How to use rollmean on dplyr grouped data
Question
I hope my example data doesn't seem too large
df <- structure(list(date = structure(c(17532, 17563, 17591, 17622,
17652, 17683, 17713, 17744, 17775, 17805, 17836, 17866, 17897,
17928, 17956, 17987, 18017, 18048, 18078, 18109, 18140, 17532,
17563, 17591, 17622, 17652, 17683, 17713, 17744, 17775, 17805,
17836, 17866, 17897, 17928, 17956, 17987, 18017, 18048, 18078,
18109, 18140, 17532, 17563, 17591, 17622, 17652, 17683, 17713,
17744, 17775, 17805, 17836, 17866, 17897, 17928, 17956, 17987,
18017, 18048, 18078, 18109, 18140, 17532, 17563, 17591, 17622,
17652, 17683, 17713, 17744, 17775, 17805, 17836, 17866, 17897,
17928, 17956, 17987, 18017, 18048, 18078, 18109, 18140, 17532,
17563, 17591, 17622, 17652, 17683, 17713, 17744, 17775, 17805,
17836, 17866, 17897, 17928, 17956, 17987, 18017, 18048, 18078,
18109, 18140, 17532, 17563, 17591, 17622, 17652, 17683, 17713,
17744, 17775, 17805, 17836, 17866, 17897, 17928, 17956, 17987,
18017, 18048, 18078, 18109, 18140, 17532, 17563, 17591, 17622,
17652, 17683, 17713, 17744, 17775, 17805, 17836, 17866, 17897,
17928, 17956, 17987, 18017, 18048, 18078, 18109, 18140, 17532,
17563, 17591, 17622, 17652, 17683, 17713, 17744, 17775, 17805,
17836, 17866, 17897, 17928, 17956, 17987, 18017, 18048, 18078,
18109, 18140), class = "Date"), Gender = c("Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Female", "Female",
"Female", "Female", "Female", "Female", "Female", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male", "Male", "Male", "Male", "Male", "Male", "Male",
"Male", "Male"), Age = c("Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Older", "Older", "Older", "Older", "Older",
"Older", "Older", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger", "Younger", "Younger", "Younger", "Younger",
"Younger", "Younger"), attribute = c("Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling A", "Feeling A", "Feeling A", "Feeling A", "Feeling A",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B", "Feeling B", "Feeling B", "Feeling B", "Feeling B",
"Feeling B"), measure_1 = c(0.33, 0.31, 0.31, 0.16, 0.37, 0.29,
0.27, 0.26, 0.24, 0.38, 0.47, 0.21, 0.32, 0.24, 0.26, 0.38, 0.38,
0.39, 0.37, 0.3, 0.29, 0.48, 0.45, 0.45, 0.35, 0.49, 0.44, 0.41,
0.44, 0.35, 0.38, 0.39, 0.55, 0.45, 0.43, 0.38, 0.38, 0.57, 0.47,
0.51, 0.48, 0.32, 0.27, 0.22, 0.13, 0.02, 0.12, 0.16, 0.15, 0.17,
0.23, 0.12, 0.31, 0.12, 0.16, 0.16, 0.16, 0.24, 0.06, 0.06, 0.17,
0.15, 0.14, 0.37, 0.35, 0.2, 0.17, 0.25, 0.2, 0.3, 0.23, 0.26,
0.14, 0.29, 0.35, 0.14, 0.32, 0.14, 0.14, 0.24, 0.18, 0.24, 0.24,
0.17, 0.4, 0.3, 0.36, 0.41, 0.38, 0.31, 0.33, 0.43, 0.27, 0.31,
0.26, 0.29, 0.25, 0.23, 0.38, 0.2, 0.29, 0.26, 0.22, 0.41, 0.25,
0.45, 0.4, 0.54, 0.51, 0.48, 0.46, 0.4, 0.48, 0.29, 0.33, 0.36,
0.48, 0.5, 0.32, 0.42, 0.43, 0.35, 0.35, 0.49, 0.44, 0.42, 0.48,
0.34, 0.44, 0.38, 0.49, 0.27, 0.33, 0.42, 0.31, 0.32, 0.31, 0.38,
0.46, 0.35, 0.4, 0.36, 0.38, 0.51, 0.41, 0.44, 0.36, 0.7, 0.57,
0.66, 0.65, 0.57, 0.62, 0.53, 0.52, 0.43, 0.52, 0.53, 0.61, 0.67,
0.59, 0.57, 0.55, 0.54, 0.67, 0.54, 0.57, 0.57), measure_2 = c(0.5,
0.47, 0.48, 0.31, 0.54, 0.45, 0.43, 0.42, 0.4, 0.55, 0.66, 0.37,
0.49, 0.4, 0.42, 0.56, 0.55, 0.57, 0.54, 0.47, 0.45, 0.66, 0.63,
0.63, 0.52, 0.67, 0.62, 0.58, 0.61, 0.52, 0.55, 0.57, 0.74, 0.63,
