scikit-learn-contrib / imbalanced-learn

A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning
https://imbalanced-learn.org
MIT License
6.8k stars 1.28k forks source link

SMOTE-NC sampling_strategy='not majority' MemoryError: Unable to allocate 135. GiB #768

Closed anubhass closed 3 years ago

anubhass commented 3 years ago

Description

I am trying to perform SMOTE-NC using sampling_strategy = 'not majority' so that I limit the samples. Still I am running in to

MemoryError: Unable to allocate 135. GiB for an array with shape (39514, 5, 92034) and data type float64.

My system configuration is 32GB RAM, 16 cores. Please help..

Steps/Code to Reproduce

Expected Results

Actual Results

Versions

chkoar commented 3 years ago

an array with shape (39514, 5, 92034)

It is strange that you are getting a message about a three dimensional array. Could you share your code and data?

glemaitre commented 3 years ago

Closing for inactivity