Clean multiple versions of text values in data set in R

cleanup_names.r

library(dplyr)
library(tidyr)
# sum_trialname contains product names, including three different versions of one product
# dropping everything after the first space gets me to a consistent product naming
# the extract function, by default, captures the initial alphanumeric data, and drops everything after the first non-alpha character
# by default, teh extract function also drops the original column (sum_trialname, in this case)

# Create a new column with clean, consistent product names
clean_data <- extract(clean_data, sum_trialname, "Product", remove=FALSE)