Track Awesome Python Data Science Updates Daily

Probably the best curated list of data science software in Python.

🏠 Home · 🔍 Search · 🔥 Feed · 📮 Subscribe · ❤️ Sponsor · 😺 krzjoa/awesome-python-data-science · ⭐ 3.2K · 🏷️ Programming Languages

[ Daily / Weekly / Overview ]

Dec 03, 2025

Machine Learning / General Purpose Machine Learning

• SciPy - Fundamental algorithms for scientific computing in Python

Computations / Synthetic Data

• NumPy - The fundamental package for scientific computing with Python

Oct 04, 2024

Data Validation / Synthetic Data

• DataComPy (⭐617)- A library to compare Pandas, Polars, and Spark data frames. It provides stats and lets users adjust for match accuracy.

Aug 29, 2024

Time Series / Others

• skforecast (⭐1.4k) - Time series forecasting with machine learning models

May 10, 2024

Genetic Programming / Others

• PyGAD (⭐2.1k) - Genetic Algorithm in Python.

May 06, 2024

Optimization / Others

• pymoo (⭐2.7k) - Multi-objective Optimization in Python.

• pycma (⭐1.3k) - Python implementation of CMA-ES.

Oct 30, 2023

Time Series / Others

• sktime (⭐9.4k) - A unified framework for machine learning with time series.

• darts (⭐9.1k) - A python library for easy manipulation and forecasting of time series.

• statsforecast (⭐4.6k) - Lightning fast forecasting with statistical and econometric models.

• mlforecast (⭐1.1k) - Scalable machine learning-based time series forecasting.

• neuralforecast (⭐3.9k) - Scalable machine learning-based time series forecasting.

• tslearn (⭐3.1k) - Machine learning toolkit dedicated to time-series data.

• tick (⭐529) - Module for statistical learning, with a particular emphasis on time-dependent modeling.

• greykite (⭐1.9k) - A flexible, intuitive, and fast forecasting library next.

• Prophet (⭐20k) - Automatic Forecasting Procedure.

• PyFlux (⭐2.1k) - Open source time series library for Python.

• bayesloop (⭐168) - Probabilistic programming framework that facilitates objective model selection for time-varying parameter models.

• luminol (⭐1.2k) - Anomaly Detection and Correlation library.

• dateutil - Powerful extensions to the standard datetime module

• maya (⭐3.4k) - makes it very easy to parse a string and for changing timezones

• Chaos Genius (⭐765) - ML powered analytics engine for outlier/anomaly detection and root cause analysis

Oct 26, 2023

Automated Machine Learning / Others

• auto-sklearn (⭐8k) - An AutoML toolkit and a drop-in replacement for a scikit-learn estimator.

• Auto-PyTorch (⭐2.5k) - Automatic architecture search and hyperparameter optimization for PyTorch.

• AutoKeras (⭐9.3k) - AutoML library for deep learning.

• AutoGluon (⭐9.6k) - AutoML for Image, Text, Tabular, Time-Series, and MultiModal Data.

• TPOT (⭐10k) - AutoML tool that optimizes machine learning pipelines using genetic programming.

• MLBox (⭐1.5k) - A powerful Automated Machine Learning python library.

Oct 19, 2023

Machine Learning / General Purpose Machine Learning

• PyCaret (⭐9.6k) - An open-source, low-code machine learning library in Python.

Reinforcement Learning / Others

• Tianshou (⭐9k) - An elegant PyTorch deep reinforcement learning library.

• DI-engine (⭐3.6k) - OpenDILab Decision AI Engine.

• Imitation (⭐1.6k) - Clean PyTorch implementations of imitation and reward learning algorithms.

Oct 11, 2023

Computer Vision / Others

• LAVIS (⭐11k) - A One-stop Library for Language-Vision Intelligence.

Oct 09, 2023

Computer Vision / Others

• PyTorch3D (⭐9.7k) - PyTorch3D is FAIR's library of reusable components for deep learning with 3D data.

Oct 06, 2023

Reinforcement Learning / Others

• MAgent2 (⭐314) - An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments.

Sep 28, 2023

Computer Vision / Others

• Decord (⭐2.4k) - An efficient video loader for deep learning with smart shuffling that's super easy to digest.

• MMEngine (⭐1.4k) - OpenMMLab Foundational Library for Training Deep Learning Models.

Deployment / NLP

• streamsync (⭐1.4k) - No-code in the front, Python in the back. An open-source framework for creating data apps.

• Vizro (⭐3.5k) - A toolkit for creating modular data visualization applications.

Conversion / Synthetic Data

• treelite (⭐798) - Universal model exchange and serialization format for decision tree forests.

