数据归一化

import numpy as np
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

iris = datasets.load_iris()

X = iris.data
y = iris.target

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size= 0.2,random_state=666)

standardScaler = StandardScaler()
standardScaler.fit(X_train)

standardScaler.mean_ #均值
standardScaler.scale_ #方差

X_train = standardScaler.transform(X_train) #归一化处理
X_test_standerd = standardScaler.transform(X_test) #测试数据集归一化


from sklearn.neighbors import KNeighborsClassifier
KNN_classifier = KNeighborsClassifier(n_neighbors=3)
KNN_classifier.fit(X_train,y_train)
KNN_classifier.score(X_test_standerd,y_test)

 自己实现数据归一化类

class StandardScaler(object):

    def __init__(self):
        self.mean_ = None
        self.scale_ = None
    
    def fit(self,X):
        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])])

        return self

    def transform(self,X):
        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

 

posted @ 2018-05-09 10:08  Erick-LONG  阅读(311)  评论(0编辑  收藏  举报