Question

我正在尝试使用长格式和tidyverse数据操作环境来完成一些估算。即，这个等式：

[(SA_2016/TOTPOP_2016 - SA_2014/TOTPOP_2014 ) / (2016 - 2014)] * (2020 - 2016) + SA_2016/TOTPOP_2016 * TARGET_2020

因此我将需要计算4个变量（我认为）

code是该地区的名称; year是2014年或2016年; TN_2020 2020年的目标人口;

SA_2015 - ＆gt; 2016年i区域总人口group_by（国家，年份，代码）
TOTPOP_2016 - ＆gt; 2016年全国总人口group_by（国家，年）
SA_2014 - ＆gt; 2014年第i区的总人口;
TOTPOP_2014 - ＆gt; 2014年全国总人口;

计算四个变量的代码：

dt %>% 
  group_by(country, year, code) %>% 
  mutate(SA_t = sum(value)) %>% 
  ungroup() %>% 
  group_by(country, year) %>% 
  mutate(TOTPOP_t=sum(value),
         TN_2020 = sum(Target_2020),

...

我将如何进行下一步：

factor1= [(SA_2016/TOTPOP_2016-SA_2014/TOTPOP_2014)/2]*4 + SA_2016/TOTPOP_2016 * TN_2020 ?

DPUT：

dt = 
structure(list(country = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L), .Label = c("ZAMBIA", "ZIMBABWE"), class = "factor"), 
adm_level = c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L), code = structure(c(1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 
1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 
1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 1L, 4L, 5L, 2L, 3L, 6L, 
2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 
2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 2L, 3L, 6L, 
2L, 3L, 6L), .Label = c("BULAWAYOBULAWAYONA", "CENTRALCHIBOMBOCHISAMBA", 
"LUSAKALUSAKAKANYAMA", "MASVINGOZAKANA", "MIDLANDSZVISHAVANE URBANNA", 
"WESTERNSHANG'OMBOSINJEMBELA"), class = "factor"), year = c(2014L, 
2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 
2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2016L, 
2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 
2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2014L, 
2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 
2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2014L, 2016L, 
2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 
2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L, 2016L), 
value = c(47708L, 16217L, 2684L, 39013L, 15588L, 1896L, 36164L, 
17131L, 1568L, 46676L, 15333L, 2644L, 39502L, 15391L, 2020L, 
39857L, 16328L, 1826L, 49727L, 17058L, 2789L, 38842L, 15658L, 
1882L, 36332L, 17361L, 1570L, 48645L, 16127L, 2747L, 39321L, 
15458L, 2004L, 40036L, 16546L, 1828L, 13437L, 22551L, 10394L, 
11123L, 18626L, 8552L, 9148L, 14996L, 7195L, 13162L, 21530L, 
10676L, 10689L, 18522L, 8404L, 8681L, 15839L, 7082L, 13726L, 
23035L, 10616L, 11520L, 19290L, 8856L, 9464L, 15514L, 7443L, 
13444L, 21989L, 10902L, 11067L, 19176L, 8699L, 8978L, 16381L, 
7323L), sex = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 
2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L), .Label = c("F", "M"), class = "factor"), 
age = c(0L, 0L, 0L, 5L, 5L, 5L, 10L, 10L, 10L, 0L, 0L, 0L, 
5L, 5L, 5L, 10L, 10L, 10L, 0L, 0L, 0L, 5L, 5L, 5L, 10L, 10L, 
10L, 0L, 0L, 0L, 5L, 5L, 5L, 10L, 10L, 10L, 0L, 0L, 0L, 5L, 
5L, 5L, 10L, 10L, 10L, 0L, 0L, 0L, 5L, 5L, 5L, 10L, 10L, 
10L, 0L, 0L, 0L, 5L, 5L, 5L, 10L, 10L, 10L, 0L, 0L, 0L, 5L, 
5L, 5L, 10L, 10L, 10L), TARGET_2020 = c(1563.028, 1563.028, 
1563.028, 1358.582, 1358.582, 1358.582, 1202.966, 1202.966, 
1202.966, 1267.404, 1267.404, 1267.404, 1235.774, 1235.774, 
1235.774, 1079.602, 1079.602, 1079.602, 1563.028, 1563.028, 
1563.028, 1358.582, 1358.582, 1358.582, 1202.966, 1202.966, 
1202.966, 1267.404, 1267.404, 1267.404, 1235.774, 1235.774, 
1235.774, 1079.602, 1079.602, 1079.602, 1534.3, 1534.3, 1534.3, 
1339.217, 1339.217, 1339.217, 1188.892, 1188.892, 1188.892, 
1257.031, 1257.031, 1257.031, 1227.773, 1227.773, 1227.773, 
1074.339, 1074.339, 1074.339, 1534.3, 1534.3, 1534.3, 1339.217, 
1339.217, 1339.217, 1188.892, 1188.892, 1188.892, 1257.031, 
1257.031, 1257.031, 1227.773, 1227.773, 1227.773, 1074.339, 
1074.339, 1074.339)), .Names = c("country", "adm_level", 
"code", "year", "value", "sex", "age", "TARGET_2020"), class = "data.frame", 
row.names = c(NA, 
-72L))

数据管理：使用长格式来对列进行乘法和除法

0 个答案: