EpistasisLab/tpot
Tpot
TPOT is a Python automated machine learning tool and pipeline framework. It automatically searches, selects, and tunes machine learning algorithms and hyperparameters to identify the most effective model architecture.
The system utilizes genetic programming to optimize these pipelines through evolutionary algorithms. To accelerate the search process, it functions as a multi-core evaluator that runs parallel training workflows across multiple processor cores.
The framework supports the definition of custom objective functions to optimize pipelines based on specific performance metrics.
Features
- Automated Machine Learning Tools - Provides a Python-based system that automates the design and optimization of machine learning pipelines.
- Genetic Algorithms - Uses evolutionary genetic algorithms to search for and refine the most effective model architecture.
- Genetic Pipeline Optimizers - Utilizes genetic programming to evolve and identify the most effective machine learning model architecture.
- Automated ML (AutoML) - Automatically selects and tunes machine learning models and hyperparameters based on the provided dataset.
- Custom Objective Configuration - Provides interfaces for injecting user-defined objective functions to optimize pipelines based on specific performance goals.
- Parallel Evaluators - Functions as a multi-core evaluator to run parallel training workflows across multiple processor cores.
- Parallel Evaluation Workflows - Speeds up the discovery of optimal pipelines by running multiple evaluations across several processor cores.
- Metric Optimization - Enables the tuning of machine learning pipelines to maximize scoring logic tailored to specific research or business goals.
- Multi-Core Parallelization - Accelerates the search process by running multiple pipeline evaluations across several processor cores simultaneously.
- Automated Machine Learning - Automates machine learning pipeline optimization.
- AutoML Frameworks - Tool for automating the creation of machine learning pipelines.
- General Machine Learning - Automated ML pipeline optimization using genetic programming.
- Machine-Learning-Frameworks - Automated machine learning tool using genetic programming.
- Machine Learning Libraries - Automated ML pipeline optimization using genetic programming.
- Optimization Tools - Optimizes machine learning pipelines using genetic programming.
- Perception and Machine Learning - Automated machine learning using genetic programming.
- Automated Machine Learning - Automated creation of scikit-learn machine learning pipelines.
