Python中学习器流水线Pipeline

'''
sklean提供的pipeline来将多个学习器组成流水线，通常流水线的形式为：
将数据标准化的学习器---特征提取的学习器---执行预测的学习器

除了最后一个学习器之外，前面的所有学习器必须提供transform方法，该方法用于数据转化（例如：
       归一化，正则化，以及特征提取
'''

from sklearn.datasets import load_digits
from sklearn import cross_validation
from sklearn.svm import LinearSVC
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline

def test_Pipeline(data):
    x_train,x_test,y_train,y_test=data
    steps=[('Linear_SVM',LinearSVC(C=1,penalty='l1',dual=False)),
           ('LogisticRegression',LogisticRegression(C=1))]
    pipeline=Pipeline(steps)
    pipeline.fit(x_train,y_train)
    print('name steps:',pipeline.named_steps)
    print('Pipeline Score:',pipeline.score(x_test,y_test))
    
if __name__=='__main__':
    data=load_digits()
    X=data.data
    y=data.target
    test_Pipeline(cross_validation.train_test_split(X,y,test_size=0.25,
                                        random_state=0,stratify=y))
    
    
    
from sklearn.datasets import load_digits
from sklearn import cross_validation
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.decomposition import PCA
'''
工作流程：先进行pca降为，然后使用Logistic回归，来分类
'''
def test_Pipeline(data):
    x_train,x_test,y_train,y_test=data
    steps=[('PCA',PCA()),
           ('LogisticRegression',LogisticRegression(C=1))]
    pipeline=Pipeline(steps)
    pipeline.fit(x_train,y_train)
    print('name steps:',pipeline.named_steps)
    print('Pipeline Score:',pipeline.score(x_test,y_test))
    
if __name__=='__main__':
    data=load_digits()
    X=data.data
    y=data.target
    test_Pipeline(cross_validation.train_test_split(X,y,test_size=0.25,
                                        random_state=0,stratify=y))