patchGNU Octave - Patches: patch #10045, [octave forge] (statistics) Add...

 
 

patch #10045: [octave forge] (statistics) Add dataset 'carbig'

Submitted by:  None
Submitted on:  Tue 16 Mar 2021 06:56:59 PM UTC
 
Category:  Forge : other Priority:  5 - Normal
Status:  Done Privacy:  Public
Assigned to:  None Originator Email:  -email is unavailable-
Open/Closed:  Closed
* Mandatory Fields

Add a New Comment (Rich Markup)
   

Comment Type & Canned Response:
       

 

Thu 25 Nov 2021 01:19:06 AM UTC, comment #4: 
Nir Krakauer <nir_krakauer>
Sun 08 Aug 2021 08:36:56 AM UTC, comment #3: 

What remains to be done to get this ready for inclusion? Just citations + cset polishing?

Philip Nienhuis <philipnienhuis>
Project Member
Tue 23 Mar 2021 08:42:03 PM UTC, comment #2: 

OK. I think it should be possible to include the dataset because UCI datasets are publicly available, as a matter of fact this dataset (and others) are included in GPL software like Weka ( https://waikato.github.io/weka-wiki/datasets/ ) and the (now unmaintained) dprep package for R. Scikit-learn includes some of the UCI datasets ( https://scikit-learn.org/stable/datasets/toy_dataset.html ), but not this one. It should be just a matter of correct citation.

Anonymous
Sun 21 Mar 2021 07:56:54 PM UTC, comment #1: 

The original dataset seems to live here:
http://lib.stat.cmu.edu/datasets/ ("cars")
and the 8 missing elements are explained at the web site you got the data from:

> This dataset is a slightly modified version of the dataset provided in the StatLib library. In line with the use by Ross Quinlan (1993) in predicting the attribute "mpg", 8 of the original instances were removed because they had unknown values for the "mpg" attribute. The original dataset is available in the file "auto-mpg.data-original".

I'm a bit unsure about the license /usage conditions; the statlib library at Carnegie Mellon (http://lib.stat.cmu.edu/datasets/) displays:

> If you use an algorithm, dataset, or other information from StatLib, please acknowledge both StatLib and the original contributor of the material.

and/but the accompanying cars.desc file says little as well. But it does mention the original authors:

> This data set is a version of the CRCARS data set of
>    Donoho, David and Ramos, Ernesto (1982), ``PRIMDATA:
>    Data Sets for Use With PRIM-H'' (DRAFT).


That's about as far as I could dig.
Hopefully another dev jumps in.

Philip Nienhuis <philipnienhuis>
Project Member
Tue 16 Mar 2021 06:56:59 PM UTC, original submission:  

This is the "carbig" dataset based on https://archive.ics.uci.edu/ml/datasets/Auto+MPG .

There is a notice in the dataset with a citation according to the citation policy of UCI: https://archive.ics.uci.edu/ml/citation_policy.html .

Differences of this "carbig" dataset compared to the one from MATLAB:

  • this is a little smaller (398 elements versus 406, I did not investigate the origin of the extra 8 elements)
  • the "origin" attribute is ["America";"Europe";"Asia"] instead of ["USA";"Germany";"France";"Italy";"Sweden";"UK";"Japan"] like in MATLAB: in the original dataset it is marked the area of origin of the car with a number (1,2,3), MATLAB changed that to the country.
Anonymous

 

(Note: upload size limit is set to 16384 kB, after insertion of the required escape characters.)

Attach Files:
   
   
Comment:
   

Attached Files
file #51078:  commit-05a6881.diff added by None (18KiB - text/x-patch - carbig.mat)

 

Depends on the following items: None found

Items that depend on this one: None found

 

Carbon-Copy List
  • -email is unavailable- added by nir_krakauer (Posted a comment)
  • -email is unavailable- added by philipnienhuis
  • -email is unavailable- added by None (Submitted the item)
  •  

    There are 0 votes so far. Votes easily highlight which items people would like to see resolved in priority, independently of the priority of the item set by tracker managers.

    Only logged-in users can vote.

     

     

     

     

    Follow 5 latest changes.

    Date Changed by Updated Field Previous Value => Replaced by
    2021-11-25 philipnienhuis StatusNeed Info => Done
        Open/ClosedOpen => Closed
    2021-08-08 philipnienhuis StatusNone => Need Info
        Carbon-Copy- => Added philipnienhuis
    2021-03-16 None Attached File- => Added commit-05a6881.diff, #51078

    Back to the top


    Powered by Savane 3.9