Open Source AI for OPV Research

PyOghma_ML is a comprehensive open source machine learning framework designed specifically for organic photovoltaic (OPV) device analysis and prediction. It provides powerful tools for data processing, neural network training, automated analysis, and publication-ready report generation.

� Open Source & Free

Completely open source and freely available. Contribute to the codebase, report issues, and collaborate with researchers worldwide.

View on GitHub →

�🔬 Multi-Laboratory Data Support

Seamlessly process experimental data from various laboratory formats including JV, TPV, CE, and CELIV characterizations.

Explore Input Module →

🧠 Advanced Neural Networks

State-of-the-art neural network architectures including Point, Ensemble, and Difference networks with residual connections.

Explore Networks Module →

⚡ Automated Training Pipeline

Complete training workflow with adaptive learning rates, model persistence, and hyperparameter optimization.

Explore Training Module →

🎯 Intelligent Prediction

Robust prediction capabilities with model loading, feature preprocessing, and batch analysis for experimental data.

Explore Predicting Module →

📊 Comprehensive Reports

Automated generation of publication-ready LaTeX reports with visualizations, statistical analysis, and performance metrics.

Explore Output Module →

📈 Scientific Visualization

Advanced matplotlib-based plotting utilities for publication-quality figures and comprehensive data visualization.

Explore Figures Module →

Quick Start Guide

Get started with PyOghma_ML in just a few lines of code. It's open source and completely free to use:

# Install PyOghma_ML
pip install PyOghma_ML

# Basic usage example
from PyOghma_ML import Input, Networks, Output

# Load experimental data
data = Input.experiment('device_data/', 'JV', 'Brabec')

# Initialize and train networks
networks = Networks.initialise('networks/', 'Point')
networks.train_networks()

# Generate comprehensive report
output = Output(networks, data)
output.build_report()

API Documentation

Core Modules

Complete API documentation for all PyOghma_ML modules and classes.

Browse API Documentation →

Training Utilities

Hyperparameter tuning, model optimization, and training configuration utilities.

View Tuning Documentation →

Document Generation

LaTeX document creation, compilation, and formatting utilities for scientific reports.

View LaTeX Documentation →

Label Management

Advanced label processing and metadata management for OghmaNano integration.

View Labels Documentation →
9+
Core Modules
3
Network Types
4+
Data Formats
Possibilities