Scikit-learn ValueError: unknown is not supported when using confusion matrix

Question

I'm using the confusion_matrix module to visualize class prediction results compared to actual values.

val= ... #shape (3000,1,30) dtype float32
pred = ... #shape (3000,1,30) dtype float32

cnf_matrix = confusion_matrix(val, pred) #ERROR HERE

I got this error:

Traceback (most recent call last): File "vis.py", line 757, in cnf_matrix = confusion_matrix(y_test, y_pred) File "C:\Anaconda\envs\nn35\lib\site-packages\sklearn\metrics\classification.py", line 240, in confusion_matrix y_type, y_true, y_pred = _check_targets(y_true, y_pred) File "C:\Anaconda\envs\nn35\lib\site-packages\sklearn\metrics\classification.py", line 89, in _check_targets raise ValueError("{0} is not supported".format(y_type)) ValueError: unknown is not supported

What did I do wrong?

matchifang matchifang · Accepted Answer · 2017-08-07T16:38:34

Problem was the shape of the true value and prediction must be (3000,30) not (3000,1,30). So I reshape it using pred= np.reshape(pred, (pred.shape[0], 30))

Scikit-learn ValueError: unknown is not supported when using confusion matrix

1 Answers