feature classifier error

I am getting the following error:

Plugin error from feature-classifier:
not enough values to unpack (expected 2, got 0)
Debug info has been saved to /tmp/qiime2-q2cli-err-csbmozz2.log

I put in the following command:

qiime feature-classifier fit-classifier-naive-bayes
–i-reference-reads type1_rep-seqs.qza
–i-reference-taxonomy 99_ref-taxonomy.qza
–o-classifier type1_classifier.qza

I have seen some other issues posted, but the taxonomy I got this from was directly from the Greengenes data posted on this website. I updated my scikit-learn, but not sure if I did it properly. Below is the full error log:

/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/q2_feature_classifier/classifier.py:101: UserWarning: The TaxonomicClassifier artifact that results from this method was trained using scikit-learn version 0.19.1. It cannot be used with other versions of scikit-learn. (While the classifier may complete successfully, the results will be unreliable.)
warnings.warn(warning, UserWarning)
Traceback (most recent call last):
File “/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/q2cli/commands.py”, line 246, in call
results = action(**arguments)
File “”, line 2, in fit_classifier_naive_bayes
File “/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/qiime2/sdk/action.py”, line 228, in bound_callable
output_types, provenance)
File “/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/qiime2/sdk/action.py”, line 363, in callable_executor
output_views = self._callable(**view_args)
File “/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/q2_feature_classifier/classifier.py”, line 310, in generic_fitter
File “/home/mboeck/anaconda3/envs/qiime2-2018.2/lib/python3.5/site-packages/q2_feature_classifier/_skl.py”, line 31, in fit_pipeline
y, X = list(zip(*data))
ValueError: not enough values to unpack (expected 2, got 0)

See this topic thread

The issue is most likely that the headers in the sequence file do not match the names in the taxonomy.

Yes, but perhaps the reference sequences are not? Or you are using the wrong rep-seqs file that does not correspond to the taxonomy file (are you using the 99% OTUs rep seqs?)

This is the file in question:

Is this a subset of the 99% OTUs rep seqs or how was that file made?

1 Like

OK thank you, I think I was using the wrong reference reads. The tutorial does not make it super clear which “reference read” I was suppose to use. It seems to be running right now. I am still struggling over here so expect more questions from me in the future.

1 Like

Thanks! I have raised an issue to add some more details to the documentation.


Not a problem! Help is what we are here for :smile:. Thank you for the detailed error message, command details, and for searching the forum for answers before posting your question :smiley:

1 Like

This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.