A curated list of nice pakages for we data people

Time Series

name	owner	stars	description
AnomalyDetection	twitter	3.1k	Anomaly detection with r
stumpy	TDAmeritrade	879	Stumpy is a powerful and scalable python library that can be used for a variety of time series data mining tasks
gluon-ts	awslabs	765	Gluonts - probabilistic time series modeling in python
RobustSTL	LeeDoYup	120	Unofficial implementation of robuststl: a robust seasonal-trend decomposition algorithm for long time series (aaai 2019)

Feature Engineering

name	owner	stars	description
featuretools	FeatureLabs	4.8k	An open source python library for automated feature engineering
Augly	facebookresearch	3.3k	A data augmentations library for audio, image, text, and video.
great_expectations	great-expectations	2.7k	Always know what to expect from your data.
categorical-encoders	scikit-learn-contrib	1.1k	A library of sklearn compatible categorical variable encoders
fancy-impute	iskandr	735	Multivariate imputation and matrix completion algorithms implemented in python
dirty-cat	dirty-cat	158	Encoding methods for dirty categorical variables

Pandas Extensions

name	owner	stars	description
pandas-profiliing	pandas-profiling	5.9k	Create html profiling reports from pandas dataframe objects
pdpipe	pdpipe	557	Easy pipelines for pandas dataframes.
pydqc	SauceCat	211	Python automatic data quality check toolkit
pandas_flavor	Zsailer	186	The easy way to write your own flavor of pandas
pandas-log	eyaltrabelsi	154	The goal of pandas-log is to provide feedback about basic pandas operations. it provides simple wrapper functions for the most common functions that add additional logs

Feature Selection

name	owner	stars	description
scikit-features	jundongl	845	Open-source feature selection repository in python
boruta	scikit-learn-contrib	615	Python implementations of the boruta all-relevant feature selection method.
ppscore	8080labs	321	Predictive power score (pps) in python
minepy	minepy	114	Minepy - maximal information-based nonparametric exploration
stability-selection	scikit-learn-contrib	94	Scikit-learn compatible implementation of stability selection.

Model Tunning

name	owner	stars	description
mlflow	mlflow	5.3k	Open source platform for the machine learning lifecycle
nnl	microsoft	4.5k	An open source automl toolkit for neural architecture search, model compression and hyper-parameter tuning.
metaflow	Netflix	2k	Build and manage real-life data science projects with ease.
skopt	scikit-optimize	1.6k	Sequential model-based optimization with a scipy.optimize interface
optuna	optuna	1.5k	A hyperparameter optimization framework

AutoML

name	owner	stars	description
jina	jina-ai	7.6k	Cloud-native neural search framework for 𝙖𝙣𝙮 kind of data
autokeras	keras-team	7k	An automl system based on keras
tpot	EpistasisLab	6.5k	A python automated machine learning tool that optimizes machine learning pipelines using genetic programming.
auto-scikitlearn	automl	4.1k	Automated machine learning with scikit-learn
darts	quark0	2.8k	Differentiable architecture search for convolutional and recurrent networks

Dimension Reduction

name	owner	stars	description
umap	lmcinnes	3.4k	Uniform manifold approximation and projection
star-clustering	josephius	83	A clustering algorithm that automatically determines the number of clusters and works without hyperparameter fine-tuning.

Machine Learning

name	owner	stars	description
pattern	clips	7.2k	Web mining module for python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.
VowpalWabbit	VowpalWabbit	6.7k	Vowpal wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
xlearn	aksnzhy	2.6k	High performance, easy-to-use, and scalable machine learning (ml) package, including linear model (lr), factorization machines (fm), and field-aware factorization machines (ffm) for python and cli interface.
lightning	scikit-learn-contrib	1.3k	Large-scale linear classification, regression and ranking in python
Metrics	benhamner	1.2k	Machine learning evaluation metrics, implemented in python, r, haskell, and matlab / octave
mlens	flennerhag	553	Ml-ensemble – high performance ensemble learning
NGBoost	stanfordmlgroup	335	Natural gradient boosting for probabilistic prediction
polylearn	scikit-learn-contrib	191	A library for factorization machines and polynomial networks for classification and regression in python.

Bayesian Statistics

name	owner	stars	description
pyro	pyro-ppl	6.2k	Deep universal probabilistic programming with python and pytorch
pymc	pymc-devs	4.6k	Probabilistic programming in python: bayesian modeling and probabilistic machine learning with theano
Edward	blei-lab	4.6k	A probabilistic programming language in tensorflow. deep generative models, variational inference.

