The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here

Java error on using k-NN Global Anomaly Detection with missing values

b_ofoghib_ofoghi Member, University Professor Posts: 2 University Professor
edited November 2018 in Help

Hi, I am using RM Studio 8.2 and I have a process in which I am using k-NN Global Anomaly Detection to find anomaly scores for a set of data instances that have missing values in some of the attributes. In doing so, I get a Java error message "Process failed. Comparison method violates its general contract!". When I replace missing values before this operator, everything goes fine. However, this is not what I am after as I would like to find anomalies before treating missing values. Any ideas why I get that error? Thanks,

image.png

Tagged:

Answers

  • sgenzersgenzer Administrator, Moderator, Employee-RapidMiner, RapidMiner Certified Analyst, Community Manager, Member, University Professor, PM Moderator Posts: 2,959 Community Manager

    hello @b_ofoghi welcome to the community! Some quick requests so we can help you:


    • Post your XML process here in this thread (see this post for instructions on How to Post on the Community)
    • Attach your dataset if possible (use a fictionalized version if there are privacy concerns)
    • Make sure you have all necessary extensions installed (see https://youtu.be/pjBqG3xtXx4)

    Scott

  • b_ofoghib_ofoghi Member, University Professor Posts: 2 University Professor

    Hi Scott,

    I worked it out. The data set had some rows of full missing values (with no values in any attribute), once these are filtered out, the outlier detection operator works fine even if there are missing values scattered here and there.

    Thanks,

Sign In or Register to comment.