O’Reilly – Mining the Social Web – Web Pages

O’Reilly – Mining the Social Web – Web Pages
English | Size: 327.88 MB
Category: CBTs

How do software programs that automatically extract information from web pages actually work? This video course, based on content from the book "Mining the Social Web" (O’Reilly Media) by Matthew Russell, teaches you how to create machines that can navigate the internet, cut through the noise, and extract the most important textual content from any web page or group of web pages. You’ll learn how to use Python to write programs that can crawl, scrape, and parse the web; as well as discover how to extract key terms and sentences from web mined documents, explore document summarization techniques used in natural language processing and artificial intelligence, and gain experience using Python’s Natural Language Toolkit (NLTK) to auto-summarize web articles. Learners should have a basic understanding of Python. [Read more…]

O’Reilly – Mining the Social Web – Mailboxes

O’Reilly – Mining the Social Web – Mailboxes
English | Size: 148.91 MB
Category: CBTs

Imagine yourself as a criminal investigator. You’ve been tasked with searching through thousands of subpoenaed email messages for the purpose of finding evidence of fraud. What tools could you use to do your job? In this course, based on content from Matthew Russell’s book, "Mining the Social Web" (O’Reilly Media), you’ll learn how to forensically examine large email data sets. Designed for learners with basic Python experience, the course explains the structure of email messages, deciphers the meanings in email metadata, and shows you how to use pandas – Python’s data analysis library – to organize, manipulate, and query email data. Bonus: You get to practice your detective skills on an email data set used in a real U.S. criminal investigation (i.e., the 2001 Enron fraud case). [Read more…]