Identifying missing values

Since identifying missing values is such an important part of the workflow of analysts, any tool we use needs to make it easy to regularly check for such values. Fortunately, pandas makes it quite simple to identify missing values.

Getting ready

We will work with the National Longitudinal Survey (NLS) data in this chapter. The NLS data has one observation per survey respondent. Data for employment, earnings, and college enrollment for each year are stored in columns with suffixes representing the year, such as weeksworked21 and weeksworked22 for weeks worked in 2021 and 2022 respectively.

We will also work with the COVID-19 data again. This dataset has one observation for each country with total COVID-19 cases and deaths, as well as some demographic data for each country.

Data note

The National Longitudinal Survey of Youth is conducted by the United States Bureau of Labor Statistics. This survey started with a cohort of individuals...