Question

我目前有这个数据框

    dat = data.frame(time= c("Q1","Q2","Q3"), 
                     measure1 = c(1,2,9   ),
                     measure2 = c(4,5,6   ))
    dat2 = dat %>% gather(key= Metric, value = Value, c(measure1, measure2)) %>% group_by(Metric, time)
dat2 = as.data.frame(dat2)

time   Metric Value
1   Q1 measure1     1
2   Q2 measure1     2
3   Q3 measure1     9
4   Q1 measure2     4
5   Q2 measure2     5
6   Q3 measure2     6

我可以像这样添加这个“测试”栏

dat2$test=  ifelse(  dat2$Metric =="measure1" &  dat2$Value >   dat2$Value[ dat2$Metric=="measure2"] ,1,
                               ifelse(  dat2$Metric == "measure2" &   dat2$Value >  dat2$Value[ dat2$Metric=="measure1"] ,1,-1)
                               ) #end ifelse

 time   Metric Value test
1   Q1 measure1     1   -1
2   Q2 measure1     2   -1
3   Q3 measure1     9    1
4   Q1 measure2     4    1
5   Q2 measure2     5    1
6   Q3 measure2     6   -1

但是我想像这样使用dplyr和mutate

dat = data.frame(time= c("Q1","Q2","Q3"), 
                 measure1 = c(1,2,9   ),
                 measure2 = c(4,5,6   ))
dat %>% gather(key= Metric, value = Value, c(measure1, measure2)) %>% group_by(Metric, time) %>%
     mutate(test= ifelse( Metric =="measure1" &  Value > Value[Metric=="measure2"] ,1,
                               ifelse( Metric =="measure2" &  Value > Value[Metric=="measure1"] ,1,-1)
                               ) #end ifelse
                        )#end mutate
dat2 = as.data.frame(dat2)
dat2

但“测试”栏都是NA

 time   Metric Value test
1   Q1 measure1     1   NA
2   Q2 measure1     2   NA
3   Q3 measure1     9   NA
4   Q1 measure2     4   NA
5   Q2 measure2     5   NA
6   Q3 measure2     6   NA

为什么不能使用mutate添加列？是否与使用as.data.frame并手动添加有关... mutate无法识别列名？

谢谢。

Answer 1

问题在于，当您按Metric分组时，对于measure1为Metric == "measure2"的群组，Value[FALSE] == numeric(0)将始终返回FALSE，mutate }，零长度对象在dat %>% gather(key= Metric, value = Value, c(measure1, measure2)) %>% group_by(time) %>% # <<<<<<<<<<<< here mutate(test= ifelse(Metric =="measure1" & Value > Value[Metric=="measure2"] ,1, ifelse(Metric =="measure2" & Value > Value[Metric=="measure1"],1,-1) ) #end ifelse ) # Source: local data frame [6 x 4] # Groups: time [3] # time Metric Value test # <fctr> <chr> <dbl> <dbl> # 1 Q1 measure1 1 -1 # 2 Q2 measure1 2 -1 # 3 Q3 measure1 9 1 # 4 Q1 measure2 4 1 # 5 Q2 measure2 5 1 # 6 Q3 measure2 6 -1：

之后转换为NA

dat %>% 
        gather(key= Metric, value = Value, c(measure1, measure2)) %>% 
        group_by(Metric, time) %>%
        mutate(test= Value[Metric == "measure2"])

# Source: local data frame [6 x 4]
# Groups: Metric, time [6]

#     time   Metric Value  test
#   <fctr>    <chr> <dbl> <dbl>
# 1     Q1 measure1     1    NA
# 2     Q2 measure1     2    NA
# 3     Q3 measure1     9    NA
# 4     Q1 measure2     4     4
# 5     Q2 measure2     5     5
# 6     Q3 measure2     6     6

通过此示例，您可以更清楚地看到按Metric分组时发生的情况：

<releaseYear>2032</releaseYear>  OR
<releaseYear></releaseYear>

无法使用dplyr mutate

1 个答案: