Алгоритмы машинного обучения

Теги: ml 

ml_monorepo Super-monorepo for machine learning and algorithmic trading

[computer-visions]

[graphs]

  • [wikidata]
  • Apache JENA - RDF хранилище
    • apache jena github Java framework for writing Semantic Web applications.
    • stain/jena-fuseki This is a Docker image for running Apache Jena Fuseki, which is a SPARQL 1.1 server with a web interface, backed by the Apache Jena TDB RDF triple store.
    • stain/jena This docker image exposes the Apache Jena command line tool riot and its variants (e.g. turtle, rdfxml), in addition to the other Jena command line tools
  • RDFLIB is a pure Python package for working with RDF. RDFLib contains most things you need to work with RDF
  • pyfuseki An easy way to mix together OWL and Jena Fuseki

evolution

Boosting

Recomendation systems

Preprocessing

  • scikit-lego custom sxcikit-learn transformers, metrics and models

Mining

  • Sber_Process_Mining - SberPM is an open-source Python library for conducting a comprehensive analysis of business processes
  • siuba is a tool for concise, flexible data-analysis over multiple data sources. It currently supports pandas DataFrames and SQL tables.

Experiments piplines and deployments

  • sacred is a tool to help you configure, organize, log and reproduce experiments
  • kedro is an open-source Python framework for creating reproducible, maintainable and modular data science code
  • MLflow is an open source platform for managing the end-to-end machine learning lifecycle
  • AutoDeploy allows configuration based MLOps
  • spacy train, manage, package, deploy nlp-models pipline
  • MLFlow Machine Learning Lifecycle Platform
  • KubeFlow the cloud-native platform for machine learning operations - pipelines, training and deployment
  • RayWorkflow provides a simple, universal API for building distributed applications, дока
  • seldon-core converts your ML models (Tensorflow, Pytorch, H2o, etc.) or language wrappers (Python, Java, etc.) into production REST/GRPC microservices.
  • [jina] Фреймворк для работы с ml-моделями
  • [docarray] is a library for nested, unstructured data in transit, including text, image, audio, video, 3D mesh, etc.

Neural networks