diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-text-explainability.spec | 342 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 344 insertions, 0 deletions
@@ -0,0 +1 @@ +/text_explainability-0.7.0.tar.gz diff --git a/python-text-explainability.spec b/python-text-explainability.spec new file mode 100644 index 0000000..7f07b3c --- /dev/null +++ b/python-text-explainability.spec @@ -0,0 +1,342 @@ +%global _empty_manifest_terminate_build 0 +Name: python-text-explainability +Version: 0.7.0 +Release: 1 +Summary: Generic explainability architecture for text machine learning models +License: GNU LGPL v3 +URL: https://text-explainability.readthedocs.io/ +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/a7/ec/731e27ff33b8ab47144b59300ce151a496151f4bb6c98ac55286b3ef24fc/text_explainability-0.7.0.tar.gz +BuildArch: noarch + +Requires: python3-instancelib +Requires: python3-genbase +Requires: python3-scikit-learn +Requires: python3-plotly +Requires: python3-sentence-transformers +Requires: python3-scikit-learn-extra +Requires: python3-imodels +Requires: python3-genbase-test-helpers +Requires: python3-fastcountvectorizer + +%description +`text_explainability` provides a **generic architecture** from which well-known state-of-the-art explainability approaches for text can be composed. This modular architecture allows components to be swapped out and combined, to **quickly develop new types of explainability approaches** for (natural language) text, or to **improve a plethora of approaches by improving a single module**. +Several example methods are included, which provide **local explanations** (_explaining the prediction of a single instance_, e.g. `LIME` and `SHAP`) or **global explanations** (_explaining the dataset, or model behavior on the dataset_, e.g. `TokenFrequency` and `MMDCritic`). By replacing the default modules (e.g. local data generation, global data sampling or improved embedding methods), these methods can be improved upon or new methods can be introduced. +© Marcel Robeer, 2021 +## Quick tour +**Local explanation**: explain a models' prediction on a given sample, self-provided or from a dataset. +```python +from text_explainability import LIME, LocalTree +# Define sample to explain +sample = 'Explain why this is positive and not negative!' +# LIME explanation (local feature importance) +LIME().explain(sample, model).scores +# List of local rules, extracted from tree +LocalTree().explain(sample, model).rules +``` +**Global explanation**: explain the whole dataset (e.g. train set, test set), and what they look like for the ground-truth or predicted labels. +```python +from text_explainability import import_data, TokenFrequency, MMDCritic +# Import dataset +env = import_data('./datasets/test.csv', data_cols=['fulltext'], label_cols=['label']) +# Top-k most frequent tokens per label +TokenFrequency(env.dataset).explain(labelprovider=env.labels, explain_model=False, k=3) +# 2 prototypes and 1 criticisms for the dataset +MMDCritic(env.dataset)(n_prototypes=2, n_criticisms=1) +``` +## Installation +See the [installation](docs/INSTALLATION.md) instructions for an extended installation guide. +| Method | Instructions | +|--------|--------------| +| `pip` | Install from [PyPI](https://pypi.org/project/text-explainability/) via `pip3 install text_explainability`. To speed up the explanation generation process use `pip3 install text_explainability[fast]`. | +| Local | Clone this repository and install via `pip3 install -e .` or locally run `python3 setup.py install`. +## Documentation +Full documentation of the latest version is provided at [https://text-explainability.readthedocs.io/](https://text-explainability.readthedocs.io/). +## Example usage +See [example usage](example_usage.md) to see an example of how the package can be used, or run the lines in `example_usage.py` to do explore it interactively. +## Explanation methods included +`text_explainability` includes methods for model-agnostic _local explanation_ and _global explanation_. Each of these methods can be fully customized to fit the explainees' needs. +| Type | Explanation method | Description | Paper/link | +|------|--------------------|-------------|-------| +| *Local explanation* | `LIME` | Calculate feature attribution with _Local Intepretable Model-Agnostic Explanations_ (LIME). | [[Ribeiro2016](https://paperswithcode.com/method/lime)], [interpretable-ml/lime](https://christophm.github.io/interpretable-ml-book/lime.html) | +| | `KernelSHAP` | Calculate feature attribution with _Shapley Additive Explanations_ (SHAP). | [[Lundberg2017](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model)], [interpretable-ml/shap](https://christophm.github.io/interpretable-ml-book/shap.html) | +| | `LocalTree` | Fit a local decision tree around a single decision. | [[Guidotti2018](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)] | +| | `LocalRules` | Fit a local sparse set of label-specific rules using `SkopeRules`. | [github/skope-rules](https://github.com/scikit-learn-contrib/skope-rules) | +| | `FoilTree` | Fit a local contrastive/counterfactual decision tree around a single decision. | [[Robeer2018](https://github.com/MarcelRobeer/ContrastiveExplanation)] | +| | `BayLIME` | Bayesian extension of LIME for include prior knowledge and more consistent explanations. | [[Zhao201](https://paperswithcode.com/paper/baylime-bayesian-local-interpretable-model)] | +| *Global explanation* | `TokenFrequency` | Show the top-_k_ number of tokens for each ground-truth or predicted label. | +| | `TokenInformation` | Show the top-_k_ token mutual information for a dataset or model. | [wikipedia/mutual_information](https://en.wikipedia.org/wiki/Mutual_information) | +| | `KMedoids` | Embed instances and find top-_n_ prototypes (can also be performed for each label using `LabelwiseKMedoids`). | [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +| | `MMDCritic` | Embed instances and find top-_n_ prototypes and top-_n_ criticisms (can also be performed for each label using `LabelwiseMMDCritic`). | [[Kim2016](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html)], [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +## Releases +`text_explainability` is officially released through [PyPI](https://pypi.org/project/text-explainability/). +See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version. +## Extensions +<a href="https://marcelrobeer.github.io/text_sensitivity/" target="_blank"><img src="https://git.science.uu.nl/m.j.robeer/text_sensitivity/-/raw/main/img/TextLogo-Logo_large_sensitivity.png" alt="T_xt sensitivity logo" width="200px"></a><p>`text_explainability` can be extended to also perform _sensitivity testing_, checking for machine learning model robustness and fairness. The `text_sensitivity` package is available through [PyPI](https://pypi.org/project/text-sensitivity/) and fully documented at [https://text-sensitivity.rtfd.io/](https://text-sensitivity.rtfd.io/).</p> +## Citation +```bibtex +@misc{text_explainability, + title = {Python package text\_explainability}, + author = {Marcel Robeer}, + howpublished = {\url{https://git.science.uu.nl/m.j.robeer/text_explainability}}, + year = {2021} +} +``` +## Maintenance +### Contributors +- [Marcel Robeer](https://www.uu.nl/staff/MJRobeer) (`@m.j.robeer`) +- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron-phd`) +### Todo +Tasks yet to be done: +* Implement local post-hoc explanations: + - Implement Anchors +* Implement global post-hoc explanations: + - Representative subset +* 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 +## Credits +- Florian Gardin, Ronan Gautier, Nicolas Goix, Bibi Ndiaye and Jean-Matthieu Schertzer. _[Skope-rules](https://github.com/scikit-learn-contrib/skope-rules)_. 2020. +- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini and Fosca Gianotti. _[Local Rule-Based Explanations of Black Box Decision Systems](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)_. 2018. +- Been Kim, Rajiv Khanna and Oluwasanmi O. Koyejo. [Examples are not Enough, Learn to Criticize! Criticism for Interpretability](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html). _Advances in Neural Information Processing Systems (NIPS 2016)_. 2016. +- Scott Lundberg and Su-In Lee. [A Unified Approach to Interpreting Model Predictions](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model). _31st Conference on Neural Information Processing Systems (NIPS 2017)_. 2017. +- Christoph Molnar. _[Interpretable Machine Learning: A Guide for Making Black Box Models Explainable](https://christophm.github.io/interpretable-ml-book/)_. 2021. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://paperswithcode.com/method/lime). _Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2016)_. 2016. