__author__ = 'Aaron Yang' __email__ = '*****@*****.**' __date__ = '11/6/2019 8:52 AM' import numpy as np from sklearn.exceptions import ConvergenceWarning from sklearn.preprocessing import LabelEncoder, MinMaxScaler from sklearn.metrics import precision_recall_fscore_support as score from ay_hw_6._global import ROOT_PATH, WDBC_FILE_PATH, SPLASH, M from ay_hw_6.util_data import load_data, train_test_split_by_class_and_ratio if __name__ == "__main__": simplefilter(action='ignore', category=ConvergenceWarning) X_data, y_data = load_data(ROOT_PATH + SPLASH + WDBC_FILE_PATH) X_data = MinMaxScaler().fit(X_data).transform(X_data) labelEncoder = LabelEncoder().fit(['B', 'M']) y_data = labelEncoder.transform(y_data) accuracyList = list() precisionList = list() recallRateList = list() f_scoreList = list() aucList = list() y_test_predict = None y_test_true = None for i in tqdm(range(2)): X_train, X_test, y_train, y_test = train_test_split_by_class_and_ratio(X_data, y_data, test_size=0.2, random_state=i, pos_class=0, neg_class=1)
# __author__ = 'Aaron Yang' __email__ = '*****@*****.**' __date__ = '11/5/2019 11:57 AM' from ay_hw_6._global import ROOT_PATH, BANK_NOTE_FILE_PATH, SPLASH from ay_hw_6.util_data import load_data, train_test_split_by_exact_number if __name__ == "__main__": X_data, y_data = load_data(ROOT_PATH + SPLASH + BANK_NOTE_FILE_PATH, X_startIndex=0, X_endIndex=4, y_index=-1) X_train, X_test, y_train, y_test = train_test_split_by_exact_number( X_data, y_data, test_size=472, random_state=2333) print("-----------\"Row Data\"-------------") print("the shape of X_data is: ", X_data.shape) print("the shape of y_data is: ", y_data.shape) print("-----------\"After Split\"-------------") print("the shape of X_train is: ", X_train.shape) print("the shape of X_test is: ", X_test.shape) print("the shape of y_train is: ", y_train.shape) print("the shape of y_test is: ", y_test.shape)