Question

我想从现有的数据框架中创建一个新数据＆＃34; ab＆＃34;。新数据框应该看起来像＆＃34; Newdf＆＃34;。

%%timeit 
ranked_cols = [col + '_ranked' for col in to_rank]

ranked = df[['date_id', 'category'] + to_rank].groupby(['date_id', 'category'], as_index = False).apply(lambda x: rank_fun(x, to_rank)) 
ranked.columns = ranked_cols        
ranked.reset_index(inplace = True)
ranked.set_index('level_1', inplace = True)  
1 loop, best of 3: 481 ms per loop

gcols = ['date_id', 'category']
rcols = ['var_1', 'var_2', 'var_3']

%timeit df.groupby(gcols)[rcols].apply(rnk_numpy).add_suffix('_ranked')
100 loops, best of 3: 16.4 ms per loop

%timeit rnk_numba(df, gcols, rcols).head()
1000 loops, best of 3: 1.03 ms per loop

我们可以使用dplyr包吗？如果有，怎么样？谢谢。

Answer 1

比dplyr更重要的是，您需要tidyr：

library(tidyr)
library(dplyr)
ab %>% 
  gather(Comp, DV) %>% 
  mutate(Comp = recode(Comp, "C1" = 1, "c2" = 2))
#    Comp DV
# 1     1  1
# 2     1  2
# 3     1  3
# 4     1  4
# 5     1  5
# 6     2 11
# 7     2 12
# 8     2 13
# 9     2 14
# 10    2 15

Answer 2

使用dplyr和tidyr会给你一些贴心的结果......

library(tidyr)
library(dplyr)
df2 <- ab %>% 
       mutate(Order=1:n()) %>% 
       gather(key=Comp,value=DV,C1,c2) %>% 
       arrange(Order) %>% 
       mutate(Comp=recode(Comp,"C1"=1,"c2"=2)) %>% 
       select(DV,Comp)

df2
   DV Comp
1   1    1
2  11    2
3   2    1
4  12    2
5   3    1
6  13    2
7   4    1
8  14    2
9   5    1
10 15    2

Answer 3

在基础R中可以使用：

Ndf <- ab[rep(1:nrow(ab),1,each=2),] 
Ndf[c(seq(2, dim(Ndf)[1], by=2)), ] <- ab[,2]
#or Ndf <- c(t(ab)) as mentioned in the comments instead of above lines

Ndf[, 2] <- rep.int(c(1:2),times=5)                            

colnames(Ndf) <- c("DV", "CMT1")

>Ndf
#       DV  CMT1
#1      1    1
#1.1    11   2
#2      2    1
#2.1    12   2
#3      3    1
#3.1    13   2
#4      4    1
#4.1    14   2
#5      5    1
#5.1    15   2

Answer 4

虽然OP要求dpylr解决方案，但我觉得有必要寻找data.table解决方案。所以，FWIW，这是使用melt()的替代方法。

请注意，此解决方案 not 依赖于ab中的特定列名称，正如另外两个dplyr解决方案所做的那样。此外，它也应该在ab中的两列以上（未经测试）。

library(data.table)
melt(setDT(ab, keep.rownames = TRUE), id.vars = "rn", value.name = "DV"
     )[, Comp := rleid(variable)
       ][order(rn)][, c("rn", "variable") := NULL][]
#    DV Comp
# 1:  1    1
# 2: 11    2
# 3:  2    1
# 4: 12    2
# 5:  3    1
# 6: 13    2
# 7:  4    1
# 8: 14    2
# 9:  5    1
#10: 15    2

数据

ab <- structure(list(C1 = 1:5, c2 = 11:15), .Names = c("C1", "c2"), 
  row.names = c(NA, -5L), class = "data.frame")
ab
#  C1 c2
#1  1 11
#2  2 12
#3  3 13
#4  4 14
#5  5 15

使用现有数据创建新数据框

4 个答案:

数据