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. [Anchors: High-Precision Model-Agnostic Explanations](https://github.com/marcotcr/anchor). _AAAI Conference on Artificial Intelligence (AAAI)_. 2018. +- Jasper van der Waa, Marcel Robeer, Jurriaan van Diggelen, Matthieu Brinkhuis and Mark Neerincx. ["Contrastive Explanations with Local Foil Trees"](https://github.com/MarcelRobeer/ContrastiveExplanation). _2018 Workshop on Human Interpretability in Machine Learning (WHI 2018)_. 2018. + +%package -n python3-text-explainability +Summary: Generic explainability architecture for text machine learning models +Provides: python-text-explainability +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-text-explainability +`text_explainability` provides a **generic architecture** from which well-known state-of-the-art explainability approaches for text can be composed. This modular architecture allows components to be swapped out and combined, to **quickly develop new types of explainability approaches** for (natural language) text, or to **improve a plethora of approaches by improving a single module**. +Several example methods are included, which provide **local explanations** (_explaining the prediction of a single instance_, e.g. `LIME` and `SHAP`) or **global explanations** (_explaining the dataset, or model behavior on the dataset_, e.g. `TokenFrequency` and `MMDCritic`). By replacing the default modules (e.g. local data generation, global data sampling or improved embedding methods), these methods can be improved upon or new methods can be introduced. +© Marcel Robeer, 2021 +## Quick tour +**Local explanation**: explain a models' prediction on a given sample, self-provided or from a dataset. +```python +from text_explainability import LIME, LocalTree +# Define sample to explain +sample = 'Explain why this is positive and not negative!' +# LIME explanation (local feature importance) +LIME().explain(sample, model).scores +# List of local rules, extracted from tree +LocalTree().explain(sample, model).rules +``` +**Global explanation**: explain the whole dataset (e.g. train set, test set), and what they look like for the ground-truth or predicted labels. +```python +from text_explainability import import_data, TokenFrequency, MMDCritic +# Import dataset +env = import_data('./datasets/test.csv', data_cols=['fulltext'], label_cols=['label']) +# Top-k most frequent tokens per label +TokenFrequency(env.dataset).explain(labelprovider=env.labels, explain_model=False, k=3) +# 2 prototypes and 1 criticisms for the dataset +MMDCritic(env.dataset)(n_prototypes=2, n_criticisms=1) +``` +## Installation +See the [installation](docs/INSTALLATION.md) instructions for an extended installation guide. +| Method | Instructions | +|--------|--------------| +| `pip` | Install from [PyPI](https://pypi.org/project/text-explainability/) via `pip3 install text_explainability`. To speed up the explanation generation process use `pip3 install text_explainability[fast]`. | +| Local | Clone this repository and install via `pip3 install -e .` or locally run `python3 setup.py install`. +## Documentation +Full documentation of the latest version is provided at [https://text-explainability.readthedocs.io/](https://text-explainability.readthedocs.io/). +## Example usage +See [example usage](example_usage.md) to see an example of how the package can be used, or run the lines in `example_usage.py` to do explore it interactively. +## Explanation methods included +`text_explainability` includes methods for model-agnostic _local explanation_ and _global explanation_. Each of these methods can be fully customized to fit the explainees' needs. +| Type | Explanation method | Description | Paper/link | +|------|--------------------|-------------|-------| +| *Local explanation* | `LIME` | Calculate feature attribution with _Local Intepretable Model-Agnostic Explanations_ (LIME). | [[Ribeiro2016](https://paperswithcode.com/method/lime)], [interpretable-ml/lime](https://christophm.github.io/interpretable-ml-book/lime.html) | +| | `KernelSHAP` | Calculate feature attribution with _Shapley Additive Explanations_ (SHAP). | [[Lundberg2017](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model)], [interpretable-ml/shap](https://christophm.github.io/interpretable-ml-book/shap.html) | +| | `LocalTree` | Fit a local decision tree around a single