吴裕雄 python 机器学习——数据预处理流水线Pipeline模型

from sklearn.svm import LinearSVC

from sklearn.pipeline import Pipeline

from sklearn import neighbors, datasets

from sklearn.datasets import load_digits

from sklearn.linear_model import LogisticRegression

from sklearn.model_selection import train_test_split

def load_diabetes():

    #使用 scikit-learn 自带的一个糖尿病病人的数据集

    diabetes = datasets.load_diabetes()

    # 拆分成训练集和测试集，测试集大小为原始数据集大小的 1/4

    return train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)

#数据预处理流水线Pipeline模型

def test_Pipeline(X_train,X_test,y_train,y_test):

    steps=[("Linear_SVM",LinearSVC(C=1,penalty='l1',dual=False)),("LogisticRegression",LogisticRegression(C=1))]

    pipeline=Pipeline(steps)

    pipeline.fit(X_train,y_train)

    print("Named steps:",pipeline.named_steps)

    print("Pipeline Score:",pipeline.score(X_test,y_test))

# 获取分类数据

X_train,X_test,y_train,y_test=load_diabetes()

# 调用 test_Pipeline

test_Pipeline(X_train,X_test,y_train,y_test)