{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"## Import Data and libraries\n\nimport pandas as pd\nfrom lightgbm import LGBMClassifier\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.model_selection import KFold\nimport re\nimport numpy as np\n\nrcc_train = pd.read_csv(\"/kaggle/input/interbank20/rcc_train.csv\")\nse_train = pd.read_csv(\"/kaggle/input/interbank20/se_train.csv\", index_col=\"key_value\")\nsunat_train = pd.read_csv(\"/kaggle/input/interbank20/sunat_train.csv\")\ny_train = pd.read_csv(\"/kaggle/input/interbank20/y_train.csv\", index_col=\"key_value\").target\n\nrcc_test= pd.read_csv(\"/kaggle/input/interbank20/rcc_test.csv\")\nse_test= pd.read_csv(\"/kaggle/input/interbank20/se_test.csv\", index_col=\"key_value\")\nsunat_test= pd.read_csv(\"/kaggle/input/interbank20/sunat_test.csv\")\n\n### Funciones para optimizar la utilizacion de memoria\ndef optimize_floats(df):\n    if isinstance(df, pd.DataFrame):\n        floats = df.select_dtypes(include=['float64']).columns.tolist()\n        df[floats] = df[floats].apply(pd.to_numeric, downcast='float')\n    elif isinstance(df, pd.Series):\n        if df.dtype == \"float64\":\n            df = df.apply(pd.to_numeric, downcast='float')\n    else:\n        pass\n    return df\n\n\ndef optimize_ints(df):\n    if isinstance(df, pd.DataFrame):\n        ints = df.select_dtypes(include=['int64']).columns.tolist()\n        df[ints] = df[ints].apply(pd.to_numeric, downcast='integer')\n    elif isinstance(df, pd.Series):\n        if df.dtype == \"int64\":\n            df = df.apply(pd.to_numeric, downcast='integer')\n    else: \n        pass\n    return df\n\n\ndef optimize(df):\n    df = optimize_floats(df)\n    df = optimize_ints(df)\n    return df\n\n\ndef df_colum_types(df):\n    with pd.option_context('display.max_rows', None, 'display.max_columns', None):\n        print(df.dtypes)\n\n\ndef df_get_name(df):\n    name =[x for x in globals() if globals()[x] is df][0]\n    return name\n\ndef mem_optimize(list):\n    for df in list:\n        if isinstance(df, pd.DataFrame):\n            print(f\"Memoria de {df_get_name(df)} antes: {df.memory_usage().sum() / (1024**2)} MBytes\")\n            df = optimize(df) \n            print(f\"Memoria de {df_get_name(df)} despues: {df.memory_usage().sum() / (1024**2)} MBytes\")\n        elif isinstance(df, pd.Series):\n            print(f\"Memoria de {df_get_name(df)} antes: {df.memory_usage() / (1024**2)} MBytes\")\n            f = optimize(df) \n            print(f\"Memoria de {df_get_name(df)} despues: {df.memory_usage() / (1024**2)} MBytes\")\n        else:\n            pass\n\ndef mem_size(lista):\n    for df in lista:\n        if isinstance(df, pd.DataFrame):\n            print(f\"Memoria de {df_get_name(df)}: {df.memory_usage().sum() / (1024**2)} MBytes\")            \n        elif isinstance(df, pd.Series):\n            print(f\"Memoria de {df_get_name(df)}: {df.memory_usage() / (1024**2)} MBytes\")\n        else:\n            pass\n\nlista_df = [rcc_test, rcc_train, se_test, se_train, sunat_test, sunat_train, y_train]\nmem_optimize(lista_df)\n\n##  [Pre-Procesamiento]\n\n\n### Drop Duplicates\n\nrcc_train = rcc_train.drop_duplicates()\nse_train = se_train.drop_duplicates()\nsunat_train = sunat_train.drop_duplicates()\n\nrcc_test = rcc_test.drop_duplicates()\nse_test= se_test.drop_duplicates()\nsunat_test= sunat_test.drop_duplicates()\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"### Export cleaned data_v1\n\n\nrcc_train.to_csv('cleaned_rcc_train.csv', index=False)\nse_train.to_csv('cleaned_se_train.csv', index=False)\nsunat_train.to_csv('cleaned_sunat_train.csv', index=False)\n\nrcc_test.to_csv('cleaned_rcc_test.csv', index=False)\nse_test.to_csv('cleaned_se_test.csv', index=False)\nsunat_test.to_csv('cleaned_sunat_test.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}