decision. | [[Guidotti2018](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)] | +| | `LocalRules` | Fit a local sparse set of label-specific rules using `SkopeRules`. | [github/skope-rules](https://github.com/scikit-learn-contrib/skope-rules) | +| | `FoilTree` | Fit a local contrastive/counterfactual decision tree around a single decision. | [[Robeer2018](https://github.com/MarcelRobeer/ContrastiveExplanation)] | +| | `BayLIME` | Bayesian extension of LIME for include prior knowledge and more consistent explanations. | [[Zhao201](https://paperswithcode.com/paper/baylime-bayesian-local-interpretable-model)] | +| *Global explanation* | `TokenFrequency` | Show the top-_k_ number of tokens for each ground-truth or predicted label. | +| | `TokenInformation` | Show the top-_k_ token mutual information for a dataset or model. | [wikipedia/mutual_information](https://en.wikipedia.org/wiki/Mutual_information) | +| | `KMedoids` | Embed instances and find top-_n_ prototypes (can also be performed for each label using `LabelwiseKMedoids`). | [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +| | `MMDCritic` | Embed instances and find top-_n_ prototypes and top-_n_ criticisms (can also be performed for each label using `LabelwiseMMDCritic`). | [[Kim2016](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html)], [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +## Releases +`text_explainability` is officially released through [PyPI](https://pypi.org/project/text-explainability/). +See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version. +## Extensions +<a href="https://marcelrobeer.github.io/text_sensitivity/" target="_blank"><img src="https://git.science.uu.nl/m.j.robeer/text_sensitivity/-/raw/main/img/TextLogo-Logo_large_sensitivity.png" alt="T_xt sensitivity logo" width="200px"></a><p>`text_explainability` can be extended to also perform _sensitivity testing_, checking for machine learning model robustness and fairness. The `text_sensitivity` package is available through [PyPI](https://pypi.org/project/text-sensitivity/) and fully documented at [https://text-sensitivity.rtfd.io/](https://text-sensitivity.rtfd.io/).</p> +## Citation +```bibtex +@misc{text_explainability, + title = {Python package text\_explainability}, + author = {Marcel Robeer}, + howpublished = {\url{https://git.science.uu.nl/m.j.robeer/text_explainability}}, + year = {2021} +} +``` +## Maintenance +### Contributors +- [Marcel Robeer](https://www.uu.nl/staff/MJRobeer) (`@m.j.robeer`) +- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron-phd`) +### Todo +Tasks yet to be done: +* Implement local post-hoc explanations: + - Implement Anchors +* Implement global post-hoc explanations: + - Representative subset +* 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 +## Credits +- Florian Gardin, Ronan Gautier, Nicolas Goix, Bibi Ndiaye and Jean-Matthieu Schertzer. _[Skope-rules](https://github.com/scikit-learn-contrib/skope-rules)_. 2020. +- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini and Fosca Gianotti. _[Local Rule-Based Explanations of Black Box Decision Systems](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)_. 2018. +- Been Kim, Rajiv Khanna and Oluwasanmi O. Koyejo. [Examples are not Enough, Learn to Criticize! Criticism for Interpretability](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html). _Advances in Neural Information Processing Systems (NIPS 2016)_. 2016. +- Scott Lundberg and Su-In Lee. [A Unified Approach to Interpreting Model Predictions](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model). _31st Conference on Neural Information Processing Systems (NIPS 2017)_. 2017. +- Christoph Molnar. _[Interpretable Machine Learning: A Guide for Making Black Box Models Explainable](https://christophm.github.io/interpretable-ml-book/)_. 2021. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://paperswithcode.com/method/lime). _Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2016)_. 2016. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. [Anchors: High-Precision Model-Agnostic Explanations](https://github.com/marcotcr/anchor). _AAAI Conference on Artificial Intelligence (AAAI)_. 2018. +- Jasper van der Waa, Marcel Robeer, Jurriaan van Diggelen, Matthieu Brinkhuis and Mark Neerincx. ["Contrastive Explanations with Local Foil Trees"](https://github.com/MarcelRobeer/ContrastiveExplanation). _2018 Workshop on Human Interpretability in Machine Learning (WHI 2018)_. 