0
我正在使用sklearn支持向量回归模型和使用MinMax来缩放功能的回归问题,但通过使用它我得到了不同的回归结果,这是否有意义?为什么缩放功能会影响回归的预测?
import pandas as pd
import numpy as np
from sklearn import svm
from sklearn.preprocessing import MinMaxScaler
np.random.seed(0)
X_training = np.random.rand(100,15)*10
Y_training = np.random.rand(100,1)*10
model = svm.SVR()
不结垢:
model.fit(X_training,Y_training)
print model.predict(X_training)[0:10]
array([ 4.99980599, 6.99479293, 4.9784396 , 5.03911175, 6.99557904,
6.57214885, 6.99454049, 5.60940831, 6.99989978, 5.98628179])
使用最小最大缩放:
scaler = MinMaxScaler()
X_scaled = scaler.fit_transform(X_training)
model.fit(X_scaled,Y_training)
model.predict(X_scaled)[0:10]
array([ 5.63521939, 6.70378514, 5.83393228, 5.33274858, 6.47539108,
5.61135278, 5.7890052 , 5.74425789, 6.15799404, 6.1980326 ])
虽然预测是大小相同的顺序存在这两种情况之间的差异显著。