吳裕雄 python 機器學習——數據預處理流水線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 自帶的一個糖尿病病人的數據集
    diabetes = datasets.load_diabetes() 
    # 拆分成訓練集和測試集，測試集大小為原始數據集大小的 1/4
    return train_test_split(diabetes.data,diabetes.target,test_size=0.25,random_state=0)  

#數據預處理流水線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))
    
# 獲取分類數據
X_train,X_test,y_train,y_test=load_diabetes() 
# 調用 test_Pipeline
test_Pipeline(X_train,X_test,y_train,y_test)