训练数据集和测试数据集不能分别归一化。
测试数据集使用与训练数据集相同的mean和std做归一化
即

(x_test - mean_train) / std_train

scikit-learn中的Scaler的使用流程

使用scikit-learn中的StandardScaler

准备数据

import numpy as np
from sklearn import datasets

iris = datasets.load_iris()
X = iris.data
y = iris.target

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, random_state=666)

scikit-learn中的StandardScaler

from sklearn.preprocessing import StandardScaler

standardScaler = StandardScaler()
standardScaler.fit(X_train)

X_train_standard = standardScaler.transform(X_train)
X_test_standard = standardScaler.transform(X_test)

StandardScaler + KNN + accuracy

from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3)
knn_clf.fit(X_train_standard, y_train)
knn_clf.score(X_test_standard, y_test)

自己实现StandardScaler并封装成类

import numpy as np

class StandardScaler:

    def __init__(self):
        self.mean_ = None
        self.scale_ = None

    def fit(self, X):
        """根据训练数据集X获取数据的均值和方差"""
        assert X.ndim == 2, "The dimension of X must be 2"

        self.mean_ = np.array([np.mean(X[:,i]) for i in range(X.shape[1])])
        self.scale_ = np.array([np.std(X[:,i]) for i in range(X.shape[1])])

    def transform(self, X):
        """将X根据这个StandardScaler进行均值方差归一化处理"""
        assert X.ndim == 2, "The dimension of X must be 2"
        assert self.mean_ is not None and self.scale_ is not None, "must fit before transform!"

        retX = np.empty(shape = X.shape, type = float)
        for col in range(X.shape[1]):
            retX[:, col] = (X[:,col] - self.mean_[col]) / self.scale_[col]
        return retX