soodoku / data-science

Lecture Slides for Introduction to Data Science

Data Science: Some Basics

1. Introduction to Data Science (presentation, tex)

   • What can Big Data do for you?
   • What is Big Data?
   • Implications for Statistics and Computation
   • What is Data Science?
   • Prerequisites

2. Get your own (Big) Data (presentation, tex)

   • Scrape web pages and pdfs. (Scripts)
   • Image to Text (Python Script using Tesseract)
   • Image to Text in R using the Abbyy FineReader Cloud OCR
   • Image to Text in R using the Captricity API
   • Web Scraping/API Applications:
     • Get Data on Journalists
     • Get Weather Data
     • Get Cricket Data
     • Get Congressional Speech Data
     • Track FB Likes, Twitter Followers, Youtube Views
     • Track Civil Rights Coverage in NY Times using NYT API
   • Get Social Networking Data
   • Regular Expressions
   • Pre-process text data
   • Assignment

3. Databases and SQL (presentation, tex)

   • What are databases?
   • Relational Model
   • Relational Algebra
   • Basic SQL
   • Views

4a. Introduction to Introduction to Statistical Learning

4b. Introduction to Statistical Learning (presentation, tex) * How to learn from data? * Nearest Neighbors * When you don't have good neighbors * Assessing model fit * Clarification about Big Data

5. Supervised Methods

6. Unsupervised Methods

   • PCA, CA
   • k-means (presentation, tex)

7. Presenting Analyses

   • ggplot2 in brief
   • Examples of ggplot in action:
     • NYT Civil Rights Coverage (R code, Graph)
     • Military Experience of UK Prime Ministers (R code, Graph)

• Suggestions for writing

8. Some Applications
   • From paper to digital (presentation, tex)
   • Text as Data
     • Sentiment Analysis
     • Model Relationship Between Words and Ideology
     • Basic Text Classifier

Suggested Books

The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition
By Trevor Hastie, Robert Tibshirani, Jerome Friedman
ISBN: 0387848576

Python Programming: An Introduction to Computer Science
By John Zelle
ISBN: 1590282418

ggplot2: Elegant Graphics for Data Analysis (Use R!)
By Hadley Wickham
ISBN: 0387981403

License

Released under the Creative Commons License.