GitHub is home to over 40 million developers working together. Join them to grow your own development teams, manage permissions, and collaborate on projects.
Web Crawling UI and HTTP API, based on Scrapy and Tornado
Library for fast text representation and classification.
Models for Medical Segmentation
Jupyter notebooks from the scikit-learn video series
A single handwritten digit classifier, using the MNIST dataset. Implemented through Artificial Neural Networks in python. A convolutional neural network implmentation in tensorflow is kept in separate branch (this one is under construction).
Model extraction attacks on Machine-Learning-as-a-Service platforms.
Journal of Statistical Education Paper on Using OkCupid Data for Data Science Courses
Cleaned code of the winning submission
Pokemon Go API Demo
A subset of the IPython in-depth tutorial for a discussion with the Berkeley DS8 team
SymPy tutorial materials for SciPy 2016
Hyperparameter optimization with approximate gradient
Image Classification using Bag of Words and Spatial Pyramid BoW
A generic crawler
A component that tries to avoid downloading duplite content
Formasaurus tells you the type of an HTML form and its fields using machine learning
Scrapy middleware for the autologin
Detect and classify pagination links
VM Setup stuff for http://bit.ly/22giU4y
Character-level Convolutional Networks for Text Classification
Given a new image, determine if it is likely derived from a known image.
A curated collection of papers on streaming algorithms
Material for open source machine learning practical
My personal tools for working with scikit/ML