R 更新数据帧'；s列基于其他列

我有一个包含个人舞台的数据框，如下所示（这只是一个非常大的舞台的样本）：

右边的5列是一个人的舞台，但还没有包含所有信息。我需要在前两列中包含信息，其中数字以年为单位，如下所示：

• 如果第1列中的值小于一年，则第一个年龄段应为“已死亡”，接下来的所有列（此人仍然死亡…）也应为“已死亡”；如果该值介于1和2之间，则第二个阶段应为“已死亡”，依此类推

• 如果第2列中的值小于一年，则SecondYStage应为“EndOfEvents”；如果该值介于1和2之间，则它应该是“EndOfEvents”，依此类推

因此，这种情况下的预期输出应为：

df_updated = structure(list(DeceasedDate = c(0.283219178082192, 
1.12678843226788, 
2.02865296803653, 0.892465753424658, NA, 0.88013698630137, NA
), LastClinicalEventMonthEnd = c(0.244862981988838, 1.03637744165398, 
10.9464611555048, 0.763698598427194, 3.35011412354135, 0.677397228564181, 
3.83687211440893), FirstYStage = c("Deceased", "2", "2", "Deceased", 
"2", "Deceased", "3.1"), SecondYStage = c("Deceased", "Deceased", 
"2", "Deceased", "2", "Deceased", "3.1"), ThirdYStage = c("Deceased", 
"Deceased", "Deceased", "Deceased", "2", "Deceased", "3.1"), 
FourthYStage = c("Deceased", "Deceased", "Deceased", "Deceased", 
"2", "Deceased", "3.1"), FifthYStage = c("Deceased", "Deceased", 
"Deceased", "Deceased", "LastEvent", "Deceased", "LastEvent"
)), row.names = c(NA, -7L), class = c("tbl_df", "tbl", "data.frame"
))

重要的一点是，应该优先考虑“死亡”，换句话说，如果有冲突，一方面有数字，“死亡”与之相矛盾，我们应该选择死亡

---

我如何以最有效的方式完成这项工作？目前我正在做if，但我认为这不是最好的行动方案

我会这样做：

从宽格式重塑为长格式

从列名计算年份

有选择地更新

值

列

重塑为宽格式

数据表 由于我在

data.table

方面比在

dplyr

方面更熟练，因此这里介绍了在

data.table

语法中实现的方法。（很抱歉，如果时间允许，我将添加一个

dplyr

解决方案。）

dplyr/tidyr 正如所承诺的，这里也是相同方法的

dplyr

/

tidyr

实现：

library(tidyr)
library(dplyr)
df %>% 
  mutate(rn = row_number()) %>% 
  gather(key, val, ends_with("Stage"), factor_key = TRUE) %>% 
  mutate(year = as.integer(key)) %>% 
  mutate(val = if_else(!is.na(DeceasedDate) & floor(DeceasedDate) < year, "Deceased", val)) %>% 
  mutate(val = if_else(is.na(DeceasedDate) & floor(LastClinicalEventMonthEnd) + 1 < year, "EndOfEvents", val)) %>% 
  select(-year) %>% 
  spread(key, val) %>% 
  arrange(rn) 

或者不创建

年份

列：

df %>% 
  mutate(rn = row_number()) %>% 
  gather(key, val, ends_with("Stage"), factor_key = TRUE) %>% 
  mutate(val = if_else(!is.na(DeceasedDate) & floor(DeceasedDate) < as.integer(key), 
                       "Deceased", val)) %>% 
  mutate(val = if_else(is.na(DeceasedDate) & floor(LastClinicalEventMonthEnd) + 1 < as.integer(key), 
                       "EndOfEvents", val)) %>% 
  spread(key, val) %>% 
  arrange(rn) 

df%>%
变异（rn=行数（））%>%
聚集（键、值、以（“阶段”）结束），因子键=真）%>%
mutate（val=if_else（！is.na（decesedDate））和floor（decesedDate）%
变异（val=if_else（is.na（decesedDate））和地板（LastClinicalEventMonthEnd）+1%
排列（键，值）%>%
安排（注册护士）

你能提供一个你正在做的事情的可复制的例子吗？@AdamWheeler举个例子，

df$FirstYStage=if_else（df$deceseddate
   rn DeceasedDate LastClinicalEventMonthEnd FirstYStage SecondYStage ThirdYStage FourthYStage FifthYStage
1:  1    0.2832192                 0.2448630    Deceased     Deceased    Deceased     Deceased    Deceased
2:  2    1.1267884                 1.0363774           2     Deceased    Deceased     Deceased    Deceased
3:  3    2.0286530                10.9464612           2            2    Deceased     Deceased    Deceased
4:  4    0.8924658                 0.7636986    Deceased     Deceased    Deceased     Deceased    Deceased
5:  5           NA                 3.3501141           2            2           2            2 EndOfEvents
6:  6    0.8801370                 0.6773972    Deceased     Deceased    Deceased     Deceased    Deceased
7:  7           NA                 3.8368721         3.1          3.1         3.1          3.1 EndOfEvents

library(tidyr)
library(dplyr)
df %>% 
  mutate(rn = row_number()) %>% 
  gather(key, val, ends_with("Stage"), factor_key = TRUE) %>% 
  mutate(year = as.integer(key)) %>% 
  mutate(val = if_else(!is.na(DeceasedDate) & floor(DeceasedDate) < year, "Deceased", val)) %>% 
  mutate(val = if_else(is.na(DeceasedDate) & floor(LastClinicalEventMonthEnd) + 1 < year, "EndOfEvents", val)) %>% 
  select(-year) %>% 
  spread(key, val) %>% 
  arrange(rn) 

  DeceasedDate LastClinicalEventMonthEnd rn FirstYStage SecondYStage ThirdYStage FourthYStage FifthYStage
1    0.2832192                 0.2448630  1    Deceased     Deceased    Deceased     Deceased    Deceased
2    1.1267884                 1.0363774  2           2     Deceased    Deceased     Deceased    Deceased
3    2.0286530                10.9464612  3           2            2    Deceased     Deceased    Deceased
4    0.8924658                 0.7636986  4    Deceased     Deceased    Deceased     Deceased    Deceased
5           NA                 3.3501141  5           2            2           2            2 EndOfEvents
6    0.8801370                 0.6773972  6    Deceased     Deceased    Deceased     Deceased    Deceased
7           NA                 3.8368721  7         3.1          3.1         3.1          3.1 EndOfEvents

df %>% 
  mutate(rn = row_number()) %>% 
  gather(key, val, ends_with("Stage"), factor_key = TRUE) %>% 
  mutate(val = if_else(!is.na(DeceasedDate) & floor(DeceasedDate) < as.integer(key), 
                       "Deceased", val)) %>% 
  mutate(val = if_else(is.na(DeceasedDate) & floor(LastClinicalEventMonthEnd) + 1 < as.integer(key), 
                       "EndOfEvents", val)) %>% 
  spread(key, val) %>% 
  arrange(rn)