2013/6/4 Joel Nothman jnoth...@student.usyd.edu.au:
NLP folks pass the blame to IR folks :P
... and IR folks always mean absolute frequency, unless stated otherwise.
--
Lars Buitinck
Scientific programmer, ILPS
University of Amsterdam
On 06/04/2013 05:55 AM, Christian Jauvin wrote:
Many thanks to all for your help and detailed answers, I really appreciate it.
So I wanted to test the discussion's takeaway, namely, what Peter
suggested: one-hot encode the categorical features with small
cardinality, and leave the others in
Hi Şükrü.
First, please call my Andy like anyone else ;)
Second, please ask questions like these on the mailing list.
I don't always have time to reply to mails.
If you want to start to contribute, please read the contributor guidelines :
Hi Christian,
I believe more in my results than in my expertise - and so should you :-) **
I think you misunderstood me: I did not claim that one-hot encoded
categorical features give better results than ordinal encoded ones - I just
claimed that ordinal encoding works as good as one-hot encoded
On Jun 4, 2013, at 2:38 AM, Lars Buitinck l.j.buiti...@uva.nl wrote:
2013/6/4 Joel Nothman jnoth...@student.usyd.edu.au:
NLP folks pass the blame to IR folks :P
... and IR folks always mean absolute frequency, unless stated otherwise.
Coming from ML, I’ve seen it used as both absolute and
Hi All,
I am new to scikit-learn, and I am very keen on starting contributing to
the project. However, I couldn't find any developer list, where I could
propose my ideas. Could you direct me to such a list or are such
discussions generally taken in the general mailing list?
Many thanks,
Karol
Welcome,
This is right list.
Gaël
--
How ServiceNow helps IT people transform IT departments:
1. A cloud service to automate IT design, transition and operations
2. Dashboards that offer high-level views of enterprise
Great, thanks.
As I mentioned, I am very interested in making some contribution to
scikit-learn library. In particular, I would like to extend the current
implementation of handling small sample size problems. What I have in mind
is adding the support for Maximum Entropy Covariance Estimate (The
imho this may fit better in scikit-image http://scikit-image.org/.
Thanks,
Ronnie
On Tue, Jun 4, 2013 at 4:33 PM, Karol Pysniak kpysn...@gmail.com wrote:
Great, thanks.
As I mentioned, I am very interested in making some contribution to
scikit-learn library. In particular, I would like to
