Track Awesome Machine Learning Updates Weekly

A curated list of awesome Machine Learning frameworks, libraries and software.

🏠 Home · 🔍 Search · 🔥 Feed · 📮 Subscribe · ❤️ Sponsor · 😺 josephmisiti/awesome-machine-learning · ⭐ 58K · 🏷️ Computer Science

[ Daily / Weekly / Overview ]

Feb 27 - Mar 05, 2023

Tools / Misc

• Humanloop – Humanloop is a platform for prompt experimentation, finetuning models for better performance, cost optimization, and collecting model generated data and user feedback.

Jan 23 - Jan 29, 2023

Python / Computer Vision

• timm (⭐24k) - PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more.

Python / General-Purpose Machine Learning

• cleanlab (⭐5.3k): The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

• AutoGluon (⭐5.3k): AutoML for Image, Text, Tabular, Time-Series, and MultiModal Data.

Jan 02 - Jan 08, 2023

C++ / General-Purpose Machine Learning

• Speedster (⭐5.1k) -Automatically apply SOTA optimization techniques to achieve the maximum inference speed-up on your hardware. [DEEP LEARNING]

Dec 05 - Dec 11, 2022

Tools / Misc

• Arize AI - Model validaiton and performance monitoring, drift detection, explainability, visualization across structured and unstructured data

Nov 21 - Nov 27, 2022

Java / General-Purpose Machine Learning

• Tribou - a machine learning library written in Java by Oracle.

OpenSource-Computer-Vision / Data Analysis / Data Visualization

• OpenCV (⭐67k) - A OpenSource Computer Vision Library

Python / General-Purpose Machine Learning

• NannyML: Python library capable of fully capturing the impact of data drift on performance. Allows estimation of post-deployment model performance without access to targets.

Python / Spiking Neural Networks

• Rockpool (⭐22) - A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

• Sinabs (⭐32) - A deep learning library for spiking neural networks which is based on PyTorch, focuses on fast training and supports inference on neuromorphic hardware.

• Tonic (⭐101) - A library that makes downloading publicly available neuromorphic datasets a breeze and provides event-based data transformation/augmentation pipelines.

Nov 07 - Nov 13, 2022

Python / General-Purpose Machine Learning

• OpenMetricLearning (⭐453) - A PyTorch-based framework to train and validate the models producing high-quality embeddings.

• SKBEL (⭐16): A Python library for Bayesian Evidential Learning (BEL) in order to estimate the uncertainty of a prediction.

Tools / Misc

• DockerDL (⭐20) - Ready to use deeplearning docker images.

Oct 03 - Oct 09, 2022

Python / General-Purpose Machine Learning

• einops (⭐6.4k) - Deep learning operations reinvented (for pytorch, tensorflow, jax and others).

Sep 26 - Oct 02, 2022

Tools / Misc

• txtai (⭐3.5k) - Build semantic search applications and workflows.

Sep 19 - Sep 25, 2022

Python / General-Purpose Machine Learning

• AutoML-Implementation-for-Static-and-Dynamic-Data-Analytics (⭐282): A tutorial to help machine learning researchers to automatically obtain optimized machine learning models with the optimal learning performance on any specific task.

Sep 05 - Sep 11, 2022

TensorFlow / General-Purpose Machine Learning

• Awesome Keras (⭐9) - A curated list of awesome Keras projects, libraries and resources.

Tools / Misc

• MLEM (⭐609) - Version and deploy your ML models following GitOps principles

Aug 29 - Sep 04, 2022

Tools / Misc

• VDP (⭐697) - open source visual data ETL to streamline the end-to-end visual data processing pipeline: extract unstructured visual data from pre-built data sources, transform it into analysable structured insights by Vision AI models imported from various ML platforms, and load the insights into warehouses or applications.

• Comet - ML platform for tracking experiments, hyper-parameters, artifacts and more. It's deeply integrated with over 15+ deep learning frameworks and orchestration tools. Users can also use the platform to monitor their models in production.

Aug 01 - Aug 07, 2022

Java / General-Purpose Machine Learning

• Chips-n-Salsa (⭐43) - A Java library for genetic algorithms, evolutionary computation, and stochastic local search, with a focus on self-adaptation / self-tuning, as well as parallel execution.

Jul 11 - Jul 17, 2022

Go / General-Purpose Machine Learning

• go-ml-benchmarks (⭐26) — benchmarks of machine learning inference for Go.

Java / General-Purpose Machine Learning

• Encog (⭐739) - An advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trainings using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks.

• Neuroph - Neuroph is lightweight Java neural network framework.

Java / Deep Learning

• Keras Beginner Tutorial - Friendly guide on using Keras to implement a simple Neural Network in Python.

JavaScript / Natural Language Processing

• nlp.js (⭐5.4k) - An NLP library built in node over Natural, with entity extraction, sentiment analysis, automatic language identify, and so more.

JavaScript / General-Purpose Machine Learning

• tensor-js (⭐32) - A deep learning library for the browser, accelerated by WebGL and WebAssembly.

Julia / General-Purpose Machine Learning

• MLJ (⭐1.6k) - A Julia machine learning framework.

Python / General-Purpose Machine Learning

• Upgini (⭐184): Free automated data & feature enrichment library for machine learning - automatically searches through thousands of ready-to-use features from public and community shared data sources and enriches your training dataset with only the accuracy improving features.

Jun 27 - Jul 03, 2022

Python / General-Purpose Machine Learning

• dirty_cat (⭐672) - facilitates machine-learning on dirty, non-curated categories. It provides transformers and encoders robust to morphological variants, such as typos.

Jun 13 - Jun 19, 2022

Clojure / General-Purpose Machine Learning

• scicloj.ml (⭐149) - A idiomatic Clojure machine learning library based on tech.ml.dataset with a unique approach for immutable data processing pipelines.

May 23 - May 29, 2022

Python / General-Purpose Machine Learning

• Shapash (⭐2.1k) : Shapash is a Python library that provides several types of visualization that display explicit labels that everyone can understand.

• Eurybia (⭐176): Eurybia monitors data and model drift over time and securizes model deployment with data validation.

• Colossal-AI (⭐18k): An open-source deep learning system for large-scale model training and inference with high efficiency and low cost.

May 16 - May 22, 2022

C++ / General-Purpose Machine Learning

• N2D2 (⭐121) - CEA-List's CAD framework for designing and simulating Deep Neural Network, and building full DNN-based applications on embedded platforms

Tools / Misc

• Qdrant – Qdrant is open source (⭐4.4k) vector similarity search engine with extended filtering support, written in Rust.

May 02 - May 08, 2022

C++ / General-Purpose Machine Learning

• oneDNN (⭐3.1k) - An open-source cross-platform performance library for deep learning applications.

Apr 11 - Apr 17, 2022

Python / Reinforcement Learning

• DI-engine (⭐2.3k) - DI-engine is a generalized Decision Intelligence engine. It supports most basic deep reinforcement learning (DRL) algorithms, such as DQN, PPO, SAC, and domain-specific algorithms like QMIX in multi-agent RL, GAIL in inverse RL, and RND in exploration problems.

Tools / Misc

• milvus – Milvus is open source (⭐15k) vector database for production AI, written in Go and C++, scalable and blazing fast for billions of embedding vectors.

Apr 04 - Apr 10, 2022

Python / Python Survival Analysis

• lifelines (⭐2k) - lifelines is a complete survival analysis library, written in pure Python

• Scikit-Survival (⭐901) - scikit-survival is a Python module for survival analysis built on top of scikit-learn. It allows doing survival analysis while utilizing the power of scikit-learn, e.g., for pre-processing or doing cross-validation.

R / General-Purpose Machine Learning

• CORElearn - CORElearn: Classification, regression, feature evaluation and ordinal evaluation. -* CoxBoost - CoxBoost: Cox models by likelihood based boosting for a single survival endpoint or competing risks [Deprecated]

Mar 21 - Mar 27, 2022

Python / General-Purpose Machine Learning

• Towhee - A Python module that encode unstructured data into embeddings.

Mar 14 - Mar 20, 2022

Python / Federated Learning

• PySyft (⭐8.6k) - A Python library for secure and private Deep Learning.

• Flower - A unified approach to federated learning, analytics, and evaluation. Federate any workload, any ML framework, and any programming language.

• Tensorflow-Federated A federated learning framework for machine learning and other computations on decentralized data.

Mar 07 - Mar 13, 2022

Tools / Misc

• Chaos Genius (⭐552) - ML powered analytics engine for outlier/anomaly detection and root cause analysis.

Jan 31 - Feb 06, 2022

Python / Computer Vision

• deepface (⭐5.7k) - A lightweight face recognition and facial attribute analysis (age, gender, emotion and race) framework for Python covering cutting-edge models such as VGG-Face, FaceNet, OpenFace, DeepFace, DeepID, Dlib and ArcFace.

• retinaface (⭐557) - deep learning based cutting-edge facial detector for Python coming with facial landmarks

Python / General-Purpose Machine Learning

• ChefBoost (⭐386) - a lightweight decision tree framework for Python with categorical feature support covering regular decision tree algorithms such as ID3, C4.5, CART, CHAID and regression tree; also some advanved bagging and boosting techniques such as gradient boosting, random forest and adaboost.

Jan 10 - Jan 16, 2022

Python / General-Purpose Machine Learning

• dtaidistance (⭐857) - High performance library for time series distances (DTW) and time series clustering.

Python / Misc Scripts / iPython Notebooks / Codebases

• handsonml (⭐25k) - Fundamentals of machine learning in python.

Jan 03 - Jan 09, 2022

Python / Data Analysis / Data Visualization

• Vaex (⭐7.8k) - A high performance Python library for lazy Out-of-Core DataFrames (similar to Pandas), to visualize and explore big tabular datasets. Documentation can be found here.

Dec 27 - Jan 02, 2021

Python / General-Purpose Machine Learning

• RexMex (⭐260) -> A general purpose recommender metrics library for fair evaluation.

• ChemicalX (⭐610) -> A PyTorch based deep learning library for drug pair scoring

• Deepchecks (⭐2.4k): Validation & testing of machine learning models and data during model development, deployment, and production. This includes checks and suites related to various types of issues, such as model performance, data integrity, distribution mismatches, and more.

Dec 20 - Dec 26, 2021

JavaScript / General-Purpose Machine Learning

• Auto ML (⭐1.6k) - Automated machine learning, data formatting, ensembling, and hyperparameter optimization for competitions and exploration- just give it a .csv file! [Deprecated]

Python / Data Analysis / Data Visualization

• ipychart (⭐71) - The power of Chart.js in Jupyter Notebook.

Dec 13 - Dec 19, 2021

C++ / General-Purpose Machine Learning

• PyCaret (⭐7k) - An open-source, low-code machine learning library in Python that automates machine learning workflows.

Clojure / General-Purpose Machine Learning

• clj-ml (⭐135) - A machine learning library for Clojure built on top of Weka and friends.

• Touchstone (⭐134) - Clojure A/B testing library.

Clojure / Deep Learning

• Flare (⭐284) - Dynamic Tensor Graph library in Clojure (think PyTorch, DynNet, etc.)

Clojure / Data Analysis

• tech.ml.dataset (⭐500) - Clojure dataframe library and pipeline for data processing and machine learning

Clojure / Data Visualization

• Pink Gorilla Notebook (⭐102) - A Clojure/Clojurescript notebook application/-library based on Gorilla-REPL

• notespace (⭐142) - Notebook experience in your Clojure namespace

• Delight (⭐296) - A listener that streams your spark events logs to delight, a free and improved spark UI

Clojure / Misc

• kixistats (⭐334) - A library of statistical distribution sampling and transducing functions

Python / Computer Vision

• detectron2 (⭐24k) - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework.

Python / General-Purpose Machine Learning

• Shapley (⭐190) -> A data-driven framework to quantify the value of classifiers in a machine learning ensemble.

• breze (⭐96) - Theano based library for deep and recurrent neural networks.

• Opytimizer (⭐553) - Python-based meta-heuristic optimization techniques.

Python / Neural Networks

• TResNet: High Performance GPU-Dedicated Architecture (⭐431) - TResNet models were designed and optimized to give the best speed-accuracy tradeoff out there on GPUs.

• Jina AI An easier way to build neural search in the cloud. Compatible with Jupyter Notebooks.

Tools / Misc

• Flyte - Flyte makes it easy to create concurrent, scalable, and maintainable workflows for machine learning and data processing.

Dec 06 - Dec 12, 2021

Java / Deep Learning

• deepjavalibrary/djl (⭐3k) - Deep Java Library (DJL) is an open-source, high-level, engine-agnostic Java framework for deep learning, designed to be easy to get started with and simple to use for Java developers.

Kotlin / Deep Learning

• KotlinDL (⭐1.1k) - Deep learning framework written in Kotlin.

Nov 29 - Dec 05, 2021

Python / General-Purpose Machine Learning

• imbalanced-ensemble (⭐194) - Python toolbox for quick implementation, modification, evaluation, and visualization of ensemble learning algorithms for class-imbalanced data. Supports out-of-the-box multi-class imbalanced (long-tailed) classification.

Nov 22 - Nov 28, 2021

Books / Misc

• Distributed Machine Learning Patterns (⭐177) - This book teaches you how to take machine learning models from your personal laptop to large distributed clusters. You’ll explore key concepts and patterns behind successful distributed machine learning systems, and learn technologies like TensorFlow, Kubernetes, Kubeflow, and Argo Workflows directly from a key maintainer and contributor, with real-world scenarios and hands-on projects.

Nov 01 - Nov 07, 2021

Python / Misc Scripts / iPython Notebooks / Codebases

• Keras Tuner (⭐2.7k) - An easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search.

Oct 18 - Oct 24, 2021

Rust / General-Purpose Machine Learning

• smartcore (⭐468) - "The Most Advanced Machine Learning Library In Rust."

• linfa (⭐2.4k) - a comprehensive toolkit to build Machine Learning applications with Rust

Oct 04 - Oct 10, 2021

Python / Computer Vision

• dockerface (⭐183) - Easy to install and use deep learning Faster R-CNN face detection for images and video in a docker container. [Deprecated]

Sep 27 - Oct 03, 2021

Python / Computer Vision

• Exadel CompreFace (⭐2.7k) - face recognition system that can be easily integrated into any system without prior machine learning skills. CompreFace provides REST API for face recognition, face verification, face detection, face mask detection, landmark detection, age, and gender recognition and is easily deployed with docker.

Python / General-Purpose Machine Learning

• Streamlit (⭐23k): Streamlit is an framework to create beautiful data apps in hours, not weeks.

• Optuna (⭐7.6k): Optuna is an automatic hyperparameter optimization software framework, particularly designed for machine learning.

Python / Misc Scripts / iPython Notebooks / Codebases

• Heart_Disease-Prediction (⭐0) - Given clinical parameters about a patient, can we predict whether or not they have heart disease?

• Flight Fare Prediction (⭐0) - This basically to gauge the understanding of Machine Learning Workflow and Regression technique in specific.

Books / Misc

• Netron - An opensource viewer for neural network, deep learning and machine learning models

• Teachable Machine - Train Machine Learning models on the fly to recognize your own images, sounds, & poses.

• Model Zoo - Discover open source deep learning code and pretrained models.

Sep 20 - Sep 26, 2021

Tools / Misc

• DVClive (⭐93) - Python library for experiment metrics logging into simply formatted local files.

Sep 06 - Sep 12, 2021

Python / Computer Vision

• computer-vision-in-action (⭐1.9k) - as known as L0CV, is a new generation of computer vision open source online learning media, a cross-platform interactive learning framework integrating graphics, source code and HTML. the L0CV ecosystem — Notebook, Datasets, Source Code, and from Diving-in to Advanced — as well as the L0CV Hub.

Books / Misc

• Grokking Machine Learning - Grokking Machine Learning teaches you how to apply ML to your projects using only standard Python code and high school-level math.

• Machine Learning Bookcamp - Learn the essentials of machine learning by completing a carefully designed set of real-world projects.

Aug 30 - Sep 05, 2021

Java / Data Analysis / Data Visualization

• Dr. Michael Thomas Flanagan's Java Scientific Library. [Deprecated]

Tools / Misc

• More tools to improve the ML lifecycle: Catalyst (⭐3.1k), PachydermIO. The following are GitHub-alike and targeting teams Weights & Biases, Neptune.ai, Comet.ml, Valohai.ai, DAGsHub.

• Weaviate – Weaviate is an open source (⭐3.5k) vector search engine and vector database. Weaviate uses machine learning to vectorize and store data, and to find answers to natural language queries. With Weaviate you can also bring your custom ML models to production scale.

Aug 23 - Aug 29, 2021

Python / Reinforcement Learning

• RLlib (⭐24k) - RLlib is an industry level, highly scalable RL library for tf and torch, based on Ray. It's used by companies like Amazon and Microsoft to solve real-world decision making problems at scale.

Jul 26 - Aug 01, 2021

Python / Computer Vision

• IoT Owl (⭐6) - Light face detection and recognition system with huge possibilities, based on Microsoft Face API and TensorFlow made for small IoT devices like raspberry pi.

Jul 05 - Jul 11, 2021

Python / General-Purpose Machine Learning

• Intel(R) Extension for Scikit-learn (⭐902) - A seamless way to speed up your Scikit-learn applications with no accuracy loss and code changes.

Jun 28 - Jul 04, 2021

C++ / General-Purpose Machine Learning

• Intel® oneAPI Data Analytics Library (⭐545) - A high performance software library developed by Intel and optimized for Intel's architectures. Library provides algorithmic building blocks for all stages of data analytics and allows to process data in batch, online and distributed modes.