Sep 27, 2023

Learning-to-Rank & Recommender Systems / Others

• LightFM (⭐5k) - A Python implementation of LightFM, a hybrid recommendation algorithm.

• Spotlight - Deep recommender models using PyTorch.

• Surprise (⭐6.7k) - A Python scikit for building and analyzing recommender systems.

• RecBole (⭐4.1k) - A unified, comprehensive and efficient recommendation library.

• allRank (⭐977) - allRank is a framework for training learning-to-rank neural models based on PyTorch.

• TensorFlow Recommenders (⭐2k) - A library for building recommender system models using TensorFlow.

• TensorFlow Ranking (⭐2.8k) - Learning to Rank in TensorFlow.

Probabilistic Graphical Models / Others

• pomegranate (⭐3.5k) - Probabilistic and graphical models for Python.

Sep 25, 2023

Machine Learning / Gradient Boosting

• XGBoost (⭐28k) - Scalable, Portable, and Distributed Gradient Boosting.

• LightGBM (⭐18k) - A fast, distributed, high-performance gradient boosting.

• CatBoost (⭐8.7k) - An open-source gradient boosting on decision trees library.

• ThunderGBM (⭐709) - Fast GBDTs and Random Forests on GPUs.

• NGBoost (⭐1.8k) - Natural Gradient Boosting for Probabilistic Prediction.

• TensorFlow Decision Forests (⭐690) - A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.

Sep 24, 2023

Reinforcement Learning / Others

• PettingZoo (⭐3.2k) - An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities.

Sep 23, 2023

Reinforcement Learning / Others

• Shimmy (⭐193) - An API conversion tool for popular external reinforcement learning environments.

• EnvPool (⭐1.2k) - C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

Sep 22, 2023

Deep Learning / JAX

• JAX (⭐34k) - Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more.

• FLAX (⭐6.9k) - A neural network library for JAX that is designed for flexibility.

• Optax (⭐2.1k) - A gradient processing and optimization library for JAX.

Reinforcement Learning / Others

• Catalyst-RL (⭐48) - PyTorch framework for RL research.

• TF-Agents (⭐3k) - A library for Reinforcement Learning in TensorFlow.

• TensorForce (⭐3.3k) - A TensorFlow library for applied reinforcement learning.

• rlpyt (⭐2.3k) - Reinforcement Learning in PyTorch.

• cleanrl (⭐8.4k) - High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG).

• Machin (⭐420) - A reinforcement library designed for pytorch.

• SKRL (⭐929) - Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Isaac Orbit and Omniverse Isaac Gym.

Graph Machine Learning / Others

• PyTorch Geometric Signed Directed (⭐143) - A signed/directed graph neural network extension library for PyTorch Geometric.

• dgl (⭐14k) - Python package built to ease deep learning on graph, on top of existing DL frameworks.

• StellarGraph (⭐3k) - Machine Learning on Graphs.

• Graph Nets (⭐5.4k) - Build Graph Nets in Tensorflow.

• TensorFlow GNN (⭐1.5k) - A library to build Graph Neural Networks on the TensorFlow platform.

• Auto Graph Learning (⭐1.1k) - An autoML framework & toolkit for machine learning on graphs.

• PyTorch-BigGraph (⭐3.4k) - Generate embeddings from large-scale graph-structured data.

• GreatX (⭐89) - A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).

• Jraph (⭐1.5k) - A Graph Neural Network Library in Jax.

Sep 21, 2023

Machine Learning / General Purpose Machine Learning

• Shogun (⭐3.1k) - Machine learning toolbox.

Deep Learning / Others

• transformers (⭐153k) - State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

• nnabla (⭐2.8k) - Neural Network Libraries by Sony.

Natural Language Processing / Others

• torchtext (⭐3.6k) - Data loaders and abstractions for text and NLP.

• KerasNLP (⭐949) - Modular Natural Language Processing workflows with Keras.

• spaCy - Industrial-Strength Natural Language Processing.

• NLTK (⭐14k) - Modules, data sets, and tutorials supporting research and development in Natural Language Processing.

• CLTK (⭐877) - The Classical Language Toolkik.

• gensim - Topic Modelling for Humans.

• pyMorfologik (⭐18) - Python binding for Morfologik.

• skift (⭐233) - Scikit-learn wrappers for Python fastText.

• Phonemizer (⭐1.5k) - Simple text-to-phonemes converter for multiple languages.

• flair (⭐14k) - Very simple framework for state-of-the-art NLP.

Computer Audition / Others

• torchaudio (⭐2.8k) - An audio library for PyTorch.

• librosa (⭐8k) - Python library for audio and music analysis.

• Yaafe (⭐246) - Audio features extraction.

