问题
I have this dataset
df=structure(list(Dt = structure(c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L,
9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L,
22L, 23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L,
35L, 36L, 37L, 38L, 39L, 1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L,
10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L,
23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L,
36L, 37L, 38L, 39L), .Label = c("2018-02-20 00:00:00.000", "2018-02-21 00:00:00.000",
"2018-02-22 00:00:00.000", "2018-02-23 00:00:00.000", "2018-02-24 00:00:00.000",
"2018-02-25 00:00:00.000", "2018-02-26 00:00:00.000", "2018-02-27 00:00:00.000",
"2018-02-28 00:00:00.000", "2018-03-01 00:00:00.000", "2018-03-02 00:00:00.000",
"2018-03-03 00:00:00.000", "2018-03-04 00:00:00.000", "2018-03-05 00:00:00.000",
"2018-03-06 00:00:00.000", "2018-03-07 00:00:00.000", "2018-03-08 00:00:00.000",
"2018-03-09 00:00:00.000", "2018-03-10 00:00:00.000", "2018-03-11 00:00:00.000",
"2018-03-12 00:00:00.000", "2018-03-13 00:00:00.000", "2018-03-14 00:00:00.000",
"2018-03-15 00:00:00.000", "2018-03-16 00:00:00.000", "2018-03-17 00:00:00.000",
"2018-03-18 00:00:00.000", "2018-03-19 00:00:00.000", "2018-03-20 00:00:00.000",
"2018-03-21 00:00:00.000", "2018-03-22 00:00:00.000", "2018-03-23 00:00:00.000",
"2018-03-24 00:00:00.000", "2018-03-25 00:00:00.000", "2018-03-26 00:00:00.000",
"2018-03-27 00:00:00.000", "2018-03-28 00:00:00.000", "2018-03-29 00:00:00.000",
"2018-03-30 00:00:00.000"), class = "factor"), ItemRelation = c(158043L,
158043L, 158043L, 158043L, 158043L, 158043L, 158043L, 158043L,
158043L, 158043L, 158043L, 158043L, 158043L, 158043L, 158043L,
158043L, 158043L, 158043L, 158043L, 158043L, 158043L, 158043L,
158043L, 158043L, 158043L, 158043L, 158043L, 158043L, 158043L,
158043L, 158043L, 158043L, 158043L, 158043L, 158043L, 158043L,
158043L, 158043L, 158043L, 234L, 234L, 234L, 234L, 234L, 234L,
234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L,
234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L,
234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L, 234L
), stuff = c(200L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 3600L,
0L, 0L, 0L, 0L, 700L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 1000L, 2600L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 400L, 700L,
200L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 3600L, 0L, 0L, 0L,
0L, 700L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1000L,
2600L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 400L, 700L), num = c(1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L, 1459L,
1459L, 1459L, 1459L, 1459L, 1459L), year = c(2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L, 2018L,
2018L, 2018L, 2018L), action = c(0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 1L, 1L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 1L, 1L, 1L, 1L)), .Names = c("Dt", "ItemRelation",
"stuff", "num", "year", "action"), class = "data.frame", row.names = c(NA,
-78L))
The next operation was performed on this data. 1. the operation of calculating the median for the first category of the action and the zero category of action by stuff ( last five non-zero observations). 2.then the median of the zero category was subtracted from the median in the first category. Solution of MKR is very accurate.
library(dplyr)
df %>% filter(stuff > 0) %>% #First filter out for stuff > 0 which of our interest
group_by(ItemRelation, num, year) %>%
mutate(m = median(stuff[action==1]),
m0 = median(tail(stuff[action==0], 5))) %>% # Calculate m and m0 for all rows
filter(action == 1) %>% # Now keep only rows with action == 1
mutate(m = m-m0) %>%
select(-Dt,-m0,-action
How to do that the calculated result for each group was multiplied by the number of ones by action, but only for those that are more than zero by stuff. For example, for stratum
ItemRelation num year
158043 1459 2018
we have 4 ones in action, and only two ones by stuff more then zero so the calculated result (m) we multiply on two.
回答1:
Data is already filter for stuff>0 in dplyr - chain. Then() represent the count per group where stuff>0 and action ==1. Hence, one can multiply the final value of m with n(). At the end, distinct will ensure that duplicate rows has been removed.
library(dplyr)
df %>% filter(stuff > 0) %>% #First filter out for stuff > 0 which of our interest
group_by(ItemRelation, num, year) %>%
mutate(m = median(stuff[action==1]),
m0 = median(tail(stuff[action==0], 5))) %>% # Calculate m and m0 for all rows
filter(action == 1) %>% # Now keep only rows with action == 1
mutate(m = (m-m0)*n()) %>%
select(-Dt,-m0,-action, - stuff) %>% distinct()
# # A tibble: 2 x 4
# # Groups: ItemRelation, num, year [2]
# ItemRelation num year m
# <int> <int> <int> <dbl>
# 1 158043 1459 2018 -900
# 2 234 1459 2018 -900
来源：https://stackoverflow.com/questions/50948339/multiply-median-for-groups-separately-in-r-by-condition