JavaScript / Demos and Scripts

• Heroes Wear Masks - A fun TensorFlow.js-based oracle that tells, whether one wears a face mask or not. It can even tell when one wears the mask incorrectly.

Jun 21 - Jun 27, 2021

Python / General-Purpose Machine Learning

• Sklearn-genetic-opt (⭐192): An AutoML package for hyperparameters tuning using evolutionary algorithms, with built-in callbacks, plotting, remote logging and more.

Jun 14 - Jun 20, 2021

Python / General-Purpose Machine Learning

• Evidently (⭐3.2k): Interactive reports to analyze machine learning models during validation or production monitoring.

May 31 - Jun 06, 2021

Python / General-Purpose Machine Learning

• FEDOT (⭐497): An AutoML framework for the automated design of composite modelling pipelines. It can handle classification, regression, and time series forecasting tasks on different types of data (including multi-modal datasets).

Python / Reinforcement Learning

• Maze (⭐225) - Application-oriented deep reinforcement learning framework addressing real-world decision problems.

May 24 - May 30, 2021

Python / Computer Vision

• OpenVisionAPI - Open source computer vision API based on open source models.

Apr 19 - Apr 25, 2021

Java / General-Purpose Machine Learning

• knn-java-library (⭐4) - Just a simple implementation of K-Nearest Neighbors algorithm using with a bunch of similarity measures.

Tools / Misc

• MLReef - MLReef is an end-to-end development platform using the power of git to give structure and deep collaboration possibilities to the ML development process.

Apr 12 - Apr 18, 2021

Scala / General-Purpose Machine Learning

• Microsoft ML for Apache Spark (⭐3.9k) -> A distributed machine learning framework Apache Spark

• ONNX-Scala (⭐115) - An ONNX (Open Neural Network eXchange) API and backend for typeful, functional deep learning in Scala (3).

Scala / Data Analysis / Data Visualization

• NDScala (⭐42) - N-dimensional arrays in Scala 3. Think NumPy ndarray, but with compile-time type-checking/inference over shapes, tensor/axis labels & numeric data types

Mar 22 - Mar 28, 2021

Python / General-Purpose Machine Learning

• Backprop (⭐229) - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.

Mar 15 - Mar 21, 2021

Python / Natural Language Processing

• DL Translate (⭐260) - A deep learning-based translation library between 50 languages, built with transformers.

Mar 08 - Mar 14, 2021

C++ / General-Purpose Machine Learning

• QuestDB A relational column-oriented database designed for real-time analytics on time series and event data.

JavaScript / General-Purpose Machine Learning

• WebDNN (⭐1.9k) - Fast Deep Neural Network JavaScript Framework. WebDNN uses next generation JavaScript API, WebGPU for GPU execution, and WebAssembly for CPU execution.

Python / General-Purpose Machine Learning

• River (⭐4.1k): A framework for general purpose online machine learning.

Feb 22 - Feb 28, 2021

Python / General-Purpose Machine Learning

• ByteHub (⭐50) - An easy-to-use, Python-based feature store. Optimized for time-series data.

Feb 08 - Feb 14, 2021

Python / General-Purpose Machine Learning

• Hub (⭐5.3k) - Fastest unstructured dataset management for TensorFlow/PyTorch. Stream & version-control data. Store even petabyte-scale data in a single numpy-like array on the cloud accessible on any machine. Visit activeloop.ai for more info.

Feb 01 - Feb 07, 2021

Tools / Misc

• Pinecone - Vector database for applications that require real-time, scalable vector embedding and similarity search.

Jan 25 - Jan 31, 2021

Python / General-Purpose Machine Learning

• Synthia (⭐33) - Multidimensional synthetic data generation in Python.

Python / Neural Networks

• sequitur (⭐317) PyTorch library for creating and training sequence autoencoders in just two lines of code

Jan 18 - Jan 24, 2021

Python / Natural Language Processing

• Rasa (⭐16k) - A "machine learning framework to automate text-and voice-based conversations."

Jan 11 - Jan 17, 2021

Python / General-Purpose Machine Learning

• Gradio (⭐13k) - A Python library for quickly creating and sharing demos of models. Debug models interactively in your browser, get feedback from collaborators, and generate public links without deploying anything.

Jan 04 - Jan 10, 2021

Python / Misc Scripts / iPython Notebooks / Codebases

• CAEs for Data Assimilation (⭐24) - Convolutional autoencoders for 3D image/field compression applied to reduced order Data Assimilation.

Dec 28 - Jan 03, 2020

Go / General-Purpose Machine Learning

• go-featureprocessing (⭐91) - Fast and convenient feature processing for low latency machine learning in Go.

Dec 21 - Dec 27, 2020

Python / Computer Vision

• Learnergy (⭐59) - Energy-based machine learning models built upon PyTorch.

Python / Natural Language Processing

• NALP (⭐23) - A Natural Adversarial Language Processing framework built over Tensorflow.

Python / General-Purpose Machine Learning

• OPFython (⭐30) - A Python-inspired implementation of the Optimum-Path Forest classifier.

Dec 14 - Dec 20, 2020

General-Purpose Machine Learning / Data Analysis / Data Visualization

• PHP-ML - Machine Learning library for PHP. Algorithms, Cross Validation, Neural Network, Preprocessing, Feature Extraction and much more in one library.

Nov 30 - Dec 06, 2020

C / General-Purpose Machine Learning

• libonnx (⭐464) - A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

Nov 09 - Nov 15, 2020

Python / General-Purpose Machine Learning

• sktime (⭐6.2k) - A unified framework for machine learning with time series

Oct 26 - Nov 01, 2020

Python / Computer Vision

• lightly (⭐2.2k) - Lightly is a computer vision framework for self-supervised learning.

Tools / Misc

• Weights & Biases - Machine learning experiment tracking, dataset versioning, hyperparameter search, visualization, and collaboration

Oct 19 - Oct 25, 2020

Clojure / General-Purpose Machine Learning

• clj-boost - Wrapper for XGBoost

• lambda-ml (⭐72) - Simple, concise implementations of machine learning techniques and utilities in Clojure.

Clojure / Deep Learning

• MXNet - Bindings to Apache MXNet - part of the MXNet project

• Deep Diamond (⭐385) - A fast Clojure Tensor & Deep Learning library

• jutsu.ai (⭐98) - Clojure wrapper for deeplearning4j with some added syntactic sugar.

• dl4clj (⭐99) - Clojure wrapper for Deeplearning4j.

Clojure / Data Analysis

• Tablecloth (⭐208) - A dataframe grammar wrapping tech.ml.dataset, inspired by several R libraries

• Panthera (⭐183) - Clojure API wrapping Python's Pandas library

• Geni (⭐255) - a Clojure dataframe library that runs on Apache Spark

Clojure / Data Visualization

• Hanami (⭐321) : Clojure(Script) library and framework for creating interactive visualization applications based in Vega-Lite (VGL) and/or Vega (VG) specifications. Automatic framing and layouts along with a powerful templating system for abstracting visualization specs

• Saite (⭐121) - Clojure(Script) client/server application for dynamic interactive explorations and the creation of live shareable documents capturing them using Vega/Vega-Lite, CodeMirror, markdown, and LaTeX

• Oz (⭐796) - Data visualisation using Vega/Vega-Lite and Hiccup, and a live-reload platform for literate-programming

• clojupyter (⭐773) - A Jupyter kernel for Clojure - run Clojure code in Jupyter Lab, Notebook and Console.

Clojure / Interop

• Java Interop - Clojure has Native Java Interop from which Java's ML ecosystem can be accessed

• JavaScript Interop - ClojureScript has Native JavaScript Interop from which JavaScript's ML ecosystem can be accessed

• Libpython-clj (⭐909) - Interop with Python

• ClojisR (⭐129) - Interop with R and Renjin (R on the JVM)

Clojure / Misc

• Neanderthal - Fast Clojure Matrix Library (native CPU, GPU, OpenCL, CUDA)

• fastmath (⭐173) - A collection of functions for mathematical and statistical computing, macine learning, etc., wrapping several JVM libraries

• matlib (⭐23) - a Clojure library of optimisation and control theory tools and convenience functions based on Neanderthal.

Clojure / Extra

• Scicloj - Curated list of ML related resources for Clojure.

Oct 12 - Oct 18, 2020

Scala / General-Purpose Machine Learning

• Smile - Statistical Machine Intelligence and Learning Engine.

Python / General-Purpose Machine Learning

• igel (⭐3k) -> A delightful machine learning tool that allows you to train/fit, test and use models without writing code

Python / Neural Networks

• TResNet: Simple and powerful neural network library for python (⭐153) - Variety of supported types of Artificial Neural Network and learning algorithms.

Ruby / Natural Language Processing

• Raspell - raspell is an interface binding for ruby. [Deprecated]

Oct 05 - Oct 11, 2020

C / General-Purpose Machine Learning

• cONNXr (⭐146) - An ONNX runtime written in pure C (99) with zero dependencies focused on small embedded devices. Run inference on your machine learning models no matter which framework you train it with. Easy to install and compiles everywhere, even in very old devices.

C / Computer Vision

• VLFeat - VLFeat is an open and portable library of computer vision algorithms, which has a Matlab toolbox.

C++ / Computer Vision

• VIGRA (⭐383) - VIGRA is a genertic cross-platform C++ computer vision and machine learning library for volumes of arbitrary dimensionality with Python bindings.

C++ / General-Purpose Machine Learning

• skynet (⭐61) - A library for learning neural networks, has C-interface, net set in JSON. Written in C++ with bindings in Python, C++ and C#.

• Hopsworks (⭐873) - A data-intensive platform for AI with the industry's first open-source feature store. The Hopsworks Feature Store provides both a feature warehouse for training and batch based on Apache Hive and a feature serving database, based on MySQL Cluster, for online applications.

Python / Natural Language Processing

• colibri-core (⭐122) - Python binding to C++ library for extracting and working with basic linguistic constructions such as n-grams and skipgrams in a quick and memory-efficient way.

• genius (⭐237) - A Chinese segment based on Conditional Random Field.

• python-zpar (⭐49) - Python bindings for ZPar (⭐134), a statistical part-of-speech-tagger, constituency parser, and dependency parser for English.

• DeepPavlov (⭐6.1k) - conversational AI library with many pre-trained Russian NLP models.

C++ / Sequence Analysis

• ToPS (⭐34) - This is an object-oriented framework that facilitates the integration of probabilistic models for sequences over a user defined alphabet. [Deprecated]

Go / General-Purpose Machine Learning

• go-mxnet-predictor (⭐55) - Go binding for MXNet c_predict_api to do inference with a pre-trained model.

Java / Natural Language Processing

• Apache cTAKES - Apache Clinical Text Analysis and Knowledge Extraction System (cTAKES) is an open-source natural language processing system for information extraction from electronic medical record clinical free-text.

Julia / General-Purpose Machine Learning

• SVM (⭐39) - SVM for Julia. [Deprecated]

Matlab / Natural Language Processing

• NLP - A NLP library for Matlab.

.NET / General-Purpose Machine Learning

• Infer.NET - Infer.NET is a framework for running Bayesian inference in graphical models. One can use Infer.NET to solve many different kinds of machine learning problems, from standard problems like classification, recommendation or clustering through to customized solutions to domain-specific problems. Infer.NET has been used in a wide variety of domains including information retrieval, bioinformatics, epidemiology, vision, and many others.

• Neural Network Designer - DBMS management system and designer for neural networks. The designer application is developed using WPF, and is a user interface which allows you to design your neural network, query the network, create and configure chat bots that are capable of asking questions and learning from your feedback. The chat bots can even scrape the internet for information to return in their output as well as to use for learning.

• Synapses (⭐66) - Neural network library in F#.

.NET / Data Analysis / Data Visualization

• Math.NET Numerics - Numerical foundation of the Math.NET project, aiming to provide methods and algorithms for numerical computations in science, engineering and everyday use. Supports .Net 4.0, .Net 3.5 and Mono on Windows, Linux and Mac; Silverlight 5, WindowsPhone/SL 8, WindowsPhone 8.1 and Windows 8 with PCL Portable Profiles 47 and 344; Android/iOS with Xamarin.

General-Purpose Machine Learning / Data Analysis / Data Visualization

• MLPNeuralNet (⭐897) - Fast multilayer perceptron neural network library for iOS and Mac OS X. MLPNeuralNet predicts new examples by trained neural networks. It is built on top of the Apple's Accelerate Framework, using vectorized operations and hardware acceleration if available. [Deprecated]

• BPN-NeuralNetwork (⭐33) - It implemented 3 layers of neural networks ( Input Layer, Hidden Layer and Output Layer ) and it was named Back Propagation Neural Networks (BPN). This network can be used in products recommendation, user behavior analysis, data mining and data analysis. [Deprecated]

• Multi-Perceptron-NeuralNetwork (⭐24) - it implemented multi-perceptrons neural network (ニューラルネットワーク) based on Back Propagation Neural Networks (BPN) and designed unlimited-hidden-layers.

• KRHebbian-Algorithm (⭐12) - It is a non-supervisor and self-learning algorithm (adjust the weights) in the neural network of Machine Learning. [Deprecated]

• KRKmeans-Algorithm (⭐23) - It implemented K-Means clustering and classification algorithm. It could be used in data mining and image compression. [Deprecated]

Python / Computer Vision

• face_recognition (⭐47k) - Face recognition library that recognizes and manipulates faces from Python or from the command line.

• imutils (⭐4.3k) - A library containing Convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

Python / General-Purpose Machine Learning

• ML Model building (⭐13) -> A Repository Containing Classification, Clustering, Regression, Recommender Notebooks with illustration to make them.

• steppy (⭐135) -> Lightweight, Python library for fast and reproducible machine learning experimentation. Introduces a very simple interface that enables clean machine learning pipeline design.

• SimpleAI (⭐924) Python implementation of many of the artificial intelligence algorithms described in the book "Artificial Intelligence, a Modern Approach". It focuses on providing an easy to use, well documented and tested library.

• neuropredict (⭐94) - Aimed at novice machine learners and non-expert programmers, this package offers easy (no coding needed) and comprehensive machine learning (evaluation and full report of predictive performance WITHOUT requiring you to code) in Python for NeuroImaging and any other type of features. This is aimed at absorbing much of the ML workflow, unlike other packages like nilearn and pymvpa, which require you to learn their API and code to produce anything useful.

• imbalanced-learn - Python module to perform under sampling and oversampling with various techniques.

• stacked_generalization (⭐114) - Implementation of machine learning stacking technique as a handy library in Python.

• PyGrid (⭐617) - Peer-to-peer network of data owners and data scientists who can collectively train AI models using PySyft

Python / Data Analysis / Data Visualization

• DataVisualization (⭐20) - A GitHub Repository Where you can Learn Datavisualizatoin Basics to Intermediate level.

• Mars (⭐2.6k) - A tensor-based framework for large-scale data computation which is often regarded as a parallel and distributed version of NumPy.

• pastalog (⭐417) - Simple, realtime visualization of neural network training performance.

R / General-Purpose Machine Learning

• party - party: A Laboratory for Recursive Partitioning

• partykit - partykit: A Toolkit for Recursive Partitioning.

Tools / Misc

• Sacred (⭐4k) - Python tool to help you configure, organize, log and reproduce experiments. Like a notebook lab in the context of Chemistry/Biology. The community has built multiple add-ons leveraging the proposed standard.

• MLFlow - platform to manage the ML lifecycle, including experimentation, reproducibility and deployment. Framework and language agnostic, take a look at all the built-in integrations.

Sep 28 - Oct 04, 2020

Python / Computer Vision

• pytessarct (⭐4.7k) - Python-tesseract is an optical character recognition (OCR) tool for python. That is, it will recognize and "read" the text embedded in images. Python-tesseract is a wrapper for Google's Tesseract-OCR Engine (⭐49k).

Sep 21 - Sep 27, 2020

Python / Data Analysis / Data Visualization

• ParaMonte (⭐186) - A general-purpose Python library for Bayesian data analysis and visualization via serial/parallel Monte Carlo and MCMC simulations. Documentation can be found here.

Fortran / General-Purpose Machine Learning

• neural-fortran (⭐281) - A parallel neural net microframework. Read the paper here.

Python / Natural Language Processing

• Pattern (⭐8.4k) - A web mining module for the Python programming language. It has tools for natural language processing, machine learning, among others.

Python / General-Purpose Machine Learning

• skorch (⭐5k) - A scikit-learn compatible neural network library that wraps PyTorch.

Python / Misc Scripts / iPython Notebooks / Codebases

• Hyperparameter-Optimization-of-Machine-Learning-Algorithms (⭐1.1k) - Code for hyperparameter tuning/optimization of machine learning and deep learning algorithms.

Sep 14 - Sep 20, 2020

Python / Computer Vision

• Self-supervised learning

Python / General-Purpose Machine Learning

• ML/DL project template (⭐1.1k)

• PyTorch Lightning (⭐22k) - The lightweight PyTorch wrapper for high-performance AI research.

• PyTorch Lightning Bolts (⭐1.5k) - Toolbox of models, callbacks, and datasets for AI/ML researchers.

• Determined (⭐2.1k) - Scalable deep learning training platform, including integrated support for distributed training, hyperparameter tuning, experiment tracking, and model management.

Sep 07 - Sep 13, 2020

Python / General-Purpose Machine Learning

• Couler (⭐795) - Unified interface for constructing and managing machine learning workflows on different workflow engines, such as Argo Workflows, Tekton Pipelines, and Apache Airflow.

