scikit learn标准化数据

from sklearn import preprocessing
import numpy as np
a=np.array([[10,2.7,3.6],
           [-100,5,-2],
           [120,20,40]],dtype=np.float64)
print(a)
print(preprocessing.scale(a))#正则化数据

运行结果， 标准化前和 标准化后

from sklearn import preprocessing
import numpy as np
from sklearn.cross_validation import train_test_split
from sklearn.datasets.samples_generator import make_classification
from sklearn.svm import SVC
import matplotlib.pyplot as plt

X,y=make_classification(n_samples=300, n_features=2, n_informative=2,
                        n_redundant=0,n_clusters_per_class=1,scale=100,
                        random_state=22)
X=preprocessing.minmax_scale(X)
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3)
clf=SVC()
clf.fit(X_train,y_train)
print (clf.score(X_test,y_test))

plt.scatter(X[:,0],X[:,1],c=y)
plt.show()

自己生成的数据

用支持向量机SVM进行分类

未处理之前分类的准确率：0.655555555556

处理之后的分类准确率：0.922222222222