sklearn normalization 数据标准化

from sklearn import preprocessing
# train data 和test_data 分开的模块
from sklearn.cross_validation import train_test_split
# 用于生成一些 classification的数据
from sklearn.datasets.samples_generator import make_classification
# 处理数据的模型svm ：support vector machine，svc：support vector classify
from sklearn.svm import SVC
# 可视化数据
import matplotlib.pyplot as plt


X,y = make_classification(n_samples=300,n_features=2,n_redundant=0,n_informative=2,
                          random_state=22,n_clusters_per_class=1,scale=100)
# plt.scatter(X[:,0],X[:,1],c=y)
# plt.show()
# 把数据浓缩到-1到1的范围,如果不写feature_range默认是从0到1的范围
#X = preprocessing.minmax_scale(X,feature_range=(-1,1))
#压缩到0-1的范围
X = preprocessing.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))

结果：0.9222222222222223