Github has not only been the go-to platform for releasing and developing state-of-the-art Data Science tools but also a very familiar platform amongst the community as a guide for free learning sources.
Here is a list of Github repositories listed in accordance with the star rating of the users on Github. And are also an amalgamation of Data science resources which would appeal to both the set of the audience — beginners as well as experts:
Data-science-ipython-notebooks – A Compilation of Python Tutorials
Topics covered:
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.
Stars: 15,056
Check here
The Open-Source Data Science Masters – Libraries and Tutorials in Python
The open-source curriculum for learning Data Science covers rudimentary concepts in both theory and technologies.
Topics covered:
Python
R
Stars: 11,723
Check here
Awesome Data Science – A One-Stop Source To Blogs And Podcasts
This is an open-source Data Science repository to learn and apply towards solving real-world problems using Data Science.
Topics covered:
Why Data Science, Data science colleges, MOOCs, Datasets, Podcasts and Blogs.
Stars: 9,484
Check here
Stanford-Tensorflow-tutorials – Assignments and Sample Code of the Main Course
This repository contains code examples for the course CS 20: TensorFlow for Deep Learning Research.
Stars: 8,204
Check here
Data science Blogs – A Collection Of Top Blogs In Alphabetical Order
This repository contains a curated list of top data science blogs which are available for free
Stars: 4,581
Check here
Deep Learning Specialization on Coursera – A Compilation of Code-based Quiz questions From the main Course
This repo contains all the code base, quiz questions, screenshot, and images, are taken from, unless specified, Deep Learning Specialization on Coursera.
Topics covered:
Keras, TensorFlow, Optimisation methods, Gradient checking, Step-by-step guide to building a neural network
Stars:3,493
Check here
Spark Notebook – A Quick Start Guide to Spark
The Spark Notebook is the open-source notebook aimed at enterprise environments, providing Data Scientists and Data Engineers with an interactive web-based editor that can combine Scala code, SQL queries, Markup and JavaScript in a collaborative manner to explore, analyse and learn from massive data sets.
Topics covered:
Spark, Scala
Stars: 2,721
Check here
Creative Applications of Deep Learning with Tensorflow – A Collection of Lecture Transcripts, Assignments and a Guide to Installation of Packages
This repository contains lecture transcripts and homework assignments as Jupyter Notebooks for the first of three Kadenze Academy courses on Creative Applications of Deep Learning w/ Tensorflow.
Topics covered:
TensorFlow, CUDA/GPU instructions
Stars: 1,269
Check here