sklearn笔记二 标准化

2.1 线性回归model常用属性

loaded_data = datasets.load_boston()
data_X = loaded_data.data
data_y = loaded_data.target

model = LinearRegression()
model.fit(data_X, data_y)

print(model.predict(data_X[:4, :]))
print(model.coef_)#权重系数
print(model.intercept_)#截距
print(model.get_params())#参数
print(model.score(data_X, data_y)) # R^2

2.2标准化
可以提升模型最后的score

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

X,Y=make_classification(n_samples=300,n_features=2,n_informative=2,n_redundant=0,
                        random_state=22,n_clusters_per_class=1,scale=100)

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

一般使用**preprocessing.scale(X)**进行标准化

#X=preprocessing.minmax_scale(X,feature_range=(-1,1))#把X标准化到-1到1
X=preprocessing.scale(X)#常用 标准化到0到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))

如果不标准化 得分会降低