Sorry, I did not read your traceback carefully... I thought the error was
raised by the GaussianProcess but is is not.
You said you checked for NaNs, but did you check for inf values as well?
2014-05-02 16:11 GMT+02:00 Vincent Dubourg <vincent.dubo...@gmail.com>:
> np.all(xtrain.std() == 0.) ?
>
>
> 2014-04-29 12:22 GMT+02:00 abhishek <abhish...@gmail.com>:
>
>> Hi,
>>
>> While using Gaussian Process, I get the following errors and I'm unable
>> to figure out why.
>>
>>
>> ---------------------------------------------------------------------------ValueError
>> Traceback (most recent call
>> last)<ipython-input-93-417d3b33b0b2> in <module>()----> 1 xtrain, xtest,
>> ytrain, ytest = cross_validation.train_test_split(training, labels) 2
>> 3 gp = GaussianProcess() 4 gp.fit(xtrain,ytrain) 5
>> /usr/local/Cellar/python/2.7.6/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/cross_validation.pyc
>> in train_test_split(*arrays, **options) 1510 test_size = 0.25
>> 1511 -> 1512 arrays = check_arrays(*arrays, **options) 1513
>> n_samples = arrays[0].shape[0] 1514 cv = ShuffleSplit(n_samples,
>> test_size=test_size,
>> /usr/local/Cellar/python/2.7.6/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/utils/validation.pyc
>> in check_arrays(*arrays, **options) 261 else: 262
>> array = np.asarray(array, dtype=dtype)--> 263
>> _assert_all_finite(array) 264 265 if array.ndim >= 3:
>> /usr/local/Cellar/python/2.7.6/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/sklearn/utils/validation.pyc
>> in _assert_all_finite(X) 40 and not np.isfinite(X).all()):
>> 41 raise ValueError("Input contains NaN, infinity"---> 42
>> " or a value too large for %r." % X.dtype) 43 44
>> ValueError: Input contains NaN, infinity or a value too large for
>> dtype('float64').
>>
>>
>>
>> The array does not contain any NaNs and Ive also tried scaling the array
>> but the same error is thrown.
>>
>> Any help would be appreciated.
>>
>> Thank you,
>> --
>> Regards
>>
>> Abhishek Thakur
>>
>> -
>>
>>
>>
>>
>> ------------------------------------------------------------------------------
>> "Accelerate Dev Cycles with Automated Cross-Browser Testing - For FREE
>> Instantly run your Selenium tests across 300+ browser/OS combos. Get
>> unparalleled scalability from the best Selenium testing platform
>> available.
>> Simple to use. Nothing to install. Get started now for free."
>> http://p.sf.net/sfu/SauceLabs
>> _______________________________________________
>> Scikit-learn-general mailing list
>> Scikit-learn-general@lists.sourceforge.net
>> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>>
>>
>
------------------------------------------------------------------------------
"Accelerate Dev Cycles with Automated Cross-Browser Testing - For FREE
Instantly run your Selenium tests across 300+ browser/OS combos. Get
unparalleled scalability from the best Selenium testing platform available.
Simple to use. Nothing to install. Get started now for free."
http://p.sf.net/sfu/SauceLabs
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
