nodevectors
nodevectors copied to clipboard
VHRanger
fit_transform tries to query non-existent node "0"
from nodevectors import Node2Vec
import networkx as nx
G = nx.Graph()
G.add_edge("1", "2")
n2v = Node2Vec(n_components=128)
n2v.fit_transform(G)
Output:
Making walks... Done, T=3.98
Mapping Walk Names... Done, T=0.07
Training W2V... WARNING: gensim word2vec version is unoptimizedTry version 3.6 if on windows, versions 3.7 and 3.8 have had issues
Done, T=0.39
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-6-43e45de9791e> in <module>
2 G.add_edge("1", "2")
3 n2v = Node2Vec(n_components=128)
----> 4 n2v.fit_transform(G)
~/miniconda3/envs/graphs/lib/python3.7/site-packages/nodevectors/node2vec.py in fit_transform(self, G)
151 pd.DataFrame.from_records(
152 pd.Series(np.arange(len(G.nodes)))
--> 153 .apply(self.predict)
154 .values)
155 )
~/miniconda3/envs/graphs/lib/python3.7/site-packages/pandas/core/series.py in apply(self, func, convert_dtype, args, **kwds)
4106 else:
4107 values = self.astype(object)._values
-> 4108 mapped = lib.map_infer(values, f, convert=convert_dtype)
4109
4110 if len(mapped) and isinstance(mapped[0], Series):
pandas/_libs/lib.pyx in pandas._libs.lib.map_infer()
~/miniconda3/envs/graphs/lib/python3.7/site-packages/nodevectors/node2vec.py in predict(self, node_name)
166 if type(node_name) is not str:
167 node_name = str(node_name)
--> 168 return self.model.wv.__getitem__(node_name)
169
170 def save_vectors(self, out_file):
~/miniconda3/envs/graphs/lib/python3.7/site-packages/gensim/models/keyedvectors.py in __getitem__(self, entities)
351 if isinstance(entities, string_types):
352 # allow calls like trained_model['office'], as a shorthand for trained_model[['office']]
--> 353 return self.get_vector(entities)
354
355 return vstack([self.get_vector(entity) for entity in entities])
~/miniconda3/envs/graphs/lib/python3.7/site-packages/gensim/models/keyedvectors.py in get_vector(self, word)
469
470 def get_vector(self, word):
--> 471 return self.word_vec(word)
472
473 def words_closer_than(self, w1, w2):
~/miniconda3/envs/graphs/lib/python3.7/site-packages/gensim/models/keyedvectors.py in word_vec(self, word, use_norm)
466 return result
467 else:
--> 468 raise KeyError("word '%s' not in vocabulary" % word)
469
470 def get_vector(self, word):
KeyError: "word '0' not in vocabulary"
Fitting and then predicting works fine:
n2v.fit(G)
for node in G:
print(n2v.predict(node))
Output:
Making walks... Done, T=0.00
Mapping Walk Names... Done, T=0.06
Training W2V... WARNING: gensim word2vec version is unoptimizedTry version 3.6 if on windows, versions 3.7 and 3.8 have had issues
Done, T=0.38
[ 0.01669522 0.01119813 -0.00566072 -0.0134473 0.01121703 0.00379648
0.01170088 -0.0121789 -0.01429367 -0.00849178 0.00943886 -0.00981773
0.00337284 -0.0013884 -0.01287963 -0.00460479 -0.00217993 -0.01019352
0.00615602 -0.00658679 0.01679845 -0.00747446 0.0019177 -0.00912566
-0.01688758 0.00983168 0.00286994 0.00739604 0.01249113 0.00116864
0.00235101 -0.01515406 -0.00786685 -0.01675885 -0.01421799 -0.00829282
-0.00385966 -0.00779916 -0.00067812 0.01312324 0.0154448 -0.0107193
-0.00059914 -0.00439935 -0.01970238 -0.00585162 -0.01741348 -0.00118494
-0.01365886 -0.007099 0.00806013 -0.00448715 -0.00633816 -0.009869
0.01835089 0.01462685 0.00408294 0.01042183 0.00773886 0.00500051
0.00697436 -0.00052141 -0.00307364 0.00916708 -0.0059573 -0.00794462
0.00316458 -0.01120937 0.00820292 -0.00175512 -0.00426679 0.00403081
0.0036373 -0.00538955 0.00169757 -0.00476247 0.00011785 -0.00015604
-0.02005355 0.00293106 -0.00457922 0.01199162 -0.01039407 -0.00975906
-0.00386479 0.00380202 0.0150509 0.00117078 0.01009431 -0.01518334
-0.01550014 -0.00316153 -0.01638743 0.00911983 -0.00656796 -0.01130522
0.00696332 0.00222521 -0.01348531 0.01745371 -0.01043333 0.00377076
0.00168364 -0.01029514 -0.01187336 -0.00047892 0.01747731 0.01539742
-0.00317966 0.01036133 0.00348293 0.00357884 0.01691393 -0.01314759
-0.00387712 0.01349622 0.00886216 0.01269572 -0.014981 0.01047694
-0.01591979 0.00815849 0.0053769 -0.01705019 0.00478466 -0.00967307
0.00100743 -0.00627678]
[ 1.74459908e-02 9.29250382e-03 -5.62654436e-03 -1.58256646e-02
