[Neuroimaging] [Nilearn] Problem with joblib when running the SpaceNet classifier

[bthirion]

     Dear Julio,

     Given the warnings on compute_epi_mask, I think that you should 
remove the folder nilearn_cache/joblib/nilearn/masking/compute_epi_mask 
and launch again.
     Best,

Bertrand Thirion


On 24/02/2017 02:36, Julio Villalon wrote:
> Hi Nilearn team,
>
> I am trying to run the SpaceNet example:
>
> https://nilearn.github.io/auto_examples/02_decoding/plot_haxby_space_net.html#sphx-glr-auto-examples-02-decoding-plot-haxby-space-net-py
>
> And I am getting the following error:
>
> ' ' '
> ValueError: Found array with 0 sample(s) (shape=(0, 129600)) while a 
> minimum of 1 is required.
>
> /Users/jvillalo/scikit-learn/sklearn/externals/joblib/memory.py:133: 
> DeprecationWarning: The file 
> 'nilearn_cache/joblib/nilearn/masking/compute_epi_mask/8ac3f6747d8c3cbe01809029506bc2c4/output.pkl' 
> has been generated with a joblib version less than 0.10. Please 
> regenerate this pickle file.
>   return numpy_pickle.load(filename, mmap_mode=mmap_mode)
> ' ' '
>
> I am using Python 3.5, Numpy 1.12, Scipy 0.18.1. I also included in my 
> PYTHONPATH the latest development versions (master branches) of 
> Nilearn and Scikit-learn.
>
> Can anyone point me in the right direction of how to solve this problem?
>
> Thank you
>
> Julio Villalon
> USC Imaging Genetics Center
>
> This is full error message:
> ------------------------------------------------
> Traceback (most recent call last):
>   File 
> "/Users/jvillalo/anaconda/lib/python3.5/site-packages/IPython/core/interactiveshell.py", 
> line 2481, in safe_execfile
>     self.compile if kw['shell_futures'] else None)
>   File 
> "/Users/jvillalo/anaconda/lib/python3.5/site-packages/IPython/utils/py3compat.py", 
> line 186, in execfile
>     exec(compiler(f.read(), fname, 'exec'), glob, loc)
>   File 
> "/Users/jvillalo/Documents/IGC/Conferences/MICCAI_2016/Gaels_code/plot_haxby_space_net.py", 
> line 70, in <module>
>     decoder.fit(X_train, y_train)
>   File "/Users/jvillalo/nilearn/nilearn/decoding/space_net.py", line 
> 783, in fit
>     multi_output=True, y_numeric=True)
>   File 
> "/Users/jvillalo/nilearn/nilearn/_utils/fixes/sklearn_validation.py", 
> line 195, in check_X_y
>     ensure_min_features)
>   File 
> "/Users/jvillalo/nilearn/nilearn/_utils/fixes/sklearn_validation.py", 
> line 97, in check_array
>     % (n_samples, shape_repr, ensure_min_samples))
> ValueError: Found array with 0 sample(s) (shape=(0, 129600)) while a 
> minimum of 1 is required.
>
> /Users/jvillalo/scikit-learn/sklearn/externals/joblib/memory.py:133: 
> DeprecationWarning: The file 
> 'nilearn_cache/joblib/nilearn/masking/compute_epi_mask/8ac3f6747d8c3cbe01809029506bc2c4/output.pkl' 
> has been generated with a joblib version less than 0.10. Please 
> regenerate this pickle file.
>   return numpy_pickle.load(filename, mmap_mode=mmap_mode)
> /Users/jvillalo/scikit-learn/sklearn/externals/joblib/memory.py:133: 
> DeprecationWarning: The file 
> 'nilearn_cache/joblib/nilearn/image/resampling/resample_img/ea3a4d90803321dbf749b23ff6acfa18/output.pkl' 
> has been generated with a joblib version less than 0.10. Please 
> regenerate this pickle file.
>   return numpy_pickle.load(filename, mmap_mode=mmap_mode)
>
> -------------------------------------------------------------
>
>
> _______________________________________________
> Neuroimaging mailing list
> Neuroimaging at python.org
> https://mail.python.org/mailman/listinfo/neuroimaging


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.python.org/pipermail/neuroimaging/attachments/20170225/37557073/attachment.html>