Deep Learning

name	owner	stars	description
Autograd	HIPS	4.4k	Efficiently computes derivatives of numpy code.
RAdam	LiyuanLucasLiu	1.8k	On the variance of the adaptive learning rate and beyond
einops	arogozhnikov	1.6k	Deep learning operations reinvented (for pytorch, tensorflow, chainer, gluon and others)
Pytorch Metric Learning	KevinMusgrave	1.3k	The easiest way to use deep metric learning in your application. modular, flexible, and extensible. written in pytorch.

Model Training

name	owner	stars	description
horovod	horovod	11.8k	Distributed training framework for tensorflow, keras, pytorch, and apache mxnet.
tfx	tensorflow	1.2k	Tfx is an end-to-end platform for deploying production ml pipelines

Distributed

name	owner	stars	description
ray	ray-project	13.3k	An open source framework that provides a simple, universal api for building distributed applications. ray is packaged with rllib, a scalable reinforcement learning library, and tune, a scalable hyperparameter tuning library.
dask	dask	7.5k	Parallel computing with task scheduling

Federated Learning

name	owner	stars	description
FATE	FederatedAI	1.1k	An industrial level federated learning framework

Confident Learning

name	owner	stars	description
cleanlab	cgnorthcutt	1.2k	Find label errors in datasets, weak supervision, and learning with noisy labels.

Causal Inference

name	owner	stars	description
Edward	blei-lab	4.6k	A probabilistic programming language in tensorflow. deep generative models, variational inference.
dowhy	microsoft	2.3k	Dowhy is a python library for causal inference that supports explicit modeling and testing of causal assumptions. dowhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
CausalML	uber	2.1k	Uplift modeling and causal inference with machine learning algorithms
EconML	microsoft	943	Alice (automated learning and intelligence for causation and economics) is a microsoft research project aimed at applying artificial intelligence concepts to economic decision making. one of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal …

NLP Preprocessing

name	owner	stars	description
jieba	fxsjy	23k	结巴中文分词
HanLP	hankcs	19.4k	Natural language processing for the next decade. tokenization, part-of-speech tagging, named entity recognition, syntactic & semantic dependency parsing, document classification
datasets	huggingface	8.6k	🤗 the largest hub of ready-to-use nlp datasets for ml models with fast, easy-to-use and efficient data manipulation tools
Chinese Word Embeddings	Embedding	6.6k	100+ chinese word vectors 上百种预训练中文词向量
sentencepiece	google	3.3k	Unsupervised text tokenizer for neural network-based text generation.
ckiptagger	ckiplab	1.1k	Ckip neural chinese word segmentation, pos tagging, and ner
jiagu	ownthink	1k	Jiagu深度学习自然语言处理工具 知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类
TextAttack	QData	902	Textattack 🐙 is a python framework for adversarial attacks, data augmentation, and model training in nlp
MiNLP	XiaoMi	494	Xiaomi natural language processing toolkits
fastHan	fastnlp	163	Fasthan是基于fastnlp与pytorch实现的中文自然语言处理工具，像spacy一样调用方便。

NLP Models

name	owner	stars	description
pytorch-transformers	huggingface	17.8k	🤗 transformers: state-of-the-art natural language processing for tensorflow 2.0 and pytorch.
xlnet	zihangdai	5.3k	Xlnet: generalized autoregressive pretraining for language understanding
MatchZoo	NTMC-Community	3.2k	Facilitating the design, comparison and sharing of deep text matching models.
GPT2-Chinese	Morizeyao	2.4k	Chinese version of gpt2 training code, using bert tokenizer.
ALBERT	brightmart	1.7k	A lite bert for self-supervised learning of language representations, 海量中文预训练albert模型
bertforkeras	bojone	1.2k	Light reimplement of bert for keras
AliceMind	alibaba	820	Alibaba's collection of encoder-decoders from mind (machine intelligence of damo) lab
FinBert	valuesimplex	356
gensen	Maluuba	284	Learning general purpose distributed sentence representations via large scale multi-task learning

Representation Learning

name	owner	stars	description
sentence-transformers	UKPLab	3k	Sentence embeddings with bert & xlnet
top2vec	ddangelov	489	Top2vec learns jointly embedded topic, document and word vectors.
glyce embedding	ShannonAI	238	Code for neurips 2019 - glyce: glyph-vectors for chinese character representations

Image Processing

name	owner	stars	description
imgaug	aleju	9k	Image augmentation for machine learning experiments.
albumentations	albumentations-team	7.2k	Fast image augmentation library and easy to use wrapper around other libraries. documentation: https://albumentations.ai/docs/ paper about library: https://www.mdpi.com/2078-2489/11/2/125
imagededupe	idealo	2.7k	😎 finding duplicate images made easy!
imutils	jrosebr1	2.6k	A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying matplotlib images easier with opencv and python.

