jackhan2008 Hi, Anyone know how to load the KDD 2000 Cup data into R? The data is a flat file in See5 format. http://www.kdd.org/kdd-cup-2000-online-retailer-website-clickstream-analysis Thanks!
Ihavenothing 回复 第1楼 的 jackhan2008: There're many different files in the zip file. Which one do you want to read?
Ihavenothing 回复 第3楼 的 jackhan2008: You can try read.table("question1agg.data", sep=",") but I believe the dataset is not clean, and you may encounter erros in reading. </p>
jackhan2008 Thanks! The data can be loaded by the following statement:- df <- read.table(file.choose(),sep=",",fill=TRUE) The parameter "fill" is set in case the rows have unequal length.