• evostra (⭐252) - A fast Evolution Strategy implementation in Python.

Tools / Misc

• Pythonizr - An online tool to generate boilerplate machine learning code that uses scikit-learn.

Aug 24 - Aug 30, 2020

Python / Computer Vision

• Scikit-Opt (⭐3.8k) - Swarm Intelligence in Python (Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Algorithm, Immune Algorithm, Artificial Fish Swarm Algorithm in Python)

• Deep High-Resolution-Net (⭐4k) - A PyTorch implementation of CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

• dream-creator (⭐56) - A PyTorch implementation of DeepDream. Allows individuals to quickly and easily train their own custom GoogleNet models with custom datasets for DeepDream.

• Lucent (⭐528) - Tensorflow and OpenAI Clarity's Lucid adapted for PyTorch.

Python / Reinforcement Learning

• Spinning Up - An educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning

Jul 20 - Jul 26, 2020

Python / General-Purpose Machine Learning

• PyTorch Geometric Temporal (⭐1.9k) -> A temporal extension of PyTorch Geometric for dynamic graph representation learning.

Tools / Misc

• CML (⭐3.6k) - A library for doing continuous integration with ML projects. Use GitHub Actions & GitLab CI to train and evaluate models in production like environments and automatically generate visual reports with metrics and graphs in pull/merge requests. Framework & language agnostic.

Jul 13 - Jul 19, 2020

Python / Data Analysis / Data Visualization

• Cartopy - Cartopy is a Python package designed for geospatial data processing in order to produce maps and other geospatial data analyses.

Python / Reinforcement Learning

• acme - An Open Source Distributed Framework for Reinforcement Learning that makes build and train your agents easily.

Tools / Misc

• CatalyzeX - Browser extension (Chrome and Firefox) that automatically finds and shows code implementations for machine learning papers anywhere: Google, Twitter, Arxiv, Scholar, etc.

Jun 08 - Jun 14, 2020

Python / Misc Scripts / iPython Notebooks / Codebases

• MiniGrad (⭐75) – A minimal, educational, Pythonic implementation of autograd (~100 loc).

May 25 - May 31, 2020

.NET / General-Purpose Machine Learning

• MxNet.Sharp (⭐139) - .NET Standard bindings for Apache MxNet with Imperative, Symbolic and Gluon Interface for developing, training and deploying Machine Learning models in C#. https://mxnet.tech-quantum.com/

Python / General-Purpose Machine Learning

• Little Ball of Fur (⭐624) -> A graph sampling extension library for NetworkX with a Scikit-Learn like API.

May 18 - May 24, 2020

Python / Computer Vision

• Openpose (⭐26k) - A real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Python / General-Purpose Machine Learning

• implicit - Fast Python Collaborative Filtering for Implicit Datasets.

• LightFM - A Python implementation of a number of popular recommendation algorithms for both implicit and explicit feedback.

• mljar-supervised (⭐2.5k) - An Automated Machine Learning (AutoML) python package for tabular data. It can handle: Binary Classification, MultiClass Classification and Regression. It provides explanations and markdown reports.

Apr 27 - May 03, 2020

Python / General-Purpose Machine Learning

• bayeso (⭐75) - A simple, but essential Bayesian optimization package, written in Python.

Apr 20 - Apr 26, 2020

Ruby / General-Purpose Machine Learning

• rumale (⭐635) - Rumale is a machine learning library in Ruby

Apr 13 - Apr 19, 2020

Go / Data Analysis / Data Visualization

• dataframe-go (⭐940) - Dataframes for machine-learning and statistics (similar to pandas).

Apr 06 - Apr 12, 2020

Go / General-Purpose Machine Learning

• goro (⭐353) - A high-level machine learning library in the vein of Keras.

Go / Reinforcement learning

• gold (⭐313) - A reinforcement learning library.

Mar 23 - Mar 29, 2020

JavaScript / Misc

• Pipcook (⭐2.4k) - A JavaScript application framework for machine learning and its engineering.

Python / Computer Vision

• neural-dream (⭐122) - A PyTorch implementation of DeepDream.

Python / General-Purpose Machine Learning

• Lightwood (⭐333) - A Pytorch based framework that breaks down machine learning problems into smaller blocks that can be glued together seamlessly with objective to build predictive models with one line of code.

Feb 24 - Mar 01, 2020

Tools / Misc

• m2cgen (⭐2.4k) - A tool that allows the conversion of ML models into native code (Java, C, Python, Go, JavaScript, Visual Basic, C#, R, PowerShell, PHP, Dart) with zero dependencies.

Feb 03 - Feb 09, 2020

Python / General-Purpose Machine Learning

• Karate Club (⭐1.8k) -> An unsupervised machine learning extension library for NetworkX with a Scikit-Learn like API.

• neon (⭐3.9k) - Nervana's high-performance (⭐2.7k) Python-based Deep Learning framework [DEEP LEARNING]. [Deprecated]

Tools / Misc

• MachineLearningWithTensorFlow2ed - a book on general purpose machine learning techniques regression, classification, unsupervised clustering, reinforcement learning, auto encoders, convolutional neural networks, RNNs, LSTMs, using TensorFlow 1.14.1.

Jan 27 - Feb 02, 2020

Python / Computer Vision

• Detectron (⭐26k) - FAIR's software system that implements state-of-the-art object detection algorithms, including Mask R-CNN. It is written in Python and powered by the Caffe2 deep learning framework. [Deprecated]

• Detecto (⭐584) - Train and run a computer vision model with 5-10 lines of code.

Python / Natural Language Processing

• PySS3 (⭐291) - Python package that implements a novel white-box machine learning model for text classification, called SS3. Since SS3 has the ability to visually explain its rationale, this package also comes with easy-to-use interactive visualizations tools (online demos).

Jan 13 - Jan 19, 2020

Python / General-Purpose Machine Learning

• Auto_ViML (⭐418) -> Automatically Build Variant Interpretable ML models fast! Auto_ViML is pronounced "auto vimal", is a comprehensive and scalable Python AutoML toolkit with imbalanced handling, ensembling, stacking and built-in feature selection. Featured in Medium article.

Python / Data Analysis / Data Visualization

• AutoViz (⭐1.2k) AutoViz performs automatic visualization of any dataset with a single line of Python code. Give it any input file (CSV, txt or JSON) of any size and AutoViz will visualize it. See Medium article.

Dec 23 - Dec 29, 2019

R / Data Manipulation | Data Analysis | Data Visualization

• dplyr - A data manipulation package that helps to solve the most common data manipulation problems.

Dec 09 - Dec 15, 2019

Python / General-Purpose Machine Learning

• scikit-multiflow (⭐677) - A machine learning framework for multi-output/multi-label and stream data.

Nov 11 - Nov 17, 2019

Python / Data Analysis / Data Visualization

• dowel (⭐27) - A little logger for machine learning research. Output any object to the terminal, CSV, TensorBoard, text logs on disk, and more with just one call to logger.log().

Python / Reinforcement Learning

• garage (⭐1.6k) - A toolkit for reproducible reinforcement learning research

• metaworld (⭐864) - An open source robotics benchmark for meta- and multi-task reinforcement learning

Nov 04 - Nov 10, 2019

Go / General-Purpose Machine Learning

• gorse (⭐6.6k) - An offline recommender system backend based on collaborative filtering written in Go.

Python / General-Purpose Machine Learning

• Pylearn2 (⭐2.7k) - A Machine Learning library based on Theano (⭐9.7k). [Deprecated]

Tools / Misc

• Kedro (⭐8.1k) - Kedro is a data and development workflow framework that implements best practices for data pipelines with an eye towards productionizing machine learning models.

• guild.ai - Tool to log, analyze, compare and "optimize" experiments. It's cross-platform and framework independent, and provided integrated visualizers such as tensorboard.

Oct 28 - Nov 03, 2019

Python / General-Purpose Machine Learning

• Fastai (⭐23k) - High-level wrapper built on the top of Pytorch which supports vision, text, tabular data and collaborative filtering.

Oct 14 - Oct 20, 2019

Python / General-Purpose Machine Learning

• Cortex (⭐7.9k) - Open source platform for deploying machine learning models in production.

Oct 07 - Oct 13, 2019

C++ / General-Purpose Machine Learning

• Featuretools (⭐6.5k) - A library for automated feature engineering. It excels at transforming transactional and relational datasets into feature matrices for machine learning using reusable feature engineering "primitives".

Elixir / General-Purpose Machine Learning

• Tensorflex (⭐304) - Tensorflow bindings for the Elixir programming language.

Go / Computer vision

• GoCV (⭐5.3k) - Package for computer vision using OpenCV 4 and beyond.

Data Analysis / Data Visualization / Data Analysis / Data Visualization

• Perl Data Language, a pluggable architecture for data and image processing, which can be used for machine learning (⭐15).

Python / Computer Vision

• neural-style-pt (⭐775) - A PyTorch implementation of Justin Johnson's neural-style (neural style transfer).

Python / Natural Language Processing

• pkuseg-python (⭐6.1k) - A better version of Jieba, developed by Peking University.

Python / General-Purpose Machine Learning

• auto_ml (⭐1.6k) - Automated machine learning for production and analytics. Lets you focus on the fun parts of ML, while outputting production-ready code, and detailed analytics of your dataset and results. Includes support for NLP, XGBoost, CatBoost, LightGBM, and soon, deep learning.

• Cogitare (⭐76): A Modern, Fast, and Modular Deep Learning and Machine Learning framework for Python.

• JAX (⭐22k) - JAX is Autograd and XLA, brought together for high-performance machine learning research.

Python / Misc Scripts / iPython Notebooks / Codebases

• Map/Reduce implementations of common ML algorithms (⭐58): Jupyter notebooks that cover how to implement from scratch different ML algorithms (ordinary least squares, gradient descent, k-means, alternating least squares), using Python NumPy, and how to then make these implementations scalable using Map/Reduce and Spark.

Python / Reinforcement Learning

• Serpent.AI (⭐6.4k) - Serpent.AI is a game agent framework that allows you to turn any video game you own into a sandbox to develop AI and machine learning experiments. For both researchers and hobbyists.

Swift / General-Purpose Machine Learning

• Swift for Tensorflow (⭐6.1k) - a next-generation platform for machine learning, incorporating the latest research across machine learning, compilers, differentiable programming, systems design, and beyond.

Sep 23 - Sep 29, 2019

JavaScript / Demos and Scripts

• NSFWJS - Indecent content checker with TensorFlow.js

• Rock Paper Scissors - Rock Paper Scissors trained in the browser with TensorFlow.js

Python / General-Purpose Machine Learning

• Cornac (⭐697) - A comparative framework for multimodal recommender systems with a focus on models leveraging auxiliary data.

Python / Neural Networks

• Machine Learning, Data Science and Deep Learning with Python - LiveVideo course that covers machine learning, Tensorflow, artificial intelligence, and neural networks.

Sep 09 - Sep 15, 2019

Tools / Misc

• ML Workspace (⭐2.9k) - All-in-one web-based IDE for machine learning and data science. The workspace is deployed as a docker container and is preloaded with a variety of popular data science libraries (e.g., Tensorflow, PyTorch) and dev tools (e.g., Jupyter, VS Code).

Sep 02 - Sep 08, 2019

Go / Natural Language Processing

• go-ngram (⭐109) - In-memory n-gram index with compression. [Deprecated]

• paicehusk (⭐29) - Golang implementation of the Paice/Husk Stemming Algorithm. [Deprecated]

• go-porterstemmer (⭐185) - A native Go clean room implementation of the Porter Stemming algorithm. [Deprecated]

Go / General-Purpose Machine Learning

• birdland (⭐40) - A recommendation library in Go.

• leaves (⭐370) - A pure Go implementation of the prediction part of GBRTs, including XGBoost and LightGBM.

• go-ml-transpiler (⭐66) - An open source Go transpiler for machine learning models.

• golearn (⭐8.8k) - Machine learning for Go.

• goml (⭐1.4k) - Machine learning library written in pure Go.

• gorgonia (⭐4.8k) - Deep learning in Go.

• therfoo (⭐18) - An embedded deep learning library for Go.

• neat (⭐67) - Plug-and-play, parallel Go framework for NeuroEvolution of Augmenting Topologies (NEAT). [Deprecated]

• GoNN (⭐352) - GoNN is an implementation of Neural Network in Go Language, which includes BPNN, RBF, PCN. [Deprecated]

• go-dnn (⭐5) - Deep Neural Networks for Golang (powered by MXNet)

Go / Spatial analysis and geometry

• go-geom (⭐660) - Go library to handle geometries.

• gogeo (⭐1.5k) - Spherical geometry in Go.

Go / Data Analysis / Data Visualization

• gota (⭐2.6k) - Dataframes.

• gonum/mat - A linear algebra package for Go.

• gonum/optimize - Implementations of optimization algorithms.

• gonum/plot - A plotting library.

• gonum/stat - A statistics library.

• glot (⭐378) - Glot is a plotting library for Golang built on top of gnuplot.

• globe (⭐1.6k) - Globe wireframe visualization.

• gonum/graph - General-purpose graph library.

• go-graph (⭐96) - Graph library for Go/Golang language. [Deprecated]

Python / General-Purpose Machine Learning

• Neuraxle (⭐560): A framework providing the right abstractions to ease research, development, and deployment of your ML pipelines.

Credits / Misc

• References for Go were mostly cut-and-pasted from gopherdata (⭐815)

Aug 19 - Aug 25, 2019

Python / Natural Language Processing

• BigARTM (⭐639) - topic modelling platform.

Jul 08 - Jul 14, 2019

Python / Misc Scripts / iPython Notebooks / Codebases

• the-elements-of-statistical-learning (⭐371) - This repository contains Jupyter notebooks implementing the algorithms found in the book and summary of the textbook.

Jun 17 - Jun 23, 2019

Julia / General-Purpose Machine Learning

• Flux - Relax! Flux is the ML library that doesn't make you tensor

Julia / Natural Language Processing

• Word Tokenizers (⭐86) - Tokenizers for Natural Language Processing in Julia

• Corpus Loaders (⭐31) - A Julia package providing a variety of loaders for various NLP corpora.

• Embeddings (⭐71) - Functions and data dependencies for loading various word embeddings

• Languages (⭐47) - Julia package for working with various human languages

• WordNet (⭐31) - A Julia package for Princeton's WordNet

Julia / Misc Stuff / Presentations

• DataDeps (⭐132) - Reproducible data setup for reproducible science.

Python / Misc Scripts / iPython Notebooks / Codebases

• Prodmodel (⭐54) - Build tool for data science pipelines.

Jun 10 - Jun 16, 2019

Python / Data Analysis / Data Visualization

• TensorWatch (⭐3.3k) - Debugging and visualization tool for machine learning and data science. It extensively leverages Jupyter Notebook to show real-time visualizations of data in running processes such as machine learning training.

Python / Neural Networks

• nn_builder (⭐158) - nn_builder is a python package that lets you build neural networks in 1 line

May 13 - May 19, 2019

R / General-Purpose Machine Learning

• spectralGraphTopology - spectralGraphTopology: Learning Graphs from Data via Spectral Constraints.

May 06 - May 12, 2019

Scala / General-Purpose Machine Learning

• TensorFlow Scala (⭐913) - Strongly-typed Scala API for TensorFlow.

Apr 29 - May 05, 2019

Python / General-Purpose Machine Learning

• MiraiML (⭐25): An asynchronous engine for continuous & autonomous machine learning, built for real-time usage.

Apr 22 - Apr 28, 2019

Python / General-Purpose Machine Learning

• BentoML (⭐4.6k): Toolkit for package and deploy machine learning models for serving in production

• numpy-ML (⭐12k): Reference implementations of ML models written in numpy

Apr 01 - Apr 07, 2019

Python / General-Purpose Machine Learning

• StellarGraph (⭐2.6k): Machine Learning on Graphs, a Python library for machine learning on graph-structured (network-structured) data.

Mar 11 - Mar 17, 2019

Python / General-Purpose Machine Learning

• Microsoft Recommenders (⭐15k): Examples and best practices for building recommendation systems, provided as Jupyter notebooks. The repo contains some of the latest state of the art algorithms from Microsoft Research as well as from other companies and institutions.

Feb 18 - Feb 24, 2019

Scala / Natural Language Processing

• Spark NLP (⭐3.1k) - Natural language processing library built on top of Apache Spark ML to provide simple, performant, and accurate NLP annotations for machine learning pipelines, that scale easily in a distributed environment.

Feb 04 - Feb 10, 2019

C++ / General-Purpose Machine Learning

• ThunderGBM (⭐653) - A fast library for GBDTs and Random Forests on GPUs.

Jan 28 - Feb 03, 2019

APL / General-Purpose Machine Learning

• naive-apl (⭐22) - Naive Bayesian Classifier implementation in APL. [Deprecated]

C / General-Purpose Machine Learning

• Hybrid Recommender System (⭐12) - A hybrid recommender system based upon scikit-learn algorithms. [Deprecated]

C++ / Computer Vision

• EBLearn - Eblearn is an object-oriented C++ library that implements various machine learning models [Deprecated]

• OpenCV - OpenCV has C++, C, Python, Java and MATLAB interfaces and supports Windows, Linux, Android and Mac OS.

C++ / General-Purpose Machine Learning

• BanditLib (⭐132) - A simple Multi-armed Bandit library. [Deprecated]

• DeepDetect (⭐2.4k) - A machine learning API and server written in C++11. It makes state of the art machine learning easy to work with and integrate into existing applications.

• igraph - General purpose graph library.

