[Scikit-learn-general] PyCon 2013 scikit-learn tutorial videos online!

2013-03-30 Thread Olivier Grisel
Hi all, The videos of the scikit-learn tutorials Jake and I gave at PyCon 10 days ago are now both online (along with IPython notebooks and exercise material on our respective github accounts): - An Introduction to scikit-learn: Machine Learning in Python http://www.youtube.com/watch?v=4ONBVNm3i

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread Andreas Mueller
On 03/30/2013 11:37 AM, Lars Buitinck wrote: 2013/3/30 mailto:amuel...@ais.uni-bonn.de>> > i thought OneHotEncoder solves that. That only works on arrays of numbers, right? True. Sorry, jetlag, disregrad my comment ;) -

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread Gael Varoquaux
On Sat, Mar 30, 2013 at 10:32:26AM -0400, Anne Dwyer wrote: > print arr1 > And here is my output: >   (0, 4)    1.0 >   (0, 0)    1.0 >   (1, 3)    1.0 >   (1, 1)    1.0 >   (2, 2)    1.0 >   (2, 0)    1.0 >   (3, 3)    1.0 >   (3, 0)    1.0 Yes, it's a sparse matrix, rather than an array. You c

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread Anne Dwyer
I'm also have a problem with OneHotEncoder. Here is the code I ran: # This is a test of the one hot encode module with a toy data set. # I have a 4 x 2 data set. The first column is gender and the #second column is pclass alread in integer form. import numpy as np arr=np.array([[0,2],[1,1],[

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread Anne Dwyer
It's not clear to me that OneHotEncoder solved the problem. Maybe you can explain further. The example hereonly shows the algorithm transforming categorical integer values. Can the algorithm take in a data set of text like categorical values

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread Lars Buitinck
2013/3/30 > i thought OneHotEncoder solves that. That only works on arrays of numbers, right? -- Lars Buitinck Scientific programmer, ILPS University of Amsterdam -- Own the Future-Intel(R) Level Up Game Demo Contest 201

Re: [Scikit-learn-general] using grid_seach

2013-03-30 Thread amueller
no, just replacing () with []. Jaques Grobler schrieb: >Hey Andy, sorry been busy all day. You mean something like this to make >it >more clear ? > >>>> kernel_param = {'kernel':('linear', 'rbf')} >>>> C_param = {'C':[1,10]} parameters = (kernel_param, C_param) #List of parameter

Re: [Scikit-learn-general] Participation in GSoC 2013

2013-03-30 Thread amueller
how do we represent missing values here? Mathieu Blondel schrieb: >On Tue, Mar 26, 2013 at 9:25 PM, Lee Zamparo wrote: >> AFAIK, you might not want all the missing values to be imputed at >once, >> especially if the dimensions of X are large. Maybe something like: >> >> >> X_transformed = es

Re: [Scikit-learn-general] Questions about converting categorical data into input data for an SVM

2013-03-30 Thread amueller
i thought OneHotEncoder solves that. Lars Buitinck schrieb: >2013/3/27 Anne Dwyer : >> Just to clarify, you are saying that there is no procedure in scikit >that >> will transform categorical feature values into numerical values like >I was >> trying to do here. Correct? > >Not that I know of.