Missing Data Imputation Mastery

This course will teach you how to impute missing values in python

1. You will learn simple imputation methods, such as mean, mode, constant, new category imputation.
2. You will learn how to use binary indicator variables to extend your data set and improve downstream task performance.
3. You will learn sophisticated imputation methods such as missForest and KNNimputation
4. You will learn deeplearning based imputation methods such denoise autoencoders and generative adverserial networks for imputation
5. You will learn about the optimization of imputation methods and their hyper-parameters
6. You will learn the different imputation families.
7. You will learn about the efficiency of each method.
8. You will get an introduction to the missing data literature
9. You will learn in-depth how each imputation method works
10. You will run examples in python using well-known libraries, e.g Sklearn, Pytorch, numpy

After finishing this course, you will have every knowledge you need to incorporate missing data imputation in your pipeline and research, having simple code, complete knowledge of how every method works and also insights in the hyper-parameter values to try for each method.

Finally, you will learn about the predictive modelling perspective of handling missing data. We adopt the AutoML framework and insights to derive real-world conclusions.

I hope you enjoy this course.

Your instructor,

George