Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Optimizer classification grid search in tree slicer #1758

Merged
merged 9 commits into from
Feb 5, 2024

Conversation

luca-rossi
Copy link
Contributor

…lytics

Description

Related Issue

Type of Change

  • 📚 Examples / docs / tutorials / dependencies update
  • 🔧 Bug fix (non-breaking change which fixes an issue)
  • 🥂 Improvement (non-breaking change which improves an existing feature)
  • 🚀 New feature (non-breaking change which adds functionality)
  • 💥 Breaking change (fix or feature that would cause existing functionality to change)
  • 🔐 Security fix

Checklist

  • I've read the CODE_OF_CONDUCT.md document.
  • I've read the CONTRIBUTING.md guide.
  • I've updated the code style using make codestyle.
  • I've written tests for all new methods and classes that I created.
  • I've written the docstring in Google format for all the methods and classes that I used.

Copy link

linear bot commented Jan 22, 2024

@mattbit
Copy link
Member

mattbit commented Jan 26, 2024

Values of Gini impurity reported by @luca-rossi by experimenting on 25 different models/datasets:

Min: 0.13991769547325106, Max: 0.6429414741103052, Mode: %s Classification
Min: 0.42965154503616043, Max: 0.6427296171394565, Mode: %s Classification
Min: 0.19451530612244894, Max: 0.602788279773157, Mode: %s Classification
Min: 0.19132653061224492, Max: 0.6244444444444445, Mode: %s Classification
Min: 0.30583900226757366, Max: 0.6261111111111111, Mode: %s Classification
Min: 0.24058810425484523, Max: 0.6131656804733727, Mode: %s Classification
Min: 0.5181402848696587, Max: 0.6404081632653061, Mode: %s Classification
Min: 0.08317580340264652, Max: 0.6397334443981675, Mode: %s Classification
Min: 0.08317580340264652, Max: 0.6294444444444445, Mode: %s Classification
Min: 0.25566106647187725, Max: 0.6416831032215647, Mode: %s Classification
Min: 0.11072664359861595, Max: 0.6127777777777778, Mode: %s Classification
Min: 0.09280190362879237, Max: 0.5509259259259259, Mode: %s Classification
Min: 0.3835616438356164, Max: 0.6309233229526134, Mode: %s Classification
Min: 0.353185595567867, Max: 0.5996430696014277, Mode: %s Classification
Min: 0.27055150884495316, Max: 0.6038062283737025, Mode: %s Classification
Min: 0.4377777777777778, Max: 0.5553633217993079, Mode: %s Classification
Min: 0.4881299458558934, Max: 0.6643598615916955, Mode: %s Classification
Min: 0.5639500297441999, Max: 0.6663648709823449, Mode: %s Classification
Min: 0.05551020408163265, Max: 0.6137543252595156, Mode: %s Classification
Min: 0.29714285714285715, Max: 0.5887573964497042, Mode: %s Classification
Min: 0.49020408163265305, Max: 0.66219723183391, Mode: %s Classification
Min: 0.060546875, Max: 0.6385041551246537, Mode: %s Classification
Min: 0.5289256198347108, Max: 0.6659729448491155, Mode: %s Classification
Min: 0.3949652777777778, Max: 0.5, Mode: %s Classification
Min: 0.36815193571950333, Max: 0.5, Mode: %s Classification
Min: 0.43827611395178967, Max: 0.5, Mode: %s Classification
Min: 0.4054820415879017, Max: 0.49991566874683757, Mode: %s Classification
Min: 0.0, Max: 0.12444444444444447, Mode: %s Classification
Min: 0.13991769547325106, Max: 0.6377777777777778, Mode: %s Classification
Min: 0.1721536351165981, Max: 0.6116071428571428, Mode: %s Classification
Min: 0.257201646090535, Max: 0.65087890625, Mode: %s Classification
Min: 0.13991769547325106, Max: 0.6385041551246537, Mode: %s Classification
Min: 0.12192816635160686, Max: 0.6259040105193951, Mode: %s Classification
Min: 0.1472, Max: 0.6029877772747849, Mode: %s Classification
Min: 0.18000000000000005, Max: 0.6247165532879819, Mode: %s Classification
Min: 0.3077500469131169, Max: 0.625, Mode: %s Classification
Min: 0.45369406867845996, Max: 0.6660494015580857, Mode: %s Classification
Min: 0.5573169789189902, Max: 0.6458768123557999, Mode: %s Classification
Min: 0.1022644265887509, Max: 0.5, Mode: %s Classification
Min: 0.14201183431952658, Max: 0.4921875, Mode: %s Classification
Min: 0.32498740236835477, Max: 0.6145404663923182, Mode: %s Classification
Min: 0.3673094582185491, Max: 0.5, Mode: %s Classification
Min: 0.3161865569272977, Max: 0.6432291666666667, Mode: %s Classification
Min: 0.22646604938271608, Max: 0.5707649876614893, Mode: %s Classification

giskard/slicing/tree_slicer.py Outdated Show resolved Hide resolved
giskard/datasets/metadata/text_metadata_provider.py Outdated Show resolved Hide resolved
giskard/slicing/tree_slicer.py Outdated Show resolved Hide resolved
giskard/slicing/tree_slicer.py Outdated Show resolved Hide resolved
giskard/slicing/tree_slicer.py Outdated Show resolved Hide resolved
giskard/slicing/tree_slicer.py Outdated Show resolved Hide resolved
Copy link

sonarcloud bot commented Feb 5, 2024

@mattbit mattbit merged commit 0eab2fa into main Feb 5, 2024
16 of 17 checks passed
@mattbit mattbit deleted the bug/GSK-2554-slow-spurious-correlation-detector branch February 5, 2024 10:28
@mattbit mattbit changed the title Slicer: remove classification grid search, simplify metadata, add ana… Optimizer classification grid search in tree slicer Feb 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants