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

Jump to bottom

simple depreciation fix #60

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

simple depreciation fix #60

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2ab4f54
depreciation warning fix gensim
maximus12793 Oct 17, 2017
05bdde1
style edit
maximus12793 Oct 17, 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
22 changes: 13 additions & 9 deletions lda2vec/corpus.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
from collections import defaultdict
import numpy as np
import difflib
import pandas as pd

try:
Expand Down Expand Up @@ -531,8 +530,10 @@ def compact_word_vectors(self, vocab, filename=None, array=None,
True
"""
n_words = len(self.compact_to_loose)
from gensim.models.word2vec import Word2Vec
model = Word2Vec.load_word2vec_format(filename, binary=True)
import gensim
model = gensim.models.KeyedVectors.load_word2vec_format(
filename, binary=True)

n_dim = model.syn0.shape[1]
data = np.random.normal(size=(n_words, n_dim)).astype('float32')
data -= data.mean()
Expand All @@ -548,9 +549,12 @@ def compact_word_vectors(self, vocab, filename=None, array=None,
choices = np.array(keys, dtype='S')
lengths = np.array(lens, dtype='int32')
s, f = 0, 0
rep0 = lambda w: w
rep1 = lambda w: w.replace(' ', '_')
rep2 = lambda w: w.title().replace(' ', '_')

def rep0(w): return w

def rep1(w): return w.replace(' ', '_')

def rep2(w): return w.title().replace(' ', '_')
reps = [rep0, rep1, rep2]
for compact in np.arange(top):
loose = self.compact_to_loose.get(compact, None)
Expand All @@ -574,7 +578,6 @@ def compact_word_vectors(self, vocab, filename=None, array=None,
sel = choices[idx]
d = damerau_levenshtein_distance_withNPArray(word, sel)
choice = np.array(keys_raw)[idx][np.argmin(d)]
# choice = difflib.get_close_matches(word, choices)[0]
vector = model[choice]
print compact, word, ' --> ', choice
except IndexError:
Expand Down Expand Up @@ -677,8 +680,9 @@ def compact_to_coocurrence(self, word_compact, indices, window_size=10):
for name, index in indices.items():
tokens[name] = index
a, b = tokens.copy(), tokens.copy()
mask = lambda x: np.prod([x[k + '_x'] == x[k + '_y']
for k in indices.keys()], axis=0)

def mask(x): return np.prod([x[k + '_x'] == x[k + '_y']
for k in indices.keys()], axis=0)
group_keys = ['word_index_x', 'word_index_y', ]
group_keys += [k + '_x' for k in indices.keys()]
total = []
Expand Down