Created by: guillaume-chevalier
What is this Python project?
Neuraxle is a Machine Learning (ML) library for building neat pipelines, providing the right abstractions to both ease research, development, and deployment of your ML applications. Features:
- Better hyperparameter space handling
- Composite design pattern for steps in a pipeline
- Streaming pipelines where all data can flow (not just like a block all at once)
- AutoML algorithms to launch hyperparameter search
- Meta pipeline steps as meta-optimizers for AutoML
- (soon) Vizualisation of hyperparameter correlation
- (soon) Automatic REST API serving of models
What's the difference between this Python project and similar ones?
Production-ready
Most research projects don't ever get to production. However, you want your project to be production-ready and already adaptable (clean) by the time you finish it. You also want things to be simple so that you can get started quickly.
Most existing machine learning pipeline frameworks are either too simple or too complicated for medium-scale projects. Neuraxle is balanced for medium-scale projects, providing simple, yet powerful abstractions that are ready to be used.
Compatibility
Neuraxle is built as a framework that enables you to define your own pipeline steps.
This means that you can use scikit-learn, Keras, TensorFlow, PyTorch and/or any other machine learning library you like within and throughout your Neuraxle pipelines.
Parallel Computing
Neuraxle offer multiple parallel processing features using joblib. Most parallel processing in Neuraxle happens in the pipeline and union modules, and as such, neuraxle can be easily parallelized on a cluster of computers using distributed as its joblib backend.
Automatic Machine Learning
One of the core goal of this framework is to enable easy automatic machine learning, and also meta-learning. It should be easy to train a meta-optimizer on many different tasks: the optimizer is a model itself that maps features of datasets and features of the hyperparameter space to a guessed performance score to predict the best hyperparameters. Hyperparameter spaces are easily defined with a range, and are only coupled to their respective pipeline steps, rather than being coupled to the whole pipeline, which enable class reuse and more modularity.
Comparison to Other Machine Learning Pipeline Frameworks
scikit-learn
Everything that works in sklearn is also useable in Neuraxle. Neuraxle
is built in a way that does not replace what already exists. Therefore,
Neuraxle adds more power to scikit-lean by providing neat abstractions,
and neuraxle is even retrocompatible with sklean if it ever needed to be
included in an already-existing sklearn pipeline (you can do that by
using .tosklearn() on your Neuraxle pipeline). We believe that
Neuraxle helps scikit-learn, and also scikit-learn will help Neuraxle.
Neuraxle is best used with scikit-learn.
Also, the top core developers of scikit-learn, Andreas C. Müller, gave a talk in which he lists the elements that are yet to be done in scikit-learn. He refers to building bigger pipelines with automatic machine learning, meta learning, improving the abstractions of the search spaces, and he also points out that it would be possible do achieve that in another library which could reuse scikit-learn. Neuraxle is here to solve those problems that are actually shared by the open-source community in general. Let's move forward with Neuraxle: join Neuraxle's community.
https://www.youtube.com/embed/Wy6EKjJT79M?start=1361&end=1528
Apache Beam
Apache Beam is a big, multi-language project and hence is complicated. Neuraxle is pythonic and user-friendly: it's easy to get started.
Also, it seems that Apache Beam has GPL and MPL dependencies, which means Apache Beam might itself be copyleft (?). Neuraxle doesn't have such copyleft dependencies.
spaCy
spaCy has copyleft dependencies or may download copyleft content, and it is built only for Natural Language Processing (NLP) projects. Neuraxle is open to any kind of machine learning projects and isn't an NLP-first project.
Kubeflow
Kubeflow is cloud-first, using Kubernetes and is more oriented towards devops. Neuraxle isn't built as a cloud-first solution and isn't tied to Kubernetes. Neuraxle instead offers many parallel processing features, such as the ability to be scaled on many cores of a computer, and even on a computer cluster (e.g.: in the cloud using any cloud provider) with joblib, using dask's distributed library as a joblib backend. A Neuraxle project is best deployed as a microservice within your software environment, and you can fully control and customize how you deploy your project (e.g.: coding yourself a pipeline step that does json conversion to accept http requests).
--
Anyone who agrees with this pull request could vote for it by adding a