A library to generate natural language explanations of ML model predictions
Project description
xplainit
xplainit is an open-source Python library designed to generate natural language explanations for machine learning model predictions. This tool is especially useful for non-technical stakeholders who need to understand how features impact predictions made by models like Random Forest, XGBoost, or other models built using Scikit-learn, TensorFlow, or PyTorch.
Key Features
- Natural Language Explanations: Translates complex model outputs into easy-to-understand narratives.
- Model Support: Works with Scikit-learn models and is extensible for TensorFlow, PyTorch, and other machine learning frameworks.
- Feature Importance Visualization: Automatically generates feature importance charts.
- Easy to Use: Minimal configuration needed to integrate into any data science pipeline.
Table of Contents
Installation
You can install xplainit directly from PyPi:
pip install xplainit
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file xplainit-0.4.tar.gz.
File metadata
- Download URL: xplainit-0.4.tar.gz
- Upload date:
- Size: 3.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
8455272f8b128563c743e968afe4ee1452326038c573a1033a43a5c5de87c10b
|
|
| MD5 |
ca0851339a354074ef8e625268dd86b7
|
|
| BLAKE2b-256 |
08975dce5c7414704b3fa9dade76dae9a899313ce8b06db40a68453efd9ad621
|
File details
Details for the file xplainit-0.4-py3-none-any.whl.
File metadata
- Download URL: xplainit-0.4-py3-none-any.whl
- Upload date:
- Size: 3.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
04dc6d37c0827919076cb4672991df627b75dd6138533eca8d969eda232e0de5
|
|
| MD5 |
78a0072eefff66db70108388f603870c
|
|
| BLAKE2b-256 |
5dc8b7d5f756fd6f729f0bf595ef2d8ed29621a42a6f99d59d21d433ade021d3
|