search

kmkolasinski / deep-learning-notes

Experiments with Deep Learning
1.35k stars 270 forks source link

About oversampling-datasets-example.ipynb #7

Closed warmestwind closed 6 years ago

warmestwind commented 6 years ago

Hi, I just learned your oversampling example, it's help me a lot. And I want to know where the sampling method come from in your example? Can you give me the specific paper name of the sampling method? Thanks!

kmkolasinski commented 6 years ago

Hello, oversampling and undersampling is a popular approach for tackling the class imbalance problem. For sure you can find a lot of materials in the internet about it, like for example this one: https://www.kaggle.com/residentmario/undersampling-and-oversampling-imbalanced-data

warmestwind commented 6 years ago

As you suggest, I read some blog about data resampling. But I also want to known the math principles of you example, please give me some more advises ,thanks!

kmkolasinski commented 6 years ago

What about this, check also the references in the last paragraph: https://www.marcoaltini.com/blog/dealing-with-imbalanced-data-undersampling-oversampling-and-proper-cross-validation