Skip to content

Commit

Permalink
Disable direct access warnings on save and load of Word2vec/Doc2vec (#…
Browse files Browse the repository at this point in the history 
…1072)
  • Loading branch information
@tmylk
tmylk authored Jan 4, 2017
1 parent 946fc26 commit b20e73b
Show file tree
Hide file tree
Showing 2 changed files with 89 additions and 82 deletions.
117 changes: 47 additions & 70 deletions docs/notebooks/word2vec.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [
{
Expand Down Expand Up @@ -134,7 +134,7 @@
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [
{
Expand Down Expand Up @@ -162,7 +162,7 @@
"output_type": "stream",
"text": [
"Word2Vec(vocab=3, size=100, alpha=0.025)\n",
"{'second': <gensim.models.word2vec.Vocab object at 0x7fb2639b6f90>, 'first': <gensim.models.word2vec.Vocab object at 0x7fb293914590>, 'sentence': <gensim.models.word2vec.Vocab object at 0x7fb293914850>}\n"
"{'second': <gensim.models.word2vec.Vocab object at 0x7fed6d4faf50>, 'first': <gensim.models.word2vec.Vocab object at 0x7fed6d4fafd0>, 'sentence': <gensim.models.word2vec.Vocab object at 0x7fed6d4faf90>}\n"
]
}
],
Expand All @@ -188,7 +188,7 @@
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [
{
Expand Down Expand Up @@ -228,7 +228,7 @@
"output_type": "stream",
"text": [
"Word2Vec(vocab=3, size=100, alpha=0.025)\n",
"{'second': <gensim.models.word2vec.Vocab object at 0x7fb2639b6f90>, 'first': <gensim.models.word2vec.Vocab object at 0x7fb293914590>, 'sentence': <gensim.models.word2vec.Vocab object at 0x7fb293914850>}\n"
"{'second': <gensim.models.word2vec.Vocab object at 0x7fed6d4faf50>, 'first': <gensim.models.word2vec.Vocab object at 0x7fed6d4fafd0>, 'sentence': <gensim.models.word2vec.Vocab object at 0x7fed6d4faf90>}\n"
]
}
],
Expand Down Expand Up @@ -269,7 +269,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"<__main__.MyText object at 0x7fb2639539d0>\n"
"<__main__.MyText object at 0x7fed6d495810>\n"
]
}
],
Expand Down Expand Up @@ -332,7 +332,7 @@
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [
{
Expand Down Expand Up @@ -655,8 +655,8 @@
{
"data": {
"text/plain": [
"((0.10128579883072975, 0.47943282766520035),\n",
" SpearmanrResult(correlation=0.072904174848358635, pvalue=0.61116578621439932),\n",
"((0.093652497483521988, 0.51332382076991245),\n",
" SpearmanrResult(correlation=0.079058717231584447, pvalue=0.58131863093325009),\n",
" 85.55240793201133)"
]
},
Expand Down Expand Up @@ -686,22 +686,11 @@
},
{
"cell_type": "code",
"execution_count": 31,
"execution_count": 17,
"metadata": {
"collapsed": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n",
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n",
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n",
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n"
]
}
],
"outputs": [],
"source": [
"from tempfile import mkstemp\n",
"\n",
Expand All @@ -712,20 +701,11 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 18,
"metadata": {
"collapsed": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n",
"WARNING:gensim.models.word2vec:direct access to index2word will not be supported in future gensim releases, please use model.wv.index2word\n"
]
}
],
"outputs": [],
"source": [
"new_model = gensim.models.Word2Vec.load(temp_path) # open the model"
]
Expand Down Expand Up @@ -753,26 +733,23 @@
},
{
"cell_type": "code",
"execution_count": 33,
"execution_count": 19,
"metadata": {
"collapsed": true
"collapsed": false
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:gensim.models.word2vec:direct access to syn0norm will not be supported in future gensim releases, please use model.wv.syn0norm\n",
"WARNING:gensim.models.word2vec:direct access to index2word will not be supported in future gensim releases, please use model.wv.index2word\n",
"WARNING:gensim.models.word2vec:Each 'sentences' item should be a list of words (usually unicode strings).First item here is instead plain <type 'str'>.\n",
"WARNING:gensim.models.word2vec:under 10 jobs per worker: consider setting a smaller `batch_words' for smoother alpha decay\n"
]
}
],
"source": [
"model = gensim.models.Word2Vec.load(temp_path)\n",
"more_sentences = ['Advanced', 'users', 'can', 'load', 'a', 'model', 'and', 'continue', \n",
