硕士水平Data Science 自学课程

http://datasciencemasters.org/

无意中看见这个，觉得非常有意思

看有没有人愿意一起学的？

The How: An Open Source Data Science Curriculum

Start here.

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

Math

• Linear Algebra / Levandosky Stanford / Book
• Statistics Stats in a Nutshell / Book
• Problem-Solving Heuristics "How To Solve It" Polya / Book
  

Computing

• Algorithms
  
  
  • Algorithms Design & Analysis I Stanford / Coursera
  • Algorithm Design Kleinberg & Tardos / Book
    
• Databases
  
  
  • Introduction to Databases Stanford / Coursera
    
• Data Mining
  
  
  • Mining Massive Data Sets Stanford / Book
  • Mining The Social Web O'Reilly / Book
  • Introduction to Information Retrieval Stanford / Book
    
• Machine Learning
  
  
  • Machine Learning / Ng Stanford / Coursera
  • Programming Collective Intelligence O'Reilly / Book
  • Statistics The Elements of Statistical Learning
    
• Probabilistic Graphical Models
  
  
  • Probabilistic Programming and Bayesian Methods for Hackers Github / Tutorials
  • PGMs / Koller Stanford / Coursera
    
• Natural Language Processing
  
  
  • NLP with Python O'Reilly / Book
    
• Analysis
  
  
  • Python for Data Analysis O'Reilly / Book
  • Big Data Analysis with Twitter UC Berkeley / Lectures
  • Social and Economic Networks: Models and Analysis / Stanford / Coursera
  • Information Visualization "Envisioning Information" Tufte / Book
    
• Python (Learning)
  
  
  • New To Python: Learn Python the Hard Way, Google's Python Class
    
• Python (Libraries)
  
  
  • Basic Packages Python, virtualenv, NumPy, SciPy, matplotlib and IPython
  • Bayesian Inference | pymc
  • Labeled data structures objects, statistical functions, etc pandas (See: Python for Data Analysis)
  • Python wrapper for the Twitter API twython
  • Tools for Data Mining & Analysis scikit-learn
  • Network Modeling & Viz networkx
  • Natural Language Toolkit NLTK
    

Capstone Project

• Toy Data Ideas
• Capstone Analysis of Your Own Design; Quora's Idea Compendium
  

---

Further Study Resources:

• Coursera
• Khan Academy
• Wolfram Alpha
• Wikipedia
• Quora
• Kindle .mobis
• Fave PopSci Read: The Signal and The Noise Nate Silver
• Zipfian Academy's List of Resources
• A Software Engineer's Guide to Getting Started w Data Science
  

Contribute

I'm not the expert -- please Share and Contribute. It's Open Source!

Here's my transcript; Please showcase your own on the wiki!

Follow me on Twitter @clarecorthell

我也算是个data scientist 了，认为这个单子是非常靠谱的，极其实用，有些课也上过，的的确确是不错的内容。

这是实在是太棒了!从明天就开始学起来吧！感谢楼主!

jimwallet 发表于 2016-11-13 17:13
谢谢提醒。我原来没有表达清楚，我是想做data engineer，做pipeline，熟悉各种框架，并且会用点jupyter数 ...

听说过insight data eng 好像不错，但具体包含什么内容就没研究过了
ML eng那个还成吧，udacity课都是流于浅显，当然入门后自己再找其他课去学，这个是可以的。
目前感觉ML入门最好的课肯定是andrew Ng在coursera那个，或者他在stanford的对等课，里面数学更多，但是道理也讲的更明白。DL入门应该是Stanford cs231n, 目前没有看见比它更好的入门课。熟悉后可以Jeff hinton在coursera那个课，但是比较dry了。

我很想报名啊 可是我没有任何编程背景 不知能否handle算法这样的课？

我很想报名啊 可是我没有任何编程背景 不知能否handle算法这样的课？

好多课啊，不知道自己能否坚持下来，先收藏了，这种把各个地方的课程打包起来的手法很新颖

niubinan 发表于 2013-9-6 00:12
我很想报名啊 可是我没有任何编程背景 不知能否handle算法这样的课？

先补一个udacity cs101就成

我是今年刚来美国的统计MS新生  这个课怎么一起学习  我编程就大一学过一年C++但是现在也忘记的差不多了 能跟上吗？     我想报名参加

有没有关于mapreduce的课程推荐？

哇同样想报名 同样没有任何编程背景 谢谢lz的推荐~！~~~

mark. 我要积极发展副业了。