removeFullNAFeatures: Removes full-NA value features in a SEER dataframe

In mribeirodantas/vidente: Collection of functions to work with SEER Database

Description

Some features in a SEER dataframe are specific to certain types of cancer. If you're analyzing only patients with breast cancer, features that have information on prostate cancer, for example, will have only NA values. These features are useless to your analysis and should be removed. plotHistNA is a good function to plot this scenario so that you know if you have features with all their rows as NA values. By making use of removeFullNAFeatures you can get rid of these features.

Usage

removeFullNAFeatures(dataframe, additional_na)

Arguments

dataframe	The dataframe with SEER data
additional_na	A vector with additional symbol(s) that should also be considered NA. This is important for some datasets exported from SEER*Stat software that come with NA values and also strings 'Blank(s)' representing also lack of values.

mribeirodantas/vidente documentation built on May 15, 2019, 4:47 p.m.