sklearn 标准化数据的方法

Sklearn

标准化数据

from __future__ import print_function
from sklearn import preprocessing
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.datasets.samples_generator import make_classification
from sklearn.svm import SVC
import matplotlib.pyplot as plt
#每一列是一个属性
a = np.array([[10, 2.7, 3.6],
                     [-100, 5, -2],
                     [120, 20, 40]], dtype=np.float64)
        
print(a)
#归一化
print(preprocessing.scale(a))
# 生成一堆数据 有两个属性 有两个相关属性
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()
X = preprocessing.scale(X)    # normalization step
#minmax_scale(X,feature_range=(-1,1))
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.3)
clf = SVC()
clf.fit(X_train, y_train)
print(clf.score(X_test, y_test))