• aubio (⭐3.6k) - A library for audio and music analysis.

• Essentia (⭐3.3k) - Library for audio and music analysis, description, and synthesis.

• LibXtract (⭐231) - A simple, portable, lightweight library of audio feature extraction functions.

• Marsyas (⭐421) - Music Analysis, Retrieval, and Synthesis for Audio Signals.

• muda (⭐235) - A library for augmenting annotated audio data.

• madmom (⭐1.5k) - Python audio and music signal processing library.

Computer Vision / Others

• torchvision (⭐17k) - Datasets, Transforms, and Models specific to Computer Vision.

• KerasCV (⭐1.1k) - Industry-strength Computer Vision workflows with Keras.

• OpenCV (⭐85k) - Open Source Computer Vision Library.

• scikit-image (⭐6.4k) - Image Processing SciKit (Toolbox for SciPy).

• imgaug (⭐15k) - Image augmentation for machine learning experiments.

• imgaug_extension - Additional augmentations for imgaug.

• Augmentor (⭐5.1k) - Image augmentation library in Python for machine learning.

• albumentations (⭐15k) - Fast image augmentation library and easy-to-use wrapper around other libraries.

Feature Engineering / General

• Featuretools (⭐7.6k) - Automated feature engineering.

• Feature Engine (⭐2.2k) - Feature engineering package with sklearn-like functionality.

• OpenFE (⭐832) - Automated feature generation with expert-level performance.

• skl-groups (⭐41) - A scikit-learn addon to operate on set/"group"-based features.

• Feature Forge (⭐385) - A set of tools for creating and testing machine learning features.

• few (⭐52) - A feature engineering wrapper for sklearn.

• scikit-mdr (⭐125) - A sklearn-compatible Python implementation of Multifactor Dimensionality Reduction (MDR) for feature construction.

• tsfresh (⭐9k) - Automatic extraction of relevant features from time series.

• dirty_cat (⭐20) - Machine learning on dirty tabular data (especially: string-based variables for classifcation and regression).

• NitroFE (⭐108) - Moving window features.

• sk-transformer (⭐11) - A collection of various pandas & scikit-learn compatible transformers for all kinds of preprocessing and feature engineering steps

Feature Engineering / Feature Selection

• scikit-feature (⭐1.6k) - Feature selection repository in Python.

• boruta_py (⭐1.6k) - Implementations of the Boruta all-relevant feature selection method.

• BoostARoota (⭐228) - A fast xgboost feature selection algorithm.

• scikit-rebate (⭐420) - A scikit-learn-compatible Python implementation of ReBATE, a suite of Relief-based feature selection algorithms for Machine Learning.

• zoofs (⭐250) - A feature selection library based on evolutionary algorithms.

Visualization / General Purposes

• Matplotlib (⭐22k) - Plotting with Python.

• seaborn (⭐14k) - Statistical data visualization using matplotlib.

• prettyplotlib (⭐1.7k) - Painlessly create beautiful matplotlib plots.

• python-ternary (⭐772) - Ternary plotting library for Python with matplotlib.

• missingno (⭐4.2k) - Missing data visualization module for Python.

• chartify (⭐3.6k) - Python library that makes it easy for data scientists to create charts.

• physt (⭐135) - Improved histograms.

Visualization / Interactive plots

• animatplot (⭐414) - A python package for animating plots built on matplotlib.

• plotly - A Python library that makes interactive and publication-quality graphs.

• Bokeh (⭐20k) - Interactive Web Plotting for Python.

• Altair - Declarative statistical visualization library for Python. Can easily do many data transformation within the code to create graph

• bqplot (⭐3.7k) - Plotting library for IPython/Jupyter notebooks

• pyecharts (⭐16k) - Migrated from Echarts (⭐65k), a charting and visualization library, to Python's interactive visual drawing library.

Visualization / Map

• folium - Makes it easy to visualize data on an interactive open street map

• geemap (⭐3.8k) - Python package for interactive mapping with Google Earth Engine (GEE)

Visualization / Automatic Plotting

• HoloViews (⭐2.9k) - Stop plotting your data - annotate your data and let it visualize itself.

• AutoViz (⭐1.9k): Visualize data automatically with 1 line of code (ideal for machine learning)

• SweetViz (⭐3.1k): Visualize and compare datasets, target values and associations, with one line of code.

Visualization / NLP

• pyLDAvis (⭐1.8k): Visualize interactive topic model

Deployment / NLP

• fastapi - Modern, fast (high-performance), a web framework for building APIs with Python

• streamlit - Make it easy to deploy the machine learning model

• gradio (⭐41k) - Create UIs for your machine learning model in Python in 3 minutes.

