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.

• DISTS-pytorch
DISTS Metric

• dproc
A convenient data flow to preprocess data using metadata.

• giotto-tda
Toolbox for Machine Learning using Topological Data Analysis.

• gitmiller
A tool to run a Jupyter Notebook from a (partial) Github repository.

• gmat
Genomic Multivariate Analysis Tools

• GPy-ABCD
Basic implementation with GPy of an Automatic Bayesian Covariance Discovery (ABCD) system

• hbp-neuromorphic-platform
Client software for the Human Brain Project Neuromorphic Computing Platform

• mvtsdata-toolkit
A Toolkit for Multivariate Time Series Data

• optbinning
OptBinning: The Python Optimal Binning library. The optimal binning is the optimal discretization of a variable into bins given a discrete or continuous numeric target. OptBinning is a library written in Python implementing a rigorous and flexible mathematical programming formulation to solving the optimal binning problem for a binary, continuous and multiclass target type, incorporating constraints not previously addressed.

• pyDMNrules
An implementation of DMN in Python. DMN rules are read from an Excel workbook

• quickregress
Provides a low-effort wrapper for sklearn’s polynomial regression

• recursive-sgd
Train a neural network – with recursion!