Support StellarGraph input and output in EdgeSplitter

[huonw]

This adjust the stellargraph.data.EdgeSplitter class so that it can consume and emit a StellarGraph object: if it is constructed like EdgeSplitter(some_stellargraph), then train_test_split will return a StellarGraph object. For backwards-compatibility, EdgeSplitter(some_networkx) still works, and returns a NetworkX object; that is, existing code will not be affected.

For now, this compatibility is useful even just for our own code as there's still quite a few of our demos that would require a lot more code to switch to use this new form, and so I have not switched them here:

• demos/link-prediction/gcn/cora-gcn-links-example.ipynb, demos/link-prediction/graphsage/cora-links-example.ipynb: unlike other demos that use the Cora dataset, these use the subject as a feature (rather than as a target), and so the graph returned by Cora().load() can't be used directly (New StellarGraph: remove use of networkx from Cora link prediction examples #1039)
• demos/link-prediction/random-walks/main.py, demos/link-prediction/random-walks-cora-lp-demo.ipynb: these seem to have their own implementation of node2vec and metapath2vec built on top of NetworkX and so aren't using StellarGraph objects anyway (or, it seems, anything from the stellargraph library other than EdgeSplitter) (related to Update demos/link-prediction/random-walks/main.py to use new datasets module #810, Demo directory for link prediction via random walks contains a very large amount of code #896 and Create a demo notebook to replace script for random walk link prediction #934)

However, some notebooks can be updated without too much code, in particular demos/calibration/calibration-pubmed-link-prediction.ipynb and demos/ensembles/ensemble-link-prediction-example.ipynb can move over to using Cora().load() (per #812 and #717) by passing the returned StellarGraph object directly into EdgeSplitter, with not many other code changes required.

See: #174

[review-notebook-app]

Check out this pull request on 

You'll be able to see Jupyter notebook diff and discuss changes. Powered by ReviewNB.

[codeclimate]

Code Climate has analyzed commit a4b3cd2 and detected 0 issues on this pull request.

View more on Code Climate.

[stellar-graph-bot]

Codecov Report

Merging #1032 into develop will decrease coverage by 0.4%.
The diff coverage is 100.0%.

@@            Coverage Diff            @@
##           develop   #1032     +/-   ##
=========================================
- Coverage     85.6%   85.1%   -0.4%     
=========================================
  Files           53      53             
  Lines         5552    5375    -177     
=========================================
- Hits          4751    4576    -175     
+ Misses         801     799      -2     

Impacted Files	Coverage Δ
stellargraph/core/graph.py	99.0% <0.0%> (-0.6%)	⬇️
stellargraph/data/edge_splitter.py	90.7% <0.0%> (+1.1%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ecd38f9...a4b3cd2. Read the comment docs.

[codecov-io]

Codecov Report

Merging #1032 into develop will decrease coverage by 0.4%.
The diff coverage is 100.0%.

@@            Coverage Diff            @@
##           develop   #1032     +/-   ##
=========================================
- Coverage     85.6%   85.1%   -0.4%     
=========================================
  Files           53      53             
  Lines         5552    5375    -177     
=========================================
- Hits          4751    4576    -175     
+ Misses         801     799      -2     

Impacted Files	Coverage Δ
stellargraph/core/graph.py	99.0% <0.0%> (-0.6%)	⬇️
stellargraph/data/edge_splitter.py	90.7% <0.0%> (+1.1%)	⬆️

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ecd38f9...a4b3cd2. Read the comment docs.

[PantelisElinas]

Hi,

this looks good. There is only one update necessary for the ensemble link prediction demo. This is a pre-existing error that can be easily fixed.

When calling model.compile(...) please change weighted_metrics=["acc"] to metrics=["acc"] and then when calling model.fit_generator(...) please change early_stopping_monitor="val_weighted_acc" to early_stopping_monitor="val_acc".

The above will remove the tensorflow warning, WARNING:tensorflow:Early stopping conditioned on metric val_weighted_acc which is not available. Available metrics are: loss,acc,val_loss,val_acc that the call to fit_generator outputs. Our generators do not output sample weights and the call to fit_generator does not specify class_weight so weighted metrics are not available. It looks like this was an error in the original notebook. We can fix it as part of this pull request or have it as a separate ticket if you prefer.

P.

[huonw]

That sort of work is definitely appropriate for a separate ticket. In that particular case, it's #933, which is fixed in #1008.