我希望我的示例数据看起来不太大
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"))
我想找到一个整洁的 %>% 类型解决方案来以 12 个月为基础滚动分组数据。也就是说，我想对多个分类变量(例如年龄、性别和测量类别)进行分组，并查找任何相关数值变量的 12 个月滚动平均值
这似乎可行，但代码不容易解释
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)})
我读过很多关于 rollmean 和 rollmeanr 的文章，但无法让它处理分组数据。如何使用如此简单的函数编写一两行解决方案？
最佳答案
1) 使用较小的示例(将来请提供最少数据)
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
给予:
# 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) 或者如果您不需要原始 value1 和 value2:
DF %>%
group_by(group) %>%
mutate_at(vars(contains("value")), rollmeanr, k = 2, fill = NA) %>%
ungroup
给予:
# 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)另一种方法是
DF %>%
group_by(group) %>%
do(cbind(., roll = rollmeanr(.[-1], k = 2, fill = NA))) %>%
ungroup
或者没有原始值变量:
DF %>%
group_by(group) %>%
do(rollmeanr(.[-1], k = 2, fill = NA) %>% as.data.frame) %>%
ungroup
关于r - 如何在 dplyr 分组数据上使用 rollmean，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/59437764/