January 2018
Beginner to intermediate
316 pages
7h 14m
English
Thus far, we have gone over several methods of imputing missing values in our categorical and numerical data, encoding our categorical variables, and creating custom transformers to fit into a pipeline. We also dove into several feature construction methods for both numerical data and text-based data.
In the next chapter, we will take a look at the features we have constructed, and consider appropriate methods of selecting the right features to use for our machine learning models.
Read now
Unlock full access