EagerSun/DL-vs-Stat_Impute

This is a thesis project about comparing imputation performances between deep learning methods and conventional statistical methods. In this project, GAIN and VAE with One-Hot and trainable embeddings for categorical variables were built for deep learning methods. MICE and Miss-Forest were chosen for representing conventional statistical methods.

语言：Python · GitHub 星标：19 · Fork：2

在 GitHub 上查看原仓库