• libfm (⭐1.5k) - A generic approach that allows to mimic most factorization models by feature engineering.

• mlpack - A scalable C++ machine learning library.

• Vowpal Wabbit (VW) (⭐8.1k) - A fast out-of-core learning system.

• LKYDeepNN (⭐44) - A header-only C++11 Neural Network library. Low dependency, native traditional chinese document.

• Polyaxon (⭐3.3k) - A platform for reproducible and scalable machine learning and deep learning.

Python / General-Purpose Machine Learning

• Caffe (⭐33k) - A deep learning framework developed with cleanliness, readability, and speed in mind.

• machine learning (⭐254) - automated build consisting of a web-interface (⭐254), and set of programmatic-interface (⭐254) API, for support vector machines. Corresponding dataset(s) are stored into a SQL database, then generated model(s) used for prediction(s), are stored into a NoSQL datastore.

• scikit-learn - A Python module for machine learning built on top of SciPy.

• metric-learn (⭐1.3k) - A Python module for metric learning.

• astroML - Machine Learning and Data Mining for Astronomy.

• hebel (⭐1.2k) - GPU-Accelerated Deep Learning Library in Python. [Deprecated]

• Chainer (⭐5.8k) - Flexible neural network framework.

• prophet - Fast and automated time series forecasting framework by Facebook.

• topik (⭐93) - Topic modelling toolkit. [Deprecated]

• Surprise - A scikit for building and analyzing recommender systems.

• Crab (⭐1.2k) - A flexible, fast recommender engine. [Deprecated]

• Bolt (⭐87) - Bolt Online Learning Toolbox. [Deprecated]

• CoverTree (⭐28) - Python implementation of cover trees, near-drop-in replacement for scipy.spatial.kdtree [Deprecated]

• Pyevolve (⭐307) - Genetic algorithm framework. [Deprecated]

• neurolab (⭐153)

• Spearmint (⭐1.5k) - Spearmint is a package to perform Bayesian optimization according to the algorithms outlined in the paper: Practical Bayesian Optimization of Machine Learning Algorithms. Jasper Snoek, Hugo Larochelle and Ryan P. Adams. Advances in Neural Information Processing Systems, 2012. [Deprecated]

• Pebl (⭐103) - Python Environment for Bayesian Learning. [Deprecated]

• pomegranate (⭐3k) - Hidden Markov Models for Python, implemented in Cython for speed and efficiency.

• pydeep (⭐1.4k) - Deep Learning In Python. [Deprecated]

• TPOT (⭐9k) - Tool that automatically creates and optimizes machine learning pipelines using genetic programming. Consider it your personal data science assistant, automating a tedious part of machine learning.

• Orange - Open source data visualization and data analysis for novices and experts.

• milk (⭐610) - Machine learning toolkit focused on supervised classification. [Deprecated]

• REP (⭐666) - an IPython-based environment for conducting data-driven research in a consistent and reproducible way. REP is not trying to substitute scikit-learn, but extends it and provides better user experience. [Deprecated]

• rgf_python (⭐364) - Python bindings for Regularized Greedy Forest (Tree) Library.

• modAL (⭐1.9k) - A modular active learning framework for Python, built on top of scikit-learn.

• Turi Create (⭐11k) - Machine learning from Apple. Turi Create simplifies the development of custom machine learning models. You don't have to be a machine learning expert to add recommendations, object detection, image classification, image similarity or activity classification to your app.

R / General-Purpose Machine Learning

• MXNet (⭐20k) - Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.

• Optunity - A library dedicated to automated hyperparameter optimization with a simple, lightweight API to facilitate drop-in replacement of grid search. Optunity is written in Python but interfaces seamlessly to R.

• ahaz - ahaz: Regularization for semiparametric additive hazards regression. [Deprecated]

• arules - arules: Mining Association Rules and Frequent Itemsets

• bmrm - bmrm: Bundle Methods for Regularized Risk Minimization Package.

• Boruta - Boruta: A wrapper algorithm for all-relevant feature selection.

• bst - bst: Gradient Boosting.

• C50 - C50: C5.0 Decision Trees and Rule-Based Models.

• caret - Classification and Regression Training: Unified interface to ~150 ML algorithms in R.

• caretEnsemble - caretEnsemble: Framework for fitting multiple caret models as well as creating ensembles of such models. [Deprecated]

• Clever Algorithms For Machine Learning

• Cubist - Cubist: Rule- and Instance-Based Regression Modelling.

• e1071 - e1071: Misc Functions of the Department of Statistics (e1071), TU Wien

• earth - earth: Multivariate Adaptive Regression Spline Models

• elasticnet - elasticnet: Elastic-Net for Sparse Estimation and Sparse PCA.

• ElemStatLearn - ElemStatLearn: Data sets, functions and examples from the book: "The Elements of Statistical Learning, Data Mining, Inference, and Prediction" by Trevor Hastie, Robert Tibshirani and Jerome Friedman Prediction" by Trevor Hastie, Robert Tibshirani and Jerome Friedman.

• evtree - evtree: Evolutionary Learning of Globally Optimal Trees.

• forecast - forecast: Timeseries forecasting using ARIMA, ETS, STLM, TBATS, and neural network models.

• forecastHybrid - forecastHybrid: Automatic ensemble and cross validation of ARIMA, ETS, STLM, TBATS, and neural network models from the "forecast" package.

• fpc - fpc: Flexible procedures for clustering.

• frbs - frbs: Fuzzy Rule-based Systems for Classification and Regression Tasks. [Deprecated]

• GAMBoost - GAMBoost: Generalized linear and additive models by likelihood based boosting. [Deprecated]

• gamboostLSS - gamboostLSS: Boosting Methods for GAMLSS.

• gbm - gbm: Generalized Boosted Regression Models.

• glmnet - glmnet: Lasso and elastic-net regularized generalized linear models.

• glmpath - glmpath: L1 Regularization Path for Generalized Linear Models and Cox Proportional Hazards Model.

• GMMBoost - GMMBoost: Likelihood-based Boosting for Generalized mixed models. [Deprecated]

• grplasso - grplasso: Fitting user specified models with Group Lasso penalty.

• grpreg - grpreg: Regularization paths for regression models with grouped covariates.

• h2o - A framework for fast, parallel, and distributed machine learning algorithms at scale -- Deeplearning, Random forests, GBM, KMeans, PCA, GLM.

• hda - hda: Heteroscedastic Discriminant Analysis. [Deprecated]

• Introduction to Statistical Learning

• ipred - ipred: Improved Predictors.

• kernlab - kernlab: Kernel-based Machine Learning Lab.

• klaR - klaR: Classification and visualization.

• lars - lars: Least Angle Regression, Lasso and Forward Stagewise. [Deprecated]

• lasso2 - lasso2: L1 constrained estimation aka ‘lasso’.

• LiblineaR - LiblineaR: Linear Predictive Models Based On The Liblinear C/C++ Library.

• LogicReg - LogicReg: Logic Regression.

• maptree - maptree: Mapping, pruning, and graphing tree models. [Deprecated]

• mboost - mboost: Model-Based Boosting.

• medley - medley: Blending regression models, using a greedy stepwise approach.

• mlr - mlr: Machine Learning in R.

• ncvreg - ncvreg: Regularization paths for SCAD- and MCP-penalized regression models.

• nnet - nnet: Feed-forward Neural Networks and Multinomial Log-Linear Models. [Deprecated]

• pamr - pamr: Pam: prediction analysis for microarrays. [Deprecated]

• penalized - penalized: L1 (lasso and fused lasso) and L2 (ridge) penalized estimation in GLMs and in the Cox model.

• penalizedLDA - penalizedLDA: Penalized classification using Fisher's linear discriminant. [Deprecated]

• penalizedSVM - penalizedSVM: Feature Selection SVM using penalty functions.

• quantregForest - quantregForest: Quantile Regression Forests.

• randomForest - randomForest: Breiman and Cutler's random forests for classification and regression.

• randomForestSRC - randomForestSRC: Random Forests for Survival, Regression and Classification (RF-SRC).

• rattle - rattle: Graphical user interface for data mining in R.

• rda - rda: Shrunken Centroids Regularized Discriminant Analysis.

• rdetools - rdetools: Relevant Dimension Estimation (RDE) in Feature Spaces. [Deprecated]

• REEMtree - REEMtree: Regression Trees with Random Effects for Longitudinal (Panel) Data. [Deprecated]

• relaxo - relaxo: Relaxed Lasso. [Deprecated]

• rgenoud - rgenoud: R version of GENetic Optimization Using Derivatives

• Rmalschains - Rmalschains: Continuous Optimization using Memetic Algorithms with Local Search Chains (MA-LS-Chains) in R.

• rminer - rminer: Simpler use of data mining methods (e.g. NN and SVM) in classification and regression. [Deprecated]

• ROCR - ROCR: Visualizing the performance of scoring classifiers. [Deprecated]

• RoughSets - RoughSets: Data Analysis Using Rough Set and Fuzzy Rough Set Theories. [Deprecated]

• rpart - rpart: Recursive Partitioning and Regression Trees.

• RPMM - RPMM: Recursively Partitioned Mixture Model.

• RSNNS - RSNNS: Neural Networks in R using the Stuttgart Neural Network Simulator (SNNS).

• RWeka - RWeka: R/Weka interface.

• RXshrink - RXshrink: Maximum Likelihood Shrinkage via Generalized Ridge or Least Angle Regression.

• sda - sda: Shrinkage Discriminant Analysis and CAT Score Variable Selection. [Deprecated]

• SuperLearner (⭐244) - Multi-algorithm ensemble learning packages.

• svmpath - svmpath: svmpath: the SVM Path algorithm. [Deprecated]

• tgp - tgp: Bayesian treed Gaussian process models. [Deprecated]

• tree - tree: Classification and regression trees.

• varSelRF - varSelRF: Variable selection using random forests.

• igraph - binding to igraph library - General purpose graph library.

Matlab / General-Purpose Machine Learning

• ThunderSVM (⭐1.5k) - An Open-Source SVM Library on GPUs and CPUs

• Convolutional-Recursive Deep Learning for 3D Object Classification - Convolutional-Recursive Deep Learning for 3D Object Classification[DEEP LEARNING].

• Spider - The spider is intended to be a complete object orientated environment for machine learning in Matlab.

• LibSVM - A Library for Support Vector Machines.

• LibLinear - A Library for Large Linear Classification.

• Pattern Recognition Toolbox (⭐142) - A complete object-oriented environment for machine learning in Matlab.

C++ / Natural Language Processing

• CRF++ - Open source implementation of Conditional Random Fields (CRFs) for segmenting/labeling sequential data & other Natural Language Processing tasks. [Deprecated]

• CRFsuite - CRFsuite is an implementation of Conditional Random Fields (CRFs) for labeling sequential data. [Deprecated]

• libfolia (⭐14) - C++ library for the FoLiA format

Common Lisp / General-Purpose Machine Learning

• mgl (⭐345) - Neural networks (boltzmann machines, feed-forward and recurrent nets), Gaussian Processes.

• mgl-gpr (⭐57) - Evolutionary algorithms. [Deprecated]

• cl-libsvm (⭐16) - Wrapper for the libsvm support vector machine library. [Deprecated]

Clojure / General-Purpose Machine Learning

• Clojush (⭐321) - The Push programming language and the PushGP genetic programming system implemented in Clojure.

• Encog (⭐137) - Clojure wrapper for Encog (v3) (Machine-Learning framework that specializes in neural-nets). [Deprecated]

• Fungp (⭐100) - A genetic programming library for Clojure. [Deprecated]

• Statistiker (⭐63) - Basic Machine Learning algorithms in Clojure. [Deprecated]

• clortex (⭐181) - General Machine Learning library using Numenta’s Cortical Learning Algorithm. [Deprecated]

• comportex (⭐153) - Functionally composable Machine Learning library using Numenta’s Cortical Learning Algorithm. [Deprecated]

Clojure / Deep Learning

• cortex (⭐1.3k) - Neural networks, regression and feature learning in Clojure.

Crystal / General-Purpose Machine Learning

• crystal-fann (⭐82) - FANN (Fast Artificial Neural Network) binding.

Erlang / General-Purpose Machine Learning

• Disco (⭐1.6k) - Map Reduce in Erlang. [Deprecated]

Go / General-Purpose Machine Learning

• go-pr (⭐62) - Pattern recognition package in Go lang. [Deprecated]

• go-ml (⭐197) - Linear / Logistic regression, Neural Networks, Collaborative Filtering and Gaussian Multivariate Distribution. [Deprecated]

• bayesian (⭐744) - Naive Bayesian Classification for Golang. [Deprecated]

• go-galib (⭐194) - Genetic Algorithms library written in Go / Golang. [Deprecated]

• Cloudforest (⭐724) - Ensembles of decision trees in Go/Golang. [Deprecated]

Go / Data Analysis / Data Visualization

• SVGo (⭐2k) - The Go Language library for SVG generation.

• RF (⭐112) - Random forests implementation in Go. [Deprecated]

Haskell / General-Purpose Machine Learning

• haskell-ml (⭐56) - Haskell implementations of various ML algorithms. [Deprecated]

• HLearn (⭐1.6k) - a suite of libraries for interpreting machine learning models according to their algebraic structure. [Deprecated]

• hnn (⭐112) - Haskell Neural Network library.

• hopfield-networks (⭐16) - Hopfield Networks for unsupervised learning in Haskell. [Deprecated]

• DNNGraph (⭐695) - A DSL for deep neural networks. [Deprecated]

• LambdaNet (⭐375) - Configurable Neural Networks in Haskell. [Deprecated]

Java / Natural Language Processing

• Cortical.io - Retina: an API performing complex NLP operations (disambiguation, classification, streaming text filtering, etc...) as quickly and intuitively as the brain.

• IRIS - Cortical.io's FREE NLP, Retina API Analysis Tool (written in JavaFX!) - See the Tutorial Video.

• CoreNLP - Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words.

• Stanford Parser - A natural language parser is a program that works out the grammatical structure of sentences.

• Stanford POS Tagger - A Part-Of-Speech Tagger (POS Tagger).

• Stanford Name Entity Recognizer - Stanford NER is a Java implementation of a Named Entity Recognizer.

• Stanford Word Segmenter - Tokenization of raw text is a standard pre-processing step for many NLP tasks.

• Tregex, Tsurgeon and Semgrex - Tregex is a utility for matching patterns in trees, based on tree relationships and regular expression matches on nodes (the name is short for "tree regular expressions").

• Stanford Phrasal: A Phrase-Based Translation System

• Stanford English Tokenizer - Stanford Phrasal is a state-of-the-art statistical phrase-based machine translation system, written in Java.

• Stanford Tokens Regex - A tokenizer divides text into a sequence of tokens, which roughly correspond to "words".

• Stanford Temporal Tagger - SUTime is a library for recognizing and normalizing time expressions.

• Stanford SPIED - Learning entities from unlabeled text starting with seed sets using patterns in an iterative fashion.

• Twitter Text Java (⭐2.9k) - A Java implementation of Twitter's text processing library.

• ClearTK (⭐132) - ClearTK provides a framework for developing statistical natural language processing (NLP) components in Java and is built on top of Apache UIMA. [Deprecated]

• NLP4J (⭐148) - The NLP4J project provides software and resources for natural language processing. The project started at the Center for Computational Language and EducAtion Research, and is currently developed by the Center for Language and Information Research at Emory University. [Deprecated]

• CogcompNLP (⭐460) - This project collects a number of core libraries for Natural Language Processing (NLP) developed in the University of Illinois' Cognitive Computation Group, for example illinois-core-utilities which provides a set of NLP-friendly data structures and a number of NLP-related utilities that support writing NLP applications, running experiments, etc, illinois-edison a library for feature extraction from illinois-core-utilities data structures and many other packages.

Scala / General-Purpose Machine Learning

• FlinkML in Apache Flink - Distributed machine learning library in Flink.

• DeepLearning.scala - Creating statically typed dynamic neural networks from object-oriented & functional programming constructs.

• ganitha (⭐109) - Scalding powered machine learning. [Deprecated]

• Saul (⭐63) - Flexible Declarative Learning-Based Programming.

Scala / Data Analysis / Data Visualization

• MLlib in Apache Spark - Distributed machine learning library in Spark

• Flink - Open source platform for distributed stream and batch data processing.

• xerial (⭐17) - Data management utilities for Scala. [Deprecated]

• PredictionIO (⭐13k) - PredictionIO, a machine learning server for software developers and data engineers.

Java / General-Purpose Machine Learning

• RankLib - RankLib is a library of learning to rank algorithms. [Deprecated]

• Stanford Classifier - A classifier is a machine learning tool that will take data items and place them into one of k classes.

• SystemML (⭐949) - flexible, scalable machine learning (ML) language.

• Weka - Weka is a collection of machine learning algorithms for data mining tasks.

• LBJava (⭐13) - Learning Based Java is a modelling language for the rapid development of software systems, offers a convenient, declarative syntax for classifier and constraint definition directly in terms of the objects in the programmer's application.

Java / Speech Recognition

• CMU Sphinx - Open Source Toolkit For Speech Recognition purely based on Java speech recognition library.

Java / Data Analysis / Data Visualization

• Hadoop (⭐13k) - Hadoop/HDFS.

• Storm - Storm is a distributed realtime computation system.

• DataMelt - Mathematics software for numeric computation, statistics, symbolic calculations, data analysis and data visualization.

JavaScript / Natural Language Processing

• Retext (⭐2.2k) - Extensible system for analyzing and manipulating natural language.

