discriminative-ai-resources

Personal Discriminative Artificial Intelligence Resources List.

Contents

• Pre-Trained Models
• Deep Learning
• General Purpose Machine Learning
• Natural Language Processing
• Time Series Forecasting
• Causal Inference
• Statistical and Probabilistic Modelling
• Auto Machine Learning
• Feature Engineering
• Model Management
• Diagnostic, Inpection or Interpretation
• Data Visualization
• Auto Data Visualization
• DataFrame Libraries
• Misc
• Tutorials and Examples
• Lists

Pre-Trained Models

• audio-pretrained-model - A collection of Audio and Speech pre-trained models.
• awesome-deeplearning - Pre-trained models from the awesome-deeplearning repository.
• camelot - A Python library to extract tabular data from PDFs.
• coreml-models - Largest list of models for Core ML (for iOS 11+).
• cv-pretrained-model - A collection of computer vision pre-trained models.
• efficientnet-pytorch - A PyTorch implementation of EfficientNet and EfficientNetV2.
• huggingface - Browse the model hub to discover, experiment and contribute to new state of the art models.
• layout-parser - A unified toolkit for Deep Learning Based Document Image Analysis.
• mmf - A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
• modelzoo - Models and code that perform audio processing, speech synthesis, and other audio related tasks.
• nlp-pretrained-model - A collection of Natural language processing pre-trained models.
• nlp-recipes - Natural Language Processing Best Practices & Examples.
• openvino - Pre-trained Deep Learning models and demos (high quality and extremely fast).
• PaddlePaddle - Awesome pre-trained models toolkit based on PaddlePaddle.
• PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle.
• pyannote-audio - Neural building blocks for speaker and speech detection.
• pytorch-image-models - PyTorch image models, scripts, pretrained weights
• stylegan - A collection of pre-trained StyleGAN models to download.
• tabula - Tabula is a tool for liberating data tables trapped inside PDF files.
• tfhub - Search and discover hundreds of trained, ready-to-deploy machine learning models.
• unilm - Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Deep Learning

• amazon-dsstne - Deep Scalable Sparse Tensor Network Engine.
• caffe - A fast open framework for deep learning.
• chainer - A flexible framework of neural networks for deep learning.
• cntk - An open source deep-learning toolkit.
• deepdetect - It makes state of the art machine learning easy to work with and integrate into existing applications.
• deeplearning4j - Open-source, distributed, scientific computing for the JVM.
• fastai - The fast.ai deep learning library, lessons, and tutorials.
• gym - A toolkit for developing and comparing reinforcement learning algorithms.
• keras - Deep Learning for humans.
• mxnet - A flexible and efficient library for deep learning.
• neon - Intel® Nervana™ reference deep learning framework.
• neupy - NeuPy is a Python library for Artificial Neural Networks and Deep Learning.
• neural-enhance - Super Resolution for images using deep learning.
• Paddle - PArallel Distributed Deep LEarning.
• singa - Distributed deep learning system.
• sonnet - TensorFlow-based neural network library.
• swflow - Simplified interface for TensorFlow for Deep Learning.
• tensorflow - Computation using data flow graphs for scalable - machine learning.
• tensorpack - A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility.
• tflearn - Deep learning library featuring a higher-level API for TensorFlow.

General Purpose Machine Learning

• aerosolve - A machine learning package built for humans.
• AmpliGraph - Python library for Representation Learning on Knowledge Graphs.
• catboost - An open-source gradient boosting library with categorical features support.
• dmtk - Microsoft Distributed Machine Learning Toolkit.
• fastFM - fastFM: A Library for Factorization Machines.
• fklearn - Functional Machine Learning.
• h2o - Open Source Fast Scalable Machine Learning Platform For Smarter Applications.
• imbalanced-learn - A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning.
• imodels - Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling.
• JSAT - Java Statistical Analysis Tool, a Java library for Machine Learning.
• libffm - A Library for Field-aware Factorization Machines.
• libfm - Library for factorization machines.
• LightGBM - A fast, distributed, high performance gradient boosting based on decision tree algorithms.
• madlib - It is an open-source library for scalable in-database analytics.
• metric-learn - Metric learning algorithms in Python.
• mlens - ML-Ensemble – high performance ensemble learning.
• mllib - MLlib is Apache Spark's scalable machine learning library.
• moa - It is an open source framework for Big Data stream mining.
• orange3 - Interactive data analysis.
• pycobra - Python library implementing ensemble methods and visualisation tools including Voronoi tesselations.
• pyod - A Python Toolbox for Scalable Outlier Detection (Anomaly Detection).
• rep - Machine Learning toolbox for Humans.
• river - Online machine learning in Python.
• scikit-learn - Machine learning in Python.
• shogun - Unified and efficient Machine Learning since 1999.
• weka - It is a collection of machine learning algorithms for data mining tasks.
• xgboost - Scalable, Portable and Distributed Gradient Boosting Library.

