Regression dataset with categorical features

Asked Jun 18 '20 at 07:26

Active Jun 18 '20 at 07:26

Viewed 72 times

I have thought of a regression technique that I want to try on several datasets. I would like these datasets to have the following properties:

Be a tabular dataset (no images).
Have at least 20k rows, and ideally around 100k.
Have some categorical variables with many levels (at least a variable with 100 levels or more).
Ideally, the target should have long tails.

Does anyone any public dataset with these properties? I have found the stack overflow developer survey to work for me, but I'd like to have some more datasets with such structure.

asked Jun 18 '20 at 07:26

David Masip

5,981
2
23
61

2

Possible duplicate of a post on Open Data: https://opendata.stackexchange.com/questions/17679/regression-dataset-with-categorical-features. – Dave Jun 18 '20 at 09:35
@Dave Page not found – Mikhail_Sam Jun 18 '20 at 14:11
1

@Mikhail_Sam He posted the same question on Open Data and has deleted it. I think he deleted the wrong one. – Dave Jun 18 '20 at 15:01
Yeah I deleted it there, I probably dit it worng – David Masip Jun 18 '20 at 15:04

Regression dataset with categorical features

0 Answers0