Complicated reshaping

Question

I want to reshape my dataframe from long to wide format and I loose some data that I\'d like to keep. For the following example:

df <- data.frame(Par1 =          


        

Answer 1

Late to the party, but here's another alternative using data.table:

require(data.table)
dt <- data.table(df, key=c("Par1", "Par2"))
dt[, list(pre=mean(Val[Type == "pre"]), 
          post=mean(Val[Type == "post"]), 
          pre.num=length(Val[Type == "pre"]), 
          post.num=length(Val[Type == "post"]), 
          ParD = paste(ParD, collapse="_")), 
by=list(Par1, Par2)]

#    Par1 Par2 pre post pre.num post.num        ParD
# 1:    A    D  10   20       1        1     foo_bar
# 2:    B    E  30   40       1        1     baz_qux
# 3:    C    F  50   65       1        2 bla_xyz_meh

---

[from Matthew] +1 Some minor improvements to save repeating the same ==, and to demonstrate local variables inside j.

dt[, list(pre=mean(Val[.pre <- Type=="pre"]),     # save .pre
          post=mean(Val[.post <- Type=="post"]),  # save .post
          pre.num=sum(.pre),                      # reuse .pre
          post.num=sum(.post),                    # reuse .post
          ParD = paste(ParD, collapse="_")), 
by=list(Par1, Par2)]

#    Par1 Par2 pre post pre.num post.num        ParD
# 1:    A    D  10   20       1        1     foo_bar
# 2:    B    E  30   40       1        1     baz_qux
# 3:    C    F  50   65       1        2 bla_xyz_meh

dt[, { .pre <- Type=="pre"                  # or save .pre and .post up front 
       .post <- Type=="post"
       list(pre=mean(Val[.pre]), 
            post=mean(Val[.post]),
            pre.num=sum(.pre),
            post.num=sum(.post), 
            ParD = paste(ParD, collapse="_")) }
, by=list(Par1, Par2)]

#    Par1 Par2 pre post pre.num post.num        ParD
# 1:    A    D  10   20       1        1     foo_bar
# 2:    B    E  30   40       1        1     baz_qux
# 3:    C    F  50   65       1        2 bla_xyz_meh

And if a list column is ok rather than a paste, then this should be faster :

dt[, { .pre <- Type=="pre"
       .post <- Type=="post"
       list(pre=mean(Val[.pre]), 
            post=mean(Val[.post]),
            pre.num=sum(.pre),
            post.num=sum(.post), 
            ParD = list(ParD)) }     # list() faster than paste()
, by=list(Par1, Par2)]

#    Par1 Par2 pre post pre.num post.num        ParD
# 1:    A    D  10   20       1        1     foo,bar
# 2:    B    E  30   40       1        1     baz,qux
# 3:    C    F  50   65       1        2 bla,xyz,meh