数据归一化 scikit-learn中的Scaler

83327712 2020-07-30

import numpy as np
from sklearn import datasets

# 获取数据
iris = datasets.load_iris()
X = iris.data
y = iris.target

# 数据分割
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)

# StandardScaler fit 训练集数据
from sklearn.preprocessing import StandardScaler
standardscaler = StandardScaler()
standardscaler.fit(X_train)

# 对训练集数据归一化
X_train = standardscaler.transform(X_train)

# 对测试集数据归一化
X_test_standard  = standardscaler.transform(X_test)

# 实例化分类器
from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3)

# 分类器 fit 归一化训练集
knn_clf.fit(X_train, y_train)

# 用归一化的测试集数据计算预测准确率
knn_clf.score(X_test_standard, y_test)

相关推荐