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

Generate Deprecated exception when using Word2Vec.load_word2vec_format #1165

Merged
merged 6 commits into from
Feb 24, 2017
Merged

Generate Deprecated exception when using Word2Vec.load_word2vec_format #1165

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
70aa53f
Add phraser to phrases docstring
tmylk Feb 23, 2017
85b44ef
Update docstring in word2vec and keyedvectors
tmylk Feb 23, 2017
005a980
Add exceptions that word2vec format deprecated
tmylk Feb 23, 2017
cf6446b
Update load/save_word2vec references
tmylk Feb 23, 2017
56ce34c
Add keyedvectors to models init
tmylk Feb 23, 2017
80b9c95
Fix ipynbs for load/save_word2vec format references
tmylk Feb 23, 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
77 changes: 22 additions & 55 deletions docs/notebooks/WMD_tutorial.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

78 changes: 27 additions & 51 deletions docs/notebooks/Word2Vec_FastText_Comparison.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

92 changes: 31 additions & 61 deletions docs/notebooks/Wordrank_comparisons.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

90 changes: 28 additions & 62 deletions docs/notebooks/deepir.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

94 changes: 27 additions & 67 deletions docs/notebooks/doc2vec-IMDB.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,9 +39,7 @@
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"import locale\n",
Expand Down Expand Up @@ -120,9 +118,7 @@
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"import os.path\n",
Expand All @@ -139,9 +135,7 @@
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -202,9 +196,7 @@
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -254,9 +246,7 @@
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"from gensim.test.test_doc2vec import ConcatenatedDoc2Vec\n",
Expand All @@ -281,9 +271,7 @@
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
Expand Down Expand Up @@ -330,7 +318,7 @@
" corrects = sum(np.rint(test_predictions) == [doc.sentiment for doc in test_data])\n",
" errors = len(test_predictions) - corrects\n",
" error_rate = float(errors) / len(test_predictions)\n",
" return (error_rate, errors, len(test_predictions), predictor)\n"
" return (error_rate, errors, len(test_predictions), predictor)"
]
},
{
Expand All @@ -356,9 +344,7 @@
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"from collections import defaultdict\n",
Expand All @@ -368,9 +354,7 @@
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -579,9 +563,7 @@
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -630,9 +612,7 @@
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -673,9 +653,7 @@
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -703,7 +681,7 @@
"print(u'TARGET (%d): «%s»\\n' % (doc_id, ' '.join(alldocs[doc_id].words)))\n",
"print(u'SIMILAR/DISSIMILAR DOCS PER MODEL %s:\\n' % model)\n",
"for label, index in [('MOST', 0), ('MEDIAN', len(sims)//2), ('LEAST', len(sims) - 1)]:\n",
" print(u'%s %s: «%s»\\n' % (label, sims[index], ' '.join(alldocs[sims[index][0]].words)))\n"
" print(u'%s %s: «%s»\\n' % (label, sims[index], ' '.join(alldocs[sims[index][0]].words)))"
]
},
{
Expand All @@ -723,9 +701,7 @@
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"word_models = simple_models[:]"
Expand All @@ -734,9 +710,7 @@
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -806,14 +780,10 @@
"('mockumentary', 0.5149033069610596),<br>\n",
"('camp-fest', 0.5122634768486023),<br>\n",
"('mystery/comedy', 0.5020694732666016)]</td></tr></table>"
],
"text/plain": [
"<IPython.core.display.HTML at 0x1535b84d0>"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
"output_type": "execute_result",
"metadata": {}
}
],
"source": [
Expand Down Expand Up @@ -855,9 +825,7 @@
{
"cell_type": "code",
"execution_count": 26,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [
{
"name": "stdout",
Expand Down Expand Up @@ -897,12 +865,10 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"This cell left intentionally erroneous. "
"This cell left intentionally erroneous."
]
},
{
Expand All @@ -915,13 +881,11 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"from gensim.models import Word2Vec\n",
"w2v_g100b = Word2Vec.load_word2vec_format('GoogleNews-vectors-negative300.bin.gz', binary=True)\n",
"from gensim.models import KeyedVectors\n",
"w2v_g100b = KeyedVectors.load_word2vec_format('GoogleNews-vectors-negative300.bin.gz', binary=True)\n",
"w2v_g100b.compact_name = 'w2v_g100b'\n",
"word_models.append(w2v_g100b)"
]
Expand All @@ -936,9 +900,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"import logging\n",
Expand All @@ -957,9 +919,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
Expand All @@ -976,7 +936,7 @@
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
"version": 3.0
},
"file_extension": ".py",
"mimetype": "text/x-python",
Expand All @@ -988,4 +948,4 @@
},
"nbformat": 4,
"nbformat_minor": 0
}
}
Loading