Numerical and categorical variables: types, units and allowed values
Distinguish quantities from categories, document units and allowed values, and check your data with pandas before converting a column.
Identify and handle missing values and duplicates
Identify missing values and duplicates with pandas, compare justified treatments and keep a documented copy. Five steps with runnable Python examples and a downloadable notebook.
Describe a dataset before building a model
Learn to describe a dataset before modeling: observations, variables, targets, distributions, missing values and limitations. Six steps with runnable Python cells and a downloadable notebook.
