qiime feature-classifier classify-sklearn mac os catalina

Technical Support
1

Hello ,

I have a problem with classifier and my new mac os catalina.
when I try to use qiime feature-classifier I have an error see below

qiime feature-classifier classify-sklearn --i-classifier /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva-132-99-nb-classifier.qza --i-reads /Users/sandrine/Desktop/16S\ pascal\ Loyer/dada-denoise-filter_seq.qza --o-classification /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva99taxonomy.qza

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 (0.22.1). Please retrain your classifier for your current deployment to prevent data-corruption errors.

Debug info has been saved to /var/folders/v5/cjcl0q1j7r502qbbv6qs_whw0000gn/T/qiime2-q2cli-err-18wd_ldr.log

I found on this forum what I must try : conda install --override-channels -c defaults scikit-learn=0.20.2

installation is Ok but when I retried taxonomy assignation a new message displayed :

(qiime2-2020.2) MacBook-Pro-de-Sandrine:~ sandrine$ conda install --override-channels -c defaults scikit-learn=0.20.2
Collecting package metadata: done
Solving environment: done


==> WARNING: A newer version of conda exists. <==
  current version: 4.6.14
  latest version: 4.8.3

Please update conda by running

    $ conda update -n base -c defaults conda



## Package Plan ##

  environment location: /Users/sandrine/miniconda3/envs/qiime2-2020.2

  added / updated specs:
    - scikit-learn=0.20.2


The following packages will be downloaded:

    package                    |            build
    ---------------------------|-----------------
    scikit-learn-0.20.2        |   py36hebd9d1a_0         5.2 MB
    ------------------------------------------------------------
                                           Total:         5.2 MB

The following packages will be REMOVED:

  q2-feature-classifier-2020.2.0-py36_0
  q2-longitudinal-2020.2.0-py36_0
  q2-sample-classifier-2020.2.0-py36_0

The following packages will be DOWNGRADED:

  scikit-learn                        0.22.1-py36hebd9d1a_0 --> 0.20.2-py36hebd9d1a_0


Proceed ([y]/n)? y


Downloading and Extracting Packages
scikit-learn-0.20.2  | 5.2 MB    | ############################################################################################# | 100% 
Preparing transaction: done
Verifying transaction: done
Executing transaction: done
QIIME is caching your current deployment for improved performance. This may take a few moments and should only happen once per deployment.
Traceback (most recent call last):
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/bin/qiime", line 11, in <module>
    sys.exit(qiime())
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 764, in __call__
    return self.main(*args, **kwargs)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 716, in main
    with self.make_context(prog_name, args, **extra) as ctx:
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 641, in make_context
    self.parse_args(ctx, args)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/click/command.py", line 43, in parse_args
    return super().parse_args(ctx, args)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 1086, in parse_args
    echo(ctx.get_help(), color=ctx.color)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 516, in get_help
    return self.command.get_help(self)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 879, in get_help
    self.format_help(ctx, formatter)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/click/core.py", line 898, in format_help
    self.format_options(ctx, formatter)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/click/command.py", line 157, in format_options
    for subcommand in self.list_commands(ctx):
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/commands.py", line 92, in list_commands
    plugins = sorted(self._plugin_lookup)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/commands.py", line 76, in _plugin_lookup
    import q2cli.core.cache
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/core/cache.py", line 404, in <module>
    CACHE = DeploymentCache()
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/core/cache.py", line 61, in __init__
    self._state = self._get_cached_state(refresh=refresh)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/core/cache.py", line 107, in _get_cached_state
    self._cache_current_state(current_requirements)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/core/cache.py", line 200, in _cache_current_state
    state = self._get_current_state()
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2cli/core/cache.py", line 238, in _get_current_state
    plugin_manager = qiime2.sdk.PluginManager()
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/qiime2/sdk/plugin_manager.py", line 54, in __new__
    self._init(add_plugins=add_plugins)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/qiime2/sdk/plugin_manager.py", line 81, in _init
    plugin = entry_point.load()
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/pkg_resources/__init__.py", line 2445, in load
    return self.resolve()
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/pkg_resources/__init__.py", line 2451, in resolve
    module = __import__(self.module_name, fromlist=['__name__'], level=0)
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2_vsearch/plugin_setup.py", line 12, in <module>
    import q2_vsearch._cluster_features
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/q2_vsearch/_cluster_features.py", line 15, in <module>
    import skbio
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/skbio/__init__.py", line 19, in <module>
    import skbio.diversity  # noqa
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/skbio/diversity/__init__.py", line 402, in <module>
    from ._driver import (alpha_diversity, beta_diversity, partial_beta_diversity,
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/skbio/diversity/_driver.py", line 13, in <module>
    import sklearn.metrics
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/__init__.py", line 34, in <module>
    from . import cluster
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/cluster/__init__.py", line 20, in <module>
    from .unsupervised import silhouette_samples
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/cluster/unsupervised.py", line 17, in <module>
    from ..pairwise import pairwise_distances_chunked
  File "/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/pairwise.py", line 31, in <module>
    from .pairwise_fast import _chi2_kernel_fast, _sparse_manhattan
ImportError: dlopen(/Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/pairwise_fast.cpython-36m-darwin.so, 2): Library not loaded: @rpath/libopenblas.dylib
  Referenced from: /Users/sandrine/miniconda3/envs/qiime2-2020.2/lib/python3.6/site-packages/sklearn/metrics/pairwise_fast.cpython-36m-darwin.so
  Reason: image not found
(qiime2-2020.2) MacBook-Pro-de-Sandrine:~ sandrine$ qiime feature-classifier classify-sklearn --i-classifier /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva-132-99-nb-classifier.qza --i-reads /Users/sandrine/Desktop/16S\ pascal\ Loyer/dada-denoise-filter_seq.qza --o-classification /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva99taxonomy.qza
QIIME is caching your current deployment for improved performance. This may take a few moments and should only happen once per deployment.

can you help me ?

Thanks a lot

sandrine

3

Hi @sdavid!

This is a pretty common "error" message - its saying that the version of silva-132-99-nb-classifier.qza is older than the version of QIIME 2 you are using. The solution is to simply download the version of the classifier that matches the version of QIIME 2 you are using:

https://docs.qiime2.org/2020.2/data-resources/#taxonomy-classifiers-for-use-with-q2-feature-classifier

But, before you do that, you'll need to fix up your conda env:

This command broke your environment - the easiest option is to conda remove -n qiime2-2020.2 and then reinstall (following the native install guide). This should go much more quickly, because conda will have cached all the packages.

Keep us posted!

:qiime2:

5

Hi
ok I try
Sandrine

6

hi

I tried and a new problem appears

(qiime2-2020.2) dy082221:~ sandrine$ qiime feature-classifier classify-sklearn --i-classifier /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva-132-99-nb-classifier.qza --i-reads /Users/sandrine/Desktop/16S\ pascal\ Loyer/dada-denoise-filter_seq.qza --o-classification /Users/sandrine/Desktop/16S\ pascal\ Loyer/silva99taxonomy.qza

Plugin error from feature-classifier:

[Errno 28] No space left on device

Debug info has been saved to /tmp/qiime2-q2cli-err-bpec7w1a.log

Sandrine

8

Hi @sdavid!

This means that your hard drive is filled up (or at least some portion, or partition, of the hard drive is filled to capacity).

Its impossible to say what is filled, specifically, without more information. Please rerun that command, with the --verbose flag, and copy-and-paste all of the output here. As well, please run df -h and return the results here, too. Thanks!

:qiime2:

10

Hi

It’s OK
thanks for your help
Regards
sandrine

11

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