Generic explainability architecture for text machine learning models
Project description
Text Explainability
A generic explainability architecture for explaining text machine learning models.
Marcel Robeer, 2021
Installation
Install from PyPI via pip3 install text_explainability
. Alternatively, clone this repository and install via pip3 install -e .
or locally run python3 setup.py install
.
Example usage
Run lines in example_usage.py
to see an example of how the package can be used.
Maintenance
Contributors
- Marcel Robeer (
@m.j.robeer
) - Michiel Bron (
@mpbron-phd
)
Todo
Tasks yet to be done:
- Add data sampling methods (e.g. representative subset, prototypes, MMD-critic)
- Implement local post-hoc explanations:
- Implement Anchors
- Implement Foil Trees + ability to turn any output into a binary classification problem (fact-foil encodings)
- Implement global post-hoc explanations
- Add support for regression models
- More complex data augmentation
- Top-k replacement (e.g. according to LM / WordNet)
- Tokens to exclude from being changed
- Bag-of-words style replacements
- Add rule-based return type
- Write more tests
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
text_explainability-0.3.1.tar.gz
(17.3 kB
view hashes)
Built Distributions
Close
Hashes for text_explainability-0.3.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 126f7fcb35afdf025beba033c9673ea4de7e85f6b76429bdb93f021637b987ed |
|
MD5 | bcfa9641983367f1a6776b65db843b31 |
|
BLAKE2b-256 | cb1e9428c06bb01e54ef16c6718d8e2ce9daa41d423fd47af4614892f58928fb |
Close
Hashes for text_explainability-0.3.1-py3.9.egg
Algorithm | Hash digest | |
---|---|---|
SHA256 | f97f5f4b84a7035cf3b089e6d16605ec3414e6695d6984270929018f648b82f9 |
|
MD5 | e047dd918fcfe86beb24f477d315cdc7 |
|
BLAKE2b-256 | 6fac73d5da2455b2a565d0285a761dad87ba0cb9aa352ad3ee90892f404a40f2 |
Close
Hashes for text_explainability-0.3.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3a26a21156dc0a192849ea5dfa06d49814b8d08b71a9a31f47ca8acebe15577f |
|
MD5 | 0a474162409b53be0e5c31054c378d2d |
|
BLAKE2b-256 | 3c13aafcb513bd0c95b65bf787f9a2fb1a33dfb73463c17eca863af48e9674d4 |