/go

The Open Source Data Science Masters

The UnlicenseUnlicense

created & maintained by @clarecorthell, founding partner of Luminant Data Science Consulting

The Open-Source Data Science Masters

The open-source curriculum for learning Data Science. Foundational in both theory and technologies, the OSDSM breaks down the core competencies necessary to making use of data.

Contents

The Internet is Your Oyster

With Coursera, ebooks, Stack Overflow, and GitHub -- all free and open -- how can you afford not to take advantage of an open source education?

The Motivation

We need more Data Scientists.

...by 2018 the United States will experience a shortage of 190,000 skilled data scientists, and 1.5 million managers and analysts capable of reaping actionable insights from the big data deluge.

-- McKinsey Report Highlights the Impending Data Scientist Shortage 23 July 2013

There are little to no Data Scientists with 5 years experience, because the job simply did not exist.

-- David Hardtke "How To Hire A Data Scientist" 13 Nov 2012

An Academic Shortfall

Classic academic conduits aren't providing Data Scientists -- this talent gap will be closed differently.

Academic credentials are important but not necessary for high-quality data science. The core aptitudes – curiosity, intellectual agility, statistical fluency, research stamina, scientific rigor, skeptical nature – that distinguish the best data scientists are widely distributed throughout the population.

We’re likely to see more uncredentialed, inexperienced individuals try their hands at data science, bootstrapping their skills on the open-source ecosystem and using the diversity of modeling tools available. Just as data-science platforms and tools are proliferating through the magic of open source, big data’s data-scientist pool will as well.

And there’s yet another trend that will alleviate any talent gap: the democratization of data science. While I agree wholeheartedly with Raden’s statement that “the crème-de-la-crème of data scientists will fill roles in academia, technology vendors, Wall Street, research and government,” I think he’s understating the extent to which autodidacts – the self-taught, uncredentialed, data-passionate people – will come to play a significant role in many organizations’ data science initiatives.

-- James Kobielus, Closing the Talent Gap 17 Jan 2013

Ready?


The Open Source Data Science Curriculum

Start here.

Intro to Data Science / UW Videos

  • Topics: Python NLP on Twitter API, Distributed Computing Paradigm, MapReduce/Hadoop & Pig Script, SQL/NoSQL, Relational Algebra, Experiment design, Statistics, Graphs, Amazon EC2, Visualization.

Data Science / Harvard Videos & Course

  • Topics: Data wrangling, data management, exploratory data analysis to generate hypotheses and intuition, prediction based on statistical methods such as regression and classification, communication of results through visualization, stories, and summaries.

Data Science with Open Source Tools Book $27

  • Topics: Visualizing Data, Estimation, Models from Scaling Arguments, Arguments from Probability Models, What you Really Need to Know about Classical Statistics, Data Mining, Clustering, PCA, Map/Reduce, Predictive Analytics
  • Example Code in: R, Python, Sage, C, Gnu Scientific Library

A Note About Direction

This is an introduction geared toward those with at least a minimum understanding of programming, and (perhaps obviously) an interest in the components of Data Science (like statistics and distributed computing). Out of personal preference and need for focus, I geared the original curriculum toward Python tools and resources. R resources can be found here.

Ethics in Machine Intelligence

Human impact is a first-class concern when building machine intelligence technology. When we build products, we deduce patterns and then reinforce them in the world. Ethics in any Engineering concerns understanding the sociotechnological impact of the products and services we are bringing to bear in the human world -- and whether they are reinforcing a future we all want to live in.

Math

Linear Algebra & Programming

Convex Optimization

Statistics

Differential Equations & Calculus

Problem Solving

Computing

Get your environment up and running with the Data Science Toolbox

Algorithms

Distributed Computing Paradigms

Databases

Data Mining

Data Design

How does the real world get translated into data? How should one structure that data to make it understandable and usable? Extends beyond database design to usability of schemas and models.

OSDSM Specialization: Web Scraping & Crawling

Machine Learning

Foundational & Theoretical

Practical

Probabilistic Modeling

Deep Learning (Neural Networks)

Social Network & Graph Analysis

Natural Language Processing

Data Analysis

One of the "unteachable" skills of data science is an intuition for analysis. What constitutes valuable, achievable, and well-designed analysis is extremely dependent on context and ends at hand.

in Python

  • Data Analysis in Python Tutorial
  • Python for Data Analysis Book $24
  • An Example Data Science Process ipynb

Data Communication and Design

Visualization

Data Visualization and Communication

Theoretical Design of Information

Applied Design of Information

Theoretical Courses / Design & Visualization

Practical Visualization Resources

OSDSM Specialization: Data Journalism

Python (Learning)

Python (Libraries)

Installing Basic Packages Python, virtualenv, NumPy, SciPy, matplotlib and IPython & Using Python Scientifically

Command Line Install Script for Scientific Python Packages

More Libraries can be found in the "awesome machine learning" repo & in related specializations

Data Structures & Analysis Packages

Machine Learning Packages

Networks Packages

Statistical Packages

  • PyMC - Bayesian Inference & Markov Chain Monte Carlo sampling toolkit
  • Statsmodels - Python module that allows users to explore data, estimate statistical models, and perform statistical tests
  • PyMVPA - Multivariate Pattern Analysis in Python

Natural Language Processing & Understanding

  • NLTK - Natural Language Toolkit
  • Gensim - Python library for topic modeling, document indexing and similarity retrieval with large corpora. Target audience is the natural language processing (NLP) and information retrieval (IR) community.

Data APIs

  • twython - Python wrapper for the Twitter API

Visualization Packages

  • matplotlib - well-integrated with analysis and data manipulation packages like numpy and pandas
  • Seaborn - a high-level statistical visualization package built on top of matplotlib

iPython Data Science Notebooks

Datasets are now here

R resources are now here

Data Science as a Profession

  • Doing Data Science: Straight Talk from the Frontline O'Reilly / Book $25
  • The Data Science Handbook: Advice and Insights from 25 Amazing Data Scientists Book $22

Capstone Project


Resources

Read

Watch & Listen

Learn


Notation

Non-Open-Source books, courses, and resources are noted with $.

Contribute

Please Contribute -- this is Open Source!

Follow me on Twitter @clarecorthell