Justify using data augmentation to balance dataset

Colin-Codes / IntentClassifier-ML-Project

Pyhton, Keras, SciKit-Learn, Matplotlib: Machine learning research project around classification of intent behind tech support emails in order to enable automatic follow up.

0 stars 0 forks source link

Justify using data augmentation to balance dataset #36

Open Colin-Codes opened 4 years ago

Colin-Codes commented 4 years ago

Linked to #30

Colin-Codes commented 4 years ago

Research alternative methods and justifications for balancing the dataset

Colin-Codes commented 4 years ago

refers to EDA and imblearn

Colin-Codes commented 4 years ago

Also, it really ought to be naug = 4, as we've increased the training set synthetically