Skip to content

Commit

Permalink
Merge pull request #815 from VesnaT/keywords_pp_fix
Browse files Browse the repository at this point in the history
[FIX] Keywords: Always invoke preprocessor __call__
  • Loading branch information
PrimozGodec authored Apr 21, 2022
2 parents 88af9f5 + e537d23 commit 3a49f97
Show file tree
Hide file tree
Showing 2 changed files with 4 additions and 2 deletions.
4 changes: 3 additions & 1 deletion orangecontrib/text/widgets/owkeywords.py
Original file line number Diff line number Diff line change
Expand Up @@ -94,7 +94,9 @@ def callback(i: float, status=""):
# Normalize words
for preprocessor in corpus.used_preprocessor.preprocessors:
if isinstance(preprocessor, BaseNormalizer):
words = [preprocessor.normalizer(w) for w in words]
dummy = Corpus(Domain((), metas=[StringVariable("Words")]),
metas=np.array(words)[:, None])
words = list(preprocessor(dummy).tokens.flatten())

# Filter scores using words
existing_words = [w for w in set(words) if w in scores.index]
Expand Down
2 changes: 1 addition & 1 deletion orangecontrib/text/widgets/tests/test_owkeywords.py
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ def test_run_with_words(self):
self.assertEqual(len(results.scores), 42)

def test_run_normalize_words(self):
normalizer = WordNetLemmatizer()
normalizer = LemmagenLemmatizer()
corpus = normalizer(self.corpus)

words = ["minor", "tree"]
Expand Down

0 comments on commit 3a49f97

Please sign in to comment.