• datapane - A collection of APIs to turn scripts and notebooks into interactive reports.

• binder - Enable sharing and execute Jupyter Notebooks

Data Manipulation / Data Frames

• pandas - Powerful Python data analysis toolkit.

• polars (⭐36k) - A fast multi-threaded, hybrid-out-of-core DataFrame library.

• Arctic (⭐3.1k) - High-performance datastore for time series and tick data.

• datatable (⭐1.9k) - Data.table for Python.

• pandas_profiling (⭐13k) - Create HTML profiling reports from pandas DataFrame objects

• cuDF (⭐9.4k) - GPU DataFrame Library.

• blaze (⭐3.2k) - NumPy and pandas interface to Big Data.

• pandasql (⭐1.4k) - Allows you to query pandas DataFrames using SQL syntax.

• pandas-gbq (⭐486) - pandas Google Big Query.

• xpandas (⭐26) - Universal 1d/2d data containers with Transformers .functionality for data analysis by The Alan Turing Institute.

• pysparkling (⭐271) - A pure Python implementation of Apache Spark's RDD and DStream interfaces.

• modin (⭐10k) - Speed up your pandas workflows by changing a single line of code.

• swifter (⭐2.6k) - A package that efficiently applies any function to a pandas dataframe or series in the fastest available manner.

• pandas-log (⭐216) - A package that allows providing feedback about basic pandas operations and finds both business logic and performance issues.

• vaex (⭐8.5k) - Out-of-Core DataFrames for Python, ML, visualize and explore big tabular data at a billion rows per second.

• xarray (⭐4k) - Xarray combines the best features of NumPy and pandas for multidimensional data selection by supplementing numerical axis labels with named dimensions for more intuitive, concise, and less error-prone indexing routines.

Data Manipulation / Pipelines

• pdpipe (⭐720) - Sasy pipelines for pandas DataFrames.

• SSPipe - Python pipe (|) operator with support for DataFrames and Numpy, and Pytorch.

• pandas-ply (⭐197) - Functional data manipulation for pandas.

• Dplython (⭐761) - Dplyr for Python.

• sklearn-pandas (⭐2.8k) - pandas integration with sklearn.

• Dataset (⭐202) - Helps you conveniently work with random or sequential batches of your data and define data processing.

• pyjanitor (⭐1.5k) - Clean APIs for data cleaning.

• meza (⭐420) - A Python toolkit for processing tabular data.

• Prodmodel (⭐58) - Build system for data science pipelines.

• dopanda (⭐480) - Hints and tips for using pandas in an analysis environment.

• Hamilton (⭐2.3k) - A microframework for dataframe generation that applies Directed Acyclic Graphs specified by a flow of lazily evaluated Python functions.

Data Manipulation / Data-centric AI

• cleanlab (⭐11k) - The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

• snorkel (⭐5.9k) - A system for quickly generating training data with weak supervision.

• dataprep (⭐2.2k) - Collect, clean, and visualize your data in Python with a few lines of code.

Data Manipulation / Synthetic Data

• ydata-synthetic (⭐1.6k) - A package to generate synthetic tabular and time-series data leveraging the state-of-the-art generative models.

Sep 20, 2023

Reinforcement Learning / Others

• Gymnasium (⭐11k) - An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym (⭐37k)).

• Stable Baselines3 (⭐12k) - A set of improved implementations of reinforcement learning algorithms based on OpenAI Baselines.

• RLlib - Scalable Reinforcement Learning.

• Acme (⭐3.9k) - A library of reinforcement learning components and agents.

• d3rlpy (⭐1.6k) - An offline deep reinforcement learning library.

• TRFL (⭐3.1k) - TensorFlow Reinforcement Learning.

• Dopamine (⭐11k) - A research framework for fast prototyping of reinforcement learning algorithms.

• keras-rl (⭐5.6k) - Deep Reinforcement Learning for Keras.

• garage (⭐2.1k) - A toolkit for reproducible reinforcement learning research.

• Horizon (⭐3.7k) - A platform for Applied Reinforcement Learning.

Graph Machine Learning / Others

• pytorch_geometric (⭐23k) - Geometric Deep Learning Extension Library for PyTorch.

• pytorch_geometric_temporal (⭐2.9k) - Temporal Extension Library for PyTorch Geometric.

• Spektral (⭐2.4k) - Deep learning on graphs.

• Karate Club (⭐2.3k) - An unsupervised machine learning library for graph-structured data.

• Little Ball of Fur (⭐713) - A library for sampling graph structured data.

Probabilistic Graphical Models / Others

• pgmpy (⭐3.1k) - A python library for working with Probabilistic Graphical Models.

• pyAgrum - A GRaphical Universal Modeler.

