Pyoxynet Documentation

Pyoxynet is a Python package for automatic interpretation of cardiopulmonary exercise test (CPET) data using deep learning models. It is part of the Oxynet project, which aims to provide universal access to quality healthcare through AI-powered diagnostic tools.

Key Features

• Inference Model: Automatically estimates exercise intensity domains from CPET data

• Generator Model: Creates synthetic CPET data using conditional GANs

• Flexible Deployment: Choose between lightweight TFLite or full TensorFlow

• Model Explainability: SHAP integration for understanding predictions

• Easy to Use: Simple API for both beginners and advanced users

Quick Example

import pyoxynet

# Load the TFLite model
tfl_model = pyoxynet.load_tf_model(n_inputs=5, past_points=40, model='CNN')

# Make inference on sample data
pyoxynet.test_pyoxynet(tfl_model)

Installation

Install the base package:

pip install pyoxynet

For TFLite inference support:

pip install "pyoxynet[tflite]" --extra-index-url https://google-coral.github.io/py-repo/

For full TensorFlow with training capabilities:

pip install "pyoxynet[full]"

Contents

User Guide

• Usage
  • Installation
  • Quick Start
  • Basic Workflow
  • Data Requirements
  • Generating Synthetic Data
  • API Reference
• Examples
  • Basic Inference Example
  • Generating Synthetic CPET Data
  • Working with Your Own Data
  • Data Processing with Optimal Filter
  • Custom Probability Functions
  • Model Explainability with SHAP
  • Advanced Usage: Custom Model Parameters

API Documentation

• API Reference
  • Utilities Module
  • Testing Module
  • Model Module

Additional Resources

• GitHub Repository
• Web Application
• Oxynet Website

Indices and tables

• Index

• Module Index

• Search Page