retrieve misclassified documents using scikitlearn

Question

I'm interested to know if there's built in functions in scikitlearn python module, that can retrieve misclassified documents.

it's simple i usually write it myself by comparing both predicted and Test vectors and retrieve the documents from the test document array. but i'm asking if there's a built in functionality for it instead of copying the functionality in each python code i write.

Answer 1

If you have a list of true labels y_test for a set of documents, e.g. ["ham", "spam", "spam", "ham"] and you convert that to a NumPy array, then you can compare it with the predictions in a one-liner:

import numpy as np

y_test = np.asarray(y_test)
misclassified = np.where(y_test != clf.predict(X_test))

Now misclassified is an array of indices into X_test.

@eickenberg is right, this kind of stuff is not implemented in scikit-learn because users are expected to be familiar enough with NumPy to do it themselves in a few lines of code.