Probabilistic Methods / Others

• pyro (⭐8.9k) - A flexible, scalable deep probabilistic programming library built on PyTorch.

• PyMC (⭐9.4k) - Bayesian Stochastic Modelling in Python.

• ZhuSuan - Bayesian Deep Learning.

• GPflow - Gaussian processes in TensorFlow.

• InferPy (⭐147) - Deep Probabilistic Modelling Made Easy.

• PyStan (⭐358) - Bayesian inference using the No-U-Turn sampler (Python interface).

• sklearn-bayes (⭐521) - Python package for Bayesian Machine Learning with scikit-learn API.

• skpro (⭐291) - Supervised domain-agnostic prediction framework for probabilistic modelling by The Alan Turing Institute.

• PyVarInf (⭐361) - Bayesian Deep Learning methods with Variational Inference for PyTorch.

• emcee (⭐1.5k) - The Python ensemble sampling toolkit for affine-invariant MCMC.

• hsmmlearn (⭐85) - A library for hidden semi-Markov models with explicit durations.

• pyhsmm (⭐570) - Bayesian inference in HSMMs and HMMs.

• GPyTorch (⭐3.8k) - A highly efficient and modular implementation of Gaussian Processes in PyTorch.

• sklearn-crfsuite (⭐432) - A scikit-learn-inspired API for CRFsuite.

Web Scraping / Synthetic Data

• BeautifulSoup: The easiest library to scrape static websites for beginners

• Scrapy: Fast and extensible scraping library. Can write rules and create customized scraper without touching the core

• Selenium: Use Selenium Python API to access all functionalities of Selenium WebDriver in an intuitive way like a real user.

• Pattern (⭐8.9k): High level scraping for well-establish websites such as Google, Twitter, and Wikipedia. Also has NLP, machine learning algorithms, and visualization

• twitterscraper (⭐2.5k): Efficient library to scrape Twitter

Apr 27, 2023

Quantum Computing / Synthetic Data

• qiskit (⭐6.8k) - Qiskit is an open-source SDK for working with quantum computers at the level of circuits, algorithms, and application modules.

Feb 22, 2023

Optimization / Others

• Optuna (⭐13k) - A hyperparameter optimization framework.

Jan 29, 2023

Machine Learning / General Purpose Machine Learning

• dlib (⭐14k) - Toolkit for making real-world machine learning and data analysis applications in C++ (Python bindings).

Machine Learning / Ensemble Methods

• Stacking (⭐228) - Simple and useful stacking library written in Python.

Machine Learning / Imbalanced Datasets

• imbalanced-learn (⭐7.1k) - Module to perform under-sampling and over-sampling with various techniques.

Deep Learning / PyTorch

• skorch (⭐6.1k) - A scikit-learn compatible neural network library that wraps PyTorch.

• ChemicalX (⭐759) - A PyTorch-based deep learning library for drug pair scoring.

Deep Learning / TensorFlow

• tfdeploy (⭐355) - Deploy TensorFlow graphs for fast evaluation and export to TensorFlow-less environments running numpy.

• Ludwig (⭐12k) - A toolbox that allows one to train and test deep learning models without the need to write code.

• Hyperas (⭐2.2k) - Keras + Hyperopt: A straightforward wrapper for a convenient hyperparameter.

Model Explanation / Others

• dalex (⭐1.5k) - moDel Agnostic Language for Exploration and explanation.

• Shapley (⭐221) - A data-driven framework to quantify the value of classifiers in a machine learning ensemble.

• tensorboard-pytorch (⭐8k) - Tensorboard for PyTorch (and chainer, mxnet, numpy, ...).

Optimization / Others

• sklearn-genetic-opt (⭐354) - Hyperparameters tuning and feature selection using evolutionary algorithms.

• OR-Tools - An open-source software suite for optimization by Google; provides a unified programming interface to a half dozen solvers: SCIP, GLPK, GLOP, CP-SAT, CPLEX, and Gurobi.

Experimentation / Synthetic Data

• Neptune - A lightweight ML experiment tracking, results visualization, and management tool.

• Sacred (⭐4.3k) - A tool to help you configure, organize, log, and reproduce experiments.

Data Validation / Synthetic Data

• pandera (⭐4.1k) - A lightweight, flexible, and expressive statistical data testing library.

Evaluation / Synthetic Data

• sklearn-evaluation (⭐3) - Model evaluation made easy: plots, tables, and markdown reports.

• AI Fairness 360 (⭐2.7k) - Fairness metrics for datasets and ML models, explanations, and algorithms to mitigate bias in datasets and models.

Quantum Computing / Synthetic Data

• cirq (⭐4.8k) - A python framework for creating, editing, and invoking Noisy Intermediate Scale Quantum (NISQ) circuits.

