Geek Answers Handbook

Convert a data frame from a "wide" format to a "long" format in R

I have the following framework:

 df = data.frame(A_1 = c(1,2,3), A_2 = c(4,5,6), A_3 = c(7,8,9), B_1 = c(10, 11, 12), B_2 = c(13, 14, 15), B_3 = c(16, 17, 18))

 #> df
 #  A_1 A_2 A_3 B_1 B_2 B_3
 #1   1   4   7  10  13  16
 #2   2   5   8  11  14  17
 #3   3   6   9  12  15  18

Column names contain both a letter and a number. The letter refers to a particular variable (for example, A is a factor, B is a factor), and the numbers in the column names refer to individuals. In other words, each person has values ​​for A and B: A_1 and B_1 are columns for Individual 1, and A_2, B_2 are columns for Individual 2, etc.

I would like to get the following result: note that all columns “A” are combined into one column “A”, and the same applies to columns “B”, etc.:

   A  B
 # 1 10
 # 2 11
 # 3 12
 # 4 13
 # 5 14
 # 6 15
 # 7 16
 # 8 17
 # 9 18

? : 20 (A, B, C,...), (: A_1, A_2, A_3).

!!

+4
3

"" "" "" . R reshape , id.

reshape(df, direction = "long", varying = names(df), sep = "_")
#     time A  B id
# 1.1    1 1 10  1
# 2.1    1 2 11  2
# 3.1    1 3 12  3
# 1.2    2 4 13  1
# 2.2    2 5 14  2
# 3.2    2 6 15  3
# 1.3    3 7 16  1
# 2.3    3 8 17  2
# 3.3    3 9 18  3

.

, , "reshape2" ( ):

library(reshape2)
dfL <- melt(as.matrix(df))
dfL <- cbind(dfL, colsplit(dfL$Var2, "_", c("Factor", "Individual")))
dcast(dfL, Individual + Var1 ~ Factor, value.var="value")
#   Individual Var1 A  B
# 1          1    1 1 10
# 2          1    2 2 11
# 3          1    3 3 12
# 4          2    1 4 13
# 5          2    2 5 14
# 6          2    3 6 15
# 7          3    1 7 16
# 8          3    2 8 17
# 9          3    3 9 18

, "data.table" 1.8.11 "" "dcast". , . , , , "id".

library(reshape2)
library(data.table)
packageVersion("data.table") ## Must be at least 1.8.11 to work
# [1] ‘1.8.11’

DT <- data.table(cbind(id = sequence(nrow(df)), df))
DTL <- melt(DT, id.vars="id")
DTL[, c("Fac", "Ind") := colsplit(variable, "_", c("Fac", "Ind"))]
dcast.data.table(DTL, Ind + id ~ Fac)
#    Ind id A  B
# 1:   1  1 1 10
# 2:   1  2 2 11
# 3:   1  3 3 12
# 4:   2  1 4 13
# 5:   2  2 5 14
# 6:   2  3 6 15
# 7:   3  1 7 16
# 8:   3  2 8 17
# 9:   3  3 9 18

Update

- merged.stack splitstackshape. , as.data.table(df, keep.rownames = TRUE), data.table(cbind(id = sequence(nrow(df)), df)) "data.table".

library(splitstackshape)
merged.stack(as.data.table(df, keep.rownames = TRUE), 
             var.stubs = c("A", "B"), sep = "_")
#    rn .time_1 A  B
# 1:  1       1 1 10
# 2:  1       2 4 13
# 3:  1       3 7 16
# 4:  2       1 2 11
# 5:  2       2 5 14
# 6:  2       3 8 17
# 7:  3       1 3 12
# 8:  3       2 6 15
# 9:  3       3 9 18

/, "tidyr" + "dplyr".

library(tidyr)
library(dplyr)
df %>%
  gather(var, value, A_1:B_3) %>%
  separate(var, c("var", "time")) %>%
  group_by(var, time) %>%
  mutate(grp = sequence(n())) %>%
  ungroup() %>%
  spread(var, value)
# Source: local data frame [9 x 4]
# 
#   time grp A  B
# 1    1   1 1 10
# 2    1   2 2 11
# 3    1   3 3 12
# 4    2   1 4 13
# 5    2   2 5 14
# 6    2   3 6 15
# 7    3   1 7 16
# 8    3   2 8 17
# 9    3   3 9 18
+12

unlist data.frame. ( Ananda, ), - ...

#  Find unique persons
IDs <- unique( gsub( "([A-Z]).*" , "\\1" , names( df ) ) )
[1] "A" "B"

# Unlist columns relevant to that person
out <- sapply( IDs , function(x) unlist( df[ , grepl( x , names( df ) ) ] , use.names = FALSE ) )

#  Change from matrix to data.frame
data.frame( out )
#  A  B
#1 1 10
#2 2 11
#3 3 12
#4 4 13
#5 5 14
#6 6 15
#7 7 16
#8 8 17
#9 9 18
+3

You can get the data in the form you need:

> m<-as.matrix(df)
> dim(m)<-c(nrow(m)*3,ncol(m)/3)
> m
      [,1] [,2]
 [1,]    1   10
 [2,]    2   11
 [3,]    3   12
 [4,]    4   13
 [5,]    5   14
 [6,]    6   15
 [7,]    7   16
 [8,]    8   17
 [9,]    9   18

The same code should work for a large data frame if there are three columns for each user. Then you just need to assign column names.

+1
source

More articles:


All Articles