In UBC-MDS/CleanR: Understand your messy data

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

summary(data) will determine the main data type of the column by calculated the type of each row entry in the column, and using the most frequent data type as the expected input for that column. It will perform two different summary statistics based on 2 different groups of datatypes of either 1) string or 2) int/float. For number columns it returns a dataframe of columns which contain dataframes of summary statistics including mean value for each column, min, max, count (number of non NA values per column) and count_NA (number of NA values per column). Similarly, for string columns it returns the unique string values and their counts. It will also provide a count of NA values which will include empty strings, and anything other than the correct data type for each column.

• Input:

  • data: dataframe that the function will use to locate NAs

• Output: returns a nested list of columns that includes all the summary statistics information

• Example: summary(data)

UBC-MDS/CleanR documentation built on May 7, 2019, 7:13 p.m.