机器学习python评估算法

from  pandas import read_csv
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import LeaveOneOut
from sklearn.model_selection import ShuffleSplit
'''K折交叉验证是用来评估机器学习算法的黄金准则
    分离训练数据集和苹果数据集，因为执行效率高，通常用于算法执行效率低，或者有大量数据的时候
    另外两种方法用来平衡算法、训练的速度和数据集的大小'''
filename = 'pima_data.csv'
names = ['preg','plas','pres','skin','test','mass','pedi','age','class']
data = read_csv(filename,names = names)
array = data.values
X = array[:,0:8]
Y = array[:,8]
#分类训练数据集和评估数据集
test_size = 0.33 #设置评估集的比例
seed = 4
#设置数据随机的粒度，当评估两个不同的算法时，可让seed相同，这样划分的集合是相同的
X_train,X_test,Y_traing,Y_test = train_test_split(X,Y,test_size=test_size,random_state=seed)
model = LogisticRegression()
model.fit(X_train,Y_traing)
result = model.score(X_test,Y_test)
# print("算法评估结果：%.3f%%" %(result * 100))

#K折交叉验证分离
'''将原始数据分为K组，将每个子集数据分别做一次验证集，其余的K-1组子集，作为训练集，K通常取3,5,10'''
num_flods = 10
seed = 7
model = LogisticRegression()
kfold = KFold(n_splits=num_flods,random_state=seed)
result = cross_val_score(model,X,Y,cv=kfold)
# print("算法评估结果：%.3f%% (%.3f%%)" %(result.mean() * 100,result.std() * 100) )  #评估的得分及标准方差

#弃一交叉验证分离
'''原始数据为N个样本，每个样本作为验证集，其余的N-1个样本作为训练集'''
loocv = LeaveOneOut()
model = LogisticRegression()
result = cross_val_score(model,X,Y,cv=loocv)
# print("算法评估结果：%.3f%% (%.3f%%)" %(result.mean() * 100,result.std() * 100) )  #评估的得分及标准方差

#重复随机分离评估数据集与训练数据集
'''将K折交叉验证重复多次'''
n_splits = 10
test_size = 0.33
seed = 7
kfold = ShuffleSplit(n_splits=n_splits,test_size=test_size,random_state=seed)
model = LogisticRegression()
result = cross_val_score(model,X,Y,cv=kfold)
print("算法评估结果：%.3f%% (%.3f%%)" %(result.mean() * 100,result.std() * 100) )  #评估的得分及标准方差