• NLP Compromise (⭐11k) - Natural Language processing in the browser.

JavaScript / Data Analysis / Data Visualization

• High Charts

• dc.js

• chartjs

• D3xter (⭐341) - Straight forward plotting built on D3. [Deprecated]

• statkit (⭐50) - Statistics kit for JavaScript. [Deprecated]

• science.js (⭐875) - Scientific and statistical computing in JavaScript. [Deprecated]

• Z3d (⭐89) - Easily make interactive 3d plots built on Three.js [Deprecated]

• C3.js - customizable library based on D3.js for easy chart drawing.

• Datamaps - Customizable SVG map/geo visualizations using D3.js. [Deprecated]

• ZingChart - library written on Vanilla JS for big data visualization.

• cheminfo - Platform for data visualization and analysis, using the visualizer (⭐35) project.

• AnyChart

• FusionCharts

• Nivo - built on top of the awesome d3 and Reactjs libraries

JavaScript / General-Purpose Machine Learning

• Convnet.js - ConvNetJS is a JavaScript library for training Deep Learning models[DEEP LEARNING] [Deprecated]

• Clusterfck - Agglomerative hierarchical clustering implemented in JavaScript for Node.js and the browser. [Deprecated]

• Clustering.js (⭐29) - Clustering algorithms implemented in JavaScript for Node.js and the browser. [Deprecated]

• Decision Trees (⭐204) - NodeJS Implementation of Decision Tree using ID3 Algorithm. [Deprecated]

• DN2A (⭐464) - Digital Neural Networks Architecture. [Deprecated]

• Node-fann (⭐185) - FANN (Fast Artificial Neural Network Library) bindings for Node.js [Deprecated]

• Kmeans.js (⭐44) - Simple JavaScript implementation of the k-means algorithm, for node.js and the browser. [Deprecated]

• Learning.js (⭐66) - JavaScript implementation of logistic regression/c4.5 decision tree [Deprecated]

• machinelearn.js (⭐525) - Machine Learning library for the web, Node.js and developers

• Brain.js (⭐14k) - Neural networks in JavaScript - continued community fork of Brain (⭐8k).

• Bayesian-Bandit (⭐44) - Bayesian bandit implementation for Node and the browser. [Deprecated]

• NeuralN (⭐274) - C++ Neural Network library for Node.js. It has advantage on large dataset and multi-threaded training. [Deprecated]

• kalman (⭐113) - Kalman filter for JavaScript. [Deprecated]

• shaman (⭐108) - Node.js library with support for both simple and multiple linear regression. [Deprecated]

JavaScript / Misc

• sylvester (⭐1.1k) - Vector and Matrix math for JavaScript. [Deprecated]

• Lyric (⭐43) - Linear Regression library. [Deprecated]

Julia / General-Purpose Machine Learning

• MachineLearning (⭐113) - Julia Machine Learning library. [Deprecated]

• Regression (⭐59) - Algorithms for regression analysis (e.g. linear regression and logistic regression). [Deprecated]

• Local Regression (⭐79) - Local regression, so smooooth!

• Naive Bayes (⭐8) - Simple Naive Bayes implementation in Julia. [Deprecated]

• Simple MCMC (⭐12) - basic MCMC sampler implemented in Julia. [Deprecated]

• Distances (⭐366) - Julia module for Distance evaluation.

• MCMC (⭐35) - MCMC tools for Julia. [Deprecated]

• Online Learning (⭐14) [Deprecated]

• MultivariateStats (⭐335) - Methods for dimensionality reduction.

• ANN (⭐57) - Julia artificial neural networks. [Deprecated]

• Mocha (⭐1.3k) - Deep Learning framework for Julia inspired by Caffe. [Deprecated]

Julia / Natural Language Processing

• Topic Models (⭐36) - TopicModels for Julia. [Deprecated]

• Text Analysis (⭐350) - Julia package for text analysis.

Julia / Data Analysis / Data Visualization

• Data Frames Meta (⭐431) - Metaprogramming tools for DataFrames.

• Julia Data (⭐6) - library for working with tabular data in Julia. [Deprecated]

• Data Read (⭐73) - Read files from Stata, SAS, and SPSS.

• Stats (⭐128) - Statistical tests for Julia.

• DataFrames (⭐1.6k) - library for working with tabular data in Julia.

• Data Arrays (⭐52) - Data structures that allow missing values. [Deprecated]

Julia / Misc Stuff / Presentations

• SignalProcessing (⭐326) - Signal Processing tools for Julia.

Lua / General-Purpose Machine Learning

• Lunatic Python

• Lua - Numerical Algorithms [Deprecated]

• Lunum (⭐32) [Deprecated]

Matlab / Computer Vision

• Shearlets - MATLAB code for shearlet transform.

• mexopencv - Collection and a development kit of MATLAB mex functions for OpenCV library.

Matlab / Data Analysis / Data Visualization

• matlab_bgl - MatlabBGL is a Matlab package for working with graphs.

• gaimc - Efficient pure-Matlab implementations of graph algorithms to complement MatlabBGL's mex functions.

.NET / General-Purpose Machine Learning

• Accord.MachineLearning - Support Vector Machines, Decision Trees, Naive Bayesian models, K-means, Gaussian Mixture models and general algorithms such as Ransac, Cross-validation and Grid-Search for machine-learning applications. This package is part of the Accord.NET Framework.

• DiffSharp - An automatic differentiation (AD) library providing exact and efficient derivatives (gradients, Hessians, Jacobians, directional derivatives, and matrix-free Hessian- and Jacobian-vector products) for machine learning and optimization applications. Operations can be nested to any level, meaning that you can compute exact higher-order derivatives and differentiate functions that are internally making use of differentiation, for applications such as hyperparameter optimization.

• Encog - An advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trains using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks.

.NET / Data Analysis / Data Visualization

• numl - numl is a machine learning library intended to ease the use of using standard modelling techniques for both prediction and clustering.

• Sho - Sho is an interactive environment for data analysis and scientific computing that lets you seamlessly connect scripts (in IronPython) with compiled code (in .NET) to enable fast and flexible prototyping. The environment includes powerful and efficient libraries for linear algebra as well as data visualization that can be used from any .NET language, as well as a feature-rich interactive shell for rapid development.

General-Purpose Machine Learning / Data Analysis / Data Visualization

• KRFuzzyCMeans-Algorithm (⭐12) - It implemented Fuzzy C-Means (FCM) the fuzzy clustering / classification algorithm on Machine Learning. It could be used in data mining and image compression. [Deprecated]

• Oml (⭐116) - A general statistics and machine learning library.

• GPR - Efficient Gaussian Process Regression in OCaml.

• Libra-Tk - Algorithms for learning and inference with discrete probabilistic models.

• Algorithm::SVMLight, implementation of Support Vector Machines with SVMLight under it. [Deprecated]

• Several machine learning and artificial intelligence models are included in the AI namespace. For instance, you can find Naïve Bayes.

Perl 6 / Data Analysis / Data Visualization

• Support Vector Machines (⭐8)

Python / Computer Vision

• PCV (⭐1.9k) - Open source Python module for computer vision. [Deprecated]

• PyTorchCV (⭐40) - A PyTorch-Based Framework for Deep Learning in Computer Vision.

Python / Natural Language Processing

• NLTK - A leading platform for building Python programs to work with human language data.

• YAlign (⭐127) - A sentence aligner, a friendly tool for extracting parallel sentences from comparable corpora. [Deprecated]

• spammy (⭐137) - A library for email Spam filtering built on top of NLTK

• loso (⭐82) - Another Chinese segmentation library. [Deprecated]

• nut (⭐119) - Natural language Understanding Toolkit. [Deprecated]

• BLLIP Parser - Python bindings for the BLLIP Natural Language Parser (also known as the Charniak-Johnson parser). [Deprecated]

• PyNLPl (⭐460) - Python Natural Language Processing Library. General purpose NLP library for Python. Also contains some specific modules for parsing common NLP formats, most notably for FoLiA, but also ARPA language models, Moses phrasetables, GIZA++ alignments.

• spaCy (⭐25k) - Industrial strength NLP with Python and Cython.

• Distance (⭐113) - Levenshtein and Hamming distance computation. [Deprecated]

• editdistance - fast implementation of edit distance.

• stanford-corenlp-python (⭐610) - Python wrapper for Stanford CoreNLP (⭐8.9k) [Deprecated]

Python / Data Analysis / Data Visualization

• SciPy - A Python-based ecosystem of open-source software for mathematics, science, and engineering.

• NumPy - A fundamental package for scientific computing with Python.

• Numba - Python JIT (just in time) compiler to LLVM aimed at scientific Python by the developers of Cython and NumPy.

• igraph - binding to igraph library - General purpose graph library.

• Pandas - A library providing high-performance, easy-to-use data structures and data analysis tools.

• Open Mining (⭐1.2k) - Business Intelligence (BI) in Python (Pandas web interface) [Deprecated]

• PyDy - Short for Python Dynamics, used to assist with workflow in the modelling of dynamic motion based around NumPy, SciPy, IPython, and matplotlib.

• astropy - A community Python library for Astronomy.

• matplotlib - A Python 2D plotting library.

• altair (⭐8.1k) - A Python to Vega translator.

• ggplot (⭐3.6k) - Same API as ggplot2 for R. [Deprecated]

• pycascading (⭐223) [Deprecated]

• windML (⭐125) - A Python Framework for Wind Energy Analysis and Prediction.

• cerebro2 (⭐24) A web-based visualization and debugging platform for NuPIC. [Deprecated]

• NuPIC Studio (⭐93) An all-in-one NuPIC Hierarchical Temporal Memory visualization and debugging super-tool! [Deprecated]

• Seaborn - A python visualization library based on matplotlib.

• Superset (⭐51k) - A data exploration platform designed to be visual, intuitive, and interactive.

• visualize_ML (⭐169) - A python package for data exploration and data analysis. [Deprecated]

Python / Misc Scripts / iPython Notebooks / Codebases

• BioPy (⭐41) - Biologically-Inspired and Machine Learning Algorithms in Python. [Deprecated]

• A gallery of interesting IPython notebooks (⭐14k)

• Python Programming for the Humanities - Course for Python programming for the Humanities, assuming no prior knowledge. Heavy focus on text processing / NLP.

• Practical XGBoost in Python - comprehensive online course about using XGBoost in Python.

Python / Neural Networks

• Neuron (⭐38) - Neuron is simple class for time series predictions. It's utilize LNU (Linear Neural Unit), QNU (Quadratic Neural Unit), RBF (Radial Basis Function), MLP (Multi Layer Perceptron), MLP-ELM (Multi Layer Perceptron - Extreme Learning Machine) neural networks learned with Gradient descent or LeLevenberg–Marquardt algorithm. [Deprecated]

• NeuralTalk (⭐5.4k) - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences. [Deprecated]

Ruby / Natural Language Processing

• Treat (⭐1.4k) - Text Retrieval and Annotation Toolkit, definitely the most comprehensive toolkit I’ve encountered so far for Ruby.

• Stemmer (⭐254) - Expose libstemmer_c to Ruby. [Deprecated]

• Twitter-text-rb (⭐2.9k) - A library that does auto linking and extraction of usernames, lists and hashtags in tweets.

Ruby / General-Purpose Machine Learning

• Ruby Machine Learning (⭐32) - Some Machine Learning algorithms, implemented in Ruby. [Deprecated]

• Machine Learning Ruby (⭐15) [Deprecated]

• jRuby Mahout (⭐163) - JRuby Mahout is a gem that unleashes the power of Apache Mahout in the world of JRuby. [Deprecated]

• Scoruby (⭐68) - Creates Random Forest classifiers from PMML files.

Ruby / Data Analysis / Data Visualization

• data-visualization-ruby (⭐68) - Source code and supporting content for my Ruby Manor presentation on Data Visualisation with Ruby. [Deprecated]

• ruby-plot - gnuplot wrapper for Ruby, especially for plotting ROC curves into SVG files. [Deprecated]

• plot-rb (⭐41) - A plotting library in Ruby built on top of Vega and D3. [Deprecated]

• scruffy (⭐31) - A beautiful graphing toolkit for Ruby.

• Glean (⭐115) - A data management tool for humans. [Deprecated]

• Arel (⭐266) [Deprecated]

Rust / General-Purpose Machine Learning

• leaf (⭐5.5k) - open source framework for machine intelligence, sharing concepts from TensorFlow and Caffe. Available under the MIT license. [Deprecated]

• RustNN (⭐318) - RustNN is a feedforward neural network library. [Deprecated]

R / Data Manipulation | Data Analysis | Data Visualization

• ggplot2 - A data visualization package based on the grammar of graphics.

• shiny is the basis for truly interactive displays and dashboards in R. However, some measure of interactivity can be achieved with htmlwidgets bringing javascript libraries to R. These include, plotly, dygraphs, highcharter, and several others.

SAS / General-Purpose Machine Learning

• Visual Data Mining and Machine Learning - Interactive, automated, and programmatic modelling with the latest machine learning algorithms in and end-to-end analytics environment, from data prep to deployment. Free trial available.

SAS / Data Analysis / Data Visualization

• SAS/STAT - For conducting advanced statistical analysis.

SAS / Natural Language Processing

• Contextual Analysis - Add structure to unstructured text using a GUI.

• Sentiment Analysis - Extract sentiment from text using a GUI.

• Text Miner - Text mining using a GUI or code.

Scala / Natural Language Processing

• Chalk (⭐259) - Chalk is a natural language processing library. [Deprecated]

Tools / Neural Networks

• layer (⭐555) - Neural network inference from the command line

Swift / General-Purpose Machine Learning

• Swift AI (⭐5.9k) - Highly optimized artificial intelligence and machine learning library written in Swift.

• BrainCore (⭐378) - The iOS and OS X neural network framework.

• swix (⭐590) - A bare bones library that includes a general matrix language and wraps some OpenCV for iOS development. [Deprecated]

• AIToolbox (⭐776) - A toolbox framework of AI modules written in Swift: Graphs/Trees, Linear Regression, Support Vector Machines, Neural Networks, PCA, KMeans, Genetic Algorithms, MDP, Mixture of Gaussians.

• Awesome CoreML (⭐538) - A curated list of pretrained CoreML models.

Jan 14 - Jan 20, 2019

C++ / General-Purpose Machine Learning

• Feast (⭐4k) - A feature store for the management, discovery, and access of machine learning features. Feast provides a consistent view of feature data for both model training and model serving.

Python / General-Purpose Machine Learning

• PyOD (⭐6.8k) -> Python Outlier Detection, comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. Featured for Advanced models, including Neural Networks/Deep Learning and Outlier Ensembles.

Dec 24 - Dec 30, 2018

General-Purpose Machine Learning / Data Analysis / Data Visualization

• Rubix ML - A high-level machine learning (ML) library that lets you build programs that learn from data using the PHP language.

Dec 17 - Dec 23, 2018

Python / General-Purpose Machine Learning

• MindsDB (⭐14k) - Open Source framework to streamline use of neural networks.

Python / Misc Scripts / iPython Notebooks / Codebases

• Homemade Machine Learning (⭐21k) - Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained

Dec 10 - Dec 16, 2018

Clojure / General-Purpose Machine Learning

• Infer (⭐176) - Inference and machine learning in Clojure. [Deprecated]

Python / General-Purpose Machine Learning

• Apache SINGA - An Apache Incubating project for developing an open source machine learning library.

R / General-Purpose Machine Learning

• L0Learn - L0Learn: Fast algorithms for best subset selection.

Tools / Misc

• Notebooks (⭐30) - A starter kit for Jupyter notebooks and machine learning. Companion docker images consist of all combinations of python versions, machine learning frameworks (Keras, PyTorch and Tensorflow) and CPU/CUDA versions.

Nov 26 - Dec 02, 2018

Python / Data Analysis / Data Visualization

• Lambdo (⭐15) - A workflow engine for solving machine learning problems by combining in one analysis pipeline (i) feature engineering and machine learning (ii) model training and prediction (iii) table population and column evaluation via user-defined (Python) functions.

Nov 05 - Nov 11, 2018

Elixir / General-Purpose Machine Learning

• emel (⭐93) - A simple and functional machine learning library written in Elixir.

Python / General-Purpose Machine Learning

• Thampi (⭐9) - Machine Learning Prediction System on AWS Lambda

Oct 29 - Nov 04, 2018

Matlab / General-Purpose Machine Learning

• Machine Learning in MatLab/Octave (⭐775) - examples of popular machine learning algorithms (neural networks, linear/logistic regressions, K-Means, etc.) with code examples and mathematics behind them being explained.

Tools / Misc

• DVC (⭐11k) - Data Science Version Control is an open-source version control system for machine learning projects with pipelines support. It makes ML projects reproducible and shareable.

Oct 22 - Oct 28, 2018

JavaScript / General-Purpose Machine Learning

• ml5 (⭐6k) - Friendly machine learning for the web!

Python / Reinforcement Learning

• Coach (⭐2.2k) - Reinforcement Learning Coach by Intel® AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

Oct 15 - Oct 21, 2018

Python / Natural Language Processing

• NeuroNER (⭐1.6k) - Named-entity recognition using neural networks providing state-of-the-art-results

R / Data Manipulation | Data Analysis | Data Visualization

• tmap for visualizing geospatial data with static maps and leaflet for interactive maps

• tm and quanteda are the main packages for managing, analyzing, and visualizing textual data.

Oct 08 - Oct 14, 2018

JavaScript / General-Purpose Machine Learning

• Netron (⭐21k) - Visualizer for machine learning models.

