Skip to main content

Machine Learning Experiment Framework

Project description

Package ml-experiment

CircleCI GitHub release Documentation Status Updates Python 3

Introduction

This Python package facilitates the fast prototyping of machine learning model with great scalability and flexibility.

Characteristics of this package:

  • Flexibility of Feature Engineering: it is convenient to define a function to put to feature-processing pipeline;
  • Flexibility of Models: there is no restriction about whether you have to use scikit-learn, TensorFlow, or PyTorch;
  • Few Specifications on Models: user only need to worry about the fit and predict_proba;
  • Training Job Specifications: features, data locations, model specifications can be specified in a Python dictionary or JSON, facilitating potential MapReduce or parallelism;
  • Scalability: data is stored temporarily in disks in batch to save memory space;
  • Statistics: statistical measures of the performance of the models and their class labels are calculated;
  • Cross Validation: cross validation option is available.
  • Ready Adaptation to Production: data pipelines and algorithms can be adapted into production codes with little changes.

There will be tutorials and documentations.

News

  • 10/18/2024: 0.0.9 released.
  • 07/28/2024: 0.0.8 released.
  • 04/11/2021: 0.0.7 released.
  • 06/24/2020: 0.0.6 released.
  • 05/31/2020: 0.0.5 released.
  • 05/12/2020: 0.0.4 released.
  • 05/03/2020: 0.0.3 released.
  • 04/29/2020: 0.0.2 released.
  • 04/24/2020: 0.0.1 released.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ml_experiment-0.0.9.tar.gz (289.1 kB view hashes)

Uploaded Source

Built Distribution

ml_experiment-0.0.9-py3-none-any.whl (21.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page