在 R 中按组补充缺失日期(年月)和值
Refill missing date(year-month) and value by groups in R
我正在尝试填写缺失的日期和费率。对于缺失的日期,我希望在2019年(1月)和2021年(1月)之间重新填写yr_month。对于费率,我希望将任何缺失值重新填充为零。
我找到的最接近的例子在这里 - 但我的挑战是我还有一个按组的列。这意味着每个患者将有 2 年的数据。
我可以高效地执行此操作的最佳方法是什么?
# A tibble: 10 x 3
# Groups: clinic, yr_month [10]
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0.528
2 patient1 2019-04 0.528
3 patient1 2020-05 0.528
4 patient1 2021-01 1.06
5 patient2 2019-01 0.0671
6 patient2 2019-02 0.436
7 patient2 2019-03 0.805
8 patient2 2019-04 0.671
9 patient2 2019-05 0.268
10 patient2 2019-06 0.101
输入
structure(list(clinic = c("patient1", "patient1", "patient1",
"patient1", "patient2", "patient2", "patient2", "patient2", "patient2",
"patient2"), yr_month = c("2019-01", "2019-04", "2020-05", "2021-01",
"2019-01", "2019-02", "2019-03", "2019-04", "2019-05", "2019-06"
), rate = c(0.527704485488127, 0.527704485488127, 0.527704485488127,
1.05540897097625, 0.0671163461861136, 0.436256250209739, 0.805396154233364,
0.671163461861136, 0.268465384744455, 0.10067451927917)), row.names = c(NA,
-10L), groups = structure(list(clinic = c("patient1", "patient1",
"patient1", "patient1", "patient2", "patient2", "patient2", "patient2",
"patient2", "patient2"), yr_month = c("2019-01", "2019-04", "2020-05",
"2021-01", "2019-01", "2019-02", "2019-03", "2019-04", "2019-05",
"2019-06"), .rows = structure(list(1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, 10L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))
预期输出:
# Groups: clinic, yr_month
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0
1 patient1 2019-02 0
1 patient1 2019-03 0
1 patient1 2019-04 0.528
1 patient1 2019-05 0
1 patient1 2019-06 0
1 patient1 2019-07 0
1 patient1 2019-08 0
1 patient1 2019-09 0
...
25 patient2 2019-01 0.0671
26 patient2 2019-02 0.436
27 patient2 2019-03 0.805
28 patient2 2019-04 0.671
29 patient2 2019-05 0.268
30 patient2 2019-06 0.101
...
48 patient2 2021-01 0
使用 tidyverse
和 zoo
您可以尝试以下操作。您可以使用 group_by
来考虑诊所内的每位患者。对于您的日期,您可以使用 zoo
中的 as.yearmon
来使用年月格式。然后,使用 tidyr
中的 complete
,您可以用 0 填充缺失的 rate
值来表示缺失的月份。
library(tidyverse)
library(zoo)
df %>%
group_by(clinic) %>%
mutate(yr_month = as.yearmon(yr_month)) %>%
arrange(yr_month) %>%
complete(yr_month = seq(first(yr_month), last(yr_month), by = 1 / 12), fill = list(rate = 0))
首先我们为您给定的月份和年份组合创建一个空数据集:
library(dplyr)
library(tidyr)
library(purrr)
month_df <- tibble(
month = rep(c(1:12), 3),
year = c(rep(2019, 12), rep(2020, 12), rep(2021, 12))
) %>%
mutate(month_ind = ifelse(nchar(month) == 1, paste0("0", month), month),
yr_month = paste0(year, "-", month_ind)) %>%
select(yr_month)
之后,给定df
是你的数据:
df %>% ungroup() %>%
group_split(clinic) %>%
map(., right_join, month_df) %>%
map(., fill, clinic) %>%
bind_rows() %>%
arrange(clinic, yr_month) %>%
mutate(rate = ifelse(is.na(rate), 0 , rate))
输出为:
# A tibble: 72 x 3
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0.528
2 patient1 2019-02 0
3 patient1 2019-03 0
4 patient1 2019-04 0.528
5 patient1 2019-05 0
6 patient1 2019-06 0
7 patient1 2019-07 0
8 patient1 2019-08 0
9 patient1 2019-09 0
10 patient1 2019-10 0
# ... with 62 more rows
我正在尝试填写缺失的日期和费率。对于缺失的日期,我希望在2019年(1月)和2021年(1月)之间重新填写yr_month。对于费率,我希望将任何缺失值重新填充为零。
我找到的最接近的例子在这里 -
我可以高效地执行此操作的最佳方法是什么?