2018. + +%package help +Summary: Development documents and examples for text-explainability +Provides: python3-text-explainability-doc +%description help +`text_explainability` provides a **generic architecture** from which well-known state-of-the-art explainability approaches for text can be composed. This modular architecture allows components to be swapped out and combined, to **quickly develop new types of explainability approaches** for (natural language) text, or to **improve a plethora of approaches by improving a single module**. +Several example methods are included, which provide **local explanations** (_explaining the prediction of a single instance_, e.g. `LIME` and `SHAP`) or **global explanations** (_explaining the dataset, or model behavior on the dataset_, e.g. `TokenFrequency` and `MMDCritic`). By replacing the default modules (e.g. local data generation, global data sampling or improved embedding methods), these methods can be improved upon or new methods can be introduced. +© Marcel Robeer, 2021 +## Quick tour +**Local explanation**: explain a models' prediction on a given sample, self-provided or from a dataset. +```python +from text_explainability import LIME, LocalTree +# Define sample to explain +sample = 'Explain why this is positive and not negative!' +# LIME explanation (local feature importance) +LIME().explain(sample, model).scores +# List of local rules, extracted from tree +LocalTree().explain(sample, model).rules +``` +**Global explanation**: explain the whole dataset (e.g. train set, test set), and what they look like for the ground-truth or predicted labels. +```python +from text_explainability import import_data, TokenFrequency, MMDCritic +# Import dataset +env = import_data('./datasets/test.csv', data_cols=['fulltext'], label_cols=['label']) +# Top-k most frequent tokens per label +TokenFrequency(env.dataset).explain(labelprovider=env.labels, explain_model=False, k=3) +# 2 prototypes and 1 criticisms for the dataset +MMDCritic(env.dataset)(n_prototypes=2, n_criticisms=1) +``` +## Installation +See the [installation](docs/INSTALLATION.md) instructions for an extended installation guide. +| Method | Instructions | +|--------|--------------| +| `pip` | Install from [PyPI](https://pypi.org/project/text-explainability/) via `pip3 install text_explainability`. To speed up the explanation generation process use `pip3 install text_explainability[fast]`. | +| Local | Clone this repository and install via `pip3 install -e .` or locally run `python3 setup.py install`. +## Documentation +Full documentation of the latest version is provided at [https://text-explainability.readthedocs.io/](https://text-explainability.readthedocs.io/). +## Example usage +See [example usage](example_usage.md) to see an example of how the package can be used, or run the lines in `example_usage.py` to do explore it interactively. +## Explanation methods included +`text_explainability` includes methods for model-agnostic _local explanation_ and _global explanation_. Each of these methods can be fully customized to fit the explainees' needs. +| Type | Explanation method | Description | Paper/link | +|------|--------------------|-------------|-------| +| *Local explanation* | `LIME` | Calculate feature attribution with _Local Intepretable Model-Agnostic Explanations_ (LIME). | [[Ribeiro2016](https://paperswithcode.com/method/lime)], [interpretable-ml/lime](https://christophm.github.io/interpretable-ml-book/lime.html) | +| | `KernelSHAP` | Calculate feature attribution with _Shapley Additive Explanations_ (SHAP). | [[Lundberg2017](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model)], [interpretable-ml/shap](https://christophm.github.io/interpretable-ml-book/shap.html) | +| | `LocalTree` | Fit a local decision tree around a single decision. | [[Guidotti2018](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)] | +| | `LocalRules` | Fit a local sparse set of label-specific rules using `SkopeRules`. | [github/skope-rules](https://github.com/scikit-learn-contrib/skope-rules) | +| | `FoilTree` | Fit a local contrastive/counterfactual decision tree around a single decision. | [[Robeer2018](https://github.com/MarcelRobeer/ContrastiveExplanation)] | +| | `BayLIME` | Bayesian extension of LIME for include prior knowledge and more consistent