Curriculum
Course: Data Science
Login

Curriculum

Data Science

Text lesson

Data Cleaning

Examine the imported data. As you can see, the data is “dirty,” containing incorrect or missing values.

img_data_raw

There are several issues with the data:

  • Some fields are blank.
  • An average pulse of 9,000 is unrealistic.
  • The value 9,000 is treated as non-numeric due to the space separator.
  • One observation of max pulse is recorded as “AF,” which is not valid.

Therefore, we need to clean the data before performing any analysis.