Why does WEKA have issues with simple stuff like downloading?

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

Why does WEKA have issues with simple stuff like downloading?

Bard1972
Hi there,

I used WEKA 3.8 Tools/Package Manager for downloading Auto WEKA 2.6 but got
a warning: Check Console for Errors? I'm using a Mac 10.14.

So then I tried to actually use WEKA and followed the video tutorial on
diabetes classification and I can't even open the file they suggest? (UCI
repository of machine learning datasets (datasets-UCI.jar, 1,190,961
Bytes)).
I downloaded the dataset and tried to "open file" but it gives this error:
"Couldn't read object: datasets-UCI.jar invalid stream header: 504B0304"

How exactly is it possible that people can code all this advanced s/ware but
can't even code it so that really basic stuff like installing a piece of
software or downloading a file
works and doesn't end up wasting hours of time? Is this what it's going to
be like using WEKA? I don't get this using RapidMiner.

If this is what it's like using WEKA I'm not unimpressed and I was really
looking forward to using it. If anyones got an idea of how to fix this it'd
be appreciated. Thanks.






--
Sent from: https://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Why does WEKA have issues with simple stuff like downloading?

Peter Reutemann
> I used WEKA 3.8 Tools/Package Manager for downloading Auto WEKA 2.6 but got
> a warning: Check Console for Errors? I'm using a Mac 10.14.

Unfortunately, I'm neither a Mac user nor do I use AutoML, I'm on Linux.

> So then I tried to actually use WEKA and followed the video tutorial on
> diabetes classification and I can't even open the file they suggest? (UCI
> repository of machine learning datasets (datasets-UCI.jar, 1,190,961
> Bytes)).

Not sure what tutorial you are referring to. I recommend you have a
look at the PDF manual that comes with you Weka download, especially
the section on the Explorer.

> I downloaded the dataset and tried to "open file" but it gives this error:
> "Couldn't read object: datasets-UCI.jar invalid stream header: 504B0304"

Weka does not support reading JAR archives
(https://en.wikipedia.org/wiki/JAR_(file_format)) natively as file
formats, its default file format is ARFF. The archive you are
referring to is a collection of UCI datasets in ARFF format, which you
need to extract. I'm sure, your Finder in OSX can do that for you.
Otherwise, any compression utility that can handle zip files will be
able to do that for you.
Also, you don't seem to have used the right way of opening the file.
If you used the "Open" button in the GenericObjectEditor, this is
(generic functionality) for restoring configurations via Java
deserialization, not for loading datasets.

> How exactly is it possible that people can code all this advanced s/ware but
> can't even code it so that really basic stuff like installing a piece of
> software or downloading a file
> works and doesn't end up wasting hours of time? Is this what it's going to
> be like using WEKA? I don't get this using RapidMiner.
>
> If this is what it's like using WEKA I'm not unimpressed and I was really
> looking forward to using it. If anyones got an idea of how to fix this it'd
> be appreciated. Thanks.

Different tools behave differently and it can be frustrating if a
tool, that you are unfamiliar with, does not behave the way you expect
it to behave. But it is most likely not the tool's fault!
Weka has been around for longer than RapidMiner and does not have the
financial backing that RapidMiner has, it is basically maintained by
volunteers. If you want these volunteers to help you, I recommend you
write your emails in a more civil tone.

Cheers, Peter
--
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 858-5174
http://www.cms.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
To unsubscribe send an email to [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html