Conversion / Synthetic Data

• sklearn-porter (⭐1.3k) - Transpile trained scikit-learn estimators to C, Java, JavaScript, and others.

Dec 22, 2022

Data Validation / Synthetic Data

• great_expectations (⭐11k) - Always know what to expect from your data.

• deepchecks (⭐3.9k) - Validation & testing of ML models and data during model development, deployment, and production.

• evidently (⭐6.9k) - Evaluate and monitor ML models from validation to production.

• TensorFlow Data Validation (⭐778) - Library for exploring and validating machine learning data.

Dec 17, 2022

Deep Learning / PyTorch

• pytorch-lightning (⭐31k) - PyTorch Lightning is just organized PyTorch.

Experimentation / Synthetic Data

• mlflow (⭐23k) - Open source platform for the machine learning lifecycle.

• dvc (⭐15k) - Data Version Control | Git for Data & Models | ML Experiments Management.

• Ax (⭐2.6k) - Adaptive Experimentation Platform.

Computations / Synthetic Data

• NumExpr (⭐2.4k) - A fast numerical expression evaluator for NumPy that comes with an integrated computing virtual machine to speed calculations up by avoiding memory allocation for intermediate results.

Jul 29, 2022

Experimentation / Synthetic Data

• envd (⭐2.2k) - 🏕️ machine learning development environment for data science and AI/ML engineering teams.

Jan 12, 2022

Machine Learning / General Purpose Machine Learning

• sklearn-expertsys (⭐490) - Highly interpretable classifiers for scikit learn.

Oct 13, 2020

Deep Learning / TensorFlow

• Keras - A high-level neural networks API running on top of TensorFlow.

Deep Learning / Others

• Tangent (⭐2.3k) - Source-to-Source Debuggable Derivatives in Pure Python.

• autograd (⭐7.4k) - Efficiently computes derivatives of numpy code.

• Caffe (⭐35k) - A fast open framework for deep learning.

Jun 17, 2020

Machine Learning / General Purpose Machine Learning

• causalml (⭐5.6k) - Uplift modeling and causal inference with machine learning algorithms.

Nov 20, 2019

Deep Learning / PyTorch

• Catalyst (⭐3.4k) - High-level utils for PyTorch DL & RL research.

Oct 29, 2019

Optimization / Others

• scikit-opt (⭐6.2k) - Heuristic Algorithms for optimization.

Oct 06, 2019

Machine Learning / General Purpose Machine Learning

• hyperlearn (⭐2.3k) - 50%+ Faster, 50%+ less RAM usage, GPU support re-written Sklearn, Statsmodels.

Sep 24, 2019

Deep Learning / TensorFlow

• tensorpack (⭐6.3k) - A Neural Net Training Interface on TensorFlow.

Sep 23, 2019

Statistics / NLP

• weightedcalcs (⭐112) - A pandas-based utility to calculate weighted means, medians, distributions, standard deviations, and more.

Distributed Computing / Synthetic Data

• PaddlePaddle (⭐23k) - PArallel Distributed Deep LEarning.

Sep 15, 2019

Statistics / NLP

• statsmodels (⭐11k) - Statistical modeling and econometrics in Python.

Sep 05, 2019

Quantum Computing / Synthetic Data

• PennyLane (⭐2.9k) - Quantum machine learning, automatic differentiation, and optimization of hybrid quantum-classical computations.

Sep 04, 2019

Deep Learning / TensorFlow

• keras-contrib (⭐1.6k) - Keras community contributions.

• Elephas (⭐1.6k) - Distributed Deep learning with Keras & Spark.

• qkeras (⭐578) - A quantization deep learning library.

Sep 03, 2019

Distributed Computing / Synthetic Data

• Horovod (⭐15k) - Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

• PySpark - Exposes the Spark programming model to Python.

• Veles (⭐915) - Distributed machine learning platform.

• Jubatus (⭐709) - Framework and Library for Distributed Online Machine Learning.

• DMTK (⭐2.7k) - Microsoft Distributed Machine Learning Toolkit.

• dask-ml (⭐942) - Distributed and parallel machine learning.

• Distributed (⭐1.7k) - Distributed computation in Python.

Aug 31, 2019

Machine Learning / General Purpose Machine Learning

• scikit-learn - Machine learning in Python.

• cuML (⭐5k) - RAPIDS Machine Learning Library.

• modAL (⭐2.3k) - Modular active learning framework for Python3.

• Sparkit-learn (⭐1.2k) - PySpark + scikit-learn = Sparkit-learn.

• MLxtend (⭐5.1k) - Extension and helper modules for Python's data analysis and machine learning libraries.

