":"2024-03-19T05:40:57.842797Z","shell.execute_reply.started":"2024-03-19T05:40:57.764398Z","shell.execute_reply":"2024-03-19T05:40:57.841013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Enginnering ( Tomadas del Starter Notebook )","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":"2024-03-19T05:41:02.580097Z","iopub.execute_input":"2024-03-19T05:41:02.582019Z","iopub.status.idle":"2024-03-19T05:41:11.985063Z","shell.execute_reply.started":"2024-03-19T05:41:02.581955Z","shell.execute_reply":"2024-03-19T05:41:11.983329Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# OBSERVACION 01. - Hasta el momento tomamos como punto de partida lo propuesto en el Starter Notebook, para realizar un análisis exploratorio de variables usadas en el modelo base y aprovechar oportunidades de mejora en esta data propuesta","metadata":{}},{"cell_type":"markdown","source":"# Análisis Exploratorio de Datos","metadata":{}},{"cell_type":"code","source":"df_pandas = data.to_pandas()\ndf_pandas.isna().sum()/df_pandas.shape[0]*100","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:41:17.543096Z","iopub.execute_input":"2024-03-19T05:41:17.545337Z","iopub.status.idle":"2024-03-19T05:41:21.659049Z","shell.execute_reply.started":"2024-03-19T05:41:17.545276Z","shell.execute_reply":"2024-03-19T05:41:21.657620Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# CONCLUSION 01. - Se advierte que las variables 'lastotherinc_902A' y 'lastotherlnsexpense_631A' tienen demasiados valores nulos, llegando incluso a un 99%, tal que introducen ruido innecesario previo al entrenamiento de datos. Se concluye eliminar estos registros","metadata":{}},{"cell_type":"code","source":"data = data.drop(['lastotherinc_902A', 'lastotherlnsexpense_631A'])\ndata.shape","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:41:25.274452Z","iopub.execute_input":"2024-03-19T05:41:25.274883Z","iopub.status.idle":"2024-03-19T05:41:25.285202Z","shell.execute_reply.started":"2024-03-19T05:41:25.274851Z","shell.execute_reply":"2024-03-19T05:41:25.283726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"# Construyendo grupos de datos de Entrenamiento, Validación y Pruebas\n","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\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":"2024-03-19T05:41:29.730301Z","iopub.execute_input":"2024-03-19T05:41:29.730839Z","iopub.status.idle":"2024-03-19T05:41:29.754210Z","shell.execute_reply.started":"2024-03-19T05:41:29.730794Z","shell.execute_reply":"2024-03-19T05:41:29.752707Z"},"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":"2024-03-19T05:41:34.050389Z","iopub.execute_input":"2024-03-19T05:41:34.051224Z","iopub.status.idle":"2024-03-19T05:41:41.399160Z","shell.execute_reply.started":"2024-03-19T05:41:34.051165Z","shell.execute_reply":"2024-03-19T05:41:41.398122Z"},"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":"2024-03-19T05:41:44.514228Z","iopub.execute_input":"2024-03-19T05:41:44.514660Z","iopub.status.idle":"2024-03-19T05:41:44.522180Z","shell.execute_reply.started":"2024-03-19T05:41:44.514625Z","shell.execute_reply":"2024-03-19T05:41:44.520397Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# OPCION 01. - Usando XGBoost","metadata":{}},{"cell_type":"code","source":"import xgboost as xgb","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:41:47.506140Z","iopub.execute_input":"2024-03-19T05:41:47.507583Z","iopub.status.idle":"2024-03-19T05:41:47.513801Z","shell.execute_reply.started":"2024-03-19T05:41:47.507525Z","shell.execute_reply":"2024-03-19T05:41:47.512487Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dtrain = xgb.DMatrix(data=X_train, label=y_train, enable_categorical=True)\ndvalid = xgb.DMatrix(data=X_valid, label=y_valid, enable_categorical=True)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:41:49.952244Z","iopub.execute_input":"2024-03-19T05:41:49.954985Z","iopub.status.idle":"2024-03-19T05:41:51.478153Z","shell.execute_reply.started":"2024-03-19T05:41:49.954921Z","shell.execute_reply":"2024-03-19T05:41:51.476924Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"parameters = {'objective': 'binary:logistic',\n              'learning_rate': 0.05,\n              'max_depth': 4,\n              'min_child_weight': 0.5,\n              'reg_alpha': 1,\n              'reg_lambda': 1,\n              'eval_metric': 'auc'}\n\nwatch_list  = [(dtrain,'train'),(dvalid,'valid')]\n\nxgb_fit = xgb.train(params = parameters, dtrain = dtrain, evals = watch_list,\n                    num_boost_round = 