The data set that we selected did have missing values in addition to other data kinds. Upon evaluating the data, we discovered that the missing values in each category are as follows.
RETRO: 20,112 values are missing.
OTHER: 7,378 values are missing.
16,392 values are missing across time.
21,983 missing data indicate injury.
DETAIL: 21,088 values are missing.
QUINN_EDUCATION: 21,835 data are missing.
COMMON: 600 values are missing.
There were no missing entries in any columns, including “NAME,” “DEPARTMENT_NAME,” “TITLE,” “TOTAL_GROSS,” and “POSTAL.”
Having said that, there are a lot of missing entries in fields like “RETRO,” “INJURED,” “DETAIL,” and “QUINN_EDUCATION,” which probably means that not all employees get these kinds of benefits.
Unlike the previous two data sets, this one can be cleaned because at least one field is empty.