Hi,
# 1) I have read in a CSV file
df = read.csv(file="GiftCards - v1.csv",stringsAsFactors=FALSE)
head(df)
str(df)
# 2) converted to a tbl_df
df2 = tbl_df(df)
# 3) fixed the names to remove leading "X" character
n = names(df2)
n2 = gsub(pattern="^\\w","\\1",n)
names(df2) = n2
# 4) somehow the col names are character strings, requiring me to use
quotes:
df2$`2006` instead of df2$2006 # ---> PROBLEM 1
# 5) I need to remove the leading $ sign followed by spaces to extract
values. The problem is # it could be a two or three digit number. I am able
to retrieve two digits correctly, but miss # out on the leading third digit.
df2$`2006`= gsub("^(.+)([0-9]{2,3}\\.[0-9]{2})","\\2",df2$`2006`) # -->
Problem 2
# 6) dump for the data frame
df2 <-
structure(list(`2006` = structure(c(3L, 2L, 1L), .Label = c("$
24.81",
"$ 39.16", "$ 146.20"), class = "factor"), `2007` = structure(c(3L,
2L, 1L), .Label = c("$ 26.25", "$ 41.95", "$ 156.24"
), class = "factor"), `2008` = structure(c(3L, 2L, 1L), .Label = c("$
24.92",
"$ 40.54", "$ 147.33"), class = "factor"), `2009` = structure(c(3L,
2L, 1L), .Label = c("$ 23.63", "$ 39.80", "$ 139.91"
), class = "factor"), `2010` = structure(c(3L, 2L, 1L), .Label = c("$
24.78",
"$ 41.48", "$ 145.61"), class = "factor"), `2011` = structure(c(3L,
2L, 1L), .Label = c("$ 27.80", "$ 43.23", "$ 155.43"
), class = "factor"), `2012` = structure(c(3L, 2L, 1L), .Label = c("$
28.79",
"$ 43.75", "$ 156.86"), class = "factor"), `2013` = structure(c(3L,
2L, 1L), .Label = c("$ 29.80", "$ 45.16", "$ 163.16"
), class = "factor")), .Names = c("2006", "2007", "2008", "2009",
"2010", "2011", "2012", "2013"), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -3L))
Thanks for the help
Br /
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
