Question

我有一个包含一个人的舞台的数据框，如下所示（这只是非常大的一个示例）：

df = 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("N/A", "2", "2", "2", "2", 
"2", "3.1"), SecondYStage = c("N/A", "N/A", "2", "N/A", "2", 
"N/A", "3.1"), ThirdYStage = c("N/A", "N/A", "2", "N/A", "2", 
"N/A", "3.1"), FourthYStage = c("N/A", "N/A", "N/A", "N/A", "2", 
"N/A", "3.1"), FifthYStage = c("N/A", "N/A", "N/A", "N/A", "N/A", 
"N/A", "N/A")), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-7L))

右边的5列是一个人的一个阶段，但尚未包含所有信息。我需要在前两列中包含这些信息，其中的数字以年为单位，如下所示：

如果第1列中的值小于一年，则FirstYStage应该为“已死”，接下来的所有列也都应为“已死”（此人仍然死亡...）；如果该值在1到2之间，则SecondYStage应该为“已死”，依此类推。
如果第2列中的值小于一年，则SecondYStage应该为“ EndOfEvents”；如果该值介于1和2之间，则SecondYStage应该为“ EndOfEvents”，依此类推。

因此，在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"
))

一个重要的观点是，应该优先考虑“死亡”，换句话说，如果发生冲突，并且一方面存在数字，而“死亡”与之矛盾，那么我们应该更喜欢死亡。

如何以最有效的方式做到这一点？目前我正在做if，但我认为这不是最佳的做法

Answer 1

这就是我要做的：

从宽格式到长格式的重塑
从列名计算年份
有选择地更新value列
重塑为宽幅格式

data.table

由于我对data.table的流利程度比对dplyr的流利，这里是用data.table语法实现的方法。（抱歉，如果时间允许，我会添加一个dplyr解决方案。）

library(data.table)
long <- melt(setDT(df)[, rn := .I], measure.vars = patterns("Stage$"))
long[, year := as.integer(variable)]   # column index     
long[floor(DeceasedDate) < year, value := "Deceased"]
long[is.na(DeceasedDate) & floor(LastClinicalEventMonthEnd) + 1 < year, value := "EndOfEvents"]
dcast(long, rn + DeceasedDate + LastClinicalEventMonthEnd ~ variable)

   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

dplyr / tidyr

如所承诺的，这也是相同方法的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)

  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

，或者不创建year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)

根据其他列更新数据框的列

1 个答案:

data.table

dplyr / tidyr