6

いくつかのデータフレームがあり、それぞれに 250 を超える変数があります。最初のデータフレームからの部分dput:

df <- structure(list(id = structure(1:6, .Label = c("00", "01", "02", "03", "04", "05", "06", "08", "09", "10", "11", "12", "13", "14", "15", "All Recordings"), class = "factor"), Geslacht = structure(c(2L, 2L, 3L, 2L, 2L, 3L), .Label = c("-", "Man", "Vrouw"), class = "factor"), Leeftijd = structure(c(2L, 3L, 3L, 4L, 4L, 4L), .Label = c("-", "13", "14", "15", "17"), class = "factor"), FD.1.01 = c(13.96, 3.46, 2.45, 4.65, 1.18, 0.76), FD.1.02 = c(2.79, 4.32, 5.28, 0.78, 4.03, 0.74), FD.1.03 = c(2.09, 2.96, 5.78, 0.52, 1.12, 0), FD.1.04 = c(0, 2.79, 1.65, 0, 2.11, 2.11), FD.1.05 = c(1.26, 0.96, 8.67, 0.34, 1.77, 2.25), FD.1.06 = c(7.27, 0.58, 12.04, 0, 0.84, 3.39), FD.1.07 = c(3.97, 0.16, 8.37, 0.92, 0, 4.05), FD.1.08 = c(4.45, 0, 4.23, 0, 0, 1.63), FD.1.09 = c(0, 0, 2.07, 0, 0, 0.46), FD.1.10 = c(0, 0, 1.87, 0, 0, 0.42), FD.1.11 = c(0, 0, 9.05, 0, 0, 0), FD.1.12 = c(0, 0, 0, 0, 0, 0), FD.1.13 = c(0, 0, 0, 0, 0, 0), FD.1.14 = c(0, 0, 0, 0, 0, 0), FD.1.15 = c(0, 0, 0, 0, 0, 0), FD.1.16 = c(0, 0, 0, 0, 0, 0), FD.1.17 = c(0, 0, 0, 0, 0, 0), FD.1.18 = c(0, 0, 0, 0, 0, 0), FD.1.19 = c(0, 0, 0, 0, 0, 0), FD.1.20 = c(0, 0, 0, 0, 0, 0), FD.1.21 = c(0, 0, 0, 0, 0, 0), FD.1.22 = c(0, 0, 0, 0, 0, 0)), .Names = c("id", "Geslacht", "Leeftijd", "FD.1.01", "FD.1.02", "FD.1.03", "FD.1.04", "FD.1.05", "FD.1.06", "FD.1.07", "FD.1.08", "FD.1.09", "FD.1.10", "FD.1.11", "FD.1.12", "FD.1.13", "FD.1.14", "FD.1.15", "FD.1.16", "FD.1.17", "FD.1.18", "FD.1.19", "FD.1.20", "FD.1.21", "FD.1.22"), row.names = c(1L, 2L, 3L, 4L, 5L, 7L), class = "data.frame")

次の方法で、データフレームをワイドからロングに再形成します。

library(reshape2)
melted.df <- melt(df, id=c("id","Geslacht","Leeftijd"), measure.vars=c("all variables starting with FD"))

ただし、どの列名が で始まるか正確にはわかりませんFD。さらに、この数はいくつかのデータフレームによって異なり、他の文字の組み合わせで始まる変数についてもそうする必要があります。

もちろん、これを手動で行うこともできますが、時間がかかり、エラーが発生しやすくなります。したがって、プログラムによるソリューションが非常に望ましいです。

これにアプローチする方法はありますか？

@akrun のdplyrソリューションで問題が発生した場所を確認できるようにするためdputに、最初の 6 行とすべての列の a:

df <- structure(list(id = structure(1:6, .Label = c("00", "01", "02", "03", "04", "05", "06", "08", "09", "10", "11", "12", "13", "14", "15", "All Recordings"), class = "factor"), Geslacht = structure(c(2L, 2L, 3L, 2L, 2L, 3L), .Label = c("-", "Man", "Vrouw"), class = "factor"), Leeftijd = structure(c(2L, 3L, 3L, 4L, 4L, 4L), .Label = c("-", "13", "14", "15", "17"), class = "factor"), FD.1.01 = c(13.96, 3.46, 2.45, 4.65, 1.18, 0.76), FD.1.02 = c(2.79, 4.32, 5.28, 0.78, 4.03, 0.74), FD.1.03 = c(2.09, 2.96, 5.78, 0.52, 1.12, 0), FD.1.04 = c(0, 2.79, 1.65, 0, 2.11, 2.11), FD.1.05 = c(1.26, 0.96, 8.67, 0.34, 1.77, 2.25), FD.1.06 = c(7.27, 0.58, 12.04, 0, 0.84, 3.39), FD.1.07 = c(3.97, 0.16, 8.37, 0.92, 0, 4.05), FD.1.08 = c(4.45, 0, 4.23, 0, 0, 1.63), FD.1.09 = c(0, 0, 2.07, 0, 0, 0.46), FD.1.10 = c(0, 0, 1.87, 0, 0, 0.42), FD.1.11 = c(0, 0, 9.05, 0, 0, 0), FD.1.12 = c(0, 0, 0, 0,   0, 0), FD.1.13 = c(0, 0, 0, 0, 0, 0), FD.1.14 = c(0, 0, 0, 0, 0, 0), FD.1.15 = c(0, 0, 0, 0, 0, 0), FD.1.16 = c(0, 0, 0, 0, 0, 0), FD.1.17 = c(0, 0, 0, 0, 0, 0), FD.1.18 = c(0, 0, 0, 0, 0, 0), FD.1.19 = c(0, 0, 0, 0, 0, 0), FD.1.20 = c(0, 0, 0, 0, 0, 0), FD.1.21 = c(0, 0, 0, 0, 0, 0), FD.1.22 = c(0, 0, 0, 0, 0, 0), Click.5.18 = c(0, 0, 0, 0, 0, 0), Click.5.19 = c(0, 0, 0, 0, 0, 0), Click.5.20 = c(0, 0, 0, 0, 0, 0), Click.5.21 = c(0, 0, 0, 0, 0, 0), Click.6.01 = c(0, 0, 0, 0, 0, 0), Click.6.02 = c(0, 0, 0, 0, 0, 0), Click.6.03 = c(0, 0, 0, 0, 0, 0), Click.6.04 = c(0, 0, 0, 0, 0, 0), Click.6.05 = c(0, 0, 0, 0, 0, 0), Click.6.06 = c(0, 0, 0, 0, 0, 0), Click.6.07 = c(0, 0, 0, 0, 0, 0), Click.6.08 = c(0, 0, 0, 0, 0, 0), Click.6.12 = c(0, 0, 0, 0, 0, 0), Click.6.13 = c(0, 0, 0, 0, 0, 0), Click.6.14 = c(0, 0, 0, 0, 0, 0), Click.6.15 = c(0, 0, 0, 0, 0, 0), Click.6.16 = c(0, 0, 0, 0, 0, 0), Click.6.17 = c(0, 0, 0, 0, 0, 0), Click.6.18 = c(0, 0, 0, 0, 0, 0), Click.6.19 = c(0, 0, 0, 0, 0, 0), Click.6.20 = c(0, 0, 0, 0, 0, 0), Click.6.21 = c(0, 0, 0, 0, 0, 0), Click.7.01 = c(0, 0, 0, 0, 0, 0), Click.7.02 = c(0, 0, 0, 0, 0, 0), Click.7.03 = c(0, 0, 0, 0, 1, 0), Click.7.04 = c(0, 0, 0, 0, 0, 0)), .Names = c("id", "Geslacht", "Leeftijd", "FD.1.01", "FD.1.02", "FD.1.03", "FD.1.04", "FD.1.05", "FD.1.06", "FD.1.07", "FD.1.08", "FD.1.09", "FD.1.10", "FD.1.11", "FD.1.12", "FD.1.13", "FD.1.14", "FD.1.15", "FD.1.16", "FD.1.17", "FD.1.18", "FD.1.19", "FD.1.20", "FD.1.21", "FD.1.22", "Click.5.18", "Click.5.19",  "Click.5.20", "Click.5.21", "Click.6.01", "Click.6.02", "Click.6.03", "Click.6.04", "Click.6.05", "Click.6.06", "Click.6.07", "Click.6.08", "Click.6.12", "Click.6.13", "Click.6.14", "Click.6.15", "Click.6.16", "Click.6.17", "Click.6.18", "Click.6.19", "Click.6.20", "Click.6.21", "Click.7.01", "Click.7.02", "Click.7.03", "Click.7.04"), row.names = c(1L, 2L, 3L, 4L, 5L, 7L), class = "data.frame")
4

3 に答える 3

8

試す：

melt(df, id=c("id","Geslacht", "Leeftijd"), 
         measure.vars=grep("^FD", colnames(df)))

また

library(dplyr)
library(tidyr)

df %>% gather(FD, Score, FD.1.01:FD.1.22)

これは、提供した例でも機能しました。

df %>% 
gather(FD, Score, grep("^FD", colnames(df))) %>%
head()
  id Geslacht Leeftijd      FD Score
1 00      Man       13 FD.1.01 13.96
2 01      Man       14 FD.1.01  3.46
3 02    Vrouw       14 FD.1.01  2.45
4 03      Man       15 FD.1.01  4.65
5 04      Man       15 FD.1.01  1.18
6 05    Vrouw       15 FD.1.01  0.76

より大きなデータセットでは、

newCols <- simplify2array(replicate(100,df[,-(1:3)]))
colnames(newCols) <- paste0("FD.1.", 23:2222)
df1 <- cbind(df, newCols)
df2 <- df1 %>% 
gather(FD, Score, grep("^FD", colnames(df1)))
dim(df2)
#[1] 13332     5

異なる colnames を持つ新しいサンプル データセットを使用します。 

res1 <- df %>% 
select(id, Geslacht, Leeftijd, grep("^FD",names(df))) %>% 
gather(FD, Score, grep("^FD",names(df)))

結果を ?melt() で比較する 

res2 <-  melt(df, id=c("id","Geslacht", "Leeftijd"), 
      measure.vars=grep("^FD", colnames(df)))
colnames(res2) <- colnames(res1)
identical(res1,res2)
 #[1] TRUE
于 2014-06-20T08:53:40.377 に答える
4

dplyrとを使用したこの問題の別の非常に簡単な解決策tidyrは次のとおりです。

melted.df <- df %>% 
  select(id, Geslacht, Leeftijd, starts_with("FD")) %>% 
  gather(FD, Score, starts_with("FD"))

またはでdata.table：

melted.df <- melt(df, id = c("id","Geslacht","Leeftijd"),
                  measure.vars = patterns("^FD"))
于 2014-07-01T11:25:52.910 に答える
4

grepcolnames の FD:

melted.df <- melt(df, id=c("id","Geslacht","Leeftijd"),
                  measure.vars=colnames(df)[grepl("^FD",colnames(df))])
于 2014-06-20T08:56:24.367 に答える