如题,代码如下:
import pandas as pd #导入数据
import numpy as np # #导入数据
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split #分离数据集
from pandas import Series,DataFrame #
from sklearn import preprocessing #数据处理
from sklearn import svm
from sklearn.svm import SVR #调用sklearn的SVR
from sklearn.model_selection import GridSearchCV
import matplotlib.pyplot as plt
dataset=pd.read_excel(r'C:\Users\hsw\Desktop\毕业设计\ITE.xlsx')
col = dataset.columns.values.tolist()
col1 =col[0:6]
data_x=np.array(dataset[col1])
data_y=dataset['ITE']
x_train,x_test,y_train,y_test = train_test_split(data_x,data_y,random_state=200,test_size = 0.2)
clf = svm.SVR()
clf.fit(x_train, y_train)
SVR(C=20, epsilon=0.1, gamma='auto',
kernel='rbf', max_iter=-1,
shrinking=True,#收缩
verbose=True#详细信息
)
print(clf.score(x_test, y_test) )
样本跟真实值是这样:
输出是这样:
0.7402323607782507
都是自己在网上找的代码然后试,也不知道该怎么写。
但是现在我改变“C”与“epsilon”的值,clf.score的值都不会改变,我变“random_state”才会改变,不知道是哪里有问题还是怎么,不知有没有大神能够解答一下疑惑……
还有要做还需要用到哪些?