Skip to content

Made off-by-one adjustments for specials tokens #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
agtsai-i wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Made off-by-one adjustments for specials tokens #41

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions lda2vec/corpus.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,7 @@ def _loose_keys_ordered(self):
""" Get the loose keys in order of decreasing frequency"""
loose_counts = sorted(self.counts_loose.items(), key=lambda x: x[1],
reverse=True)
loose_counts = [i for i in loose_counts if i[0] not in self.specials.values()]
keys = np.array(loose_counts)[:, 0]
counts = np.array(loose_counts)[:, 1]
order = np.argsort(counts)[::-1].astype('int32')
Expand Down Expand Up @@ -415,7 +416,7 @@ def compact_to_flat(self, word_compact, *components):
self._check_finalized()
n_docs = word_compact.shape[0]
max_length = word_compact.shape[1]
idx = word_compact > self.n_specials
idx = word_compact >= self.n_specials
components_raveled = []
msg = "Length of each component must much `word_compact` size"
for component in components:
Expand Down Expand Up @@ -552,7 +553,7 @@ def compact_word_vectors(self, vocab, filename=None, array=None,
rep1 = lambda w: w.replace(' ', '_')
rep2 = lambda w: w.title().replace(' ', '_')
reps = [rep0, rep1, rep2]
for compact in np.arange(top):
for compact in np.arange(min(top, n_words)):
loose = self.compact_to_loose.get(compact, None)
if loose is None:
continue
Expand Down