search

abess-team / skscope

skscope: Sparse-Constrained OPtimization via itErative-solvers
https://skscope.readthedocs.io
MIT License
315 stars 13 forks source link

[Feature] add CoxPH model #42

Closed chenpnn closed 1 year ago

codecov[bot] commented 1 year ago

Codecov Report

Patch coverage: 97.56% and project coverage change: +0.09% :tada:

Comparison is base (c43a359) 95.80% compared to head (6a02adb) 95.89%. Report is 24 commits behind head on master.

Additional details and impacted files ```diff @@ Coverage Diff @@ ## master #42 +/- ## ========================================== + Coverage 95.80% 95.89% +0.09% ========================================== Files 17 17 Lines 1861 1902 +41 Branches 653 653 ========================================== + Hits 1783 1824 +41 Misses 48 48 Partials 30 30 ``` | [Files Changed](https://app.codecov.io/gh/abess-team/skscope/pull/42?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=abess-team) | Coverage Δ | | |---|---|---| | [skscope/skmodel.py](https://app.codecov.io/gh/abess-team/skscope/pull/42?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=abess-team#diff-c2tzY29wZS9za21vZGVsLnB5) | `95.45% <97.56%> (+0.55%)` | :arrow_up: | ... and [1 file with indirect coverage changes](https://app.codecov.io/gh/abess-team/skscope/pull/42/indirect-changes?src=pr&el=tree-more&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=abess-team)

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

Mamba413 commented 1 year ago

@chenpnn Please do not import scikit-survival. In my opinion, it is hard to install this library via github action.

Mamba413 commented 1 year ago

@chenpnn ，by the way, does it multivariate failure time model or just simple cox model?

chenpnn commented 1 year ago

@chenpnn ，by the way, does it multivariate failure time model or just simple cox model?

It is just a simple cox model with scikit-survival type method and data-type.

chenpnn commented 1 year ago

@chenpnn Please do not import scikit-survival. In my opinion, it is hard to install this library via github action.

Shall we rewrite the corresponding functions which we imported from scikit-survival?

Mamba413 commented 1 year ago

@chenpnn 1. Implementing the Cox model has no gain because it is already implemented in abess. 2. Maybe you can directly use their implementation. BTW, does scikit-survival support the multivariate failure time model?