Question

I have the following data frame:

structure(list(name = c("jones", "williams", "jones", 
                              "williams", "williams", "jones", "williams", "williams", "jones", 
                              "williams", "williams", "jones", "williams", "williams", "jones", 
                              "williams", "williams", "jones", "williams", "williams", "jones", 
                              "williams", "jones", "jones", "jones", "jones", 
                              "jones", "jones", "jones", "jones"), state = c("NY", 
                                                                             "NC", "NY", "NC", "TX", "NY", "NC", "TX", "NY", "TX", "NC", "NY", 
                                                                             "TX", "NC", "NY", "TX", "NC", "NY", "TX", "NC", "NY", "NC", "NY", 
                                                                             "NY", "NY", "NY", "NY", "NY", "NY", "NY"), year = structure(c(1995, 
                                                                                                                                           1995, 1996, 1996, 1996, 1997, 1997, 1997, 1998, 1998, 1998, 1999, 
                                                                                                                                           1999, 1999, 2000, 2000, 2000, 2001, 2001, 2001, 2002, 2002, 2003, 
                                                                                                                                           2004, 2005, 2006, 2007, 2008, 2009, 2010), format.stata = "%8.0g"), 
             year_of_election = c(NA, 1992, NA, 1992, 1996, NA, 1992, 
                                  1996, NA, 1998, 1998, 1999, 1998, 1998, 1999, 1998, 1998, 
                                  1999, 1998, 1998, 1999, 1998, 1999, 1999, 1999, 1999, 1999, 
                                  1999, 2009, 2009)), class = c("grouped_df", "tbl_df", "tbl", 
                                                                "data.frame"), row.names = c(NA, -30L), groups = structure(list(
                                                                  name = c("williams", "williams", "jones"), state = c("NC", 
                                                                                                                               "TX", "NY"), .rows = structure(list(c(2L, 4L, 7L, 11L, 14L, 
                                                                                                                                                                     17L, 20L, 22L), c(5L, 8L, 10L, 13L, 16L, 19L), c(1L, 3L, 
                                                                                                                                                                                                                      6L, 9L, 12L, 15L, 18L, 21L, 23L, 24L, 25L, 26L, 27L, 28L, 
                                                                                                                                                                                                                      29L, 30L)), ptype = integer(0), class = c("vctrs_list_of", 
                                                                                                                                                                                                                                                                "vctrs_vctr", "list"))), row.names = c(NA, -3L), .drop = TRUE, class = c("tbl_df", 
                                                                                                                                                                                                                                                                                                                                         "tbl", "data.frame")))

我想设立一个新的一栏,称为“选举年份”,该栏将取代本年度选举的下一个学年。因此,例如,在纽约市-纽约-1995年,“不选举年”应为4年,因为1999年是选举的下一年。关于纽约-1999年,我想是零。而到2000年,明年将是2009年。关于纽约-2009年,我想是零。因此。如果没有“快”年,我就希望成为美国人。

这是我目前正在使用的这一法典,它偏离了相反的方向。

df <- df %>%
  arrange(name, state, year) %>%
  group_by(name, state) %>%
  mutate(
    years_until_reelection = lead(year_of_election) - year
  ) %>%
  ungroup()

Answer 1

也许这一自我参与:

library(dplyr)
df %>%
  left_join(select(df, name, state, next_election = year_of_election), 
            join_by(name, state, year <= next_election), multiple = "first") %>%
  mutate(years_until_reelection = next_election - year) %>%
  ungroup() %>%
  print(n=99)
# # A tibble: 30 × 6
#    name     state  year year_of_election next_election years_until_reelection
#    <chr>    <chr> <dbl>            <dbl>         <dbl>                  <dbl>
#  1 jones    NY     1995               NA          1999                      4
#  2 williams NC     1995             1992          1998                      3
#  3 jones    NY     1996               NA          1999                      3
#  4 williams NC     1996             1992          1998                      2
#  5 williams TX     1996             1996          1996                      0
#  6 jones    NY     1997               NA          1999                      2
#  7 williams NC     1997             1992          1998                      1
#  8 williams TX     1997             1996          1998                      1
#  9 jones    NY     1998               NA          1999                      1
# 10 williams TX     1998             1998          1998                      0
# 11 williams NC     1998             1998          1998                      0
# 12 jones    NY     1999             1999          1999                      0
# 13 williams TX     1999             1998            NA                     NA
# 14 williams NC     1999             1998            NA                     NA
# 15 jones    NY     2000             1999          2009                      9
# 16 williams TX     2000             1998            NA                     NA
# 17 williams NC     2000             1998            NA                     NA
# 18 jones    NY     2001             1999          2009                      8
# 19 williams TX     2001             1998            NA                     NA
# 20 williams NC     2001             1998            NA                     NA
# 21 jones    NY     2002             1999          2009                      7
# 22 williams NC     2002             1998            NA                     NA
# 23 jones    NY     2003             1999          2009                      6
# 24 jones    NY     2004             1999          2009                      5
# 25 jones    NY     2005             1999          2009                      4
# 26 jones    NY     2006             1999          2009                      3
# 27 jones    NY     2007             1999          2009                      2
# 28 jones    NY     2008             1999          2009                      1
# 29 jones    NY     2009             2009          2009                      0
# 30 jones    NY     2010             2009            NA                     NA

Answer 2

It is your "year of election" column is indicating the previous election and not the future election.
The below code zeros out the election year column when year <> election year and then refills it with the future election.

library(dplyr)
library(tidyr)

answer <- df %>% 
             group_by(name, state) %>% 
             mutate(year_of_election= ifelse(year==year_of_election, year_of_election, NA)) %>%
             fill(year_of_election, .direction = "up") %>% 
             mutate(years_until_reelection = year_of_election - year) %>%
             arrange(name, state, year)

answer

友情链接