我有以下数据。
dput(mydata)
structure(list(groupSize = structure(c(2L, 1L, 2L, 1L, 4L, 4L,
3L, 3L, 2L, 2L, 1L, 1L, 3L, 3L, 4L, 4L, 2L, 2L, 1L, 1L, 3L, 3L,
4L, 4L, 3L, 3L, 2L, 2L, 1L, 1L, 4L, 4L, 2L, 2L, 4L, 4L, 3L, 3L,
1L, 1L), .Label = c("small", "intermediate", "large", "huge"), class = "factor"),
gender = structure(c(1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L,
1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 2L,
1L), .Label = c("F", "M", "U"), class = "factor"), startYear = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L), .Label = c("2014", "2015",
"2016", "2017", "2018"), class = "factor"), count = c(7546,
3500, 5930, 7668, 18114, 13826, 11943, 10083, 147, 2791,
17158, 19389, 2063, 17901, 11007, 1660, 6660, 15198, 496,
18716, 17385, 12726, 11409, 4711, 16140, 244, 15251, 6485,
5014, 1104, 438, 10930, 15582, 15626, 2121, 6339, 135, 15432,
12263, 10607)), row.names = c(NA, -40L), class = c("data.table",
"data.frame"))
我想计算一下每一年每个组别大小的男性和女性的比例。因此，我会得到例如，在2014年的groupsize "小 "有45％的女性和55％的男性。如何能做到这一点的data.table在R中？
如果你要找比例，你可以做 。
library(data.table)
mydata[, prop := count/sum(count) * 100, by = .(startYear, groupSize)]
# groupSize gender startYear count prop
# 1: intermediate F 2014 7546 55.9958445
# 2: small F 2014 3500 31.3395415
# 3: intermediate M 2014 5930 44.0041555
# 4: small M 2014 7668 68.6604585
# 5: huge F 2014 18114 56.7125861
# 6: huge M 2014 13826 43.2874139
# 7: large F 2014 11943 54.2222828
# 8: large M 2014 10083 45.7777172
#....
你可以得到比例 M 内容如下。
mydata[ , by = .(groupSize, startYear),
.(pct_M = weighted.mean(gender == 'M', w = count))]
# groupSize startYear pct_M
# 1: intermediate 2014 0.44004156
# 2: small 2014 0.68660458
# 3: huge 2014 0.43287414
# 4: large 2014 0.45777717
# 5: intermediate 2015 0.94996596
# 6: small 2015 0.53052234
# 7: large 2015 0.89666400
# 8: huge 2015 0.86895082
# 9: intermediate 2016 0.69530607
# 10: small 2016 0.97418280
# 11: large 2016 0.42263625
# 12: huge 2016 0.70775434
# 13: large 2017 0.01489258
# 14: intermediate 2017 0.70164704
# 15: small 2017 0.81954887
# 16: huge 2017 0.96147080
# 17: intermediate 2018 0.49929505
# 18: huge 2018 0.25070922
# 19: large 2018 0.99132781
# 20: small 2018 0.53620463
这相当于略显繁琐的。
mydata[ , by = .(groupSize, startYear),
.(pct_M = sum(count[gender == 'M'])/sum(count))]
计算，并以方便人类的形式，与 dcast():
library(data.table)
mydata[, .(gender, prop = count / sum(count)), by = .(startYear, groupSize)
][, dcast(.SD, startYear + groupSize ~ gender)]
# startYear groupSize F M
# 1: 2014 small 0.313395415 0.68660458
# 2: 2014 intermediate 0.559958445 0.44004156
# 3: 2014 large 0.542222828 0.45777717
# 4: 2014 huge 0.567125861 0.43287414
# 5: 2015 small 0.469477659 0.53052234
# 6: 2015 intermediate 0.050034037 0.94996596
# 7: 2015 large 0.103336005 0.89666400
# 8: 2015 huge 0.131049183 0.86895082
# 9: 2016 small 0.025817198 0.97418280
# 10: 2016 intermediate 0.304693934 0.69530607
# 11: 2016 large 0.577363754 0.42263625
# 12: 2016 huge 0.292245658 0.70775434
# 13: 2017 small 0.180451128 0.81954887
# 14: 2017 intermediate 0.298352963 0.70164704
# 15: 2017 large 0.985107422 0.01489258
# 16: 2017 huge 0.038529205 0.96147080
# 17: 2018 small 0.463795365 0.53620463
# 18: 2018 intermediate 0.500704947 0.49929505
# 19: 2018 large 0.008672191 0.99132781
# 20: 2018 huge 0.749290780 0.25070922
Base R解决方案。
with(df, count/ave(count, groupSize, startYear, FUN = sum))