S Hamidizade
2016-09-26 17:57:19 UTC
Dear scikit-learners
I would appreciate if you could kindly let me know how to deal with the
following problems when doing feature selection using python. In fact,
attached is the scripts and data set which I used.
1- Could you kindly please let me know how to address unbalanced issue
(weighting, thresholding, resampling)?
a. AdaBoost: Cohen's Kappa is too low-20%.
b. NeuralNetwork-sknn: Cohen's Kappa is terribly low-0%.
2- Could you kindly please let me know if I should use nested cross
validation just like that I do in the attached scripts or should use one
cross validation loop just like this post
<http://stackoverflow.com/questions/33376078/python-feature-selection-in-pipeline-how-determine-feature-names>.
In the first case, I don't know how to print the names (or indices) of
selected features.
Thanks in advance.
Best regards,
I would appreciate if you could kindly let me know how to deal with the
following problems when doing feature selection using python. In fact,
attached is the scripts and data set which I used.
1- Could you kindly please let me know how to address unbalanced issue
(weighting, thresholding, resampling)?
a. AdaBoost: Cohen's Kappa is too low-20%.
b. NeuralNetwork-sknn: Cohen's Kappa is terribly low-0%.
2- Could you kindly please let me know if I should use nested cross
validation just like that I do in the attached scripts or should use one
cross validation loop just like this post
<http://stackoverflow.com/questions/33376078/python-feature-selection-in-pipeline-how-determine-feature-names>.
In the first case, I don't know how to print the names (or indices) of
selected features.
Thanks in advance.
Best regards,