• Reproducible Experiment Platform (REP) (⭐699) - Machine Learning toolbox for Humans.

• scikit-multilearn (⭐953) - Multi-label classification for python.

• seqlearn (⭐700) - Sequence classification toolkit for Python.

• pystruct (⭐669) - Simple structured learning framework for Python.

• RuleFit (⭐425) - Implementation of the rulefit.

• metric-learn (⭐1.4k) - Metric learning algorithms in Python.

Machine Learning / Ensemble Methods

• ML-Ensemble - High performance ensemble learning.

• stacked_generalization (⭐118) - Library for machine learning stacking generalization.

• vecstack (⭐702) - Python package for stacking (machine learning technique).

Machine Learning / Imbalanced Datasets

• imbalanced-algorithms (⭐241) - Python-based implementations of algorithms for learning on imbalanced data.

Machine Learning / Random Forests

• rpforest (⭐224) - A forest of random projection trees.

• sklearn-random-bits-forest (⭐9) - Wrapper of the Random Bits Forest program written by (Wang et al., 2016).

• rgf_python (⭐382) - Python Wrapper of Regularized Greedy Forest.

Machine Learning / Kernel Methods

• pyFM (⭐926) - Factorization machines in python.

• fastFM (⭐1.1k) - A library for Factorization Machines.

• tffm (⭐782) - TensorFlow implementation of an arbitrary order Factorization Machine.

• scikit-rvm (⭐237) - Relevance Vector Machine implementation using the scikit-learn API.

• ThunderSVM (⭐1.6k) - A fast SVM Library on GPUs and CPUs.

Deep Learning / PyTorch

• PyTorch (⭐95k) - Tensors and Dynamic neural networks in Python with strong GPU acceleration.

• ignite (⭐4.7k) - High-level library to help with training neural networks in PyTorch.

Deep Learning / TensorFlow

• TensorFlow (⭐192k) - Computation using data flow graphs for scalable machine learning by Google.

• TensorLayer (⭐7.4k) - Deep Learning and Reinforcement Learning Library for Researcher and Engineer.

• TFLearn (⭐9.6k) - Deep learning library featuring a higher-level API for TensorFlow.

• Sonnet (⭐9.9k) - TensorFlow-based neural network library.

• Polyaxon (⭐3.7k) - A platform that helps you build, manage and monitor deep learning models.

• tensorflow-upstream (⭐698) - TensorFlow ROCm port.

• TensorFlow Fold (⭐1.8k) - Deep learning with dynamic computation graphs in TensorFlow.

• TensorLight (⭐11) - A high-level framework for TensorFlow.

• Mesh TensorFlow (⭐1.6k) - Model Parallelism Made Easier.

Model Explanation / Others

• Contrastive Explanation (⭐44) - Contrastive Explanation (Foil Trees).

• yellowbrick (⭐4.4k) - Visual analysis and diagnostic tools to facilitate machine learning model selection.

• scikit-plot (⭐2.4k) - An intuitive library to add plotting functionality to scikit-learn objects.

• shap (⭐25k) - A unified approach to explain the output of any machine learning model.

• Lime (⭐12k) - Explaining the predictions of any machine learning classifier.

• FairML (⭐368) - FairML is a python toolbox auditing the machine learning models for bias.

• model-analysis (⭐1.3k) - Model analysis tools for TensorFlow.

• themis-ml (⭐126) - A library that implements fairness-aware machine learning algorithms.

• treeinterpreter (⭐762) - Interpreting scikit-learn's decision tree and random forest predictions.

Genetic Programming / Others

• gplearn (⭐1.8k) - Genetic Programming in Python.

• karoo_gp (⭐164) - A Genetic Programming platform for Python with GPU support.

• sklearn-genetic (⭐323) - Genetic feature selection module for scikit-learn.

Optimization / Others

• BoTorch (⭐3.4k) - Bayesian optimization in PyTorch.

• hyperopt-sklearn (⭐1.6k) - Hyper-parameter optimization for sklearn.

• sklearn-deap (⭐773) - Use evolutionary algorithms instead of gridsearch in scikit-learn.

• sigopt_sklearn (⭐75) - SigOpt wrappers for scikit-learn methods.

• GPflowOpt (⭐272) - Bayesian Optimization using GPflow.

Statistics / NLP

• pandas_summary (⭐522) - Extension to pandas dataframes describe function.

• Pandas Profiling (⭐13k) - Create HTML profiling reports from pandas DataFrame objects.

• Alphalens (⭐4k) - Performance analysis of predictive (alpha) stock factors.

Computations / Synthetic Data

• Dask (⭐14k) - Parallel computing with task scheduling.

