将数据预处理加入模型选择过程

将数据预处理加入模型选择过程

# 将数据预处理加入模型选择过程
import numpy as np
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline, FeatureUnion
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
​
# set random seed  设置随机数种子
np.random.seed(0)
​
# load data
iris = datasets.load_iris()
features = iris.data
target = iris.target
​
# create a preprocessing obejct taht includes StandardScaler features and PCA
# 创建预处理对象
preprocess = FeatureUnion([("std", StandardScaler()), ("pca", PCA())])
​
# create a pipeline  创建一个流水线
pipe = Pipeline([("preprocess", preprocess),
                 ("classifier", LogisticRegression())
                ])
​
# create a space of candidate values 创建候选值
search_space = [{
    "preprocess__pca__n_components": [1, 2, 3],
    "classifier__penalty": ["l1", "l2"],
    "classifier__C": np.logspace(0, 4, 10)
}]
​
# create grid search  执行网格搜索
clf = GridSearchCV(pipe, search_space, cv=5, verbose=0, n_jobs=-1)
​
# fit grid search   训练模型
best_model = clf.fit(features, target)
​
# view best model  查看最佳参数
best_model.best_estimator_.get_params()['preprocess__pca__n_components']
2