Bugfix: use subjects.index to generate node embeddings #1665
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In the demo notebook
demos/embeddings/keras-node2vec-embeddings.ipynb
,demos/node-classification/attri2vec-node-classification.ipynb
,demos/node-classification/keras-node2vec-node-classification.ipynb
, node embeddings are generated by passingG.nodes()
into the node generator. For example, indemos/embeddings/keras-node2vec-embeddings.ipynb
, node embeddings are generated asnode_gen = Node2VecNodeGenerator(G, batch_size).flow(G.nodes())
node_embeddings = embedding_model.predict(node_gen, workers=4, verbose=1)
Though the order of
G.nodes()
is consistent withsubjects
, it is more desirable to usesubjects.index
to generate node embeddings to avoid confusing readers.In this pull request, I replace the
G.nodes()
withsubjects.index
in the above three demo notebooks.