I have data in a data.table that is as follows:
> x<-df[sample(nrow(df), 10),]
> x
> Importer Exporter
I think with will work with aggregate
in base R
:
my.data <- read.csv(text = '
Importer, Exporter, Date
Ecuador, United Kingdom, 2004-01-13
Mexico, United States, 2013-11-19
Australia, United States, 2006-08-11
United States, United States, 2009-05-04
India, United States, 2007-07-16
Guatemala, Guatemala, 2014-07-02
Israel, Israel, 2000-02-22
India, United States, 2014-02-11
Peru, Peru, 2007-03-26
Poland, France, 2014-09-15
', header = TRUE, stringsAsFactors = TRUE, strip.white = TRUE)
my.data$my.Date <- as.Date(my.data$Date, format = "%Y-%m-%d")
my.data <- data.frame(my.data,
year = as.numeric(format(my.data$my.Date, format = "%Y")),
month = as.numeric(format(my.data$my.Date, format = "%m")),
day = as.numeric(format(my.data$my.Date, format = "%d")))
my.data$my.decade <- my.data$year - (my.data$year %% 10)
importer.count <- with(my.data, aggregate(cbind(count = Importer) ~ my.decade + Importer, FUN = function(x) { NROW(x) }))
exporter.count <- with(my.data, aggregate(cbind(count = Exporter) ~ my.decade + Exporter, FUN = function(x) { NROW(x) }))
colnames(importer.count) <- c('my.decade', 'country', 'importer.count')
colnames(exporter.count) <- c('my.decade', 'country', 'exporter.count')
my.counts <- merge(importer.count, exporter.count, by = c('my.decade', 'country'), all = TRUE)
my.counts$importer.count[is.na(my.counts$importer.count)] <- 0
my.counts$exporter.count[is.na(my.counts$exporter.count)] <- 0
my.counts
# my.decade country importer.count exporter.count
# 1 2000 Australia 1 0
# 2 2000 Ecuador 1 0
# 3 2000 India 1 0
# 4 2000 Israel 1 1
# 5 2000 Peru 1 1
# 6 2000 United States 1 3
# 7 2000 United Kingdom 0 1
# 8 2010 Guatemala 1 1
# 9 2010 India 1 0
# 10 2010 Mexico 1 0
# 11 2010 Poland 1 0
# 12 2010 United States 0 2
# 13 2010 France 0 1