Awesome Python Data Science

Adaptive Experimentation Platform

Neural Network Libraries

Microsoft Distributed Machine Learning Toolkit

A package which efficiently applies any function to a pandas dataframe or series in the fastest available manner

Algorithms for explaining machine learning models

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

Automatic architecture search and hyperparameter optimization for PyTorch

Algorithms for outlier, adversarial and drift detection

An efficient video loader for deep learning with smart shuffling that's super easy to digest

Fast numerical array expression evaluator for Python, NumPy, Pandas, PyTables and more

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

Scrape Twitter for Tweets

An intuitive library to add plotting functionality to scikit-learn objects.

Graph Neural Networks with Keras and Tensorflow 2.

A modular active learning framework for Python

Source-to-Source Debuggable Derivatives in Pure Python

Optax is a gradient processing and optimization library for JAX.

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

Reinforcement Learning in PyTorch

Feature engineering and selection open-source Python library compatible with sklearn.

Open-source low code data preparation library in python. Collect, clean and visualization your data in python with a few lines of code.

library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

🏕️ Reproducible development environment for humans and agents

Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization

Open source time series library for Python

A toolkit for reproducible reinforcement learning research.

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

Automatically Visualize any dataset, any size with a single line of code. Created by Ram Seshadri. Collaborators Welcome. Permission Granted upon Request.

Natural Gradient Boosting for Probabilistic Prediction

A Python package for manipulating 2-dimensional tabular data structures

Genetic Programming in Python, with a scikit-learn inspired API

A flexible, intuitive and fast forecasting library

Python library for interactive topic model visualization. Port of the R LDAvis package.

Deep learning with dynamic computation graphs in TensorFlow

Interpretability and explainability of data and machine learning models

Clean PyTorch implementations of imitation and reward learning algorithms

A high performance Python graph library implemented in Rust.

Painlessly create beautiful matplotlib plots.

Lightweight and extensible compatibility layer between dataframe libraries!

A distributed task scheduler for Dask

Python audio and music signal processing library

An offline deep reinforcement learning library

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave

Hyper-parameter optimization for sklearn

Synthetic data generators for tabular and time-series data

Hyperparameter Experiments with TensorFlow and Keras

Python implementations of the Boruta all-relevant feature selection method.

Mesh TensorFlow: Model Parallelism Made Easier

ThunderSVM: A Fast SVM Library on GPUs and CPUs