🎉 🎉 RAPIDMINER 9.10 IS OUT!!! 🎉🎉

Download the latest version helping analytics teams accelerate time-to-value for streaming and IIOT use cases.

CLICK HERE TO DOWNLOAD

"Clustering files"

hunhun Member Posts: 1 Contributor I
edited June 2019 in Help
Hello!

I have a question about clutering. I have some GPS data (the most important are longitude and latitude attribute). I would like to cluster the files, but not in rows.

E.g.: I have 10 csv files (contains lon and lat attributes with 1000-2000 rows). 8 routes are similar (home -> work) and 2 routes are different (home -> shop and work -> restaurant). I would like that: cluster0: the 8 similar routes, and cluster1: the others. Or cluster0: 8 similar, cluster1: other one, cluster2: other one.

Any idea, how can I do that?

Thanks in advance.

Adam
Tagged:

Answers

  • mschmitzmschmitz Administrator, Moderator, Employee, RapidMiner Certified Analyst, RapidMiner Certified Expert, University Professor Posts: 3,055  RM Data Scientist
    Hi Adam,

    i think you can simply calculate statistics per file using loop files and aggregate. Stuff like
    #Entries
    #Most common entry
    ...
    And then use clustering on those 8 examples. At least that would be my first guess.

    ~Martin
    - Head of Data Science Services at RapidMiner -
    Dortmund, Germany
Sign In or Register to comment.