Metadata-Version: 2.4
Name: llm-pig
Version: 0.1.0
Summary: A Python library to visualize LLM perplexity metrics in interactive graphs
Author: Juan Morysson Viana Marciano
Author-email: juanmorysson@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Dist: pandas (>=2.0.0)
Requires-Dist: plotly (>=5.0.0)
Description-Content-Type: text/markdown

# llm-pig 🐷

`llm-pig` is a comprehensive Python library designed for advanced LLM perplexity analysis, covering both token-level micro inspection and macro-level dataset evaluation. It provides clean, interactive HTML visualizations powered by Pandas and Plotly.

---

## Features

* **Token-Level Curve Analysis**: Interactive line charts tracking token uncertainty across a prompt or document.
* **Cascading Bar Charts**: Sorted bar representations highlighting peak perplexity tokens.
* **SHAP-Style Text Highlights**: Individual and comparative multi-model text highlights using dynamic color gradient scales.
* **Macro Statistical Distribution**: Comprehensive Boxplots and Violin Plots summarizing model performance across large test datasets (including Min, Q1, Median, Q3, and Max metrics).

---

## Installation

Install the package via pip:

```bash
pip install llm-pig
