Transcript Data preparation for data mining

Data preparation for data mining
4 credits
Data mining
Title:
dm-process .ps
Creator:
fig2dev Version 3.2 Patchlevel 1
Prev iew :
This EPS picture w as not s av ed
w ith a preview inc luded in it.
Comment:
This EPS picture w ill print to a
Pos tSc ript printer, but not to
other ty pes of printers.
Data preparation
Transforming (ie. fixing) of raw data into
form suitable for modeling (tool).
° detect and fix errors
° replace missing values
° transform variables, especially categorial to numerical
° transform distributions
° time-series processing
° (image preprocessing)
Contents of the course
• A look of experience into data mining
• A uniquely complete look into data
preparation
• Some fooling around with Matlab
• Discussion! Critique! Arguments!
To pass the course
•
•
•
•
Keep a presentation (30-45 minutes)
Attend the course
Home exercises
Practical exercise
Timetable
• Introductory lecture on September 22nd
• First student presentation on September
29th
• DL for exercises: January 16th
• Post-course lecture: January 19th
The book
• $40 + posting in
Amazon
• group order?
• master copy available