# A tibble: 10 x 3
# Groups: clinic, yr_month [10]
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0.528
2 patient1 2019-04 0.528
3 patient1 2020-05 0.528
4 patient1 2021-01 1.06
5 patient2 2019-01 0.0671
6 patient2 2019-02 0.436
7 patient2 2019-03 0.805
8 patient2 2019-04 0.671
9 patient2 2019-05 0.268
10 patient2 2019-06 0.101
输入
structure(list(clinic = c("patient1", "patient1", "patient1",
"patient1", "patient2", "patient2", "patient2", "patient2", "patient2",
"patient2"), yr_month = c("2019-01", "2019-04", "2020-05", "2021-01",
"2019-01", "2019-02", "2019-03", "2019-04", "2019-05", "2019-06"
), rate = c(0.527704485488127, 0.527704485488127, 0.527704485488127,
1.05540897097625, 0.0671163461861136, 0.436256250209739, 0.805396154233364,
0.671163461861136, 0.268465384744455, 0.10067451927917)), row.names = c(NA,
-10L), groups = structure(list(clinic = c("patient1", "patient1",
"patient1", "patient1", "patient2", "patient2", "patient2", "patient2",
"patient2", "patient2"), yr_month = c("2019-01", "2019-04", "2020-05",
"2021-01", "2019-01", "2019-02", "2019-03", "2019-04", "2019-05",
"2019-06"), .rows = structure(list(1L, 2L, 3L, 4L, 5L, 6L, 7L,
8L, 9L, 10L), ptype = integer(0), class = c("vctrs_list_of",
"vctrs_vctr", "list"))), row.names = c(NA, 10L), class = c("tbl_df",
"tbl", "data.frame"), .drop = TRUE), class = c("grouped_df",
"tbl_df", "tbl", "data.frame"))
预期输出:
# Groups: clinic, yr_month
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0
1 patient1 2019-02 0
1 patient1 2019-03 0
1 patient1 2019-04 0.528
1 patient1 2019-05 0
1 patient1 2019-06 0
1 patient1 2019-07 0
1 patient1 2019-08 0
1 patient1 2019-09 0
...
25 patient2 2019-01 0.0671
26 patient2 2019-02 0.436
27 patient2 2019-03 0.805
28 patient2 2019-04 0.671
29 patient2 2019-05 0.268
30 patient2 2019-06 0.101
...
48 patient2 2021-01 0
使用 tidyverse
和 zoo
您可以尝试以下操作。您可以使用 group_by
来考虑诊所内的每位患者。对于您的日期,您可以使用 zoo
中的 as.yearmon
来使用年月格式。然后,使用 tidyr
中的 complete
,您可以用 0 填充缺失的 rate
值来表示缺失的月份。
library(tidyverse)
library(zoo)
df %>%
group_by(clinic) %>%
mutate(yr_month = as.yearmon(yr_month)) %>%
arrange(yr_month) %>%
complete(yr_month = seq(first(yr_month), last(yr_month), by = 1 / 12), fill = list(rate = 0))
首先我们为您给定的月份和年份组合创建一个空数据集:
library(dplyr)
library(tidyr)
library(purrr)
month_df <- tibble(
month = rep(c(1:12), 3),
year = c(rep(2019, 12), rep(2020, 12), rep(2021, 12))
) %>%
mutate(month_ind = ifelse(nchar(month) == 1, paste0("0", month), month),
yr_month = paste0(year, "-", month_ind)) %>%
select(yr_month)
之后,给定df
是你的数据:
df %>% ungroup() %>%
group_split(clinic) %>%
map(., right_join, month_df) %>%
map(., fill, clinic) %>%
bind_rows() %>%
arrange(clinic, yr_month) %>%
mutate(rate = ifelse(is.na(rate), 0 , rate))
输出为:
# A tibble: 72 x 3
clinic yr_month rate
<chr> <chr> <dbl>
1 patient1 2019-01 0.528
2 patient1 2019-02 0
3 patient1 2019-03 0
4 patient1 2019-04 0.528
5 patient1 2019-05 0
6 patient1 2019-06 0
7 patient1 2019-07 0
8 patient1 2019-08 0
9 patient1 2019-09 0
10 patient1 2019-10 0
# ... with 62 more rows