" 'training', 'it', 'with', 'more', 'sentences']\n",
"more_sentences = [['Advanced', 'users', 'can', 'load', 'a', 'model', 'and', 'continue', \n",
" 'training', 'it', 'with', 'more', 'sentences']]\n",
"model.build_vocab(more_sentences, update=True)\n",
"model.train(more_sentences, )\n",
"\n",
Expand All @@ -795,18 +772,18 @@
},
{
"cell_type": "code",
"execution_count": 34,
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"[('ensure', 0.9957192540168762)]"
"[('longer', 0.9889242649078369)]"
]
},
"execution_count": 34,
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -817,7 +794,7 @@
},
{
"cell_type": "code",
"execution_count": 35,
"execution_count": 21,
"metadata": {
"collapsed": false
},
Expand All @@ -828,7 +805,7 @@
"'sentence'"
]
},
"execution_count": 35,
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -839,7 +816,7 @@
},
{
"cell_type": "code",
"execution_count": 36,
"execution_count": 22,
"metadata": {
"collapsed": false
},
Expand All @@ -848,8 +825,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
"0.999075350666\n",
"0.994927937956\n"
"0.999177346162\n",
"0.9956625533\n"
]
}
],
Expand All @@ -874,37 +851,37 @@
},
{
"cell_type": "code",
"execution_count": 29,
"execution_count": 23,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"array([ 0.0044026 , 0.0197748 , -0.02639075, -0.00805756, -0.02940564,\n",
" -0.03424382, 0.00585153, -0.08163424, -0.01097746, -0.01996135,\n",
" 0.02069173, -0.02237663, -0.06126078, -0.01786143, -0.01912139,\n",
" 0.04299303, -0.02625322, -0.00262815, 0.02180346, -0.02537277,\n",
" -0.06165754, -0.00596116, 0.0625946 , 0.04605089, 0.02265292,\n",
" 0.01248171, -0.00406209, 0.01647919, -0.01257895, 0.00213343,\n",
" 0.0013593 , 0.06606596, 0.00893093, -0.00202957, 0.02115596,\n",
" 0.0191715 , -0.03835866, 0.01671978, 0.01097227, -0.06311714,\n",
" -0.07220271, 0.00545426, -0.04120893, -0.02457557, 0.02904521,\n",
" -0.05145161, 0.03559498, 0.00507238, -0.01168406, 0.03649417,\n",
" 0.01431915, 0.00701938, -0.03449947, 0.00628083, 0.01424492,\n",
" -0.01694195, 0.05345082, -0.02725438, 0.02032493, -0.03279101,\n",
" -0.02823507, -0.04623265, 0.01619413, -0.03048068, -0.01032882,\n",
" -0.05897115, -0.07391553, 0.03485925, 0.04940247, -0.00280599,\n",
" -0.00966417, 0.00758454, -0.04670098, 0.01224129, -0.04389989,\n",
" -0.05034593, 0.03377169, -0.00763094, 0.04285096, 0.03868506,\n",
" -0.01992619, 0.03243366, -0.01554415, 0.00177458, 0.01495264,\n",
" 0.00747898, -0.08512215, -0.07518613, 0.06046252, -0.0258348 ,\n",
" -0.05520898, -0.04187159, -0.04409514, -0.00446168, -0.02488452,\n",
" -0.02667282, -0.02259186, 0.01971211, -0.04830339, -0.00232734], dtype=float32)"
"array([ 0.00437901, 0.02313748, -0.02936309, -0.008752 , -0.03265081,\n",
" -0.03857959, 0.00654852, -0.0923382 , -0.01189023, -0.02187135,\n",
" 0.02219572, -0.02655028, -0.06957301, -0.02087111, -0.02286052,\n",
" 0.04829395, -0.03034872, -0.00357749, 0.02391322, -0.02807236,\n",
" -0.06825348, -0.00669135, 0.06967571, 0.05163613, 0.02806929,\n",
" 0.01239634, -0.00480743, 0.01985245, -0.01433731, 0.00375685,\n",
" 0.00060874, 0.07473379, 0.01165777, -0.00219114, 0.02414591,\n",
" 0.02177458, -0.04234934, 0.01883218, 0.01372305, -0.07125106,\n",
" -0.07948184, 0.00423239, -0.0464657 , -0.02693122, 0.03259234,\n",
" -0.05827391, 0.03877009, 0.00561458, -0.01218846, 0.04278557,\n",
" 0.01462523, 0.007201 , -0.03836477, 0.00855641, 0.0169761 ,\n",
" -0.01902537, 0.05948593, -0.03107592, 0.02312824, -0.03672323,\n",
" -0.03216219, -0.05264312, 0.01833 , -0.03556807, -0.01106968,\n",
" -0.06612992, -0.08438165, 0.04030743, 0.05524538, -0.00266636,\n",
" -0.00996253, 0.00714844, -0.05092834, 0.01251214, -0.05092845,\n",
" -0.05681988, 0.03765561, -0.00957785, 0.04912213, 0.04425321,\n",
" -0.021587 , 0.03699207, -0.01726504, 0.00114953, 0.01761538,\n",
" 0.00806294, -0.09447837, -0.08522288, 0.06803837, -0.02660622,\n",
" -0.06076197, -0.04739827, -0.05012174, -0.0040967 , -0.02732807,\n",
" -0.02925751, -0.02515732, 0.0224477 , -0.05377112, -0.00109009], dtype=float32)"
]
},
"execution_count": 29,
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
Expand Down
Loading

0 comments on commit b20e73b

Please sign in to comment.