500, early_stopping_rounds=50, verbose_eval=1)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:41:54.032995Z","iopub.execute_input":"2024-03-19T05:41:54.033498Z","iopub.status.idle":"2024-03-19T05:43:45.201875Z","shell.execute_reply.started":"2024-03-19T05:41:54.033460Z","shell.execute_reply":"2024-03-19T05:43:45.200775Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"frame = {'Gain':  xgb_fit.get_score(importance_type='gain'), # ganancia en prediccion por la variable\n        'Cover':  xgb_fit.get_score(importance_type='cover'),# profundidad del arbol\n        'Weight': xgb_fit.get_score(importance_type='weight')} # en cuantos arboles sale la variable\n\nresult = pd.DataFrame(frame)\nresult","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:43:50.835427Z","iopub.execute_input":"2024-03-19T05:43:50.835900Z","iopub.status.idle":"2024-03-19T05:43:50.863586Z","shell.execute_reply.started":"2024-03-19T05:43:50.835864Z","shell.execute_reply":"2024-03-19T05:43:50.862319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Examinando los Mejores Hiper-parámetros para el modelo usado","metadata":{}},{"cell_type":"code","source":"#from sklearn.model_selection import GridSearchCV","metadata":{"execution":{"iopub.status.busy":"2024-03-18T22:31:29.747470Z","iopub.execute_input":"2024-03-18T22:31:29.747970Z","iopub.status.idle":"2024-03-18T22:31:29.754720Z","shell.execute_reply.started":"2024-03-18T22:31:29.747938Z","shell.execute_reply":"2024-03-18T22:31:29.753244Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#param_grid = {\n#    'objective': ['binary:logistic'],\n#    'learning_rate': [0.01, 0.025, 0.05],\n#    'max_depth': [3, 4, 5],\n#    'min_child_weight': [0.01, 0.25, 0.5],\n#    'reg_alpha': [1],\n#    'reg_lambda': [1],\n#    'eval_metric': ['auc'],\n#    'n_estimators': [100, 200, 300],\n#    'num_boost_round': [500],\n#    'early_stopping_rounds': [50],\n#    'enable_categorical': [True]\n#}","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#param_grid = {\n#    'objective': ['binary:logistic'],\n#    'learning_rate': [0.01, 0.05],\n#    'max_depth': [4],\n#    'min_child_weight': [0.01, 0.5],\n#    'reg_alpha': [1],\n#    'reg_lambda': [1],\n#    'eval_metric': ['auc'],\n#    'num_boost_round': [500],\n#    'early_stopping_rounds': [50],\n#    'enable_categorical': [True]\n#}","metadata":{"execution":{"iopub.status.busy":"2024-03-18T22:31:36.353582Z","iopub.execute_input":"2024-03-18T22:31:36.354829Z","iopub.status.idle":"2024-03-18T22:31:36.361803Z","shell.execute_reply.started":"2024-03-18T22:31:36.354779Z","shell.execute_reply":"2024-03-18T22:31:36.360552Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Inicializar el estimador XGBoost\n#xgb_model = xgb.XGBClassifier()\n# Inicializar el objeto GridSearchCV \n#xgb_grid_search = GridSearchCV(estimator=xgb_model, param_grid=param_grid, cv=5, verbose=1, n_jobs=-1)","metadata":{"execution":{"iopub.status.busy":"2024-03-18T22:31:40.220371Z","iopub.execute_input":"2024-03-18T22:31:40.221187Z","iopub.status.idle":"2024-03-18T22:31:40.228219Z","shell.execute_reply.started":"2024-03-18T22:31:40.221140Z","shell.execute_reply":"2024-03-18T22:31:40.226552Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Realizar la búsqueda de hiperparámetros\n#xgb_grid_search.fit(X_train, y_train, eval_set=[(X_valid, y_valid)])","metadata":{"execution":{"iopub.status.busy":"2024-03-18T22:31:45.844423Z","iopub.execute_input":"2024-03-18T22:31:45.844895Z","iopub.status.idle":"2024-03-19T01:35:53.034124Z","shell.execute_reply.started":"2024-03-18T22:31:45.844862Z","shell.execute_reply":"2024-03-19T01:35:53.030799Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#xgb_grid_search","metadata":{"execution":{"iopub.status.busy":"2024-03-19T01:59:37.419045Z","iopub.execute_input":"2024-03-19T01:59:37.419612Z","iopub.status.idle":"2024-03-19T01:59:37.440861Z","shell.execute_reply.started":"2024-03-19T01:59:37.419570Z","shell.execute_reply":"2024-03-19T01:59:37.439398Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#xgb_grid_search.cv_results_","metadata":{"execution":{"iopub.status.busy":"2024-03-19T01:59:53.466073Z","iopub.execute_input":"2024-03-19T01:59:53.466515Z","iopub.status.idle":"2024-03-19T01:59:53.484424Z","shell.execute_reply.started":"2024-03-19T01:59:53.466482Z","shell.execute_reply":"2024-03-19T01:59:53.483411Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Volviendo a calcular la métrica con los hiper-parámetros obtenidos\nNo se pudo tomar los valores de la variable best_resutls de xgb_grid_search. Cuando se retomó el Notebook, había cerrado la