Data hygiene: Dealing with junk and missing values
Cleaning data can take up to 80% of an analyst's time. Before plotting, answer three questions: are there empty cells? duplicate rows? correct dtypes for columns (e.g. is a number stored as text)?
Cleaning data can take up to 80% of an analyst's time. Before plotting, answer three questions: are there empty cells? duplicate rows? correct dtypes for columns (e.g. is a number stored as text)?