{"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_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import os\nimport random\nimport joblib\nimport gc\nimport itertools\nfrom itertools import combinations\nimport scipy as sp\nimport numpy as np\nimport pandas as pd\nfrom tqdm.notebook import tqdm\n\nimport lightgbm as lgb\nfrom sklearn.preprocessing import LabelEncoder\nfrom hyperopt import STATUS_OK, Trials, fmin, hp, tpe\nfrom sklearn.model_selection import StratifiedKFold, train_test_split\n\n\npd.set_option('display.width', 1000)\npd.set_option('display.max_rows', 500)\npd.set_option('display.max_columns', 500)\nimport warnings; warnings.filterwarnings('ignore')","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:03.622820Z","iopub.execute_input":"2022-08-03T02:20:03.623350Z","iopub.status.idle":"2022-08-03T02:20:05.975718Z","shell.execute_reply.started":"2022-08-03T02:20:03.623246Z","shell.execute_reply":"2022-08-03T02:20:05.974606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -qq investpy","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:05.977383Z","iopub.execute_input":"2022-08-03T02:20:05.978457Z","iopub.status.idle":"2022-08-03T02:20:20.856765Z","shell.execute_reply.started":"2022-08-03T02:20:05.978421Z","shell.execute_reply":"2022-08-03T02:20:20.855560Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import investpy","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:20.858309Z","iopub.execute_input":"2022-08-03T02:20:20.858673Z","iopub.status.idle":"2022-08-03T02:20:20.885579Z","shell.execute_reply.started":"2022-08-03T02:20:20.858623Z","shell.execute_reply":"2022-08-03T02:20:20.884765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_difference(data, num_features):\n    df1 = []\n    customer_ids = []\n    \n    for customer_id, df in tqdm(data.groupby(['customer_ID'])):\n        diff_df1 = df[num_features].diff(1).iloc[[-1]].values.astype(np.float16)#float32をfloat16に変えた\n        df1.append(diff_df1)\n        customer_ids.append(customer_id)\n    \n    df1 = np.concatenate(df1, axis = 0)\n    df1 = pd.DataFrame(df1, columns = [col + '_diff1' for col in df[num_features].columns])\n    df1['customer_ID'] = customer_ids\n    return df1","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:20.888704Z","iopub.execute_input":"2022-08-03T02:20:20.889375Z","iopub.status.idle":"2022-08-03T02:20:20.897069Z","shell.execute_reply.started":"2022-08-03T02:20:20.889321Z","shell.execute_reply":"2022-08-03T02:20:20.896064Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# trainデータの前処理","metadata":{}},{"cell_type":"code","source":"def read_preprocess_traindata(train_, train_labels_):    \n    # 特徴量の指定(customerとS_2以外のすべて)\n    features = train_.drop(['customer_ID', 'target', 'S_2'], axis = 1).columns.to_list()\n    # カテゴリ変数の指定\n    cat_features = [\n        \"B_30\",\n        \"B_38\",\n        \"D_114\",\n        \"D_116\",\n        \"D_117\",\n        \"D_120\",\n        \"D_126\",\n        \"D_63\",\n        \"D_64\",\n        \"D_66\",\n        \"D_68\",\n    ]\n    \n    # 数値変数の個数(特徴量の中からカテゴリ変数で指定したものを除く)\n    num_features = [col for col in features if col not in cat_features]\n    \n    # floatデータのメモリ削減(もともとfloat32だったものをfloat16まで減らす)\n    print('Starting reducing memory. (num feature: cast float32 to float16)')\n    float_cols = list(train_.dtypes[train_.dtypes == 'float32'].index)\n    for col in tqdm(float_cols):\n        train_[col] = train_[col].astype(np.float16)\n    \n    # 特徴量の生成\n    print('Starting training feature engineer...')    \n    train_num_agg = train_.groupby(\"customer_ID\")[num_features].agg(['mean', 'std', 'min', 'max', 'last'])\n    train_num_agg.columns = ['_'.join(x) for x in train_num_agg.columns]\n    train_num_agg.reset_index(inplace = True)\n    train_cat_agg = train_.groupby(\"customer_ID\")[cat_features].agg(['count', 'last', 'nunique'])\n    train_cat_agg.columns = ['_'.join(x) for x in train_cat_agg.columns]\n    train_cat_agg.reset_index(inplace = True)\n    \n    print('Starting reducing memory. (new features:cast 64->8)')\n    # floatデータのメモリ削減(もともとfloat32だったものをfloat16まで減らす)\n    cols = list(train_num_agg.dtypes[train_num_agg.dtypes == 'float64'].index)    \n    for col in tqdm(cols):\n        train_num_agg[col] = train_num_agg[col].astype(np.float16)\n        \n    # intデータのメモリ削減(もともとint32だったものをint8まで減らす)\n    cols = list(train_cat_agg.dtypes[train_cat_agg.dtypes == 'int64'].index)    \n    for col in tqdm(cols):\n        train_cat_agg[col] = train_cat_agg[col].astype(np.int8)\n        \n    print('Starting calculate difference...')\n    train_diff = get_difference(train_, num_features)\n    train_ = train_num_agg.merge(train_cat_agg, how = 'inner', on = 'customer_ID').merge(train_diff, how = 'inner', on = 'customer_ID').merge(train_labels_, how = 'inner', on = 'customer_ID')\n    \n    del train_num_agg, train_cat_agg, train_diff\n    gc.collect()\n    \n    # floatデータのメモリ削減(もともとfloat32だったものをfloat16まで減らす)\n    print('Starting reducing memory. (num feature: cast float16 to float32)')\n    float_cols = list(train_.dtypes[train_.dtypes == 'float16'].index)\n    for col in tqdm(float_cols):\n        train_[col] = train_[col].astype(np.float32)\n    \n    print('Saving file ...')\n    train_.to_parquet('train_fe.parquet')\n    print('Finished Saving file.')","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:20.898569Z","iopub.execute_input":"2022-08-03T02:20:20.899335Z","iopub.status.idle":"2022-08-03T02:20:20.916041Z","shell.execute_reply.started":"2022-08-03T02:20:20.899300Z","shell.execute_reply":"2022-08-03T02:20:20.915165Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 相関の高いデータはdropする\nDrop_columns_list = ['D_87',\n                     'D_55','D_61','D_74','D_75','D_77',\n                     'D_104','D_107','D_118','D_119',\n                     'D_131','D_132','D_143','D_141',\n                     'S_7',  'S_24',\n                     'B_11', 'B_13', 'B_15', 'B_18',\n                     'B_20', 'B_23', 'B_33', 'B_37',\n                    ]","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:20.951460Z","iopub.execute_input":"2022-08-03T02:20:20.952270Z","iopub.status.idle":"2022-08-03T02:20:20.959527Z","shell.execute_reply.started":"2022-08-03T02:20:20.952232Z","shell.execute_reply":"2022-08-03T02:20:20.958545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## trainデータの前処理を実行","metadata":{}},{"cell_type":"code","source":"train = pd.read_parquet('../input/amex-parquet/train_data.parquet')\ntrain_labels = pd.read_csv('../input/amex-default-prediction/train_labels.csv')","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:20.962464Z","iopub.execute_input":"2022-08-03T02:20:20.963256Z","iopub.status.idle":"2022-08-03T02:20:54.756086Z","shell.execute_reply.started":"2022-08-03T02:20:20.963210Z","shell.execute_reply":"2022-08-03T02:20:54.754937Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"orig_len = len(train)\ntrain = train.drop(Drop_columns_list, axis=1)","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:54.757370Z","iopub.execute_input":"2022-08-03T02:20:54.757703Z","iopub.status.idle":"2022-08-03T02:20:54.762627Z","shell.execute_reply.started":"2022-08-03T02:20:54.757671Z","shell.execute_reply":"2022-08-03T02:20:54.761608Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ECONOMIC = ['ISM Non-Manufacturing PMI', 'ISM Manufacturing PMI']","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:56.993692Z","iopub.execute_input":"2022-08-03T02:20:56.994043Z","iopub.status.idle":"2022-08-03T02:20:56.998652Z","shell.execute_reply.started":"2022-08-03T02:20:56.994011Z","shell.execute_reply":"2022-08-03T02:20:56.997652Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#train => 2017 to 2018\neconomic_data = investpy.economic_calendar(countries=['united states'], from_date='01/01/2017', to_date='28/03/2018')\neconomic_data = economic_data[economic_data[\"importance\"]==\"high\"]\neconomic_data = economic_data[[\"date\", \"event\", \"actual\"]]\neconomic_data = economic_data[economic_data['event'].str.contains(ECONOMIC[0]) | economic_data['event'].str.contains(ECONOMIC[1])]\neconomic_data['actual'] = economic_data['actual'].astype(np.float32)\neconomic_data = economic_data.reset_index(drop=\"True\")\ndisplay(economic_data.head(5))","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:20:57.000327Z","iopub.execute_input":"2022-08-03T02:20:57.000949Z","iopub.status.idle":"2022-08-03T02:21:15.044485Z","shell.execute_reply.started":"2022-08-03T02:20:57.000910Z","shell.execute_reply":"2022-08-03T02:21:15.043323Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"S_2_unique = train[\"S_2\"].unique()\nS2_to_ISM_list = []\n\nfor date_str in S_2_unique:\n    yyyy = date_str[0:4]\n    mm = date_str[5:7]\n    dd = date_str[8:10]\n    economic_date_df = economic_data[economic_data[\"date\"].str.contains(f\"{mm}/{yyyy}\")]\n    ISM_Manu_value = economic_date_df[economic_date_df[\"event\"].str.contains(\"ISM Manufacturing PMI\")][\"actual\"].values[0]\n    ISM_NonManu_value = economic_date_df[economic_date_df[\"event\"].str.contains(\"ISM Non-Manufacturing PMI\")][\"actual\"].values[0]\n    S2_to_ISM_list.append([date_str, ISM_Manu_value, ISM_NonManu_value])\nS2_to_ISM_df = pd.DataFrame(S2_to_ISM_list, columns=[\"S_2\", \"ISM_Manu\", \"ISM_NonManu\"])\ndisplay(S2_to_ISM_df.head(5))\nS2_to_ISM_df.to_csv(\"S2_to_ISM.csv\", index=False)\ndel economic_data, economic_date_df","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:21:15.458018Z","iopub.execute_input":"2022-08-03T02:21:15.458662Z","iopub.status.idle":"2022-08-03T02:21:16.141435Z","shell.execute_reply.started":"2022-08-03T02:21:15.458600Z","shell.execute_reply":"2022-08-03T02:21:16.140355Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = pd.merge(train, S2_to_ISM_df, on=\"S_2\", how=\"left\")\nprint(orig_len, len(train))","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:21:16.149365Z","iopub.execute_input":"2022-08-03T02:21:16.149809Z","iopub.status.idle":"2022-08-03T02:21:33.381958Z","shell.execute_reply.started":"2022-08-03T02:21:16.149778Z","shell.execute_reply":"2022-08-03T02:21:33.380703Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[[\"S_2\",\"ISM_Manu\",\"ISM_NonManu\"]].head(5)","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:21:33.383612Z","iopub.execute_input":"2022-08-03T02:21:33.383962Z","iopub.status.idle":"2022-08-03T02:21:37.205816Z","shell.execute_reply.started":"2022-08-03T02:21:33.383932Z","shell.execute_reply":"2022-08-03T02:21:37.204779Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"read_preprocess_traindata(train, train_labels)\ndel train, train_labels","metadata":{"execution":{"iopub.status.busy":"2022-08-03T02:21:37.207183Z","iopub.execute_input":"2022-08-03T02:21:37.207742Z","iopub.status.idle":"2022-08-03T02:22:11.612775Z","shell.execute_reply.started":"2022-08-03T02:21:37.207710Z","shell.execute_reply":"2022-08-03T02:22:11.611231Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}