Hi Kyle,
No, it's not in scikit-learn yet.
We do have GMMs, though, which are another way to do clustering with soft
memberships.
Mathieu
On Thu, Sep 26, 2013 at 5:14 AM, Kyle Kastner kastnerk...@gmail.com wrote:
I looked around, but was unable to find a fuzzy clustering algorithm in
2013/9/26 Gael Varoquaux gael.varoqu...@normalesup.org:
On Mon, Sep 16, 2013 at 09:19:23AM +0200, Gilles Louppe wrote:
So basically, do we agree that the goal of our proposal to this
workshop will only be to further promote the project in the scientific
community?
Sounds good to me :)
2013/9/25 Peter Prettenhofer peter.prettenho...@gmail.com:
Hi Kyle,
personally, I'd love to see SAX in sklearn or any other python library that
I could easily use with sklearn. We don't have any time-series specific
functionality yet (eg. lagged features transformer). So if we choose to add
Hi.
I try to reproduce the best fitting plot from
http://www.astroml.org/book_figures/chapter4/fig_GMM_1D.html on my data.
I have sample data, in stead of histogram data.
I have the following code, but get an error because the dimension of my
data is 2.
Could anybody help me with this?
My data
Hi,
I've noticed that I get an error using CountVectorizer (or any class that
uses fit_transform) in python 2.6.1 with an unspecified vocabulary, as the
underlying defaultdict method cannot take 'None'. Is there a fix or do I
just need a more recent install of python?
Thanks,
Akhil
When I run: nosetests sklearn --exe
I get:
/System/Library/Frameworks/Python.framework/Versions/2.7/Extras/lib/python/numpy/lib/utils.py:1132:
DeprecationWarning: The compiler package is deprecated and removed in Python
3.x.
import compiler
The docs are now written to $previous_path + /stable/, and this broke my
upload script. I've updated my script and it should be fixed now.
Fabian
On Tue, Sep 3, 2013 at 4:41 PM, Fabian Pedregosa
fabian.pedreg...@inria.frwrote:
I think it still runs on my machine. I'm looking into it ...
On
Hello,
I wondered if it's possible to add my own correlation functions in the SK learn
GP class? I'm working on a thesis revolving the stock market and non-stationary
time series so I'd like to use other correlation functions than the basic ones
that are provided in SK Learn. Can I maybe add
Hi,
I am an M.Tech student. I am doing my main project in speaker recognition.
ie..recognizing people from their voice. And i will consider python as my
software. My project has a training phase. HMM,ANN,GMM,SVM,DTW can be used
for feature matching in speaker recognition, My question is that can i
2013/9/7 Tasos Ventouris tasosventou...@hotmail.com:
Hello, I have to questions where I would like your feedback.
The first one:
Here is my code:
from sklearn.feature_extraction.text import TfidfVectorizer
documents = [doc1,doc2,doc3]
tfidf = TfidfVectorizer().fit_transform(documents)
2013/9/26 Olivier Grisel olivier.gri...@ensta.org:
2013/9/7 Tasos Ventouris tasosventou...@hotmail.com:
I tried to run my script and then create a string from the list for each
text and inlcude those texts into the TfidfVectorizer. I am satisfied from
the results, but unfortunately, if I have
I think you have trained the model on 2d data and evaluating best model on
1d data.
It should be logprob, responsibilities = M_best.eval(x)
should be conataing X not x because X is 2d and x is 1d
On Tue, Sep 17, 2013 at 11:21 AM, Anna Bos anna.n@gmail.com wrote:
Hi.
I try to reproduce
2013/9/17 Sundeep Sivan sundeepsi...@gmail.com:
Hi,
I am an M.Tech student. I am doing my main project in speaker recognition.
ie..recognizing people from their voice. And i will consider python as my
software. My project has a training phase. HMM,ANN,GMM,SVM,DTW can be used
for feature
HMM is widely used in speaker recognition. You can explore HMM.
On Tue, Sep 17, 2013 at 4:03 PM, Sundeep Sivan sundeepsi...@gmail.comwrote:
Hi,
I am an M.Tech student. I am doing my main project in speaker recognition.
ie..recognizing people from their voice. And i will consider python as my
2013/9/26 Kyle Kastner kastnerk...@gmail.com:
I had not thought about use inside a Pipeline - though now that you mention
it, that seems like the ideal use case for an algorithm like this. Is this
the PR you mentioned?
https://github.com/scikit-learn/scikit-learn/pull/1454
Yes but because of
2013/9/16 Akhil Shah akhil...@gmail.com:
Hi,
I've noticed that I get an error using CountVectorizer (or any class that
uses fit_transform) in python 2.6.1 with an unspecified vocabulary, as the
underlying defaultdict method cannot take 'None'. Is there a fix or do I
just need a more recent
2013/9/26 Kyle Kastner kastnerk...@gmail.com
I had not thought about use inside a Pipeline - though now that you
mention it, that seems like the ideal use case for an algorithm like this.
Is this the PR you mentioned?
https://github.com/scikit-learn/scikit-learn/pull/1454
As far as lagged
2013/9/20 Pieter Savenberg pieter.savenb...@ugent.be:
Hello,
I wondered if it's possible to add my own correlation functions in the SK
learn GP class? I'm working on a thesis revolving the stock market and
non-stationary time series so I'd like to use other correlation functions
than the
2013/9/26 Peter Prettenhofer peter.prettenho...@gmail.com:
2013/9/26 Kyle Kastner kastnerk...@gmail.com
I had not thought about use inside a Pipeline - though now that you
mention it, that seems like the ideal use case for an algorithm like this.
Is this the PR you mentioned?
eval() expects data of the same dimension as the fit. Your fit data is
shape (48, 2), which is interpreted as 48 points in 2 dimensions. Your
eval data is shape (48,) which scikit-learn cannot interpret as (n_samples,
n_features). If you fit the model on two-dimensional data, you must call
eval
2013/9/26 Olivier Grisel olivier.gri...@ensta.org:
I have no problem with 2.6.7:
I tried with 2.6.1, 2.6.6 and 2.6.8. Only the first has a problem. As
I already said on SO, this is probably a bug in Python 2.6.1, but it
should be easy to fix: just construct the defaultdict from some
callable,
21 matches
Mail list logo
