interpret-text
A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.
File Explorer
Download Latest Version (.zip)- all-tests-job-template.yml
- conda-path-step-template.yml
- conda-setup-step-template.yml
- package-installation-step-template.yml
- test-run-step-template.yml
- Code-Coverage.yml
- Nightly.yml
- PR-Gate.yml
- PyPI-Release.yml
- Interpret-text viz dashboard.gif
- generative_text_huggingface_gpt.ipynb
- generative_text_huggingface_gpt.ipynb
- generative_text_huggingface_roberta.ipynb
- generative_text_openai_gpt3.ipynb
- generative_text_openai_gpt4_or_gpt3.5.ipynb
- utils_data_shared.py
- utils_mnli.py
- utils_sst2.py
- text_classification_classical_text_explainer.ipynb
- text_classification_introspective_rationale_explainer.ipynb
- text_classification_unified_information_explainer.ipynb
- README.md
- __init__.py
- base_model_config.py
- introspective_rationale_model_config.py
- model_config_constants.py
- __init__.py
- base_text_preprocessor.py
- bert_preprocessor.py
- glove_preprocessor.py
- __init__.py
- base_explainer.py
- base_text_model.py
- base_text_tokenizer.py
- constants.py
- structured_model_mixin.py
- text_explainer_utils.py
- timer.py
- utils_bert.py
- utils_classical.py
- utils_introspective_rationale.py
- utils_pytorch.py
- utils_unified.py
- __init__.py
- components.py
- explainer.py
- model.py
- __init__.py
- constants.py
- interpret-text-widget-0.1.7.tgz
- explanationDashboard.tsx
- extension.ts
- index.ts
- labplugin.ts
- .gitignore
- LICENSE
- package.json
- README.md
- tsconfig.json
- webpack.config.js
- yarn.lock
- extension.js
- extension.js.map
- index.js
- index.js.map
- __init__.py
- _version.py
- ExplanationDashboard.py
- ExplanationWidget.py
- README.md
- yarn.lock
- __init__.py
- classical.py
- explanation.py
- unified_information.py
- explainers.py
- perturbation_tools.py
- text_utils.py
- isp_dataset.py
- isp_pipeline.py
- isp_utils.py
- app.py
- hf_tooling.py
- misc_utils.py
- models.py
- openai_tooling.py
- streamlit_frontend.py
- basketball_players.pkl
- football_teams.pkl
- movies.pkl
- schools.pkl
- songs.pkl
- words.pkl
- collection.py
- Llama-2-13b-hf_books_localized_track.pkl
- Llama-2-13b-hf_movie_awards_localized_track.pkl
- Llama-2-13b-hf_nobel_city_localized_track.pkl
- Llama-2-70b-hf_books_localized_track.pkl
- Llama-2-70b-hf_movie_awards_localized_track.pkl
- Llama-2-70b-hf_nobel_city_localized_track.pkl
- Llama-2-7b-hf_books_localized_track.pkl
- Llama-2-7b-hf_movie_awards_localized_track.pkl
- Llama-2-7b-hf_nobel_city_localized_track.pkl
- app_hierarchical.py
- app_internals_db.py
- app_paper_db.py
- app_viz_dataset.py
- Curate MultiConstraint Dataset.ipynb
- Eval Multi Constraint.ipynb
- Eval Single Constraint.ipynb
- hooks.py
- __init__.py
- interpret-text-widget.json
- __init__.py
- LICENSE
- setup.cfg
- setup.py
- test_notebook_classical_explainer.py
- test_notebook_introspective_rationale_explainer.py
- test_notebook_unified_information_explainer.py
- common_utils.py
- datasets.py
- model_config_constants.py
- test_classical_explainer.py
- test_introspective_rationale_explainer.py
- test_unified_information_explainer.py
- test_unified_utils.py
- utils_test.py
- common.py
- conftest.py
- README.md
- _utils.py
- build_wheels.py
- generate_conda_files.py
- set-variable-from-file.ps1
- en.json
- localization.ts
- BarChart.tsx
- TextHightlighting.tsx
- IChartProps.ts
- IExplanationDashboardProps.ts
- CommonUtils.ts
- ExplanationDashboard.scss
- ExplanationDashboard.tsx
- .eslintignore
- .eslintrc.json
- .gitignore
- index.ts
- package-lock.json
- package.json
- tsconfig.json
- newsgroupBinaryData.js
- .babelrc
- .eslintrc.json
- .gitignore
- App.jsx
- index.html
- index.js
- main.js
- package-lock.json
- package.json
- viztesting.sh
- webpack.config.js
- README.md
- .flake8
- .gitignore
- .pre-commit-config.yaml
- azure-pipelines.yml
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- DatasetReferences.md
- LICENSE
- README.md
- requirements.txt
- SECURITY.md
- setup.md
- yarn.lock
# Installation Guide
1. Get the code
git clone https://github.com/interpretml/interpret-text
Downloads the entire project code from GitHub to your computer.
cd interpret-text
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install interpret-text
Installs the package published on PyPI directly β no need to clone the source.
pip install notebook
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Node.js
EasyPrerequisites
β οΈ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.
cd python/interpret_text/experimental/widget/js
This project's files live in a subfolder, so move into it first.
npm install
Downloads and installs the libraries listed in package.json.
npm start
Starts the development/run server.
After running the command, open the address shown in the terminal (usually something like http://localhost:3000) in your browser.
4. Python
EasyPrerequisites
pip install -e .
Installs the Python libraries listed in requirements.txt (or similar).
jupyter nbextension install interpret_text.experimental.widget --py --sys-prefix
Type this command into your terminal and run it.
jupyter nbextension enable interpret_text.experimental.widget --py --sys-prefix
Type this command into your terminal and run it.
pip install interpret-text
Installs the package published on PyPI directly β no need to clone the source.
pip install notebook
Installs the package published on PyPI directly β no need to clone the source.
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)