bag: Multi-indicators / "Bag o Words"

In nfultz/stackoverflow: Stack Overflow's Greatest Hits

Description

This creates an indicator matrix from several columns.

Usage

bag(..., prefix = ".", levels = NULL)

Arguments

...	the columns to bag
prefix	a prefix for the column names
levels	levels shared among all columns

Value

a n*p indicator matrix

Author(s)

Neal Fultz

References

https://stackoverflow.com/questions/47055856/search-multiple-columns-for-string-to-set-indicator-variable/57381877#57381877

Examples

df2 <- structure(list(Dx1 = c("231", "231", "001", "245", "231", "001", 
"231", "001", "231", "001", "001", "245", "001", "231", "245", 
"245", "001", "231", "245", "001"), Dx2 = c("001", "001", "001", 
"001", "001", "001", "001", "234", "001", "234", "001", "001", 
"001", "001", "001", "777", "777", "234", "001", "234"), Dx3 = c("456", 
"001", "444", "444", "001", "001", "444", "001", "001", "001", 
"444", "001", "444", "456", "456", "444", "444", "456", "001", 
"456")), class = "data.frame", row.names = c(NA, -20L))

Y <- 1:nrow(df2)
m <- lm(Y~bag(Dx1, Dx2, Dx3), df2)
summary(m)

nfultz/stackoverflow documentation built on Aug. 4, 2020, 5:31 a.m.