Scanning all new published packages on PyPI I know that the quality is often quite bad. I try to filter out the worst ones and list here the ones which might be worth a look, being followed or inspire you in some way.

Fill missing values in DataFrames with Restricted Boltzmann Machines. Fill missing values in a pandas DataFrame using a Restricted Boltzmann Machine. Provides a class implementing the scikit-learn transformer interface for creating and training a Restricted Boltzmann Machine. This can then be sampled from to fill in missing values in training data or new data of the same format. Utility functions for applying the transformations to a pandas DataFrame are provided, with the option to treat columns as either continuous numerical or categorical features.

Neural network draw. Metaphor-draw is a drawind too for neural networks. It can be used as well with MLP model and GraphMachine models.

A machine learning mini-batch pipeline for out-of-memory training

Wrapper for machine learning experiments

A simple extension for Jupyter Notebook and Jupyter Lab to beautify Python code automatically using Black.

Data engineering & Data science Framework

A Python package for supervised and unsupervised machine learning. pycaret is the free software and open source machine learning library for python programming language. It is built around several popular machine learning libraries in python. It’s primary objective is to simplify problem solving through machine learning by providing an easy to use unified API.

A plotter for reinforcement learning

Deep learning on Apache Spark with Pytorch. This is an implementation of Pytorch on Spark. The goal of this library is to provide a simple, understandable interface in using Torch on Spark. With SparkTorch, you can easily integrate your deep learning model with a ML Spark Pipeline. Underneath, SparkTorch uses a parameter server to train the Pytorch network in a distributed manner. Through the api, the user can specify the style of training, whether that is Hogwild or async with locking.

useful package for pipelines testing and data mocking for new generation data warehouse

An feature extraction algorithm

A set of tools to evaluate the reproducibility of computations