explanations. | [[Zhao201](https://paperswithcode.com/paper/baylime-bayesian-local-interpretable-model)] | +| *Global explanation* | `TokenFrequency` | Show the top-_k_ number of tokens for each ground-truth or predicted label. | +| | `TokenInformation` | Show the top-_k_ token mutual information for a dataset or model. | [wikipedia/mutual_information](https://en.wikipedia.org/wiki/Mutual_information) | +| | `KMedoids` | Embed instances and find top-_n_ prototypes (can also be performed for each label using `LabelwiseKMedoids`). | [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +| | `MMDCritic` | Embed instances and find top-_n_ prototypes and top-_n_ criticisms (can also be performed for each label using `LabelwiseMMDCritic`). | [[Kim2016](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html)], [interpretable-ml/prototypes](https://christophm.github.io/interpretable-ml-book/proto.html) | +## Releases +`text_explainability` is officially released through [PyPI](https://pypi.org/project/text-explainability/). +See [CHANGELOG.md](CHANGELOG.md) for a full overview of the changes for each version. +## Extensions +<a href="https://marcelrobeer.github.io/text_sensitivity/" target="_blank"><img src="https://git.science.uu.nl/m.j.robeer/text_sensitivity/-/raw/main/img/TextLogo-Logo_large_sensitivity.png" alt="T_xt sensitivity logo" width="200px"></a><p>`text_explainability` can be extended to also perform _sensitivity testing_, checking for machine learning model robustness and fairness. The `text_sensitivity` package is available through [PyPI](https://pypi.org/project/text-sensitivity/) and fully documented at [https://text-sensitivity.rtfd.io/](https://text-sensitivity.rtfd.io/).</p> +## Citation +```bibtex +@misc{text_explainability, + title = {Python package text\_explainability}, + author = {Marcel Robeer}, + howpublished = {\url{https://git.science.uu.nl/m.j.robeer/text_explainability}}, + year = {2021} +} +``` +## Maintenance +### Contributors +- [Marcel Robeer](https://www.uu.nl/staff/MJRobeer) (`@m.j.robeer`) +- [Michiel Bron](https://www.uu.nl/staff/MPBron) (`@mpbron-phd`) +### Todo +Tasks yet to be done: +* Implement local post-hoc explanations: + - Implement Anchors +* Implement global post-hoc explanations: + - Representative subset +* 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 +## Credits +- Florian Gardin, Ronan Gautier, Nicolas Goix, Bibi Ndiaye and Jean-Matthieu Schertzer. _[Skope-rules](https://github.com/scikit-learn-contrib/skope-rules)_. 2020. +- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini and Fosca Gianotti. _[Local Rule-Based Explanations of Black Box Decision Systems](https://paperswithcode.com/paper/local-rule-based-explanations-of-black-box)_. 2018. +- Been Kim, Rajiv Khanna and Oluwasanmi O. Koyejo. [Examples are not Enough, Learn to Criticize! Criticism for Interpretability](https://papers.nips.cc/paper/2016/hash/5680522b8e2bb01943234bce7bf84534-Abstract.html). _Advances in Neural Information Processing Systems (NIPS 2016)_. 2016. +- Scott Lundberg and Su-In Lee. [A Unified Approach to Interpreting Model Predictions](https://paperswithcode.com/paper/a-unified-approach-to-interpreting-model). _31st Conference on Neural Information Processing Systems (NIPS 2017)_. 2017. +- Christoph Molnar. _[Interpretable Machine Learning: A Guide for Making Black Box Models Explainable](https://christophm.github.io/interpretable-ml-book/)_. 2021. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://paperswithcode.com/method/lime). _Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2016)_. 2016. +- Marco Tulio Ribeiro, Sameer Singh and Carlos Guestrin. [Anchors: High-Precision Model-Agnostic Explanations](https://github.com/marcotcr/anchor). _AAAI Conference on Artificial Intelligence (AAAI)_. 2018. +- Jasper van der Waa, Marcel Robeer, Jurriaan van Diggelen, Matthieu Brinkhuis and Mark Neerincx. ["Contrastive Explanations with Local Foil Trees"](https://github.com/MarcelRobeer/ContrastiveExplanation). _2018 Workshop on Human Interpretability in Machine Learning (WHI 2018)_. 2018. + +%prep +%autosetup -n text-explainability-0.7.0 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-text-explainability -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Thu May 18 2023 Python_Bot <Python_Bot@openeuler.org> - 0.7.0-1 +- Package Spec generated @@ -0,0 +1 @@ +0a4439700c8b00768a8ef49bfe81b2d8 text_explainability-0.7.0.tar.gz |