Object Detection

name	owner	stars	description
mmdetection	open-mmlab	7.4k	Open mmlab detection toolbox and benchmark
keras-YOLO3	qqwweee	5.8k	A keras implementation of yolov3 (tensorflow backend)
Light Facial Detection	Linzaer	3.9k	💎1mb lightweight face detection model (1mb轻量级人脸检测模型)
SSD-Tensorflow	balancap	3.8k	Single shot multibox detector in tensorflow
detr	facebookresearch	3.4k	End-to-end object detection with transformers
FastMaskRCNN	CharlesShang	3k	Mask rcnn in tensorflow
u2net	NathanUA	873	"The code for our newly accepted paper in pattern recognition 2020: ""u^2-net: going deeper with nested u-structure for salient object detection."""
TFace	Tencent	454	A trusty face recognition research platform developed by tencent youtu lab

OCR

name	owner	stars	description
easyOCR	JaidedAI	8.3k	Ready-to-use ocr with 40+ languages supported including chinese, japanese, korean and thai
chineseocr-lite	ouyanghuiyu	5.7k	超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8m) + crnn(2.5m) + anglenet(378kb)) 总模型仅4.7m
InvoiceNet	naiveHobo	1.5k	Deep neural network to extract intelligent information from invoice documents.

Recommendation

name	owner	stars	description
recommenders	microsoft	6.6k	Best practices on recommendation systems
DeepCTR	shenweichen	3.3k	Easy-to-use,modular and extendible package of deep-learning based ctr models.
DeepFM	ChenglongChen	1.5k	Tensorflow implementation of deepfm for ctr prediction.
neural-collaborative-filtering	hexiangnan	988	Neural collaborative filtering
deepmatch	shenweichen	781	A deep matching model library for recommendations & advertising. it's easy to train models and to export representation vectors which can be used for ann search.
xDeepFM	Leavingseason	656

Outlier Detection

name	owner	stars	description
alibi-detect	SeldonIO	206	Algorithms for outlier and adversarial instance detection, concept drift and metrics.

Graph

name	owner	stars	description
graph_nets	deepmind	3.9k	Build graph nets in tensorflow
dgl	dmlc	3.4k	Python package built to ease deep learning on graph, on top of existing dl frameworks.
graphSAGE	williamleif	1.9k	Representation learning on large graphs using stochastic graph convolutions.
SNAP	snap-stanford	1.5k	Stanford network analysis platform (snap) is a general purpose network analysis and graph mining library.
stellargraph	stellargraph	1.2k	Stellargraph - machine learning on graphs
plato	Tencent	874	腾讯高性能分布式图计算框架plato
spektral	danielegrattarola	810	Graph neural networks with keras and tensorflow 2.
simple-graph	dpapathanasiou	499	"This is a simple graph database in sqlite, inspired by ""sqlite as a document database"""

Searching

name	owner	stars	description
faiss	facebookresearch	9.7k	A library for efficient similarity search and clustering of dense vectors.
annoy	spotify	6.7k	Approximate nearest neighbors in c++/python optimized for memory usage and loading/saving to disk
haystack	deepset-ai	2.1k	🔍 end-to-end python framework for building natural language search interfaces to data. leverages transformers and the state-of-the-art of nlp. supports dpr, elasticsearch, hugging face’s hub, and much more!

Adversarial Learning

name	owner	stars	description
pytorch-CycleGAN-and-pix2pix	junyanz	13.1k	Image-to-image translation in pytorch
CycleGAN	junyanz	9.7k	Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.
GANHacks	soumith	8.4k	"Starter from ""how to train a gan?"" at nips2016"
pix2pix	phillipi	7.7k	Image-to-image translation with conditional adversarial nets
DCGAN	carpedm20	6.5k	"A tensorflow implementation of ""deep convolutional generative adversarial networks"""
ALAE	podgorskiy	1.8k	[cvpr2020] adversarial latent autoencoders
DoppelGANger	fjxmlzn	45	Using gans for sharing networked time series data: challenges, initial promise, and open questions, imc 2020

Model Interpretation

name	owner	stars	description
SHAP	slundberg	7.2k	A unified approach to explain the output of any machine learning model.
LIME	marcotcr	6.8k	Lime: explaining the predictions of any machine learning classifier
Tensorwatch	microsoft	2.5k	Debugging, monitoring and visualization for python machine learning and data science
eli5	TeamHG-Memex	1.8k	A library for debugging/inspecting machine learning classifiers and explaining their predictions
PDPBox	SauceCat	382	Python partial dependence plot toolbox

