Statistics node bug


No matter which columns you put into the include and exclude box in the Statistics node, the output generated is still on all the columns in the original table.



The column selection "Nominal values" refers to the nominal value computation only; the statistic moments for the numeric columns are always determined - only the median is optional.

Finding some strangeness in the Statistics Node. Displays incorrect data as compared to Data Explorer.

In attached file… The column Credit-Amount has many values but in Statistics node appears in the Nomial tab with 1 value… this is not the case and is displayed properly in Data Explorer node.

credit-data-training.xlsx (46.4 KB)

This looks like a bug with the Statistics node. I briefly glanced at our internal ticketing system and didn’t see any mention of this, so I may need to file a report.

The good news is that seems relatively minor, in that the numeric view looks correct, it’s just this field is showing up in the nominal view for some reason. Also, the Data Explorer node (which I would generally recommend since its view looks nicer) appears unaffected.

Thanks for reporting!