Python机器学习：KNN算法08scikit-learn中的Scaler

归一化

from sklearn import datasets
import numpy as np

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(X,y,test_size=0.2,random_state=666)

#sklearn中的StandarScaler
from sklearn.preprocessing import StandardScaler
standardScaler = StandardScaler()
standardScaler.fit(X_train)

standardScaler.mean_

array([5.83416667, 3.08666667, 3.70833333, 1.17      ])

standardScaler.scale_#数据分布范围，方差~

array([0.81019502, 0.44327067, 1.76401924, 0.75317107])

归一化

X_train = standardScaler.transform(X_train)

print(X_train)

部分结果

这个归一化使用的也是训练集中的均值和方差

X_test_standard = standardScaler.transform(X_test)

使用KNN算法看看分类效果

from sklearn.neighbors import KNeighborsClassifier
knn_clf = KNeighborsClassifier(n_neighbors=3

knn_clf.fit(X_train,y_train)

KNeighborsClassifier(n_neighbors=3)

knn_clf.score(X_test,y_test)#没归一化

0.3333333333333333

使用归一化的数据集，正确率100.。。

knn_clf.score(X_test_standard,y_test)

1.0

另外还自己封装了一个类，可以处理ndim=2的矩阵

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获得数据的均值和方差"""
        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"

        resX = np.empty(shape=X.shape,dtype=float)

        for col in range(X.shape[1]):
            resX[:,col] = (X[:,col] - self.mean_[col]) / self.scale_[col]

        return resX

fit之后就保存了均值和方差…