Natural Language Processing

• allennlp - An open-source NLP research library, built on PyTorch.
• anago - A Python library for sequence labeling implemented in Keras.
• CoreNLP - Stanford CoreNLP: A Java suite of core NLP tools.
• dimsum16 - Detecting Minimal Semantic Units and their Meanings - (DiMSUM).
• finetune - Scikit-learn style model finetuning for NLP.
• flair - A very simple framework for state-of-the-art NLP.
• flashtext - Extract Keywords from sentence or Replace keywords in sentences.
• fuzzywuzzy - Fuzzy String Matching in Python.
• gensim - Topic Modelling for Humans.
• gluon - A toolkit that enables easy text preprocessing to help you speed up your NLP research.
• Kashgari - NLP Transfer learning framework for text-labeling and text-classification.
• magnitude - A fast, efficient universal vector embedding utility package.
• mallet - It is a Java-based package for machine learning applications to text.
• nltk - Natural Language Toolkit.
• pattern - Web mining module for Python, with tools for scraping, NLP, ML, network analysis and viz.
• polyglot - Multilingual text (NLP) processing toolkit.
• rasa - Open source machine learning framework to automate text- and voice-based conversations.
• senpy - A sentiment and emotion analysis server in Python.
• snips-nlu - Snips Python library to extract meaning from text.
• spaCy - Industrial-strength Natural Language Processing (NLP) in Python.
• textacy - A Python library for performing a variety of NLP tasks.
• TextBlob - Simple, Pythonic, text processing.
• textgenrnn - Easily train your own text-generating neural network on any text dataset.
• word2vec - Python interface to Google word2vec.

Time Series Forecasting

• auto-ts - Automatically build models on time series datasets with a single line of code.
• darts - A python library for easy manipulation and forecasting of time series.
• pmdarima - Time series analysis (including auto arima) for Python.
• prophet - A procedure for forecasting time series data based on an additive model.
• pyflux - Open source time series library for Python.
• pysts - A Python package for time series classification.
• scikit-hts - Hierarchical time series forecasting for humans.
• sktime-dl - A sktime companion package for deep learning based on TensorFlow.
• sktime - A unified framework for machine learning with time series.
• statsmodels.tsa - Time Series analysis from statsmodels package.
• traces - A Python library for unevenly-spaced time series analysis.
• tsai - Time series Timeseries Deep Learning Pytorch fastai.
• tsfresh - Automatic extraction of relevant features from time series.

Causal Inference

• causallib - Modular causal inference analysis and model evaluations.
• causalml - Uplift modeling and causal inference with machine learning algorithms.
• causalnex - Helps data scientists to infer causation rather than observing correlation.
• dowhy - A Python library for causal inference that supports explicit modeling and testing of causal assumptions.
• EconML - Automated Learning and Intelligence for Causation and Economics.

Statistical and Probabilistic Modelling

• BayesianOptimization - A Python implementation of global optimization with gaussian processes.
• edward - A probabilistic programming language in TensorFlow.
• hmmlearn - Hidden Markov Models in Python, with scikit-learn like API.
• lifelines - Survival analysis in Python.
• lifetimes - Lifetime value in Python.
• lightweight_mmm - Easy to use Bayesian Marketing Mix Modeling (MMM).
• mord - Ordinal regression algorithms.
• pomegranate - Fast, flexible and easy to use probabilistic modelling in Python.
• pyglmnet - Python implementation of elastic-net regularized generalized linear models.
• pymc3 - Probabilistic Programming in Python.
• python-mle - A Python package for performing Maximum Likelihood Estimates.
• RoBo - A Robust Bayesian Optimization framework.
• statsmodels - Statistical modeling and econometrics in Python.
• tea-lang - DSL for experimental design and statistical analysis.
• pingouin - Statistical package in Python based on Pandas.

