A nice free book on mining datasets thanks to Jure Leskovec, Anand Rajaraman and Jeff Ullman
It covers well the topic and it opens to other correlated subjects.
I like it at lot because there is a ton of material around it:
- Powerpoint Slides
- Videos
Follows the table of contents:
- Data Mining
- Map-Reduce and the New Software Stack
- Finding Similar Items
- Mining Data Streams
- Link Analysis
- Frequent Itemsets
- Clustering
- Advertising on the Web
- Recommendation Systems
- Mining Social-Network Graphs
- Dimensionality Reduction
- Large-Scale Machine Learning
Follows the links down below :
- http://infolab.stanford.edu/~ullman/mmds/bookL.pdf
- Errata: http://infolab.stanford.edu/~ullman/mmds/errata-v2.html
- Beta Version of the Third Edition that contains additional material : http://i.stanford.edu/~ullman/mmdsn.html
- The main website that contains additional materials with links to Slides, Videos: http://www.mmds.org/