setwd("/Users/jameshanley/Dropbox/Courses/bios601/CaseControlStudies/BirthMonthSports")

ds = read.csv("NHLnameB.csv",header=TRUE,as.is=rep(TRUE,11))
head(ds); tail(ds) ; length(ds$Birthplace)
cdn = c("BC", "SASK", "MAN" , "ONT", "QUE", "NB")

CDN = c( grep("BC",ds$Birthplace) ,
         grep("ALTA",ds$Birthplace),
         grep("SASK",ds$Birthplace),
         grep("MAN",ds$Birthplace),
         grep("ONT",ds$Birthplace),
         grep("PQ",ds$Birthplace),
         grep("NB",ds$Birthplace),
         grep("NS",ds$Birthplace),
         grep("PEI",ds$Birthplace),
         grep("NFLD",ds$Birthplace),
         grep("NW",ds$Birthplace),
         grep("Yuk",ds$Birthplace)
            
       )
ds=ds[CDN,]
head(ds); tail(ds) ; length(ds$Birthplace)
ds$month = as.numeric(substr(ds$Birthdate,1,2))
table(ds$month)