Python / Natural Language Processing

• Dedupe (⭐3.7k) - A python library for accurate and scalable fuzzy matching, record deduplication and entity-resolution.

Oct 01 - Oct 07, 2018

Java / General-Purpose Machine Learning

• liblinear-java (⭐307) - Java version of liblinear.

Sep 17 - Sep 23, 2018

Python / Data Analysis / Data Visualization

• Dash (⭐18k) - A framework for creating analytical web applications built on top of Plotly.js, React, and Flask

Python / Misc Scripts / iPython Notebooks / Codebases

• SVM Explorer (⭐152) - Interactive SVM Explorer, using Dash and scikit-learn

Sep 10 - Sep 16, 2018

Python / Data Analysis / Data Visualization

• PyCM (⭐1.4k) - PyCM is a multi-class confusion matrix library written in Python that supports both input data vectors and direct matrix, and a proper tool for post-classification model evaluation that supports most classes and overall statistics parameters

Aug 27 - Sep 02, 2018

Python / General-Purpose Machine Learning

• steppy-toolkit (⭐21) -> Curated collection of the neural networks, transformers and models that make your machine learning work faster and more effective.

Python / Kaggle Competition Source Code

• open-solution-home-credit (⭐434) -> source code and experiments results for Home Credit Default Risk.

• open-solution-googleai-object-detection (⭐46) -> source code and experiments results for Google AI Open Images - Object Detection Track.

• open-solution-salt-identification (⭐121) -> source code and experiments results for TGS Salt Identification Challenge.

• open-solution-ship-detection (⭐55) -> source code and experiments results for Airbus Ship Detection Challenge.

• open-solution-data-science-bowl-2018 (⭐160) -> source code and experiments results for 2018 Data Science Bowl.

• open-solution-value-prediction (⭐36) -> source code and experiments results for Santander Value Prediction Challenge.

• open-solution-toxic-comments (⭐151) -> source code for Toxic Comment Classification Challenge.

Swift / General-Purpose Machine Learning

• PredictionBuilder (⭐11) - A library for machine learning that builds predictions using a linear regression.

Aug 20 - Aug 26, 2018

.NET / Computer Vision

• Emgu CV - Cross platform wrapper of OpenCV which can be compiled in Mono to be run on Windows, Linus, Mac OS X, iOS, and Android.

Aug 13 - Aug 19, 2018

Go / General-Purpose Machine Learning

• eaopt (⭐830) - An evolutionary optimization library.

General-Purpose Machine Learning / Data Analysis / Data Visualization

• 19 Questions (⭐16) - A machine learning / bayesian inference assigning attributes to objects.

Python / Natural Language Processing

• Snips NLU (⭐3.8k) - Natural Language Understanding library for intent classification and entity extraction

Python / General-Purpose Machine Learning

• keras (⭐57k) - High-level neural networks frontend for TensorFlow (⭐172k), CNTK (⭐17k) and Theano (⭐9.7k).

Jul 30 - Aug 05, 2018

TensorFlow / General-Purpose Machine Learning

• Golden TensorFlow - A page of content on TensorFlow, including academic papers and links to related topics.

Jul 09 - Jul 15, 2018

Python / Computer Vision

• albumentations (⭐12k) - А fast and framework agnostic image augmentation library that implements a diverse set of augmentation techniques. Supports classification, segmentation, detection out of the box. Was used to win a number of Deep Learning competitions at Kaggle, Topcoder and those that were a part of the CVPR workshops.

Jul 02 - Jul 08, 2018

Python / Reinforcement Learning

• Roboschool (⭐2.1k) - Open-source software for robot simulation, integrated with OpenAI Gym.

• Retro (⭐2.9k) - Retro Games in Gym

• SLM Lab (⭐1.1k) - Modular Deep Reinforcement Learning framework in PyTorch.

Jun 25 - Jul 01, 2018

C++ / General-Purpose Machine Learning

• PyCUDA - Python interface to CUDA

JavaScript / Demos and Scripts

• The Bot (⭐5) - Example of how the neural network learns to predict the angle between two points created with Synaptic (⭐6.9k).

• Half Beer (⭐7) - Beer glass classifier created with Synaptic (⭐6.9k).

Python / General-Purpose Machine Learning

• mlens (⭐770) - A high performance, memory efficient, maximally parallelized ensemble learning, integrated with scikit-learn.

May 28 - Jun 03, 2018

Scala / General-Purpose Machine Learning

• doddle-model (⭐141) - An in-memory machine learning library built on top of Breeze. It provides immutable objects and exposes its functionality through a scikit-learn-like API.

May 07 - May 13, 2018

JavaScript / General-Purpose Machine Learning

• TensorFlow.js - A WebGL accelerated, browser based JavaScript library for training and deploying ML models.

.NET / General-Purpose Machine Learning

• GeneticSharp (⭐1.1k) - Multi-platform genetic algorithm library for .NET Core and .NET Framework. The library has several implementations of GA operators, like: selection, crossover, mutation, reinsertion and termination.

• ML.NET (⭐8.3k) - ML.NET is a cross-platform open-source machine learning framework which makes machine learning accessible to .NET developers. ML.NET was originally developed in Microsoft Research and evolved into a significant framework over the last decade and is used across many product groups in Microsoft like Windows, Bing, PowerPoint, Excel and more.

• Vulpes (⭐116) - Deep belief and deep learning implementation written in F# and leverages CUDA GPU execution with Alea.cuBase.

Apr 30 - May 06, 2018

Python / General-Purpose Machine Learning

• xLearn (⭐3k) - A high performance, easy-to-use, and scalable machine learning package, which can be used to solve large-scale machine learning problems. xLearn is especially useful for solving machine learning problems on large-scale sparse data, which is very common in Internet services such as online advertisement and recommender systems.

Rust / General-Purpose Machine Learning

• RusticSOM (⭐27) - A Rust library for Self Organising Maps (SOM).

Mar 19 - Mar 25, 2018

Matlab / General-Purpose Machine Learning

• MXNet (⭐20k) - Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Go, JavaScript and more.

Mar 05 - Mar 11, 2018

JavaScript / General-Purpose Machine Learning

• xgboost-node (⭐32) - Run XGBoost model and make predictions in Node.js.

Feb 26 - Mar 04, 2018

Python / General-Purpose Machine Learning

• neonrvm (⭐33) - neonrvm is an open source machine learning library based on RVM technique. It's written in C programming language and comes with Python programming language bindings.

Feb 12 - Feb 18, 2018

JavaScript / Misc

• MLPleaseHelp (⭐5) - MLPleaseHelp is a simple ML resource search engine. You can use this search engine right now at https://jgreenemi.github.io/MLPleaseHelp/, provided via GitHub Pages.

Python / General-Purpose Machine Learning

• Parris (⭐320) - Parris, the automated infrastructure setup tool for machine learning algorithms.

Feb 05 - Feb 11, 2018

R / General-Purpose Machine Learning

• CatBoost (⭐7k) - General purpose gradient boosting on decision trees library with categorical features support out of the box for R.

JavaScript / General-Purpose Machine Learning

• Keras.js (⭐4.9k) - Run Keras models in the browser, with GPU support provided by WebGL 2.

Python / Data Analysis / Data Visualization

• lime (⭐10k) - Lime is about explaining what machine learning classifiers (or models) are doing. It is able to explain any black box classifier, with two or more classes.

Python / Misc Scripts / iPython Notebooks / Codebases

• Introduction to Machine Learning with Python (⭐6.6k) - Notebooks and code for the book "Introduction to Machine Learning with Python"

• Pydata book (⭐19k) - Materials and IPython notebooks for "Python for Data Analysis" by Wes McKinney, published by O'Reilly Media

Jan 01 - Jan 07, 2018

Lua / General-Purpose Machine Learning

• Torch7
  • cephes (⭐45) - Cephes mathematical functions library, wrapped for Torch. Provides and wraps the 180+ special mathematical functions from the Cephes mathematical library, developed by Stephen L. Moshier. It is used, among many other places, at the heart of SciPy. [Deprecated]
  • autograd (⭐545) - Autograd automatically differentiates native Torch code. Inspired by the original Python version.
  • graph (⭐36) - Graph package for Torch. [Deprecated]
  • randomkit (⭐35) - Numpy's randomkit, wrapped for Torch. [Deprecated]
  • signal (⭐47) - A signal processing toolbox for Torch-7. FFT, DCT, Hilbert, cepstrums, stft.
  • nn (⭐1.3k) - Neural Network package for Torch.
  • torchnet (⭐993) - framework for torch which provides a set of abstractions aiming at encouraging code re-use as well as encouraging modular programming.
  • nngraph (⭐297) - This package provides graphical computation for nn library in Torch7.
  • nnx (⭐96) - A completely unstable and experimental package that extends Torch's builtin nn library.
  • rnn (⭐933) - A Recurrent Neural Network library that extends Torch's nn. RNNs, LSTMs, GRUs, BRNNs, BLSTMs, etc.
  • dpnn (⭐193) - Many useful features that aren't part of the main nn package.
  • dp (⭐344) - A deep learning library designed for streamlining research and development using the Torch7 distribution. It emphasizes flexibility through the elegant use of object-oriented design patterns. [Deprecated]
  • optim (⭐197) - An optimization library for Torch. SGD, Adagrad, Conjugate-Gradient, LBFGS, RProp and more.
  • unsup (⭐85) - A package for unsupervised learning in Torch. Provides modules that are compatible with nn (LinearPsd, ConvPsd, AutoEncoder, ...), and self-contained algorithms (k-means, PCA). [Deprecated]
  • manifold (⭐134) - A package to manipulate manifolds.
  • svm (⭐43) - Torch-SVM library. [Deprecated]
  • lbfgs (⭐2) - FFI Wrapper for liblbfgs. [Deprecated]
  • vowpalwabbit (⭐2) - An old vowpalwabbit interface to torch. [Deprecated]
  • OpenGM (⭐8) - OpenGM is a C++ library for graphical modelling, and inference. The Lua bindings provide a simple way of describing graphs, from Lua, and then optimizing them with OpenGM. [Deprecated]
  • spaghetti (⭐2) - Spaghetti (sparse linear) module for torch7 by @MichaelMathieu [Deprecated]
  • LuaSHKit (⭐3) - A Lua wrapper around the Locality sensitive hashing library SHKit [Deprecated]
  • kernel smoothing (⭐5) - KNN, kernel-weighted average, local linear regression smoothers. [Deprecated]
  • cutorch (⭐335) - Torch CUDA Implementation.
  • cunn (⭐209) - Torch CUDA Neural Network Implementation.
  • imgraph (⭐22) - An image/graph library for Torch. This package provides routines to construct graphs on images, segment them, build trees out of them, and convert them back to images. [Deprecated]
  • videograph (⭐9) - A video/graph library for Torch. This package provides routines to construct graphs on videos, segment them, build trees out of them, and convert them back to videos. [Deprecated]
  • saliency (⭐6) - code and tools around integral images. A library for finding interest points based on fast integral histograms. [Deprecated]
  • stitch (⭐4) - allows us to use hugin to stitch images and apply same stitching to a video sequence. [Deprecated]
  • sfm (⭐3) - A bundle adjustment/structure from motion package. [Deprecated]
  • fex (⭐10) - A package for feature extraction in Torch. Provides SIFT and dSIFT modules. [Deprecated]
  • OverFeat (⭐594) - A state-of-the-art generic dense feature extractor. [Deprecated]
  • wav2letter (⭐6.2k) - a simple and efficient end-to-end Automatic Speech Recognition (ASR) system from Facebook AI Research.

Dec 18 - Dec 24, 2017

C++ / General-Purpose Machine Learning

• proNet-core (⭐3) - A general-purpose network embedding framework: pair-wise representations optimization Network Edit.

Go / Natural Language Processing

• sentences (⭐348) - Golang implementation of Punkt sentence tokenizer.

Nov 06 - Nov 12, 2017

Python / General-Purpose Machine Learning

• xRBM (⭐55) - A library for Restricted Boltzmann Machine (RBM) and its conditional variants in Tensorflow.

Oct 30 - Nov 05, 2017

C / Computer Vision

• CCV (⭐6.9k) - C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library.

C++ / General-Purpose Machine Learning

• DLib - A suite of ML tools designed to be easy to imbed in other applications.

• Stan - A probabilistic programming language implementing full Bayesian statistical inference with Hamiltonian Monte Carlo sampling.

Python / General-Purpose Machine Learning

• Shogun (⭐2.9k) - The Shogun Machine Learning Toolbox.

• XGBoost (⭐24k) - Python bindings for eXtreme Gradient Boosting (Tree) Library.

• Bayesian Methods for Hackers (⭐25k) - Book/iPython notebooks on Probabilistic Programming in Python.

• Featureforge (⭐380) A set of tools for creating and testing machine learning features, with a scikit-learn compatible API.

• thinking bayes (⭐1.6k) - Book on Bayesian Analysis.

• nilearn (⭐940) - Machine learning for NeuroImaging in Python.

• Theano (⭐9.7k) - Optimizing GPU-meta-programming code generating array oriented optimizing math compiler in Python.

• TensorFlow (⭐172k) - Open source software library for numerical computation using data flow graphs.

• Neural Networks and Deep Learning (⭐14k) - Code samples for my book "Neural Networks and Deep Learning" [DEEP LEARNING].

• Annoy (⭐11k) - Approximate nearest neighbours implementation.

• skbayes (⭐486) - Python package for Bayesian Machine Learning with scikit-learn API.

• Xcessiv (⭐1.3k) - A web-based application for quick, scalable, and automated hyperparameter tuning and stacked ensembling.

C++ / Natural Language Processing

• BLLIP Parser (⭐218) - BLLIP Natural Language Parser (also known as the Charniak-Johnson parser).

Common Lisp / General-Purpose Machine Learning

• cl-online-learning (⭐46) - Online learning algorithms (Perceptron, AROW, SCW, Logistic Regression).

• cl-random-forest (⭐55) - Implementation of Random Forest in Common Lisp.

Clojure / Natural Language Processing

• Clojure-openNLP (⭐741) - Natural Language Processing in Clojure (opennlp).

• Infections-clj (⭐203) - Rails-like inflection library for Clojure and ClojureScript.

Clojure / Data Visualization

• Envision (⭐78) - Clojure Data Visualisation library, based on Statistiker and D3.

Go / General-Purpose Machine Learning

• gobrain (⭐535) - Neural Networks written in Go.

Java / General-Purpose Machine Learning

• Datumbox (⭐1.1k) - Machine Learning framework for rapid development of Machine Learning and Statistical applications.

• htm.java (⭐302) - General Machine Learning library using Numenta’s Cortical Learning Algorithm.

• Mahout (⭐2k) - Distributed machine learning.

• rapaio (⭐64) - statistics, data mining and machine learning toolbox in Java.

• RapidMiner - RapidMiner integration into Java code.

Java / Data Analysis / Data Visualization

• Impala (⭐28) - Real-time Query for Hadoop.

Java / Deep Learning

• Deeplearning4j (⭐13k) - Scalable deep learning for industry with parallel GPUs.

JavaScript / Natural Language Processing

• Twitter-text (⭐2.9k) - A JavaScript implementation of Twitter's text processing library.

• natural (⭐10k) - General natural language facilities for node.

• Knwl.js (⭐5.3k) - A Natural Language Processor in JS.

JavaScript / General-Purpose Machine Learning

• figue - K-means, fuzzy c-means and agglomerative clustering.

• Gaussian Mixture Model (⭐26) - Unsupervised machine learning with multivariate Gaussian mixture model.

• mil-tokyo - List of several machine learning libraries.

• Synaptic (⭐6.9k) - Architecture-free neural network library for Node.js and the browser.

• kNear (⭐45) - JavaScript implementation of the k nearest neighbors algorithm for supervised learning.

• Pavlov.js (⭐500) - Reinforcement learning using Markov Decision Processes.

Julia / General-Purpose Machine Learning

• MLBase (⭐180) - A set of functions to support the development of machine learning algorithms.

• DA (⭐9) - Julia package for Regularized Discriminant Analysis.

• Mixed Models (⭐354) - A Julia package for fitting (statistical) mixed-effects models.

• Decision Tree (⭐8) - Decision Tree Classifier and Regressor.

• Neural (⭐47) - A neural network in Julia.

• Mamba (⭐252) - Markov chain Monte Carlo (MCMC) for Bayesian analysis in Julia.

• GLM (⭐531) - Generalized linear models in Julia.

• Gaussian Processes (⭐289) - Julia package for Gaussian processes.

• GLMNet (⭐88) - Julia wrapper for fitting Lasso/ElasticNet GLM models using glmnet.

• Kernel Density (⭐145) - Kernel density estimators for Julia.

• NMF (⭐85) - A Julia package for non-negative matrix factorization.

• XGBoost (⭐257) - eXtreme Gradient Boosting Package in Julia.

• ManifoldLearning (⭐81) - A Julia package for manifold learning and nonlinear dimensionality reduction.

• Merlin (⭐145) - Flexible Deep Learning Framework in Julia.

• ROCAnalysis (⭐29) - Receiver Operating Characteristics and functions for evaluation probabilistic binary classifiers.

• GaussianMixtures (⭐83) - Large scale Gaussian Mixture Models.

• ScikitLearn (⭐521) - Julia implementation of the scikit-learn API.

• Knet (⭐1.4k) - Koç University Deep Learning Framework.

Julia / Data Analysis / Data Visualization

• Graph Layout (⭐47) - Graph layout algorithms in pure Julia.

• LightGraphs (⭐678) - Graph modelling and analysis.

• Hypothesis Tests (⭐257) - Hypothesis tests for Julia.

