Gru4rec

[xiaofeifei1800]

Implement GRU4REC model following by 'Session-based Recommendations with Recurrent Neural Networks'. Test the model performance against MovieLen 1M, achieve recall@50 = 0.19 (the test script is in ./examples/run_gru4rec.py).

[codecov[bot]]

Codecov Report

Merging #26 (c2feb6a) into master (6b059ca) will decrease coverage by 8.22%. The diff coverage is 0.00%.

:exclamation: Current head c2feb6a differs from pull request most recent head c227b95. Consider uploading reports for the commit c227b95 to get more accurate results

@@            Coverage Diff             @@
##           master      #26      +/-   ##
==========================================
- Coverage   88.35%   80.12%   -8.23%     
==========================================
  Files          11       12       +1     
  Lines         747      780      +33     
==========================================
- Hits          660      625      -35     
- Misses         87      155      +68     

Flag	Coverage Δ
pytest	80.12% <0.00%> (-8.23%)	:arrow_down:

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
deepmatch/models/gru4rec.py	0.00% <0.00%> (ø)
deepmatch/models/ncf.py	15.38% <0.00%> (-84.62%)	:arrow_down:
deepmatch/layers/core.py	88.23% <0.00%> (-0.16%)	:arrow_down:
deepmatch/inputs.py	88.23% <0.00%> (ø)
deepmatch/models/fm.py	100.00% <0.00%> (ø)
deepmatch/models/sdm.py	95.94% <0.00%> (ø)
deepmatch/models/dssm.py	100.00% <0.00%> (ø)
deepmatch/models/mind.py	92.75% <0.00%> (ø)
deepmatch/layers/__init__.py	100.00% <0.00%> (ø)
deepmatch/models/youtubednn.py	96.87% <0.00%> (ø)
... and 1 more

---

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 106bb4e...c227b95. Read the comment docs.