Actually, this data file is not even in hdfs format (maybe if it was,
the matlab would be created automatically?)
It is just an upload of a csv file (without file ending) in a zip file.
This is not really a supported format for mldata.
How could we read that as a numpy array?
That requires serious magic (even more than pandas has).
I don't think scikit-learn is in the business of parsing csv files, and
mldata isn't either.
One could argue mldata made a mistake when it allowed people to upload
data like this.
But maybe some datasets are raw texts? or raw binary?
On 12/09/2015 01:17 PM, Luca Puggini wrote:
Yes openml seems a better choice.
I would really like to have an easy way to import public datasets.
I think that fetch_mldata should throw a warning when it is imported
if we think this is not working 100%.
Best,
Luca
On Wed, Dec 9, 2015 at 5:35 PM Andreas Mueller <t3k...@gmail.com
<mailto:t3k...@gmail.com>> wrote:
I guess we use the matlab data with is not required by mldata.
We could add code that tries to fetch the matlab, and if that doesn't
work uses the hdf5,
with a soft dependency.
Not sure we want that as mldata seems somewhat defunc.
Maybe openml would be a better source (maybe once they finish their
python interface?).
Cheers,
Andy
On 12/09/2015 12:08 PM, Sebastian Raschka wrote:
> Hm, I have problems with that, too. Iris seems to work though.
Just checked out the default link where scikit tries to fetch
from, it’s
>
> http://mldata.org/repository/data/download/matlab/
>
> So, for iris it would be
>
> http://mldata.org/repository/data/download/matlab/iris/
>
> but
>
> http://mldata.org/repository/data/download/matlab/mhc-nips11/
>
> doesn’t exist on their website.
>
> Anyways, I would probably download the file manually for now via:
> http://mldata.org/repository/data/download/mhc-nips11/
>
> or you could try to override the
>
> MLDATA_BASE_URL
>
> path by setting it to
>
> http://mldata.org/repository/data/download/
>
> (not sure if the mhc-nips11 data is in a supported format though)
>
> Best,
> Sebastian
>
>> On Dec 9, 2015, at 6:00 AM, Luca Puggini <lucapug...@gmail.com
<mailto:lucapug...@gmail.com>> wrote:
>>
>> Hi,
>> I am trying to fetch this dataset from mldata.
>> http://mldata.org/repository/data/viewslug/mhc-nips11/
>>
>> I have tried:
>> data = fetch_mldata('mhc-nips11', data_home=DG.load_path)
>>
>> but I obtain an error :
>> HTTP Error 404: Dataset 'mhc-nips11' not found on mldata.org
<http://mldata.org>.
>>
>> I do not understand how to identify the name of the dataset
from the webpage.
>>
>> Can you help me?
>>
>> Thanks a lot!
>>
>> Luca
>> --
>> Sent by mobile phone
>>
>>
------------------------------------------------------------------------------
>> _______________________________________________
>> Scikit-learn-general mailing list
>> Scikit-learn-general@lists.sourceforge.net
<mailto:Scikit-learn-general@lists.sourceforge.net>
>> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
>
------------------------------------------------------------------------------
> _______________________________________________
> Scikit-learn-general mailing list
> Scikit-learn-general@lists.sourceforge.net
<mailto:Scikit-learn-general@lists.sourceforge.net>
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
------------------------------------------------------------------------------
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
<mailto:Scikit-learn-general@lists.sourceforge.net>
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
--
Sent by mobile phone
------------------------------------------------------------------------------
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
------------------------------------------------------------------------------
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
