aggregate - Merging output in R -
max=aggregate(cbind(a$value,date=a$date) ~ format(a$date, "%m") + cut(a$class, breaks=c(0,2,4,6,8,10,12,14)) , data = a, max)[-1] max$date=as.date(max$date, origin = "1970-01-01") sample data :
date grade value 2008-09-01 1 20 2008-09-02 2 30 2008-09-03 3 50 . . 2008-09-30 2 75 . . 2008-10-01 1 95 . . 2008-11-01 4 90 . . 2008-12-01 1 70 2008-12-02 2 40 2008-12-28 4 30 2008-12-29 1 40 2008-12-31 3 50 my expected output according above table first month :
date grade value 2008-09-30 (0,2] 75 2008-09-02 (2,4] 50 output in real data :
format(date, "%m") 1 09 2 10 3 11 4 12 5 09 6 10 7 11 cut(a$grade, breaks = c(0, 2, 4, 6, 8, 10, 12, 14)) value 1 (0,2] 0.30844444 2 (0,2] 1.00000000 3 (0,2] 1.00000000 4 (0,2] 0.73333333 5 (2,4] 0.16983488 6 (2,4] 0.09368000 7 (2,4] 0.10589335 date 1 2008-09-30 2 2008-10-31 3 2008-11-28 4 2008-12-31 5 2008-09-30 6 2008-10-31 7 2008-11-28 the output not according sample data , data big . simple logic there grades 1 10 , want find highest value month in corresponding grade groups . eg : need highest value each group (0,2],(0,4] etc
i used aggregate condition function max , 2 grouping 2 columns date , grade . when run code , display value of max , 3 tables output 1 after other. want plot output not able because of .so how can merge these output ?
try:
library(dplyr) %>% group_by(month=format(date, "%m"), grade=cut(grade, breaks=seq(0,14,by=2))) %>% summarise_each(funs(max)) # month grade date value #1 09 (0,2] 2008-09-30 75 #2 09 (2,4] 2008-09-03 50 #3 10 (0,2] 2008-10-01 95 #4 11 (2,4] 2008-11-01 90 #5 12 (0,2] 2008-12-29 70 #6 12 (2,4] 2008-12-31 50 or using data.table
library(data.table) setdt(a)[, list(date=max(date), value=max(value)), by= list(month=format(date, "%m"), grade=cut(grade, breaks=seq(0,14, by=2)))] # month grade date value #1: 09 (0,2] 2008-09-30 75 #2: 09 (2,4] 2008-09-03 50 #3: 10 (0,2] 2008-10-01 95 #4: 11 (2,4] 2008-11-01 90 #5: 12 (0,2] 2008-12-29 70 #6: 12 (2,4] 2008-12-31 50 or using aggregate
res <- transform(with(a, aggregate(cbind(value, date), list(month=format(date, "%m") ,grade=cut(grade, breaks=seq(0,14, by=2))), max)), date=as.date(date, origin="1970-01-01")) res[order(res$month),] # month grade value date #1 09 (0,2] 75 2008-09-30 #4 09 (2,4] 50 2008-09-03 #2 10 (0,2] 95 2008-10-01 #5 11 (2,4] 90 2008-11-01 #3 12 (0,2] 70 2008-12-29 #6 12 (2,4] 50 2008-12-31 data
<- structure(list(date = structure(c(14123, 14124, 14125, 14152, 14153, 14184, 14214, 14215, 14241, 14242, 14244), class = "date"), grade = c(1l, 2l, 3l, 2l, 1l, 4l, 1l, 2l, 4l, 1l, 3l), value = c(20l, 30l, 50l, 75l, 95l, 90l, 70l, 40l, 30l, 40l, 50l)), .names = c("date", "grade", "value"), row.names = c(na, -11l), class = "data.frame") update
if want include year in grouping
library(dplyr) %>% group_by(month=format(date, "%m"), year=format(date, "%y"), grade=cut(grade, breaks=seq(0,14, by=2)))%>% summarise_each(funs(max)) # month year grade date value #1 09 2008 (0,2] 2008-09-30 75 #2 09 2008 (2,4] 2008-09-03 50 #3 09 2009 (0,2] 2009-09-30 75 #4 09 2009 (2,4] 2009-09-03 50 #5 10 2008 (0,2] 2008-10-01 95 #6 10 2009 (0,2] 2009-10-01 95 #7 11 2008 (2,4] 2008-11-01 90 #8 11 2009 (2,4] 2009-11-01 90 #9 12 2008 (0,2] 2008-12-29 70 #10 12 2008 (2,4] 2008-12-31 50 #11 12 2009 (0,2] 2009-12-29 70 #12 12 2009 (2,4] 2009-12-31 50 data
<- structure(list(date = structure(c(14123, 14124, 14125, 14152, 14153, 14184, 14214, 14215, 14241, 14242, 14244, 14488, 14489, 14490, 14517, 14518, 14549, 14579, 14580, 14606, 14607, 14609 ), class = "date"), grade = c(1l, 2l, 3l, 2l, 1l, 4l, 1l, 2l, 4l, 1l, 3l, 1l, 2l, 3l, 2l, 1l, 4l, 1l, 2l, 4l, 1l, 3l), value = c(20l, 30l, 50l, 75l, 95l, 90l, 70l, 40l, 30l, 40l, 50l, 20l, 30l, 50l, 75l, 95l, 90l, 70l, 40l, 30l, 40l, 50l)), .names = c("date", "grade", "value"), row.names = c("1", "2", "3", "4", "5", "6", "7", "8", "9", "10", "11", "12", "21", "31", "41", "51", "61", "71", "81", "91", "101", "111"), class = "data.frame") 
Comments
Post a Comment