机器学习基础自学四（混沌矩阵）

from pandas import read_csv
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix#混沌矩阵
from sklearn.model_selection import train_test_split

# 导入数据
filename =  'D:\example\MachineLearning-master\pima_data.csv'
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
# 将数据分为输入数据和输出结果
array = data.values
X = array[:, 0:8]
Y = array[:, 8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds, random_state=seed)
model = LogisticRegression()

scoring = 'neg_log_loss'#对数损失函数，值越小，模型越好
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print('neg_log_loss %.3f (%.3f)' % (result.mean(), result.std()))


scoring = 'roc_auc'#AUC图，值越大，诊断准确性越高
result = cross_val_score(model, X, Y, cv=kfold, scoring=scoring)
print('AUC %.3f (%.3f)' % (result.mean(), result.std()))