Metadata-Version: 2.1
Name: dime-xai
Version: 0.0.4a14
Summary: Explains DIETClassifier model predictions in Rasa chatbot framework.
Home-page: https://github.com/thisisishara/dime-xai
Author: Ishara Dissanayake
Author-email: thisismaduishara@gmail.com
License: Apache License 2.0
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Environment :: GPU
Classifier: Framework :: Flask
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
Requires-Dist: rasa (~=2.8.8)
Requires-Dist: rasa-sdk (<3.0.0,>=2.8.1)
Requires-Dist: requests (<3.0,>=2.23)
Requires-Dist: ruamel.yaml (<0.17.0,>=0.16.5)
Requires-Dist: numpy (<1.19,>=1.16)
Requires-Dist: setuptools (>=41.0.0)
Requires-Dist: scipy (<2.0.0,>=1.4.1)
Requires-Dist: regex (<2021.8,>=2020.6)
Requires-Dist: tensorflow (<2.4,>=2.3.4)
Requires-Dist: scikit-learn (<0.25,>=0.22)
Requires-Dist: pymongo (<3.11,>=3.8)
Requires-Dist: tqdm (<5.0,>=4.31)
Requires-Dist: pandas (<=1.4.3,>=1.3.5)
Requires-Dist: gensim (~=4.1.2)
Requires-Dist: flask (~=2.1.2)
Requires-Dist: werkzeug (~=2.1.2)
Requires-Dist: termgraph (~=0.5.3)
Requires-Dist: flask-cors (~=3.0.10)
Requires-Dist: waitress (~=2.1.2)
Requires-Dist: python-dotenv (~=0.20.0)
Requires-Dist: psutil (~=5.9.1)

# DIME XAI 0.0.4a14 Pre-release 👽
```text
Pre-release of DIME (Dual Interpretable Model-agnostic Explanations) mainly aimed at Explaining DIET Classifiers in RASA 2.8.X. Models.
```
## Features 🦄
- Explain RASA DIET Classifiers using feature importance
- Generate dual feature importance scores
- No Surrogate models, thus efficient
- Total confidence drop as the feature importance score
- Explain both local and REST models
- Easy to use DIME CLI
- GUI with a dedicated server on-demand
- Generate, Store, Download, Upload, Peak DIME explanations. Read more on [docs](https://dime-xai.github.io)
- Full Unicode support

## What's Cooking? 🍪
- DIME for Jupyter Notebooks
- Stopwords List Generation
- DIME Example Notebooks
- DIME for non-DIET text classification models

## Limitations and Known Issues 🤏🏽
- Global Importance is disabled for REST models due to performance bottlenecks
- Explaining RASA models locally on Notebooks such as CoLab is not supported yet due to dependency issues
- Benchmark tests are in progress

📒 Docs: https://dime-xai.github.io  
📦 PyPi: https://pypi.org/project/dime-xai/0.0.4a14/  
🪵 Full Changelog: Refer the relevant GitHub branch  

