X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state = 2020, stratify=y)
X_train_user = X_train[y_train == 'ji2hwh']
X_train_attacker = X_train[y_train != 'ji2hwh']
outlier_prop = len(X_train_user) / len(X_train_attacker)
svm = OneClassSVM(kernel='rbf', nu=outlier_prop, gamma=0.000001)
svm.fit(X_train_user)
pred = svm.predict(X_test)
y_test[y_test == 'ji2hwh'] = 1
y_test[y_test != 1] = -1
print(accuracy_score(y_test, pred))
I am getting Classification metrics can't handle a mix of unknown and binary targets error in the above code. 'ji2hwh' is just a userID who I am considering as my target user for my one-class classification and the rest of the users as attackers. x is a feature vector and y contains the user's ID. I cannot figure out why I am getting this error , since the variable pred returns a ndarray with [-1,1] values and y_test seems correctly assigned the appropriate values ,also in the same set of values [-1,1]. What can I do to overcome this compile error ?
The whole error message:
File "C:\Users\User\Desktop\MobileUserAuth\data_exploration.py", line 94, in <module>
print(accuracy_score(y_test, pred))
File "C:\Users\User\anaconda3\lib\site-packages\sklearn\utils\validation.py", line 72, in inner_f
return f(**kwargs)
File "C:\Users\User\anaconda3\lib\site-packages\sklearn\metrics\_classification.py", line 187, in accuracy_score
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "C:\Users\User\anaconda3\lib\site-packages\sklearn\metrics\_classification.py", line 90, in _check_targets
raise ValueError("Classification metrics can't handle a mix of {0} "
ValueError: Classification metrics can't handle a mix of unknown and binary targets
I am posting one solution to my problem I found after some days , perhaps it could help someone facing the same issue and since I didn't got one.
Just simply type cast the y_test to int and the error about the unknown target will be solved. So before calling the accuracy_score type:
y_test = y_test.astype('int')