import numpy as np
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
import matplotlib.pyplot as plt
iris=datasets.load_iris()
# print(list(iris.keys()))
# print(iris['DESCR'])
# print(iris['feature_names'])
X=iris['data'][:,3:]
# print(X)
# print(iris['target'])
y=iris['target']
print(X)
print(y)
param_grid={'C':[1e3,5e3,1e4,5e4,1e5],
'gamma':[0.0001,0.0005,0.001,0.005,0.01,0.1]}
model1=GridSearchCV(SVC(kernel='rbf',class_weight='balanced'),param_grid,cv=5)
model1=model1.fit(X,y)
model2=GridSearchCV(SVC(kernel='sigmoid',class_weight='balanced'),param_grid,cv=5)
model2=model2.fit(X,y)
test_labels=np.zeros(150)
test_labels[75:150]=1
result1=model1.predict(X)
test_labels=np.zeros(150)
test_labels[75:150]=1
result2=model2.predict(X)
print(confusion_matrix(test_labels,result1))
print(confusion_matrix(test_labels,result2))
model3=GridSearchCV(SVC(kernel='poly',class_weight='balanced'),param_grid,cv=5)
model3=model3.fit(X,y)
test_labels=np.zeros(150)
test_labels[75:150]=1
result3=model3.predict(X)
print(confusion_matrix(test_labels,result3))
model4=GridSearchCV(SVC(kernel='linear',class_weight='balanced'),param_grid,cv=5)
test_labels=np.zeros(150)
test_labels[75:150]=1
model4=model4.fit(X,y)
result4=model4.predict(X)
print(confusion_matrix(test_labels,result4))
改变四个核函数之后训练出来的模型为什么后面三个结果是一样的,这是巧合还是就是会出现这种情况