Auto Machine Learning

• adanet - AdaNet is a lightweight TensorFlow-based framework for AutoML.
• AlphaPy - Automated Machine Learning AutoML for Python.
• auto-sklearn - Automated Machine Learning with scikit-learn.
• auto_ml - Automated machine learning for analytics & production.
• autogluon - AutoML for Text, Image, and Tabular Data.
• autokeras - Accessible AutoML for deep learning.
• automl-gs - AutoML tool that offers a zero code/model definition interface to getting an optimized model.
• diaml - Semi-automated machine learning pipelines.
• FLAML - A fast and lightweight AutoML library.
• ludwig - Ludwig is a toolbox that allows to train deep learning models without coding.
• MLBox - It is a powerful Automated Machine Learning python library.
• nni - An open source AutoML toolkit for automate machine learning lifecycle.
• onepanel-automl - Onepanel AutoML.
• optuna - A hyperparameter optimization framework.
• pycaret - An open-source, low-code machine learning library in Python.
• SMAC3 - Sequential Model-based Algorithm Configuration.
• TPOT - Tree-Based Pipeline Optimization Tool.
• TransmogrifAI - Automated machine learning for structured data.
• xcessiv - A web-based application for automated hyperparameter tuning and stacked ensembling in Python.

Feature Engineering

• categorical-encoding - A library of sklearn compatible categorical variable encoders.
• datacleaner - A Python tool that automatically cleans data sets and readies them for analysis.
• feature-selector - Feature selector is a tool for dimensionality reduction of machine learning datasets.
• featuretools - Automated feature engineering.
• gokinjo - A feature extraction library based on k-nearest neighbor algorithm in Python.
• hypertools - A Python toolbox for gaining geometric insights into high-dimensional data.
• umap - A dimension reduction technique that can be used for visualisation.

Model Management

• BentoML - Model serving made easy.
• cog - Containers for machine learning.
• cookiecutter-ds - Logical and flexible project structure for doing and sharing data science work.
• ds-process-management - Resources for Data Science Process management.
• dvc - Data & models versioning for ML projects, make them shareable and reproducible.
• firefly - Function as a service.
• hopsworks - Full-stack platform for scale-out data science.
• kedro - A Python library for building robust production-ready data and analytics pipelines.
• lore - A python framework to make machine learning approachable.
• marvin - The toolbox helps data scientists to develop, test, and run marvin engines.
• metaflow - Build and manage real-life data science projects with ease.
• mlflow - Open source platform for the machine learning lifecycle.
• neptune - Log, organize, compare, register, and share all your ML model metadata in a single place.

Diagnostic, Inpection or Interpretation

• anchor - High-Precision Model-Agnostic Explanations.
• ann-visualizer - A python library for visualizing Artificial Neural Networks with Keras.
• awesome-interpretable-machine-learning - Opinionated list of resources facilitating model interpretability.
• eli5 - A library for debugging/inspecting machine learning classifiers and explaining their predictions.
• explainerdashboard - Quickly build Explainable AI dashboards.
• interpret - Fit interpretable models. Explain blackbox machine learning.
• lime - Explaining the predictions of any machine learning classifier.
• lucid - A collection of infrastructure and tools for research in neural network interpretability.
• PDPbox - Python partial dependence plot toolbox.
• SHAP - A unified approach to explain the output of any machine learning model.
• what-if-tool - Easy-to-use interface for expanding understanding of a black-box classification/regression model.
• yellowbrick - Visual analysis and diagnostic tools to facilitate machine learning model selection.

