Skip to content

Commit

Permalink
Merge pull request #823 from dianna-ai/756-add-notebook-for-eulaw
Browse files Browse the repository at this point in the history 
add eulaw with lime notebook (refs #756)
  • Loading branch information
@elboyran
elboyran authored Oct 11, 2024
2 parents f3cda01 + e4980d8 commit 116ffeb
Show file tree
Hide file tree
Showing 6 changed files with 1,094 additions and 34 deletions.
23 changes: 12 additions & 11 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -200,7 +200,7 @@ Explore the explanations of your trained model using the DIANNA dashboard (for n
_Dianna dashboard screenshot here_
<!-- <a href="https://github.com/dianna-ai/dianna/tree/main/dianna/dashboard" target="_blank">
<img width="1000" align="center" alt="Dianna dashboard screenshot" src="https://raw.githubusercontent.com/dianna-ai/dianna/main/dianna/dashboard/dashboard-screenshot.png">
</a>
</a>
-->

## Datasets
Expand Down Expand Up @@ -260,9 +260,10 @@ And here are links to notebooks showing how we created our models on the benchma

### Text

| Models | Generation |
| :---------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [Movie reviews model](https://zenodo.org/record/5910598) | [Stanford sentiment treebank model generation](https://github.com/dianna-ai/dianna-exploration/blob/main/example_data/model_generation/movie_reviews/generate_model.ipynb) |
| Models | Generation |
|:---------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Movie reviews model](https://zenodo.org/record/5910598) | [Stanford sentiment treebank model generation](https://github.com/dianna-ai/dianna-exploration/blob/main/example_data/model_generation/movie_reviews/generate_model.ipynb) |
| [Regalatory statement classifier](https://zenodo.org/record/8200001) | [EU-law regulatory-statement-classification](https://github.com/nature-of-eu-rules/regulatory-statement-classification) |

### Time series

Expand Down Expand Up @@ -306,13 +307,13 @@ Also [GradCAM](https://openaccess.thecvf.com/content_ICCV_2017/papers/Selvaraju_
Our goal is that the scientific community embrases XAI as a source for novel and unexplored perspectives on scientific problems.
Here, we offer [tutorials](./tutorials) on specific scientific use-cases of uisng XAI:

| Use-case (data) \ XAI | [RISE](http://bmvc2018.org/contents/papers/1064.pdf) | [LIME](https://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf) | [KernelSHAP](https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf) |
| :----------------------------------------------------------------| :----------------------------------------------------| :---------------------------------------------------------------------| :-------------------------------------------------------------------------------------------------------|
| Biology (Phytomorphology): Tree Leaves classification (images) | | ✅ | |
| Astronomy: Fast Radio Burst detection (timeseries) | ✅ | | |
| Land-atmosphere modeling: Latent heat flux prediction (tabular) | | | ✅ |
| Social sciences (text) | work in progress | ... |... |
| Climate | planned | ... | ... |
| Use-case (data) \ XAI | [RISE](http://bmvc2018.org/contents/papers/1064.pdf) | [LIME](https://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf) | [KernelSHAP](https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf) |
|:-------------------------------------------------------------------|:-----------------------------------------------------| :---------------------------------------------------------------------| :-------------------------------------------------------------------------------------------------------|
| Biology (Phytomorphology): Tree Leaves classification (images) | | ✅ | |
| Astronomy: Fast Radio Burst detection (timeseries) | ✅ | | |
| Land-atmosphere modeling: Latent heat flux prediction (tabular) | | | ✅ |
| Social sciences: EU-law regulatory statement classification (text) | | ✅ | |
| Climate | planned | ... | ... |

## Reference documentation

Expand Down
4 changes: 4 additions & 0 deletions dianna/utils/downloader.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,10 @@
"doi:10.5281/zenodo.10656613/apertif_frb_dynamic_spectrum_model.onnx",
"sha256:3c87db3c6257d7f251a7bdceb3197d5bb482b8edc19870219fb7ca7c204dd257"
],
"inlegal_bert_xgboost_classifier.json": [
"doi:10.5281/zenodo.8200001/inlegal_bert_xgboost_classifier.json",
"68a672f29aac4a19c404c24f4c5da82a1ce7f704ccce701b0a1073c63730e127"
],
"stemmus_scope_emulator_model_LEtot.onnx": [
"doi:10.5281/zenodo.12623256/stemmus_scope_emulator_model_LEtot.onnx",
"sha256:8c8f34ad5a2c519b1f3c67a4eb0c645c96cac1de166277bfb24e7887c2ce83be"
Expand Down
3 changes: 3 additions & 0 deletions docs/tutorials/9-lime_text_eulaw.nblink
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{
"path": "../../tutorials/explainers/LIME/lime_text_eulaw.ipynb"
}
3 changes: 3 additions & 0 deletions setup.cfg
View file
Original file line number Diff line number Diff line change
Expand Up @@ -112,6 +112,9 @@ notebooks =
torch
torchvision
ipywidgets
freetype-py
transformers
xgboost

[options.entry_points]
console_scripts =
Expand Down
Loading

0 comments on commit 116ffeb

Please sign in to comment.