数据归一化 scikit-learn中的Scaler

1 import numpy as np
2 from sklearn import datasets
3
4 # 获取数据
5 iris = datasets.load_iris()
6 X = iris.data
7 y = iris.target
8
9 # 数据分割
10 from sklearn.model_selection import train_test_split
11 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)
12
13 # StandardScaler fit 训练集数据
14 from sklearn.preprocessing import StandardScaler
15 standardscaler = StandardScaler()
16 standardscaler.fit(X_train)
17
18 # 对训练集数据归一化
19 X_train = standardscaler.transform(X_train)
20
21 # 对测试集数据归一化
22 X_test_standard = standardscaler.transform(X_test)
23
24 # 实例化分类器
25 from sklearn.neighbors import KNeighborsClassifier
26 knn_clf = KNeighborsClassifier(n_neighbors=3)
27
28 # 分类器 fit 归一化训练集
29 knn_clf.fit(X_train, y_train)
30
31 # 用归一化的测试集数据计算预测准确率
32 knn_clf.score(X_test_standard, y_test)