Data Visualization

• altair - Declarative statistical visualization library for Python.
• animatplot - A python package for animating plots build on matplotlib.
• bokeh - Interactive Web Plotting for Python.
• chartify - Python library that makes it easy for data scientists to create charts.
• dash - Interactive, Reactive Web Apps for Python.
• folium - Python Data to Leaflet.js Maps.
• ft-visual-vocabulary - The core of a newsroom-wide training session aimed at improving chart literacy.
• holoviews - Stop plotting your data - annotate your data and let it visualize itself.
• ipyvolume - 3d plotting for Python in the Jupyter notebook based on IPython widgets using WebGL.
• matplotlib - Plotting with Python.
• plotnine - A grammar of graphics for Python.
• scattertext - Beautiful visualizations of how language differs among document types.
• scikit-plot - An intuitive library to add plotting functionality to scikit-learn objects.
• seaborn - Statistical data visualization.
• speedml - Speedml is a Python package to speed start machine learning projects.
• streamlit - The fastest way to build custom ML tools.
• vega - A visualization grammar.
• veles - Binary data analysis and visualization tool.
• vispy - Interactive scientific visualization that is designed to be fast, scalable, and easy to use.
• wordcloud - A little word cloud generator in Python.

Auto Data Visualization

• AutoViz - Automatically visualize any dataset, any size with a single line of code.
• dataprep - The easiest way to prepare data in Python.
• dtale - Visualizer for pandas data structures.
• PandasGUI - A GUI for Pandas DataFrames.
• pandas-profiling - Create HTML profiling reports from pandas DataFrame objects.
• sweetviz - Visualize and compare datasets, target values and associations, with one line of code.

DataFrame Libraries

• cuDF - GPU DataFrame Library.
• dask - Parallel computing with task scheduling.
• datatables - A Python package for manipulating 2-dimensional tabular data structures.
• modin - Speed up your Pandas workflows by changing a single line of code.
• pandas - Fast, powerful, flexible and easy to use open source data analysis and manipulation tool.
• pandas_flavor - The easy way to write your own flavor of Pandas.
• sklearn-pandas - Pandas integration with sklearn.
• terality - Serverless data processing engine.
• vaex - Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python.

Misc

• deap - Distributed Evolutionary Algorithms in Python
• feather - Fast, interoperable binary data frame storage for Python and R.
• gplearn - Genetic Programming in Python.
• PyGAD - Python 3 library for building the genetic algorithm and training machine learning algorithms.
• gtdata - Download and play with key datasets from Google Trend.
• librosa - Python library for audio and music analysis.
• m2cgen - Transform ML models into a native code with zero dependencies
• mahout - It is a distributed linear algebra framework and mathematically expressive Scala DSL.
• mlxtend - A library of extension and helper modules for Python's data analysis and machine learning libraries.
• pythia - A modular framework for Visual Question Answering research from Facebook AI Research (FAIR).
• snorkel - A system for quickly generating training data with weak supervision.

Tutorials and Examples

• 100 Days of ML Code - 100 Days of ML Coding.
• BayesianModelling - A python tutorial on bayesian modeling techniques.
• ds-ipython-notebooks - Data science Python notebooks.
• EffectiveTensorflow - TensorFlow tutorials and best practices.
• kaggle-past-solutions - A searchable compilation of Kaggle past solutions.
• MLAlgorithms - Minimal and clean examples of machine learning algorithms implementations.
• MLFromScratch - Machine Learning From Scratch.
• MLPB - Machine Learning Problem Bible.
• tf-models - Models and examples built with TensorFlow.
• Virgilio - Your new Mentor for Data Science E-Learning.

Lists

• awesome-datascience - An awesome Data Science repository to learn and apply for real world problems.
• awesome-deep-learning-papers - The most cited deep learning papers.
• awesome-machine-learning - A curated list of awesome Machine Learning frameworks, libraries and software.
• Deep Learning Drizzle - Learn Deep Lerning from exciting lectures.
• Deep-Learning-Papers-Reading-Roadmap - Deep Learning papers reading roadmap.
• Deep-Learning-World - Organized Resources for Deep Learning Researchers and Developers.
• ml4se - A complete daily plan for studying to become a machine learning engineer.
• ossu-data-science - Path to a free self-taught education in Data Science!
• python-machine-learning-book - The "Python Machine Learning (1st edition)" book code repository and info resource.
• OCEANIS - List of AI and Autonomous and Intelligent Systems standards and standards in progress.