# Memory ERROR: qiime feature-classifier classify-sklearn
**URL:** https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066
**Category:** User Support
**Created:** [March 31, 2019, 3:44am UTC](https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066 "2019-03-31T03:44:13Z")
**Posts on this page:** 4
**Page:** 1
### Author:  [@PatoUru](https://forum.qiime2.org/u/PatoUru)
#### Post date: [March 31, 2019, 3:44am UTC](https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066/1 "2019-03-31T03:44:13Z")
Hi all,
I'm in the next stage:
$ qiime feature-classifier classify-sklearn --i-classifier silva-132-99-nb-classifier.qza --i-reads rep-seqs\_97.qza --p-confidence 0.8 --p-read-orientation reverse-complement --o-classification rep-seqs\_97\_SILVAtaxonomy.qza
And I have the following error:
Plugin error from feature-classifier:
Debug info has been saved to /tmp/qiime2-q2cli-err-9ir5\_cmn.log
Traceback (most recent call last):
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/q2cli/commands.py", lin
e 274, in **call**
results = action (\*\* arguments)
File "\ ", line 2, in classify\_sklearn
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/qiime2/sdk/action.py",
line 231, in bound\_callable
output\_types, provenance)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/qiime2/sdk/action.py",
line 365, in _callable\_executor_
output\_views = self._callable (\*\* view\_args)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/q2\_feature\_classifier/c
lassifier.py ", line 215, in classify\_sklearn
confidence = confidence)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/q2\_feature\_classifier/_
skl.py ", line 45, in predict
for chunk in \_chunks (reads, chunk\_size)) for m in c)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/externals/jobli
b / parallel.py ", line 917, in **call**
if self.dispatch\_one\_batch (iterator):
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/externals/jobli
b / parallel.py ", line 759, in dispatch\_one\_batch
self.\_dispatch (tasks)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/externals/jobli
b / parallel.py ", line 716, in \_dispatch
job = self.\_backend.apply\_async (batch, callback = cb)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/externals/jobli
b / \_parallel\_backends.py ", line 182, in apply\_async
result = ImmediateResult (func)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/externals/jobli
b / \_parallel\_backends.py ", line 549, in **init**
self.results = batch ()
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/q2\_feature\_classifier/\_skl.py", line 52, in \_predict\_chunk
return \_predict\_chunk\_with\_conf (pipeline, separator, confidence, chunk)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/q2\_feature\_classifier/\_skl.py", line 66, in \_predict\_chunk\_with\_conf
prob\_pos = pipeline.predict\_proba (X)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/utils/metaestimators.py", line 118, in
out = lambda \* args, \*\* kwargs: self.fn (obj, \* args, \*\* kwargs)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/pipeline.py", line 382, in predict\_proba
return self.steps [-1] [- 1] .predict\_proba (Xt)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/naive\_bayes.py", line 104, in predict\_proba
return np.exp (self.predict\_log\_proba (X))
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/naive\_bayes.py", line 84, in predict\_log\_proba
jll = self.\_joint\_log\_likelihood (X)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/naive\_bayes.py", line 731, in _joint\_log\_likelihood
return (safe\_sparse\_dot (X, self.feature\_log\_prob_.T) +
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/sklearn/utils/extmath.py", line 168, in safe\_sparse\_dot
ret = a \* b
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/scipy/sparse/base.py", line 473, in **mul**
return self.\_mul\_multivector (other)
File "/home/patricia/miniconda2/envs/qiime2-2019.1/lib/python3.6/site-packages/scipy/sparse/compressed.py", line 477, in \_mul\_multivector
dtype = upcast\_char (self.dtype.char, other.dtype.char))
MemoryError
From what I was reading in the forums, I understand that my computer has limited capacity.
What would be the way to do the taxonomic assignment? Is there another method available that allows me to finish the analysis on my computer?
Characteristics of the computer
core i7, 16GB RAM
Thank you very much in advance
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [April 1, 2019, 12:27pm UTC](https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066/2 "2019-04-01T12:27:32Z")
> [@PatoUru](#):
>
> From what I was reading in the forums, I understand that my computer has limited capacity.
> What would be the way to do the taxonomic assignment? Is there another method available that allows me to finish the analysis on my computer?
This is a fairly common issue, please see these posts for troubleshooting advice: [Search results for 'feature classifier memory error' - QIIME 2 Forum](https://forum.qiime2.org/search?q=feature%20classifier%20memory%20error)
hint: try a different classifier (e.g., greengenes) or use the `reads-per-batch` parameter.
---
### Author:  [@Nicholas\_Bokulich](https://forum.qiime2.org/u/Nicholas_Bokulich)
#### Post date: [April 1, 2019, 2:19pm UTC](https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066/3 "2019-04-01T14:19:56Z")
An off-topic reply has been split into a new topic: [The scikit-learn version (0.19.1) used to generate this artifact does not match the current version of scikit-learn installed (0.20.2). Please retrain your classifier for your current deployment to prevent data-corruption errors](https://forum.qiime2.org/t/the-scikit-learn-version-0-19-1-used-to-generate-this-artifact-does-not-match-the-current-version-of-scikit-learn-installed-0-20-2-please-retrain-your-classifier-for-your-current-deployment-to-prevent-data-corruption-errors/9083)
Please keep replies on-topic in the future.
---
### Author:  [@system](https://forum.qiime2.org/u/system)
#### Post date: [May 2, 2019, 8:25pm UTC](https://forum.qiime2.org/t/memory-error-qiime-feature-classifier-classify-sklearn/9066/4 "2019-05-02T20:25:28Z")
This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.