Deep Fast Machine Learning Utils: A Python Library for Streamlined Machine Learning Prototyping

TL;DR

DFMLU is a Python library that streamlines machine learning prototyping by automating model development, feature selection, and data management, compatible with popular ML frameworks.

Contribution

Introduces DFMLU, a library that automates and simplifies key ML prototyping tasks, enhancing productivity and integration with existing frameworks.

Findings

Provides tools for neural network search and feature selection.

Supports data handling and visualization tasks.

Facilitates faster ML prototyping workflows.

Abstract

Machine learning (ML) research and application often involve time-consuming steps such as model architecture prototyping, feature selection, and dataset preparation. To support these tasks, we introduce the Deep Fast Machine Learning Utils (DFMLU) library, which provides tools designed to automate and enhance aspects of these processes. Compatible with frameworks like TensorFlow, Keras, and Scikit-learn, DFMLU offers functionalities that support model development and data handling. The library includes methods for dense neural network search, advanced feature selection, and utilities for data management and visualization of training outcomes. This manuscript presents an overview of DFMLU's functionalities, providing Python examples for each tool.