• RDataSets (⭐151) - Julia package for loading many of the data sets available in R.

• Time Series (⭐312) - Time series toolkit for Julia.

• Sampling (⭐1) - Basic sampling algorithms for Julia.

Julia / Misc Stuff / Presentations

• JuliaCon Presentations (⭐69) - Presentations for JuliaCon.

• Images (⭐504) - An image library for Julia.

Lua / Demos and Scripts

• Atari2600 (⭐18) - Scripts to generate a dataset with static frames from the Arcade Learning Environment.

Matlab / Computer Vision

• Bandlets - MATLAB code for bandlet transform.

Matlab / General-Purpose Machine Learning

• Training a deep autoencoder or a classifier on MNIST digits - Training a deep autoencoder or a classifier on MNIST digits[DEEP LEARNING].

Python / Natural Language Processing

• Quepy (⭐1.2k) - A python framework to transform natural language questions to queries in a database query language.

• python-ucto (⭐28) - Python binding to ucto (a unicode-aware rule-based tokenizer for various languages).

• Fuzzy Wuzzy (⭐8.8k) - Fuzzy String Matching in Python.

• textacy (⭐2k) - higher-level NLP built on Spacy.

• CLTK (⭐763) - The Classical Language Toolkit.

• yase (⭐12) - Transcode sentence (or other sequence) to list of word vector .

• Polyglot (⭐2.1k) - Multilingual text (NLP) processing toolkit.

• DrQA (⭐4.3k) - Reading Wikipedia to answer open-domain questions.

Python / Data Analysis / Data Visualization

• vispy (⭐3k) - GPU-based high-performance interactive OpenGL 2D/3D data visualization library.

• SparklingPandas (⭐365) Pandas on PySpark (POPS).

• bqplot (⭐3.4k) - An API for plotting in Jupyter (IPython).

Python / Misc Scripts / iPython Notebooks / Codebases

• Diffusion Segmentation (⭐2) - A collection of image segmentation algorithms based on diffusion methods.

• Scipy Tutorials (⭐2) - SciPy tutorials. This is outdated, check out scipy-lecture-notes.

• Crab (⭐85) - A recommendation engine library for Python.

• BayesPy (⭐99) - Bayesian Inference Tools in Python.

• scikit-learn tutorials (⭐122) - Series of notebooks for learning scikit-learn.

• group-lasso (⭐37) - Some experiments with the coordinate descent algorithm used in the (Sparse) Group Lasso model.

• mne-python-notebooks (⭐22) - IPython notebooks for EEG/MEG data processing using mne-python.

• Neon Course (⭐92) - IPython notebooks for a complete course around understanding Nervana's Neon.

• pandas cookbook (⭐6k) - Recipes for using Python's pandas library.

• climin (⭐177) - Optimization library focused on machine learning, pythonic implementations of gradient descent, LBFGS, rmsprop, adadelta and others.

Python / Kaggle Competition Source Code

• wiki challenge (⭐12) - An implementation of Dell Zhang's solution to Wikipedia's Participation Challenge on Kaggle.

• kaggle insults (⭐154) - Kaggle Submission for "Detecting Insults in Social Commentary".

• kaggle_acquire-valued-shoppers-challenge (⭐68) - Code for the Kaggle acquire valued shoppers challenge.

• kaggle-cifar (⭐45) - Code for the CIFAR-10 competition at Kaggle, uses cuda-convnet.

• kaggle-blackbox (⭐116) - Deep learning made easy.

• kaggle-accelerometer (⭐16) - Code for Accelerometer Biometric Competition at Kaggle.

• kaggle-advertised-salaries (⭐57) - Predicting job salaries from ads - a Kaggle competition.

• kaggle amazon (⭐27) - Amazon access control challenge.

• kaggle-bestbuy_big (⭐9) - Code for the Best Buy competition at Kaggle.

• Kaggle Dogs vs. Cats (⭐68) - Code for Kaggle Dogs vs. Cats competition.

• Kaggle Galaxy Challenge (⭐487) - Winning solution for the Galaxy Challenge on Kaggle.

• Kaggle Gender (⭐22) - A Kaggle competition: discriminate gender based on handwriting.

• Kaggle Merck (⭐10) - Merck challenge at Kaggle.

• Kaggle Stackoverflow (⭐47) - Predicting closed questions on Stack Overflow.

• wine-quality (⭐24) - Predicting wine quality.

Ruby / Natural Language Processing

• UEA Stemmer (⭐51) - Ruby port of UEALite Stemmer - a conservative stemmer for search and indexing.

Ruby / General-Purpose Machine Learning

• Awesome Machine Learning with Ruby (⭐1.9k) - Curated list of ML related resources for Ruby.

• rb-libsvm (⭐276) - Ruby language bindings for LIBSVM which is a Library for Support Vector Machines.

Ruby / Data Analysis / Data Visualization

• rsruby (⭐330) - Ruby - R bridge.

R / General-Purpose Machine Learning

• biglasso - biglasso: Extending Lasso Model Fitting to Big Data in R.

• XGBoost.R (⭐551) - R binding for eXtreme Gradient Boosting (Tree) Library.

Scala / Data Analysis / Data Visualization

• Scalding (⭐3.4k) - A Scala API for Cascading.

• Summing Bird (⭐2.1k) - Streaming MapReduce with Scalding and Storm.

• Algebird (⭐2.2k) - Abstract Algebra for Scala.

Scala / General-Purpose Machine Learning

• Conjecture (⭐359) - Scalable Machine Learning in Scalding.

• brushfire (⭐397) - Distributed decision tree ensemble learning in Scala.

• DynaML (⭐199) - Scala Library/REPL for Machine Learning Research.

Swift / General-Purpose Machine Learning

• Swift Brain (⭐331) - The first neural network / machine learning library written in Swift. This is a project for AI algorithms in Swift for iOS and OS X development. This project includes algorithms focused on Bayes theorem, neural networks, SVMs, Matrices, etc...

TensorFlow / General-Purpose Machine Learning

• Awesome TensorFlow (⭐17k) - A list of all things related to TensorFlow.

Oct 16 - Oct 22, 2017

Python / General-Purpose Machine Learning

• CNTK (⭐17k) - Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit. Documentation can be found here.

JavaScript / General-Purpose Machine Learning

• JSMLT (⭐25) - Machine learning toolkit with classification and clustering for Node.js; supports visualization (see visualml.io).

JavaScript / Misc

• stdlib (⭐3.3k) - A standard library for JavaScript and Node.js, with an emphasis on numeric computing. The library provides a collection of robust, high performance libraries for mathematics, statistics, streams, utilities, and more.

Oct 09 - Oct 15, 2017

Python / General-Purpose Machine Learning

• Edward - A library for probabilistic modelling, inference, and criticism. Built on top of TensorFlow.

Sep 11 - Sep 17, 2017

Swift / General-Purpose Machine Learning

• Awesome Core ML Models (⭐5.7k) - A curated list of machine learning models in CoreML format.

Aug 14 - Aug 20, 2017

Python / General-Purpose Machine Learning

• ML-From-Scratch (⭐22k) - Implementations of Machine Learning models from scratch in Python with a focus on transparency. Aims to showcase the nuts and bolts of ML in an accessible way.

Aug 07 - Aug 13, 2017

Crystal / General-Purpose Machine Learning

• machine (⭐42) - Simple machine learning algorithm.

Python / General-Purpose Machine Learning

• PyTorch (⭐63k) - Tensors and Dynamic neural networks in Python with strong GPU acceleration

Jul 31 - Aug 06, 2017

Java / Data Analysis / Data Visualization

• Onyx (⭐2k) - Distributed, masterless, high performance, fault tolerant data processing. Written entirely in Clojure.

Jul 10 - Jul 16, 2017

C++ / General-Purpose Machine Learning

• Distributed Machine learning Tool Kit (DMTK) - A distributed machine learning (parameter server) framework by Microsoft. Enables training models on large data sets across multiple machines. Current tools bundled with it include: LightLDA and Distributed (Multisense) Word Embedding.

JavaScript / General-Purpose Machine Learning

• LDA.js (⭐279) - LDA topic modelling for Node.js

• Node-SVM (⭐295) - Support Vector Machine for Node.js

JavaScript / Misc

• simple-statistics (⭐2.9k) - A JavaScript implementation of descriptive, regression, and inference statistics. Implemented in literate JavaScript with no dependencies, designed to work in all modern browsers (including IE) as well as in Node.js.

Matlab / General-Purpose Machine Learning

• Machine Learning Module (⭐446) - Class on machine w/ PDF, lectures, code

Jun 26 - Jul 02, 2017

Swift / General-Purpose Machine Learning

• Perfect TensorFlow (⭐169) - Swift Language Bindings of TensorFlow. Using native TensorFlow models on both macOS / Linux.

Jun 19 - Jun 25, 2017

Ruby / Natural Language Processing

• Awesome NLP with Ruby (⭐986) - Curated link list for practical natural language processing in Ruby.

Jun 05 - Jun 11, 2017

Swift / General-Purpose Machine Learning

• Bender (⭐1.7k) - Fast Neural Networks framework built on top of Metal. Supports TensorFlow models.

May 29 - Jun 04, 2017

JavaScript / Data Analysis / Data Visualization

• D3.js

• Learn JS Data

May 22 - May 28, 2017

Go / Natural Language Processing

• word-embedding (⭐388) - Word Embeddings: the full implementation of word2vec, GloVe in Go.

Java / General-Purpose Machine Learning

• AMIDST Toolbox - A Java Toolbox for Scalable Probabilistic Machine Learning.

May 15 - May 21, 2017

General-Purpose Machine Learning / Data Analysis / Data Visualization

• MXnet for Deep Learning, in Perl (⭐20k), also released in CPAN.

Perl 6 / Data Analysis / Data Visualization

• Naïve Bayes (⭐3)

May 08 - May 14, 2017

Scala / Natural Language Processing

• Montague (⭐52) - Montague is a semantic parsing library for Scala with an easy-to-use DSL.

May 01 - May 07, 2017

Python / Neural Networks

• NeuralTalk (⭐5.3k) - NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

Python / Reinforcement Learning

• DeepMind Lab (⭐6.8k) - DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning.

• Gym (⭐30k) - OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms.

• ViZDoom (⭐1.5k) - ViZDoom allows developing AI bots that play Doom using only the visual information (the screen buffer). It is primarily intended for research in machine visual learning, and deep reinforcement learning, in particular.

Apr 24 - Apr 30, 2017

Python / Data Analysis / Data Visualization

• Bowtie (⭐756) - A dashboard library for interactive visualizations using flask socketio and react.

Apr 10 - Apr 16, 2017

General-Purpose Machine Learning / Data Analysis / Data Visualization

• TensorFlow (⭐277) - OCaml bindings for TensorFlow.

Mar 27 - Apr 02, 2017

Python / General-Purpose Machine Learning

• Image-to-Image Translation with Conditional Adversarial Networks (⭐141) - Implementation of image to image (pix2pix) translation from the paper by isola et al.[DEEP LEARNING]

Mar 06 - Mar 12, 2017

Python / General-Purpose Machine Learning

• fuku-ml (⭐280) - Simple machine learning library, including Perceptron, Regression, Support Vector Machine, Decision Tree and more, it's easy to use and easy to learn for beginners.

Feb 20 - Feb 26, 2017

Python / Data Analysis / Data Visualization

• scikit-plot (⭐2.3k) - A visualization library for quick and easy generation of common plots in data analysis and machine learning.

Feb 13 - Feb 19, 2017

C++ / General-Purpose Machine Learning

• MLDB - The Machine Learning Database is a database designed for machine learning. Send it commands over a RESTful API to store data, explore it using SQL, then train machine learning models and expose them as APIs.

• sofia-ml - Suite of fast incremental algorithms.

• Timbl - A software package/C++ library implementing several memory-based learning algorithms, among which IB1-IG, an implementation of k-nearest neighbor classification, and IGTree, a decision-tree approximation of IB1-IG. Commonly used for NLP.

C++ / Natural Language Processing

• frog (⭐72) - Memory-based NLP suite developed for Dutch: PoS tagger, lemmatiser, dependency parser, NER, shallow parser, morphological analyzer.

• ucto (⭐59) - Unicode-aware regular-expression based tokenizer for various languages. Tool and C++ library. Supports FoLiA format.

C++ / Speech Recognition

• Kaldi (⭐12k) - Kaldi is a toolkit for speech recognition written in C++ and licensed under the Apache License v2.0. Kaldi is intended for use by speech recognition researchers.

Java / General-Purpose Machine Learning

• ELKI - Java toolkit for data mining. (unsupervised: clustering, outlier detection etc.)

JavaScript / Data Analysis / Data Visualization

• amCharts

Julia / Data Analysis / Data Visualization

• Gadfly (⭐1.8k) - Crafty statistical graphics for Julia.

Lua / General-Purpose Machine Learning

• SciLua

.NET / Computer Vision

• OpenCVDotNet - A wrapper for the OpenCV project to be used with .NET applications.

Python / Natural Language Processing

• TextBlob - Providing a consistent API for diving into common natural language processing (NLP) tasks. Stands on the giant shoulders of NLTK and Pattern, and plays nicely with both.

Python / General-Purpose Machine Learning

• graphlab-create - A library with various machine learning models (regression, clustering, recommender systems, graph analytics, etc.) implemented on top of a disk-backed DataFrame.

• gensim (⭐14k) - Topic Modelling for Humans.

Python / Data Analysis / Data Visualization

• d3py (⭐1.4k) - A plotting library for Python, based on D3.js.

• pygal - A Python SVG Charts Creator.

Python / Misc Scripts / iPython Notebooks / Codebases

• Optunity examples - Examples demonstrating how to use Optunity in synergy with machine learning libraries.

Ruby / Misc

• Listof (⭐26) - Community based data collection, packed in gem. Get list of pretty much anything (stop words, countries, non words) in txt, JSON or hash. Demo/Search for a list

SAS / General-Purpose Machine Learning

• Enterprise Miner - Data mining and machine learning that creates deployable models using a GUI or code.

• Factory Miner - Automatically creates deployable machine learning models across numerous market or customer segments using a GUI.

SAS / Data Analysis / Data Visualization

• University Edition - FREE! Includes all SAS packages necessary for data analysis and visualization, and includes online SAS courses.

SAS / Demos and Scripts

• ML_Tables (⭐123) - Concise cheat sheets containing machine learning best practices.

• enlighten-apply (⭐123) - Example code and materials that illustrate applications of SAS machine learning techniques.

• enlighten-integration (⭐60) - Example code and materials that illustrate techniques for integrating SAS with other analytics technologies in Java, PMML, Python and R.

• enlighten-deep (⭐20) - Example code and materials that illustrate using neural networks with several hidden layers in SAS.

• dm-flow (⭐55) - Library of SAS Enterprise Miner process flow diagrams to help you learn by example about specific data mining topics.

Jan 30 - Feb 05, 2017

Scala / Data Analysis / Data Visualization

• Hydrosphere Mist (⭐320) - a service for deployment Apache Spark MLLib machine learning models as realtime, batch or reactive web services.

Jan 02 - Jan 08, 2017

Go / Natural Language Processing

• snowball (⭐36) - Snowball Stemmer for Go.

Dec 19 - Dec 25, 2016

Python / Neural Networks

• Data Driven Code (⭐26) - Very simple implementation of neural networks for dummies in python without using any libraries, with detailed comments.

Nov 14 - Nov 20, 2016

Python / Data Analysis / Data Visualization

• somoclu (⭐244) Massively parallel self-organizing maps: accelerate training on multicore CPUs, GPUs, and clusters, has python API.

Oct 24 - Oct 30, 2016

C / General-Purpose Machine Learning

• Recommender (⭐256) - A C library for product recommendations/suggestions using collaborative filtering (CF).

C++ / General-Purpose Machine Learning

• CUDA - This is a fast C++/CUDA implementation of convolutional [DEEP LEARNING]

• DyNet (⭐3.3k) - A dynamic neural network library working well with networks that have dynamic structures that change for every training instance. Written in C++ with bindings in Python.

• Fido (⭐411) - A highly-modular C++ machine learning library for embedded electronics and robotics.

• LightGBM (⭐15k) - Microsoft's fast, distributed, high performance gradient boosting (GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

• ROOT - A modular scientific software framework. It provides all the functionalities needed to deal with big data processing, statistical analysis, visualization and storage.

• shark - A fast, modular, feature-rich open-source C++ machine learning library.

C++ / Natural Language Processing

• MIT Information Extraction Toolkit (⭐2.8k) - C, C++, and Python tools for named entity recognition and relation extraction

Oct 17 - Oct 23, 2016

Python / Data Analysis / Data Visualization

• PyDexter (⭐31) - Simple plotting for Python. Wrapper for D3xterjs; easily render charts in-browser.

Python / Misc Scripts / iPython Notebooks / Codebases

• Suiron (⭐706) - Machine Learning for RC Cars.

R / General-Purpose Machine Learning

• TDSP-Utilities (⭐364) - Two data science utilities in R from Microsoft: 1) Interactive Data Exploration, Analysis, and Reporting (IDEAR) ; 2) Automated Modelling and Reporting (AMR).

Aug 22 - Aug 28, 2016

Scala / General-Purpose Machine Learning

• SwiftLearner (⭐39) - Simply written algorithms to help study ML or write your own implementations.

Aug 08 - Aug 14, 2016

Swift / General-Purpose Machine Learning

• MLKit (⭐152) - A simple Machine Learning Framework written in Swift. Currently features Simple Linear Regression, Polynomial Regression, and Ridge Regression.

