ModuleNotFoundError: No module named 'imblearn'

I tried running the following code:

from imblearn import under_sampling, over_sampling from imblearn.over_sampling import SMOTE sm = SMOTE(random_state=12, ratio = 1.0) x_SMOTE, y_SMOTE = sm.fit_sample(X, y) 

which gives me the error message:

ModuleNotFoundError: No module named 'imblearn' 

I have tried installing the imblearn module in multiple ways, they all seem to work (there are no errors given during the installation but when I run the above code, I get an error message).

I tried istalling imblearn using the following suggested in other stackoverflow questions:

pip install -U imbalanced-learn pip install imblearn !pip install imblearn pip install -c glemaitre imbalanced-learn pip install imblearn==0.0 

None of these seem to help... Any ideas? Thank you!

5

13 Answers

I installed the module named imblearn using anaconda command prompt.

conda install -c conda-forge imbalanced-learn 

Then imported the packages

from imblearn import under_sampling, over_sampling from imblearn.over_sampling import SMOTE 

Again, I tried to install imblearn through pip, it works for me.

(base) C:\WINDOWS\system32>pip install -U imbalanced-learn Requirement already up-to-date: imbalanced-learn in c:\users\ashok\anaconda3\lib\site-packages (0.4.3) Requirement already satisfied, skipping upgrade: numpy>=1.8.2 in c:\users\ashok\anaconda3\lib\site-packages (from imbalanced-learn) (1.15.3) Requirement already satisfied, skipping upgrade: scipy>=0.13.3 in c:\users\ashok\anaconda3\lib\site-packages (from imbalanced-learn) (0.19.1) Requirement already satisfied, skipping upgrade: scikit-learn>=0.20 in c:\users\ashok\anaconda3\lib\site-packages (from imbalanced-learn) (0.20.0) 

On AWS SageMaker, follow the documentation:

!pip install imbalanced-learn 

in a notebook cell.

This worked for me

  1. First install the package in your environment:
pip install -U imbalanced-learn 
  1. Next:
conda install -c conda-forge imbalanced-learn 

Open anaconda prompt and install below module:

conda install -c conda-forge imbalanced-learn conda install -c conda-forge/label/gcc7 imbalanced-learn conda install -c conda-forge/label/cf201901 imbalanced-learn 

Those who have permission issue or failed to install it can follow this.

  • conda create --name dsc_new
  • conda activate dsc_new
  • conda install -c conda-forge imbalanced-learn
  • try on your notebook pip install imbalanced-learn --user

I was dealing with the same problem. Updating packages, upgrading pip or python version did not resolve the problem for me.

The issue was that pip installed package to one folder, but my jupyter notebook imported packages from another folder. To get the path from where your packages are imported, you may use:

import site site.getsitepackages() # /your/path/from/python 

Then you may check in terminal where pip installs your packages :

pip show imblearn 

If the paths do not coincide, you may manually set the path for pip in terminal:

pip config set global.target /your/path/from/python 

And install your package again by

pip install imblearn 

I have been fixed it by applying the following inside a Jupyter Notebook.

!pip install imbalanced-learn==0.6.0 !pip install scikit-learn==0.22.1 

I had the same issue which was rectified by using:

 !pip install -U imbalanced-learn 

Then this:

 conda install -c conda-forge imbalanced-learn 

Updated my conda:

 conda update -n base -c conda-forge conda 

Restarted the kernel.

try this way:

from imblearn import under_sampling from imblearn import over_sampling from imblearn.over_sampling import SMOTE 

OR

import imblearn * 
1

I've come across the same problem a few days ago - trying to use imblearn inside a Jupyter Notebook. This question led me to the solution:

conda install -c glemaitre imbalanced-learn 

Notice, one of the commands you tried (pip install -c glemaitre imbalanced-learn) doesn't make sense: -c glemaitre is an argument for Anaconda python distributions, which tells conda (Anaconda's CLI) to download the module from a source different than the defaults (glemaitre's channel). Since that argument is conda-specific, it doen't apply to pip commands.

1

Using python=3.6.10 and below worked for me.

If you are still experiencing error after installing imblearn either on Anaconda terminal while using Vscode. Try to restart Vscode for it to reflect.

It is working for me this way

pip install imblearn 

And i import this way :

from imblearn.combine import SMOTETomek 

Your Answer

Sign up or log in

Sign up using Google Sign up using Facebook Sign up using Email and Password

Post as a guest

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

You Might Also Like