Create link prediction scoring funcs utility file

monarch-initiative / embiggen

🍇 Embiggen is the Python Graph Representation learning, Prediction and Evaluation submodule of the GRAPE library.

BSD 3-Clause "New" or "Revised" License

39 stars 12 forks source link

Create link prediction scoring funcs utility file #106

Closed callahantiff closed 4 years ago

callahantiff commented 4 years ago

Creating this issue as part of the conversation in #105.

TODO - Add Link Prediction Scoring functions to Utility Script

[x] Common Neighbors
[x] Jaccard’s Coefficient
[x] Adamic-Adar
[x] Preferential Attachment
[ ] See here for additional scoring functions worth considering, including:
- Degree Product
- Sorenson Similarity
- Leicht-Holme-Newman Similarity
- Shortest Path
- Resource Allocation
- Katz
- SimRank
- Rooted Page Rank

@vidarmehr - Does that cover everything?

vidarmehr commented 4 years ago

@callahantiff Yes. Thank you, Tiffany!

vidarmehr commented 4 years ago

@vidarmehr I will work on this over the weekend.

vidarmehr commented 4 years ago

@callahantiff I have created the branch "linkprediction_functions" in which I have implemented Degree Product score, Jaccard's score, Adamic adar's index and Common Neighbors's score in link_prediction_functions.py. I am going to add more unittests in test_link_prediction_functions.py, make a pull request and ask you to review the code. Thanks.

callahantiff commented 4 years ago

@callahantiff I have created the branch "linkprediction_functions" in which I have implemented Degree Product score, Jaccard's score, Adamic adar's index and Common Neighbors's score in link_prediction_functions.py. I am going to add more unittests in test_link_prediction_functions.py, make a pull request and ask you to review the code. Thanks.

Awesome @vidarmehr, that sounds fantastic!

vidarmehr commented 4 years ago

Degree Product score, Jaccard's score, Adamic adar's index and Common Neighbors's score were implemented in the linkprediction_functionions branch which was merged to develop. So, I close this issue.