Aug 01 - Aug 07, 2016

Elixir / General-Purpose Machine Learning

• Simple Bayes (⭐385) - A Simple Bayes / Naive Bayes implementation in Elixir.

Elixir / Natural Language Processing

• Stemmer (⭐144) - An English (Porter2) stemming implementation in Elixir.

Jul 04 - Jul 10, 2016

Python / General-Purpose Machine Learning

• Lasagne (⭐3.8k) - Lightweight library to build and train neural networks in Theano.

Jun 27 - Jul 03, 2016

Python / Misc Scripts / iPython Notebooks / Codebases

• Introduction to machine learning with scikit-learn (⭐3.5k) - IPython notebooks from Data School's video tutorials on scikit-learn.

Jun 20 - Jun 26, 2016

Python / Natural Language Processing

• jellyfish (⭐1.8k) - a python library for doing approximate and phonetic matching of strings.

Python / Data Analysis / Data Visualization

• SOMPY (⭐498) - Self Organizing Map written in Python (Uses neural networks for data analysis).

• HDBScan (⭐91) - implementation of the hdbscan algorithm in Python - used for clustering

May 09 - May 15, 2016

C++ / General-Purpose Machine Learning

• DSSTNE (⭐4.4k) - A software library created by Amazon for training and deploying deep neural networks using GPUs which emphasizes speed and scale over experimental flexibility.

Python / Data Analysis / Data Visualization

• Dora (⭐611) - Tools for exploratory data analysis in Python.

• Ruffus - Computation Pipeline library for python.

Apr 25 - May 01, 2016

Scala / Data Analysis / Data Visualization

• Spark Notebook - Interactive and Reactive Data Science using Scala and Spark.

Mar 28 - Apr 03, 2016

Python / General-Purpose Machine Learning

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

Mar 14 - Mar 20, 2016

C / General-Purpose Machine Learning

• Darknet (⭐24k) - Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.

Feb 15 - Feb 21, 2016

Rust / General-Purpose Machine Learning

• rusty-machine (⭐1.2k) - a pure-rust machine learning library.

Feb 01 - Feb 07, 2016

Java / General-Purpose Machine Learning

• Samoa SAMOA is a framework that includes distributed machine learning for data streams with an interface to plug-in different stream processing platforms.

JavaScript / General-Purpose Machine Learning

• Brain (⭐8k) - Neural networks in JavaScript [Deprecated]

Python / General-Purpose Machine Learning

• Brainstorm (⭐1.3k) - Fast, flexible and fun neural networks. This is the successor of PyBrain.

Rust / General-Purpose Machine Learning

• deeplearn-rs (⭐202) - deeplearn-rs provides simple networks that use matrix multiplication, addition, and ReLU under the MIT license.

• rustlearn (⭐557) - a machine learning framework featuring logistic regression, support vector machines, decision trees and random forests.

Jan 18 - Jan 24, 2016

C++ / General-Purpose Machine Learning

• Warp-CTC (⭐4k) - A fast parallel implementation of Connectionist Temporal Classification (CTC), on both CPU and GPU.

Python / Computer Vision

• OpenFace - Free and open source face recognition with deep neural networks.

Jan 11 - Jan 17, 2016

Python / General-Purpose Machine Learning

• DIGITS (⭐4.1k) - The Deep Learning GPU Training System (DIGITS) is a web application for training deep learning models.

Jan 04 - Jan 10, 2016

C++ / Gesture Detection

• grt (⭐800) - The Gesture Recognition Toolkit (GRT) is a cross-platform, open-source, C++ machine learning library designed for real-time gesture recognition.

Python / General-Purpose Machine Learning

• pgmpy (⭐2.3k) A python library for working with Probabilistic Graphical Models.

Dec 21 - Dec 27, 2015

Natural Language Processing / Data Analysis / Data Visualization

• jieba-php (⭐1.2k) - Chinese Words Segmentation Utilities.

Python / Computer Vision

• Scikit-Image (⭐5.2k) - A collection of algorithms for image processing in Python.

Python / Misc Scripts / iPython Notebooks / Codebases

• TDB (⭐1.4k) - TensorDebugger (TDB) is a visual debugger for deep learning. It features interactive, node-by-node debugging and visualization for TensorFlow.

Dec 14 - Dec 20, 2015

Java / General-Purpose Machine Learning

• aerosolve (⭐4.8k) - A machine learning library by Airbnb designed from the ground up to be human friendly.

Nov 30 - Dec 06, 2015

Python / Data Analysis / Data Visualization

• ggfortify (⭐507) - Unified interface to ggplot2 popular R packages.

Nov 16 - Nov 22, 2015

JavaScript / Data Analysis / Data Visualization

• datakit (⭐291) - A lightweight framework for data analysis in JavaScript

Matlab / General-Purpose Machine Learning

• Pattern Recognition and Machine Learning (⭐5.7k) - This package contains the matlab implementation of the algorithms described in the book Pattern Recognition and Machine Learning by C. Bishop.

Python / Data Analysis / Data Visualization

• bokeh (⭐17k) - Interactive Web Plotting for Python.

• plotly - Collaborative web plotting for Python and matplotlib.

• Blaze (⭐3.1k) - NumPy and Pandas interface to Big Data.

Python / Misc Scripts / iPython Notebooks / Codebases

• 2012-paper-diginorm (⭐8)

• Dive into Machine Learning with Python Jupyter notebook and scikit-learn (⭐11k) - "I learned Python by hacking first, and getting serious later. I wanted to do this with Machine Learning. If this is your style, join me in getting a bit ahead of yourself."

Oct 19 - Oct 25, 2015

Python / Misc Scripts / iPython Notebooks / Codebases

• data-science-ipython-notebooks (⭐25k) - Continually updated Data Science Python Notebooks: Spark, Hadoop MapReduce, HDFS, AWS, Kaggle, scikit-learn, matplotlib, pandas, NumPy, SciPy, and various command lines.

Sep 28 - Oct 04, 2015

JavaScript / General-Purpose Machine Learning

• ml.js (⭐2.3k) - Machine learning and numerical analysis tools for Node.js and the Browser!

Aug 31 - Sep 06, 2015

General-Purpose Machine Learning / Data Analysis / Data Visualization

• YCML (⭐116) - A Machine Learning framework for Objective-C and Swift (OS X / iOS).

• PredictionBuilder (⭐110) - A library for machine learning that builds predictions using a linear regression.

Aug 24 - Aug 30, 2015

Python / Natural Language Processing

• KoNLPy - A Python package for Korean natural language processing.

Aug 03 - Aug 09, 2015

Java / General-Purpose Machine Learning

• H2O (⭐6.2k) - ML engine that supports distributed learning on Hadoop, Spark or your laptop via APIs in R, Python, Scala, REST/JSON.

Scala / General-Purpose Machine Learning

• H2O Sparkling Water (⭐939) - H2O and Spark interoperability.

Jun 22 - Jun 28, 2015

C++ / Natural Language Processing

• MeTA (⭐661) - MeTA : ModErn Text Analysis is a C++ Data Sciences Toolkit that facilitates mining big text data.

JavaScript / Data Analysis / Data Visualization

• Sigma.js - JavaScript library dedicated to graph drawing.

Python / Computer Vision

• Vigranumpy (⭐383) - Python bindings for the VIGRA C++ computer vision library.

May 04 - May 10, 2015

Python / General-Purpose Machine Learning

• mlxtend (⭐4.3k) - A library consisting of useful tools for data science and machine learning tasks.

Apr 27 - May 03, 2015

General-Purpose Machine Learning / Data Analysis / Data Visualization

• MAChineLearning (⭐38) - An Objective-C multilayer perceptron library, with full support for training through backpropagation. Implemented using vDSP and vecLib, it's 20 times faster than its Java equivalent. Includes sample code for use from Swift.

Apr 13 - Apr 19, 2015

JavaScript / Misc

• regression-js (⭐886) - A javascript library containing a collection of least squares fitting methods for finding a trend in a set of data.

Python / Misc Scripts / iPython Notebooks / Codebases

• GreatCircle (⭐72) - Library for calculating great circle distance.

Mar 23 - Mar 29, 2015

Java / General-Purpose Machine Learning

• ORYX (⭐1.8k) - Lambda Architecture Framework using Apache Spark and Apache Kafka with a specialization for real-time large-scale machine learning.

.NET / General-Purpose Machine Learning

• Accord-Framework -The Accord.NET Framework is a complete framework for building machine learning, computer vision, computer audition, signal processing and statistical applications.

Feb 16 - Feb 22, 2015

Python / Natural Language Processing

• PyStanfordDependencies (⭐66) - Python interface for converting Penn Treebank trees to Stanford Dependencies.

Dec 15 - Dec 21, 2014

Python / General-Purpose Machine Learning

• deap (⭐5k) - Evolutionary algorithm framework.

Dec 08 - Dec 14, 2014

R / General-Purpose Machine Learning

• Machine Learning For Hackers (⭐3.6k)

Dec 01 - Dec 07, 2014

.NET / Computer Vision

• AForge.NET - Open source C# framework for developers and researchers in the fields of Computer Vision and Artificial Intelligence. Development has now shifted to GitHub.

• Accord.NET - Together with AForge.NET, this library can provide image processing and computer vision algorithms to Windows, Windows RT and Windows Phone. Some components are also available for Java and Android.

Python / Natural Language Processing

• python-frog (⭐46) - Python binding to Frog, an NLP suite for Dutch. (pos tagging, lemmatisation, dependency parsing, NER)

Python / General-Purpose Machine Learning

• python-timbl (⭐16) - A Python extension module wrapping the full TiMBL C++ programming interface. Timbl is an elaborate k-Nearest Neighbours machine learning toolkit.

Aug 25 - Aug 31, 2014

Python / Data Analysis / Data Visualization

• PyQtGraph (⭐3.1k) - A pure-python graphics and GUI library built on PyQt4 / PySide and NumPy.

Aug 04 - Aug 10, 2014

Clojure / Data Analysis

• PigPen (⭐543) - Map-Reduce for Clojure.

Python / Data Analysis / Data Visualization

• Petrel (⭐246) - Tools for writing, submitting, debugging, and monitoring Storm topologies in pure Python.

• emcee (⭐1.3k) - The Python ensemble sampling toolkit for affine-invariant MCMC.

Python / Misc Scripts / iPython Notebooks / Codebases

• Allen Downey’s Data Science Course (⭐41) - Code for Data Science at Olin College, Spring 2014.

• Allen Downey’s Think Bayes Code (⭐1.6k) - Code repository for Think Bayes.

• Allen Downey’s Think Complexity Code (⭐95) - Code for Allen Downey's book Think Complexity.

• Allen Downey’s Think OS Code (⭐516) - Text and supporting code for Think OS: A Brief Introduction to Operating Systems.

Jul 28 - Aug 03, 2014

Java / General-Purpose Machine Learning

• Meka - An open source implementation of methods for multi-label classification and evaluation (extension to Weka).

Python / Natural Language Processing

• jieba (⭐30k) - Chinese Words Segmentation Utilities.

Python / General-Purpose Machine Learning

• pyhsmm (⭐528) - library for approximate unsupervised inference in Bayesian Hidden Markov Models (HMMs) and explicit-duration Hidden semi-Markov Models (HSMMs), focusing on the Bayesian Nonparametric extensions, the HDP-HMM and HDP-HSMM, mostly with weak-limit approximations.

• SKLL (⭐532) - A wrapper around scikit-learn that makes it simpler to conduct experiments.

Jul 21 - Jul 27, 2014

C++ / Computer Vision

• DLib - DLib has C++ and Python interfaces for face detection and training general object detectors.

Clojure / Data Analysis

• Incanter - Incanter is a Clojure-based, R-like platform for statistical computing and graphics.

Java / Natural Language Processing

• MALLET - A Java-based package for statistical natural language processing, document classification, clustering, topic modelling, information extraction, and other machine learning applications to text.

• OpenNLP - a machine learning based toolkit for the processing of natural language text.

• LingPipe - A tool kit for processing text using computational linguistics.

Java / Data Analysis / Data Visualization

• Spark (⭐35k) - Spark is a fast and general engine for large-scale data processing.

JavaScript / Data Analysis / Data Visualization

• NVD3.js

• dimple

Julia / General-Purpose Machine Learning

• PGM (⭐50) - A Julia framework for probabilistic graphical models.

• Clustering (⭐307) - Basic functions for clustering data: k-means, dp-means, etc.

Julia / Data Analysis / Data Visualization

• Distributions (⭐968) - A Julia package for probability distributions and associated functions.

Julia / Misc Stuff / Presentations

• DSP (⭐326) - Digital Signal Processing (filtering, periodograms, spectrograms, window functions).

Lua / General-Purpose Machine Learning

• Numeric Lua

Lua / Demos and Scripts

• Core torch7 demos repository (⭐43).
  • linear-regression, logistic-regression
  • face detector (training and detection as separate demos)
  • mst-based-segmenter
  • train-a-digit-classifier
  • train-autoencoder
  • optical flow demo
  • train-on-housenumbers
  • train-on-cifar
  • tracking with deep nets
  • kinect demo
  • filter-bank visualization
  • saliency-networks

• Training a Convnet for the Galaxy-Zoo Kaggle challenge(CUDA demo) (⭐36)

• torch-datasets (⭐37) - Scripts to load several popular datasets including:
  • BSR 500
  • CIFAR-10
  • COIL
  • Street View House Numbers
  • MNIST
  • NORB

Matlab / Computer Vision

• Contourlets - MATLAB source code that implements the contourlet transform and its utility functions.

• Curvelets - The Curvelet transform is a higher dimensional generalization of the Wavelet transform designed to represent images at different scales and different angles.

.NET / Natural Language Processing

• Stanford.NLP for .NET (⭐570) - A full port of Stanford NLP packages to .NET and also available precompiled as a NuGet package.

Python / Computer Vision

• SimpleCV - An open source computer vision framework that gives access to several high-powered computer vision libraries, such as OpenCV. Written on Python and runs on Mac, Windows, and Ubuntu Linux.

Python / Natural Language Processing

• SnowNLP (⭐6k) - A library for processing Chinese text.

• Rosetta (⭐207) - Text processing tools and wrappers (e.g. Vowpal Wabbit)

Python / General-Purpose Machine Learning

• MLlib in Apache Spark - Distributed machine learning library in Spark

• BigML - A library that contacts external servers.

• pattern (⭐8.4k) - Web mining module for Python.

• NuPIC (⭐6.3k) - Numenta Platform for Intelligent Computing.

• PyBrain (⭐2.8k) - Another Python Machine Learning Library.

• python-recsys (⭐1.5k) - A Python library for implementing a Recommender System.

• Restricted Boltzmann Machines (⭐930) -Restricted Boltzmann Machines in Python. [DEEP LEARNING]

Python / Data Analysis / Data Visualization

• NetworkX - A high-productivity software for complex networks.

• PyMC (⭐7.3k) - Markov Chain Monte Carlo sampling toolkit.

• zipline (⭐16k) - A Pythonic algorithmic trading library.

• SymPy (⭐10k) - A Python library for symbolic mathematics.

• statsmodels (⭐8.2k) - Statistical modelling and econometrics in Python.

• Kartograph.py (⭐1k) - Rendering beautiful SVG maps in Python.

Python / Misc Scripts / iPython Notebooks / Codebases

• pattern_classification (⭐4k)

• thinking stats 2 (⭐8)

• hyperopt (⭐1.4k)

• numpic (⭐6.3k)

• ipython-notebooks (⭐555)

• decision-weights (⭐32)

• Sarah Palin LDA (⭐10) - Topic Modelling the Sarah Palin emails.

• sentiment-analyzer (⭐53) - Tweets Sentiment Analyzer

• sentiment_classifier (⭐173) - Sentiment classifier using word sense disambiguation.

• jProcessing (⭐144) - Kanji / Hiragana / Katakana to Romaji Converter. Edict Dictionary & parallel sentences Search. Sentence Similarity between two JP Sentences. Sentiment Analysis of Japanese Text. Run Cabocha(ISO--8859-1 configured) in Python.

Python / Kaggle Competition Source Code

• kaggle-bestbuy_small (⭐7)

Ruby / General-Purpose Machine Learning

• CardMagic-Classifier (⭐653) - A general classifier module to allow Bayesian and other types of classifications.

Ruby / Data Analysis / Data Visualization

• SciRuby

• Bioruby (⭐368)

Ruby / Misc

• Big Data For Chimps (⭐168)

Scala / Natural Language Processing

• ScalaNLP - ScalaNLP is a suite of machine learning and numerical computing libraries.

• Breeze (⭐3.4k) - Breeze is a numerical processing library for Scala.

• FACTORIE (⭐553) - FACTORIE is a toolkit for deployable probabilistic modelling, implemented as a software library in Scala. It provides its users with a succinct language for creating relational factor graphs, estimating parameters and performing inference.

Scala / Data Analysis / Data Visualization

• BIDMat (⭐265) - CPU and GPU-accelerated matrix library intended to support large-scale exploratory data analysis.

Scala / General-Purpose Machine Learning

• adam (⭐945) - A genomics processing engine and specialized file format built using Apache Avro, Apache Spark and Parquet. Apache 2 licensed.

• bioscala (⭐105) - Bioinformatics for the Scala programming language

• BIDMach (⭐916) - CPU and GPU-accelerated Machine Learning Library.

• Figaro (⭐752) - a Scala library for constructing probabilistic models.

Credits / Misc

• Some of the python libraries were cut-and-pasted from vinta (⭐158k)