Skip to content
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

#1441: Fix issues with WordOccurenceAccumulator on Windows. #1449

Merged
merged 2 commits into from
Jun 26, 2017
Merged

#1441: Fix issues with WordOccurenceAccumulator on Windows. #1449

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8eabfcb
#1441: Fix issues with `WordOccurenceAccumulator` on Windows.
Jun 25, 2017
1701bcd
#1441: Use pre-scipy0.17 version of `scipy.sparse.diags` function by …
Jun 26, 2017
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
11 changes: 6 additions & 5 deletions gensim/topic_coherence/text_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,7 +221,6 @@ def __init__(self, *args):
self._co_occurrences = sps.lil_matrix((self._vocab_size, self._vocab_size), dtype='uint32')

self._uniq_words = np.zeros((self._vocab_size + 1,), dtype=bool) # add 1 for none token
self._mask = self._uniq_words[:-1] # to exclude none token
self._counter = Counter()

def __str__(self):
Expand Down Expand Up @@ -251,9 +250,10 @@ def partial_accumulate(self, texts, window_size):

def analyze_text(self, window, doc_num=None):
self._slide_window(window, doc_num)
if self._mask.any():
self._occurrences[self._mask] += 1
self._counter.update(itertools.combinations(np.nonzero(self._mask)[0], 2))
mask = self._uniq_words[:-1] # to exclude none token
if mask.any():
self._occurrences[mask] += 1
self._counter.update(itertools.combinations(np.nonzero(mask)[0], 2))

def _slide_window(self, window, doc_num):
if doc_num != self._current_doc_num:
Expand All @@ -273,7 +273,8 @@ def _symmetrize(self):
"""
co_occ = self._co_occurrences
co_occ.setdiag(self._occurrences) # diagonal should be equal to occurrence counts
self._co_occurrences = co_occ + co_occ.T - sps.diags(co_occ.diagonal(), dtype='uint32')
self._co_occurrences = \
co_occ + co_occ.T - sps.diags(co_occ.diagonal(), offsets=0, dtype='uint32')

def _get_occurrences(self, word_id):
return self._occurrences[word_id]
Expand Down