sesión. Se está cerrando la submission con el valor original calculado","metadata":{}},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"code","source":"#parameters = {'objective': 'binary:logistic',\n#              'learning_rate': 0.05,\n#              'max_depth': 4,\n#              'min_child_weight': 0.5,\n#              'reg_alpha': 1,\n#              'reg_lambda': 1,\n#              'eval_metric': 'auc'}\n\n#watch_list  = [(dtrain,'train'),(dvalid,'valid')]\n\n#xgb_fit = xgb.train(params = parameters, dtrain = dtrain, evals = watch_list,\n#num_boost_round = 500, early_stopping_rounds=50, verbose_eval=1)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Retomando valores calculados originalmente dado que no se pudo obtener los hiper-parámetros","metadata":{}},{"cell_type":"code","source":"dtrain = xgb.DMatrix(data=X_train, label=y_train, enable_categorical=True)\ndvalid = xgb.DMatrix(data=X_valid, label=y_valid, enable_categorical=True)\n\nparameters = {'objective': 'binary:logistic',\n              'learning_rate': 0.05,\n              'max_depth': 4,\n              'min_child_weight': 0.5,\n              'reg_alpha': 1,\n              'reg_lambda': 1,\n              'eval_metric': 'auc'}\n\nwatch_list  = [(dtrain,'train'),(dvalid,'valid')]\n\nxgb_fit = xgb.train(params = parameters, dtrain = dtrain, evals = watch_list,\n                    num_boost_round = 500, early_stopping_rounds=50, verbose_eval=1)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:44:25.124242Z","iopub.execute_input":"2024-03-19T05:44:25.124828Z","iopub.status.idle":"2024-03-19T05:46:26.095779Z","shell.execute_reply.started":"2024-03-19T05:44:25.124781Z","shell.execute_reply":"2024-03-19T05:46:26.094210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Evaluando el Modelo con data de Test","metadata":{}},{"cell_type":"code","source":"for base, X in [(base_train, X_train), (base_valid, X_valid), (base_test, X_test)]:\n    datamatrix = xgb.DMatrix(data=X, enable_categorical=True)\n    y_pred = xgb_fit.predict(datamatrix)\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":"2024-03-19T05:46:30.853007Z","iopub.execute_input":"2024-03-19T05:46:30.853437Z","iopub.status.idle":"2024-03-19T05:46:44.857509Z","shell.execute_reply.started":"2024-03-19T05:46:30.853403Z","shell.execute_reply":"2024-03-19T05:46:44.856188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def gini_stability(base, w_fallingrate=88.0, w_resstd=-0.5):\n    gini_in_time = base.loc[:, [\"WEEK_NUM\", \"target\", \"score\"]]\\\n        .sort_values(\"WEEK_NUM\")\\\n        .groupby(\"WEEK_NUM\")[[\"target\", \"score\"]]\\\n        .apply(lambda x: 2*roc_auc_score(x[\"target\"], x[\"score\"])-1).tolist()\n    \n    x = np.arange(len(gini_in_time))\n    y = gini_in_time\n    a, b = np.polyfit(x, y, 1)\n    y_hat = a*x + b\n    residuals = y - y_hat\n    res_std = np.std(residuals)\n    avg_gini = np.mean(gini_in_time)\n    return avg_gini + w_fallingrate * min(0, a) + w_resstd * res_std\n\nstability_score_train = gini_stability(base_train)\nstability_score_valid = gini_stability(base_valid)\nstability_score_test = gini_stability(base_test)\n\nprint(f'The stability score on the train set is: {stability_score_train}') \nprint(f'The stability score on the valid set is: {stability_score_valid}') \nprint(f'The stability score on the test set is: {stability_score_test}')  ","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:46:50.964738Z","iopub.execute_input":"2024-03-19T05:46:50.965197Z","iopub.status.idle":"2024-03-19T05:46:52.300488Z","shell.execute_reply.started":"2024-03-19T05:46:50.965163Z","shell.execute_reply":"2024-03-19T05:46:52.299187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Generando Submission","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\ndatamatrix = xgb.DMatrix(data=X_submission, enable_categorical=True)\ny_submission_pred = xgb_fit.predict(datamatrix)","metadata":{"execution":{"iopub.status.busy":"2024-03-19T05:46:58.716870Z","iopub.execute_input":"2024-03-19T05:46:58.717285Z","iopub.status.idle":"2024-03-19T05:46:58.861759Z","shell.execute_reply.started":"2024-03-19T05:46:58.717253Z","shell.execute_reply":"2024-03-19T05:46:58.860486Z"},"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":"2024-03-19T05:47:03.219504Z","iopub.execute_input":"2024-03-19T05:47:03.220038Z","iopub.status.idle":"2024-03-19T05:47:03.232894Z","shell.execute_reply.started":"2024-03-19T05:47:03.219997Z","shell.execute_reply":"2024-03-19T05:47:03.231379Z"},"trusted":true},"execution_count":null,"outputs":[]}]}