Error when running latest silva-132-99-nb-classifier.qza

Thank you in advance for your help, it is greatly appreciated. I am running qiime2 using docker. I just downloaded the silva classifier, silva-132-99-nb-classifier.qza, from the resources page (Data resources — QIIME 2 2019.1.0 documentation). When I run the command below, I get the error message shown.

(qiime2-2018.11) root@4173742a49c0:/data/Silva_DB# qiime feature-classifier classify-sklearn \

--i-classifier silva-132-99-nb-classifier.qza
--i-reads /data/ZymoData_test/rep-seqs-trunc-Ian_Pat1.qza
--o-classification taxonomy-Ian_Pat1.qza
--verbose
Traceback (most recent call last):
File "/opt/conda/envs/qiime2-2018.11/lib/python3.5/site-packages/q2cli/commands.py", line 274, in call
results = action(**arguments)
File "", line 2, in classify_sklearn
File "/opt/conda/envs/qiime2-2018.11/lib/python3.5/site-packages/qiime2/sdk/action.py", line 225, in bound_callable
spec.view_type, recorder)
File "/opt/conda/envs/qiime2-2018.11/lib/python3.5/site-packages/qiime2/sdk/result.py", line 287, in _view
result = transformation(self._archiver.data_dir)
File "/opt/conda/envs/qiime2-2018.11/lib/python3.5/site-packages/qiime2/core/transform.py", line 70, in transformation
new_view = transformer(view)
File "/opt/conda/envs/qiime2-2018.11/lib/python3.5/site-packages/q2_feature_classifier/_taxonomic_classifier.py", line 64, in _1
% (sklearn_version, sklearn.version))
ValueError: The scikit-learn version (0.20.2) used to generate this artifact does not match the current version of scikit-learn installed (0.19.1). Please retrain your classifier for your current deployment to prevent data-corruption errors.

Plugin error from feature-classifier:

The scikit-learn version (0.20.2) used to generate this artifact does not match the current version of scikit-learn installed (0.19.1). Please retrain your classifier for your current deployment to prevent data-corruption errors.

See above for debug info.

I saw a similar error message described in another post and the solution was to download an updated version of the classifier. But, I've just download this classifier from the resources site so I don't think it is out of date. Is my docker version out of date (I downloaded it about a month ago)? Can you offer any suggestions for what I need to do?

Hi @Skeet,
I think you are right on the money with the problem being incompatible versions of scikit between the classifier and what you have installed.
Your best option is to just update your qiime2 version to the newest 2019.1 one and that classifier should be ok then. A second, not recommended, option is to just download the classifier from the previous version that matches your current qiime2 environment.

1 Like

An off-topic reply has been split into a new topic: Feature-classifier no space left on device error in docket

Please keep replies on-topic in the future.