6.62352284e-03 -1.04596815e-03 7.46087125e-03 -1.52283600e-02
-1.47760203e-02 -4.99586575e-03 8.37715156e-03 -1.14215305e-02
8.03218782e-03 -4.57122130e-03 -1.37374401e-02 -6.70122309e-03
5.60258329e-03 -1.36625227e-02 2.69854977e-03 -2.01221928e-03
1.41100660e-02 -1.21530667e-02 7.38256099e-03 -7.29203923e-03
-1.45003749e-02 8.89602769e-03 -1.07536477e-03 1.66074419e-03
7.48369843e-03 8.18155764e-04 3.80413979e-03 -1.41491415e-02
-1.12004904e-03 -1.57257933e-02 -1.23076690e-02 -9.28518735e-03
-5.15399221e-03 -5.42826438e-03 9.19695070e-04 9.03129764e-03
1.57911442e-02 -5.36569115e-03 -1.36574614e-03 -2.82609137e-03
-1.89300030e-02 -5.67972986e-03 -1.65421404e-02 -3.22455773e-04
-1.18535999e-02 -7.90045224e-03 9.72144585e-03 -7.91174080e-03
-4.45207767e-03 -1.19799254e-02 1.93504207e-02 1.06750363e-02
4.26934101e-03 1.17199738e-02 6.25003641e-03 1.98470801e-03
4.88949660e-03 7.53012951e-04 -8.29974841e-03 6.85363356e-03
-2.72968784e-03 -5.58869634e-03 1.48452440e-04 -8.40961654e-03
3.35645187e-03 -3.52724968e-03 3.98239447e-03 -2.40911031e-03
4.06429684e-03 -3.92150227e-03 6.94983220e-03 -8.35845713e-03
9.88924527e-04 -1.79716619e-03 -1.90840866e-02 2.46768352e-03
-4.37452644e-03 1.30511560e-02 -6.40019309e-03 -1.33609995e-02
3.72520881e-04 5.42262476e-03 1.41993044e-02 7.35963322e-03
1.08134123e-02 -1.49347940e-02 -1.22990599e-02 -9.69778374e-03
-1.74602009e-02 8.74316972e-03 -5.31877764e-03 -7.91502465e-03
3.98375420e-03 4.59250668e-03 -1.26426788e-02 1.60577614e-02
-1.03733260e-02 4.70442930e-03 6.72380021e-03 -1.34339379e-02
-1.50517235e-02 3.45687894e-03 1.50700649e-02 1.58219878e-02
4.28991532e-03 9.33015719e-03 7.03065936e-03 3.41207208e-03
1.49237625e-02 -1.07398266e-02 -1.00340396e-02 9.12039913e-03
1.27081424e-02 1.08739929e-02 -1.16528282e-02 4.42440435e-03
-1.53663196e-02 3.64650693e-03 5.37529076e-03 -1.76296048e-02
3.67483153e-05 -7.88922701e-03 -5.40610822e-03 -1.80462585e-03]
Looking at the code, it seems to be related to the particular way the nodes are passed for prediction inside the fit_transform method in the node2vec implementation. Not sure why, but the predictions are performed using a np.arange. This range won't reflect the actual nodes in the graph, so an exception is raised.
The other embedders don't do that.
Still not working.
>pip show nodevectors
Name: nodevectors
Version: 0.1.23
Summary: Fast network node embeddings
Home-page: https://github.com/VHRanger/nodevectors/
Author: Matt Ranger
Author-email: UNKNOWN
License: MIT
Location: e:\users\user\miniconda3\envs\graph\lib\site-packages
Requires: scipy, networkx, csrgraph, gensim, pandas, numpy, scikit-learn, numba
Required-by:
>python
Python 3.7.9 (default, Aug 31 2020, 17:10:11) [MSC v.1916 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> from nodevectors import Node2Vec
>>> import networkx as nx
>>> G = nx.Graph()
>>> G.add_edge("1", "2")
>>> n2v = Node2Vec(n_components=128)
>>> n2v.fit_transform(G)
Making walks... Done, T=2.98
Mapping Walk Names... Done, T=0.04
Training W2V... Done, T=0.05
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "E:\Users\user\miniconda3\envs\graph\lib\site-packages\nodevectors\node2vec.py", line 155, in fit_transform
.apply(self.predict)
File "E:\Users\user\AppData\Roaming\Python\Python37\site-packages\pandas\core\series.py", line 3848, in apply
mapped = lib.map_infer(values, f, convert=convert_dtype)
File "pandas\_libs\lib.pyx", line 2329, in pandas._libs.lib.map_infer
File "E:\Users\user\miniconda3\envs\graph\lib\site-packages\nodevectors\node2vec.py", line 170, in predict
return self.model.wv.__getitem__(node_name)
File "E:\Users\user\miniconda3\envs\graph\lib\site-packages\gensim\models\keyedvectors.py", line 353, in __getitem__
return self.get_vector(entities)
File "E:\Users\user\miniconda3\envs\graph\lib\site-packages\gensim\models\keyedvectors.py", line 471, in get_vector
return self.word_vec(word)
File "E:\Users\user\miniconda3\envs\graph\lib\site-packages\gensim\models\keyedvectors.py", line 468, in word_vec
raise KeyError("word '%s' not in vocabulary" % word)
KeyError: "word '0' not in vocabulary"
I can see there is still a np.arrange being passed to the predict function.
