search

scikit-learn-contrib / boruta_py

Python implementations of the Boruta all-relevant feature selection method.
BSD 3-Clause "New" or "Revised" License
1.46k stars 252 forks source link

visualization - box plot like R-Cran package #89

Open bhaskatripathi opened 3 years ago

bhaskatripathi commented 3 years ago

Hi, I just wanted to check if there is a way to see the visualization of box-plot and Z-importance scores like R-CRAN package https://www.analyticsvidhya.com/blog/2016/03/select-important-variables-boruta-package/

ThomasBury commented 3 years ago

Hi, I just wanted to check if there is a way to see the visualization of box-plot and Z-importance scores like R-CRAN package https://www.analyticsvidhya.com/blog/2016/03/select-important-variables-boruta-package/

Hi, not currently in Boruta_Py. You can check https://github.com/Ekeany/Boruta-Shap or https://github.com/ThomasBury/arfs

tjhallum commented 3 years ago

I love @bhaskatripathi's suggestion for a box-plot visualization and Z-importance scores like the R-CRAN package.

I originally used R's Boruta package with great success - largely due to the easily interpretable visualization and Z-importance scores.

So, when my professional projects took me toward Python, I naturally sought out a Python Boruta implementation...however, absent the visualization and Z-importance scores...I find the utility of this Python implementation to be lacking compared to what I was accustomed to with the R implementation.

Would love to see a box-plot visualization and Z-importance scores added in future versions of this package.

Thank you!!!

ThomasBury commented 2 years ago

Hi, I just wanted to check if there is a way to see the visualization of box-plot and Z-importance scores like R-CRAN package https://www.analyticsvidhya.com/blog/2016/03/select-important-variables-boruta-package/

Hi, not currently in Boruta_Py. You can check https://github.com/Ekeany/Boruta-Shap or https://github.com/ThomasBury/arfs

In addition to the two above packages, there is a PR with (among others) this implemented: https://github.com/scikit-learn-contrib/boruta_py/pull/100