0.61, 0.56, 0.56, 0.77, 0.66, 0.7, 0.67, 0.49, 0.38, 0.32, 0.23,
0.12, 0.22, 0.26, 0.25, 0.27, 0.34, 0.22, 0.41, 0.21, 0.26, 0.26,
0.26, 0.34, 0.16, 0.16, 0.27, 0.25, 0.24, 0.48, 0.45, 0.31, 0.27,
0.36, 0.3, 0.4, 0.34, 0.36, 0.24, 0.39, 0.45, 0.24, 0.43, 0.24,
0.24, 0.35, 0.28, 0.34, 0.35, 0.27, 0.51, 0.43, 0.48, 0.52, 0.49,
0.44, 0.46, 0.54, 0.4, 0.44, 0.4, 0.42, 0.39, 0.37, 0.49, 0.34,
0.42, 0.39, 0.36, 0.52, 0.39, 0.56, 0.51, 0.63, 0.6, 0.58, 0.56,
0.51, 0.58, 0.42, 0.46, 0.48, 0.58, 0.59, 0.45, 0.52, 0.54, 0.47,
0.47, 0.58, 0.54, 0.53, 0.7, 0.62, 0.68, 0.64, 0.7, 0.59, 0.62,
0.67, 0.61, 0.61, 0.61, 0.65, 0.69, 0.63, 0.65, 0.64, 0.64, 0.71,
0.66, 0.68, 0.63, 0.81, 0.75, 0.8, 0.79, 0.75, 0.77, 0.72, 0.72,
0.67, 0.72, 0.72, 0.77, 0.8, 0.76, 0.75, 0.73, 0.73, 0.8, 0.73,
0.75, 0.74)), class = "data.frame", row.names = c(NA, -168L), na.action = structure(169:176, .Names = c("169",
"170", "171", "172", "173", "174", "175", "176"), class = "omit"))
I'd like to find a tidy type %>% solution to rolling grouped data on a 12 month basis. That is, I would like to group multiple categorical variables (such as age and gender and measurement classes) and find the rolling 12 month average for any associated numeric variables
This seems to work but the code is not easy to interpret
df1 <- df # mutate(date = as.Date(date)) %>% select(-date) %>% group_by(Gender, Age, attribute) %>% mutate_if(is.numeric, function(x, n = 12){stats::filter(x, rep(1 / n, n), sides = 1)})
I've read many posts on rollmean and rollmeanr but can't get it working with grouped data. How can I write a one or two line solution using such a straightforward function?
1 answers
solution1
2 ACCPTED 2019-12-21 16:22:37
1) Using a smaller example (please provide minimal data in the future)
DF <- data.frame(group = c(1, 1, 1, 2, 2, 2), value1 = 1:6, value2 = 7:12)
library(dplyr)
library(zoo)
DF %>%
group_by(group) %>%
mutate_at(vars(contains("value")), list(roll = ~ rollmeanr(., k = 2, fill = NA))) %>%
ungroup
giving:
# A tibble: 6 x 5
group value1 value2 value1_roll value2_roll
<dbl> <int> <int> <dbl> <dbl>
1 1 1 7 NA NA
2 1 2 8 1.5 7.5
3 1 3 9 2.5 8.5
4 2 4 10 NA NA
5 2 5 11 4.5 10.5
6 2 6 12 5.5 11.5
2) or if you don't need the original value1 and value2 :
DF %>%
group_by(group) %>%
mutate_at(vars(contains("value")), rollmeanr, k = 2, fill = NA) %>%
ungroup
giving:
# A tibble: 6 x 3
group value1 value2
<dbl> <dbl> <dbl>
1 1 NA NA
2 1 1.5 7.5
3 1 2.5 8.5
4 2 NA NA
5 2 4.5 10.5
6 2 5.5 11.5
3) Another approach is
DF %>%
group_by(group) %>%
do(cbind(., roll = rollmeanr(.[-1], k = 2, fill = NA))) %>%
ungroup
or without the original value variables:
DF %>%
group_by(group) %>%
do(rollmeanr(.[-1], k = 2, fill = NA) %>% as.data.frame) %>%
ungroup
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.
Related Question
rollmean with grouped data.table returns a logical
rollmean with dplyr and magrittr
how to compare rows in dplyr grouped data?
How to assign deciles in a grouped data using dplyr?
How to get the frequency from grouped data with dplyr?
cumsum in grouped data with dplyr
Grouped data in dplyr
Accessing grouped data in dplyr
How do I use dplyr::across with a multi-argument function on a grouped data frame?
How to use dplyr to create a new variable based on a function result in a grouped data?
Related Tags