Spatial Analysis / Synthetic Data

• GeoPandas (⭐5k) - Python tools for geographic data.

Aug 30, 2019

Model Explanation / Others

• Auralisation (⭐42) - Auralisation of learned features in CNN (for audio).

• CapsNet-Visualization (⭐396) - A visualization of the CapsNet layers to better understand how it works.

• lucid (⭐4.7k) - A collection of infrastructure and tools for research in neural network interpretability.

• Netron (⭐32k) - Visualizer for deep learning and machine learning models (no Python code, but visualizes models from most Python Deep Learning frameworks).

• FlashLight - Visualization Tool for your NeuralNetwork.

Aug 27, 2019

Machine Learning / General Purpose Machine Learning

• xLearn (⭐3.1k) - High Performance, Easy-to-use, and Scalable Machine Learning Package.

• mlpack (⭐5.5k) - A scalable C++ machine learning library (Python bindings).

• pyGAM (⭐929) - Generalized Additive Models in Python.

Machine Learning / Kernel Methods

• liquidSVM (⭐68) - An implementation of SVMs.

Model Explanation / Others

• Alibi (⭐2.6k) - Algorithms for monitoring and explaining machine learning models.

• anchor (⭐812) - Code for "High-Precision Model-Agnostic Explanations" paper.

• aequitas (⭐739) - Bias and Fairness Audit Toolkit.

• ELI5 (⭐2.8k) - A library for debugging/inspecting machine learning classifiers and explaining their predictions.

• L2X (⭐125) - Code for replicating the experiments in the paper Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.

• PDPbox (⭐861) - Partial dependence plot toolbox.

• PyCEbox (⭐165) - Python Individual Conditional Expectation Plot Toolbox.

• Skater - Python Library for Model Interpretation.

• AI Explainability 360 (⭐1.7k) - Interpretability and explainability of data and machine learning models.

Genetic Programming / Others

• DEAP (⭐6.3k) - Distributed Evolutionary Algorithms in Python.

• monkeys (⭐124) - A strongly-typed genetic programming framework for Python.

Optimization / Others

• Spearmint (⭐1.6k) - Bayesian optimization.

• SMAC3 (⭐1.2k) - Sequential Model-based Algorithm Configuration.

• Optunity (⭐423) - Is a library containing various optimizers for hyperparameter tuning.

• hyperopt (⭐7.6k) - Distributed Asynchronous Hyperparameter Optimization in Python.

• SafeOpt (⭐150) - Safe Bayesian Optimization.

• scikit-optimize (⭐2.8k) - Sequential model-based optimization with a scipy.optimize interface.

• Solid (⭐580) - A comprehensive gradient-free optimization framework written in Python.

• PySwarms (⭐1.4k) - A research toolkit for particle swarm optimization in Python.

• Platypus (⭐637) - A Free and Open Source Python Library for Multiobjective Optimization.

• POT (⭐2.7k) - Python Optimal Transport library.

• Talos (⭐1.6k) - Hyperparameter Optimization for Keras Models.

• nlopt (⭐2.1k) - Library for nonlinear optimization (global and local, constrained or unconstrained).

Statistics / NLP

• scikit-posthocs (⭐376) - Pairwise Multiple Comparisons Post-hoc Tests.

Evaluation / Synthetic Data

• recmetrics (⭐581) - Library of useful metrics and plots for evaluating recommender systems.

• Metrics (⭐1.7k) - Machine learning evaluation metric.

Computations / Synthetic Data

• bottleneck (⭐1.2k) - Fast NumPy array functions written in C.

• CuPy (⭐11k) - NumPy-like API accelerated with CUDA.

• scikit-tensor (⭐406) - Python library for multilinear algebra and tensor factorizations.

• numdifftools (⭐276) - Solve automatic numerical differentiation problems in one or more variables.

• quaternion (⭐652) - Add built-in support for quaternions to numpy.

• adaptive (⭐1.2k) - Tools for adaptive and parallel samping of mathematical functions.

Spatial Analysis / Synthetic Data

• PySal (⭐1.4k) - Python Spatial Analysis Library.

Quantum Computing / Synthetic Data

• QML (⭐207) - A Python Toolkit for Quantum Machine Learning.

Conversion / Synthetic Data

• ONNX (⭐20k) - Open Neural Network Exchange.

• MMdnn (⭐5.8k) - A set of tools to help users inter-operate among different deep learning frameworks.

Dec 22, 2017

Optimization / Others

• Bayesian Optimization (⭐8.5k) - A Python implementation of global optimization with gaussian processes.

Statistics / NLP

• stockstats (⭐1.4k) - Supply a wrapper StockDataFrame based on the pandas.DataFrame with inline stock statistics/indicators support.