我想使用数据集中提供的权重计算加权方差,同时对国家和城市进行分组,但是函数返回NAs
:
library(Hmisc) #for the 'wtd.var' function
weather_winter.std<-weather_winter %>%
group_by(country, capital_city) %>%
summarise(across(starts_with("winter"),wtd.var))
控制台提供的输出(长格式时):
# A tibble: 35 x 3
# Groups: country [35]
country capital_city winter
<chr> <chr> <dbl>
1 ALBANIA Tirane NA
2 AUSTRIA Vienna NA
3 BELGIUM Brussels NA
4 BULGARIA Sofia NA
5 CROATIA Zagreb NA
6 CYPRUS Nicosia NA
7 CZECHIA Prague NA
8 DENMARK Copenhagen NA
9 ESTONIA Tallinn NA
10 FINLAND Helsinki NA
# … with 25 more rows
这是我用来将数据从宽格式转换为长格式的代码:
weather_winter <- weather_winter %>% pivot_longer(-c(31:33))
weather_winter$name <- NULL
names(weather_winter)[4] <- "winter"
一些示例数据:
structure(list(`dec-wet_2011` = c(12.6199998855591, 12.6099996566772,
14.75, 11.6899995803833, 18.2899990081787), `dec-wet_2012` = c(13.6300001144409,
14.2199993133545, 14.2299995422363, 16.1000003814697, 18.0299987792969
), `dec-wet_2013` = c(4.67999982833862, 5.17000007629395, 4.86999988555908,
7.56999969482422, 5.96000003814697), `dec-wet_2014` = c(14.2999992370605,
14.4799995422363, 13.9799995422363, 15.1499996185303, 16.1599998474121
), `dec-wet_2015` = c(0.429999977350235, 0.329999983310699, 1.92999994754791,
3.30999994277954, 7.42999982833862), `dec-wet_2016` = c(1.75,
1.29999995231628, 3.25999999046326, 6.60999965667725, 8.67999935150146
), `dec-wet_2017` = c(13.3400001525879, 13.3499994277954, 15.960000038147,
10.6599998474121, 14.4699993133545), `dec-wet_2018` = c(12.210000038147,
12.4399995803833, 11.1799993515015, 10.75, 18.6299991607666),
`dec-wet_2019` = c(12.7199993133545, 13.3800001144409, 13.9899997711182,
10.5299997329712, 12.3099994659424), `dec-wet_2020` = c(15.539999961853,
16.5200004577637, 11.1799993515015, 14.7299995422363, 13.5499992370605
), `jan-wet_2011` = c(8.01999950408936, 7.83999967575073,
10.2199993133545, 13.8899993896484, 14.5299997329712), `jan-wet_2012` = c(11.5999994277954,
11.1300001144409, 12.5500001907349, 10.1700000762939, 22.6199989318848
), `jan-wet_2013` = c(17.5, 17.4099998474121, 15.5599994659424,
13.3199996948242, 20.9099998474121), `jan-wet_2014` = c(12.5099992752075,
12.2299995422363, 15.210000038147, 9.73999977111816, 9.63000011444092
), `jan-wet_2015` = c(17.6900005340576, 16.9799995422363,
11.75, 9.9399995803833, 19), `jan-wet_2016` = c(15.6099996566772,
15.5, 14.5099992752075, 10.3899993896484, 18.4499988555908
), `jan-wet_2017` = c(9.17000007629395, 9.61999988555908,
9.30999946594238, 15.8499994277954, 11.210000038147), `jan-wet_2018` = c(8.55999946594238,
9.10999965667725, 13.2599992752075, 9.85999965667725, 15.8899993896484
), `jan-wet_2019` = c(17.0699996948242, 16.8699989318848,
14.5699996948242, 19.0100002288818, 19.4699993133545), `jan-wet_2020` = c(6.75999975204468,
6.25999975204468, 6.00999975204468, 5.35999965667725, 8.15999984741211
), `feb-wet_2011` = c(9.1899995803833, 8.63999938964844,
6.21999979019165, 9.82999992370605, 4.67999982833862), `feb-wet_2012` = c(12.2699995040894,
11.6899995803833, 8.27999973297119, 14.9399995803833, 13.0499992370605
), `feb-wet_2013` = c(15.3599996566772, 15.9099998474121,
17.0599994659424, 13.3599996566772, 16.75), `feb-wet_2014` = c(10.1999998092651,
11.1399993896484, 13.8599996566772, 10.7399997711182, 7.35999965667725
), `feb-wet_2015` = c(11.9200000762939, 12.2699995040894,
8.01000022888184, 14.5299997329712, 5.71999979019165), `feb-wet_2016` = c(14.6999998092651,
14.7799997329712, 16.7899990081787, 4.90000009536743, 19.3500003814697
), `feb-wet_2017` = c(8.98999977111816, 9.17999935150146,
11.7699995040894, 6.3899998664856, 13.9899997711182), `feb-wet_2018` = c(16.75,
16.8599987030029, 12.0599994659424, 16.1900005340576, 8.51000022888184
), `feb-wet_2019` = c(7.58999967575073, 7.26999998092651,
8.21000003814697, 7.57999992370605, 8.81999969482422), `feb-wet_2020` = c(10.6399993896484,
10.4399995803833, 13.4399995803833, 8.53999996185303, 19.939998626709
), country = c("SERBIA", "SERBIA", "SLOVENIA", "GREECE",
"CZECHIA"), capital_city = c("Belgrade", "Belgrade", "Ljubljana",
"Athens", "Prague"), weight = c(20.25, 19.75, 14.25, 23.75,
14.25)), row.names = c(76L, 75L, 83L, 16L, 5L), class = "data.frame")
您的代码似乎提供了正确答案,现在有更多数据:
# Groups: country [4]
country capital_city winter
<chr> <chr> <dbl>
1 CZECHIA Prague 27.2
2 GREECE Athens 14.6
3 SERBIA Belgrade 19.1
4 SLOVENIA Ljubljana 16.3
这就是你要找的吗?
我冒昧地简化了您的代码:
weather_winter <- weather_winter %>%
pivot_longer(-c(31:33), values_to = "winter") %>%
select(-name)
weather_winter.std <- weather_winter %>%
group_by(country, capital_city) %>%
summarise(winter = wtd.var(winter))
只有一个“冬天”列,就不需要across()
.
最后,您没有使用权重。如果需要这些,则将最后一行更改为:
summarise(winter = wtd.var(winter, weights = weight))
给予:
# A tibble: 4 x 3
# Groups: country [4]
country capital_city winter
<chr> <chr> <dbl>
1 CZECHIA Prague 26.3
2 GREECE Athens 14.2
3 SERBIA Belgrade 18.8
4 SLOVENIA Ljubljana 15.8
本文收集自互联网,转载请注明来源。
如有侵权,请联系 [email protected] 删除。
我来说两句