Visualization

name	owner	stars	description
Dash	plotly	10.8k	Analytical web apps for python & r. no javascript required.
prettymaps	marceloprates	7.2k	A small set of python functions to draw pretty maps from openstreetmap data. based on osmnx, matplotlib and shapely libraries.
Seaborn	mwaskom	6.6k	Statistical data visualization using matplotlib
Plotly	plotly	5.8k	An open-source, interactive graphing library for python (includes plotly express) ✨
streamlit	streamlit	5.4k	Streamlit — the fastest way to build custom ml tools
folium	python-visualization	4.3k	Python data. leaflet.js maps.
altair	altair-viz	4.3k	Declarative statistical visualization library for python
dash sample apps	plotly	2k	Open-source demos hosted on dash gallery
scikit-plot	reiinakano	1.7k	An intuitive library to add plotting functionality to scikit-learn objects.
CNN-Visualizer	poloclub	1.7k	Learning convolutional neural networks with interactive visualization. https://poloclub.github.io/cnn-explainer/

Development Toolkit

name	owner	stars	description
free-apis	public-apis	65.9k	A collective list of free apis for use in software and web development.
bash-bible	dylanaraps	23.3k	📖 a collection of pure bash alternatives to external processes.
python-fire	google	15.8k	Python fire is a library for automatically generating command line interfaces (clis) from absolutely any python object.
black	psf	13.7k	The uncompromising python code formatter
PySnooper	cool-RR	12.9k	Never use print for debugging again
poetry	sdispater	7.1k	Python dependency management and packaging made easy.
free api	fangzesheng	6.5k	收集免费的接口服务,做一个api的搬运工
fastapi	tiangolo	6.5k	Fastapi framework, high performance, easy to learn, fast to code, ready for production
playwright-python	microsoft	4.9k	Python version of the playwright testing and automation library.
hypothesis	HypothesisWorks	4k	Hypothesis is a powerful, flexible, and easy to use library for property-based testing.
modin	modin-project	3.6k	Modin: speed up your pandas workflows by changing a single line of code
pyautogui	asweigart	3.2k	A cross-platform gui automation python module for human beings. used to programmatically control the mouse & keyboard.
jupytext	mwouts	3k	Jupyter notebooks as markdown documents, julia, python or r scripts
papermill	nteract	2.7k	📚 parameterize, execute, and analyze notebooks
handclacs	connorferster	2.3k	Python library for converting python calculations into rendered latex.
lark	lark-parser	2k	Lark is a parsing toolkit for python, built with a focus on ergonomics, performance and modularity.
sqlfluff	sqlfluff	1.8k	A sql linter and auto-formatter for humans
handout	danijar	1.8k	Turn python scripts into handouts with markdown and figures
urwind	urwid	1.7k	Console user interface library for python (official repo)
more-itertools	more-itertools	1.5k	More routines for operating on iterables, beyond itertools
xarray	pydata	1.5k	N-d labeled arrays and datasets in python
icecream - debugging	gruns	1.4k	🍦 sweet and creamy print debugging.
pygooglenews	kotartemiy	816	If google news had a python library
bottleneck	pydata	540	Fast numpy array functions written in c
wily	tonybaloney	445	A python application for tracking, reporting on timing and complexity in python code

