How to evaluate a soft Voting classifier being trained on some data

Question

I have taken 3 classification models,

clf1 = DecisionTreeClassifier(max_depth=4)
clf2 = KNeighborsClassifier(n_neighbors=7)
clf3 = SVC(kernel='rbf', probability=True)

I am passing them to voting classifier as parameters and choose soft voting.

eclf = VotingClassifier(estimators=[('dt', clf1), ('knn', clf2), ('svc', clf3)], voting='soft', weights=[2,1,2])

clf1 = clf1.fit(titanic_train1,y_train)
clf2 = clf2.fit(titanic_train1,y_train)
clf3 = clf3.fit(titanic_train1,y_train)
eclf = eclf.fit(titanic_train1,y_train)

Here i am getting error ,AttributeError: 'VotingClassifier' object has no attribute 'best_score_'

print("CvScore",eclf.best_score_)
print("Train accuracy",eclf.score(titanic_train1, y_train))

I want to find best tuning parameters for this model?

Answer 1

VotingClassifier does not have a best_score_ attribute. You can look at the scikit-learn documentation here to see that the best_score_ attribute is missing.

If you're trying to get a cross validation score you need to use something like K-Fold or GridSearchCV where K-Fold will give you an idea for how well the classifier generalizes to naive data and GridSearchCV will help determine the best parameter configuration for the model.