网格搜索和交叉验证 SVM

Question

我正在使用网格搜索的最佳参数对 10 倍交叉验证实施支持向量机，我需要了解预测结果为什么不同我在训练集上得到了两个准确度结果测试通知我需要训练集上最佳参数的预测结果以供进一步分析代码和结果如下所述。任何解释

from __future__ import print_function

from sklearn import datasets

from sklearn.model_selection import train_test_split

from sklearn.model_selection import GridSearchCV

from sklearn.metrics import classification_report

from sklearn.svm import SVC

from sklearn.metrics import accuracy_score

from time import *

from sklearn import metrics

X=datascaled.iloc[:,0:13]

y=datascaled['num']

np.random.seed(1)

# Split the dataset in two equal parts

X_train, X_test, y_train, y_test = train_test_split(

    X, y, test_size=0.3, random_state=0)

# Set the parameters by cross-validation

tuned_parameters =  [{'kernel': ['rbf'], 'gamma': [1e-2, 1e-3, 1e-4, 1e-5],

                     'C': [0.001, 0.10, 0.1, 10, 25, 50, 100, 1000]},

                    {'kernel': ['sigmoid'], 'gamma': [1e-2, 1e-3, 1e-4, 1e-5],

                     'C': [0.001, 0.10, 0.1, 10, 25, 50, 100, 1000] },{'kernel': ['linear'], 'C': [0.001, 0.10, 0.1, 10, 25, 50, 100, 1000]}]              

print()

clf = GridSearchCV(SVC(), tuned_parameters, cv=10,

                       scoring='accuracy')

t0 = time()

clf.fit(X_train, y_train)

t = time() - t0

print("Best parameters set found on development set:")

print()

print(clf.best_params_)

print()

print('Training accuracy')

print(clf.best_score_)

print(clf.best_estimator_)

print()

print()

print('****Results****')

svm_pred=clf.predict(X_train)

#print("\t\taccuracytrainkfold: {}".format(metrics.accuracy_score(y_train, svm_pred)))

print("=" * 52)

print("time cost: {}".format(t))

print()

print("confusion matrix\n", metrics.confusion_matrix(y_train, svm_pred))

print()

print("\t\taccuracy: {}".format(metrics.accuracy_score(y_train, svm_pred)))

print("\t\troc_auc_score: {}".format(metrics.roc_auc_score(y_train, svm_pred)))

print("\t\tcohen_kappa_score: {}".format(metrics.cohen_kappa_score(y_train, svm_pred)))

print()