Tutorial

name	owner	stars	description
Python 100 days	jackfrued	70.8k	Python - 100天从新手到大师
Command line tutorial in one page	jlevy	66.5k	Master the command line, in one page
Deep Learning 500 Questions	scutan90	35.3k	深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 tan 2018.06
Learn Regex	ziishaned	31.9k	Learn regex the easy way
500 lines or less	aosabook	23.9k	500 lines or less
Data Science Tutorial notebook	donnemartin	17.7k	Data science python notebooks: deep learning (tensorflow, theano, caffe, keras), scikit-learn, kaggle, big data (spark, hadoop mapreduce, hdfs), matplotlib, pandas, numpy, scipy, python essentials, aws, and various command lines.
Awesome tensorflow	jtoy	15.3k	Tensorflow - a curated list of dedicated resources http://tensorflow.org
NLP progress	sebastianruder	13k	Repository to track the progress in natural language processing (nlp), including the datasets and the current state-of-the-art for the most common nlp tasks.
《神经网络与深度学习》- 邱锡鹏	nndl	12k	《神经网络与深度学习》 邱锡鹏著 neural network and deep learning
wtfpython-cn	leisurelicht	9.2k	Wtfpython的中文翻译/施工结束/ 能力有限，欢迎帮我改进翻译
object-detection-papers	hoya012	8.1k	A paper list of object detection using deep learning.
MLAlgorithms	rushter	7.8k	Minimal and clean examples of machine learning algorithms implementations
numpy-ml	ddbourgin	7.8k	Machine learning, in numpy
Reinforcement-learning-introduction	ShangtongZhang	7.7k	Python implementation of reinforcement learning: an introduction
deep learning drizzle	kmario23	7.1k	Drench yourself in deep learning, reinforcement learning, machine learning, computer vision, and nlp by learning from these exciting lectures!!
Google Research	google-research	6k	Google ai research
GNN Papers	thunlp	5.7k	Must-read papers on graph neural networks (gnn)
minGPT	karpathy	5.3k	A minimal pytorch re-implementation of the openai gpt (generative pretrained transformer) training
UGATIT	taki0112	4.4k	Official tensorflow implementation of u-gat-it: unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation
tensorflow2_tutorials_chinese	czy36mengfei	4k	Tensorflow2中文教程，持续更新(当前版本:tensorflow2.0)，tag: tensorflow 2.0 tutorials
Tensorflow-2.x-Tutorials	dragen1860	3.7k	Tensorflow 2.x version's tutorials and examples, including cnn, rnn, gan, auto-encoders, fasterrcnn, gpt, bert examples, etc. tf 2.0版入门实例代码，实战教程。
Machine Learning Notes from Prof. Yida Xu	roboticcam	3.5k	My continuously updated machine learning, probabilistic models and deep learning notes and demos (1500+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(1500+页)和视频链接
Awesome graph classification	benedekrozemberczki	2.5k	A collection of important graph embedding, classification and representation learning papers with implementations.
NLP-Beginner	FudanNLP	2.3k	Nlp上手教程
openNRE	thunlp	2k	An open-source package for neural relation extraction (nre)
Microsoft NLP examples	microsoft	1.9k	Natural language processing best practices & examples
anomaly detection	yzhao062	1.9k	Anomaly detection related books, papers, videos, and toolboxes
Stanford Natural Language Understanding Course	cgpotts	727	Code for stanford cs224u
Generative Models in TF2	timsainb	690	Implementations of a number of generative models in tensorflow 2. gan, vae, seq2seq, vaegan, gaia, spectrogram inversion. everything is self contained in a jupyter notebook for easy export to colab.
Dimensional reduction algos	heucoder	553	Pca、lda、mds、lle、tsne等降维算法的python实现
Generative Deep Learning	davidADSP	491	The official code repository for examples in the o'reilly book 'generative deep learning'
reinforcement learning	dalmia	417	Notes for the reinforcement learning course by david silver along with implementation of various algorithms.
Keras Text classification	yongzhuo	277	中文长文本分类、短句子分类、多标签分类、两句子相似度（chinese text classification of keras nlp, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，fasttext，textcnn，charcnn，textrnn, rcnn, dcnn, dpcnn, vdcnn, crnn, bert, xlnet, albert, attention, deepmoji, han, 胶囊网络-capsulenet, transformer-encode, seq2seq, ent, dmn,
Graph neural network implementation by Microsoft	microsoft	161	Tensorflow implementations of graph neural networks

Fun Stuff

name	owner	stars	description
funNLP	fighting41love	14.9k	中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、it词库、财经词库、成语词库、地名词库、历史名人词库、诗词词库、医学词库、饮食词库、法律词库、汽车词库、动物词库、中文聊天语料、中文谣言数据、百度中文问答数据集、句子相似度匹配算法集合、bert资源、文本生成&摘要相关工具、coconlp信息抽取工具、国内电话号码正则匹配、清华大学xlore:中英文跨语言百科知识图谱、清华大学人工智能技术…
tiler	nuno-faria	3.8k	👷 build images with images
Hacking neural nets	Kayzaks	1.9k	A small course on exploiting and defending neural networks
KnockKnock	huggingface	1.7k	🚪✊knock knock: get notified when your training ends with only two additional lines of code
break-capcha	zhaipro	1.4k	使用机器学习算法完成对12306验证码的自动识别
GNE	kingname	908	新闻网页正文通用抽取器 alpha 版.
pyforest	8080labs	689	Pyforest - feel the bliss of automated imports

Trading

name	owner	stars	description
zipline	quantopian	11.2k	Zipline, a pythonic algorithmic trading library
tensortrade	tensortrade-org	2k	An open source reinforcement learning framework for training, evaluating, and deploying robust trading agents.
mlfinlab	hudson-and-thames	1.3k	Mlfinlab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.
tf-quant	google	773	High-performance tensorflow library for quantitative finance.

Contribution Guide

Add your favourite packages to package.json, and run package_info.py to update the page :)