On Tue, May 15, 2012 at 4:38 AM, Robert Layton <[email protected]>wrote:
> On 15 May 2012 04:20, JAGANADH G <[email protected]> wrote:
>
>> Hi All
>>
>> Is it possible to apply linear discriminant analysis in text data ?
>> If so how can I prepare the data for same
>>
>> If it is a dumb question forgive
>>
>> Thanks in advance
>>
>> Hello,
>
> You cannot apply the method directly to the text, but you can to a
> representation (usually numerical) of the text.
> A simple one would be to pick 50 words and have the frequency of each word
> for each document.
> See here for an example: http://en.wikipedia.org/wiki/Bag_of_words_model
>
> Other representations exist, you will have to consult the relevant area of
> research to find the better representations for your purpose (are you doing
> topic classification, authorship attribution, language detection, etc?).
>
> - Robert
>
Thanks Robert,
I am trying to topic classification .
I will do some exercises and will get back to you
Thanks
--
**********************************
JAGANADH G
http://jaganadhg.in
*ILUGCBE*
http://ilugcbe.org.in
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
