[R] choose the lines2

[arun]

HI,
You can do this:

dat1<- read.csv("dat7.csv",header=TRUE,stringsAsFactors=FALSE,sep="\t")
dat.bru<- dat1[!is.na(dat1$evnmt_brutal),]


fun2<- function(dat){  
      lst1<- split(dat,dat$patient_id)
    lst2<- lapply(lst1,function(x) x[cumsum(x$evnmt_brutal==0)>0,])
    lst3<- lapply(lst2,function(x) x[!(all(x$evnmt_brutal==1)|all(x$evnmt_brutal==0)),])
    lst4<- lst3[lapply(lst3,nrow)!=0]
    lst5<- lapply(seq_along(lst4),function(i){
                     do.call(rbind,lapply(which(lst4[[i]]$evnmt_brutal==1),function(x) {
                                        x1<-c(x-2,x-1,x)
                                        x2<-x1[!any(x1==0)]
                                        x3<-lst4[[i]][x2,]
                                        x4<-x3[!is.na(match(paste(x3$evnmt_brutal,collapse=""),"001")),]
                                        x4[!any(duplicated(x4$number))]
                                        }
                                        ))
                                    })
   lst6<-lst5[lapply(lst5,nrow)!=0]
   names(lst6)<- unlist(lapply(lst6,function(x) unique(x$patient_id)))
   Mean_01<-do.call(rbind,lapply(lst6,function(x) cbind(Mean_Middle0=mean(x[seq(nrow(x))%%3==2,"basdai_d"]),Mean_1=mean(x[seq(nrow(x))%%3==0,"basdai_d"]))))
rownames(Mean_01)<- names(lst6)

     lst7<-list(lst6,Mean_01)
   lst7
   #lapply(lst7,head,2)   
   }                  

fun2(dat.bru)
head(fun2(dat.bru)[[1]],3)
#$`2`
#    X patient_id number responsed_at  t basdai_d evnmt_brutal
#13 13          2     12   2011-07-05 12     -1.0            0
#14 14          2     13   2011-08-07 13      0.9            0
#15 15          2     14   2011-09-11 14     -0.8            1
#
#$`5`
 #   X patient_id number responsed_at t basdai_d evnmt_brutal
#52 52          5      8   2011-01-11 7     -2.8            0
#53 53          5      9   2011-02-13 8      0.0            0
#54 54          5     10   2011-03-19 9     -1.2            1
#
#$`6`
 #   X patient_id number responsed_at  t basdai_d evnmt_brutal
#74 74          6      9   2011-02-05  8     0.80            0
#75 75          6     10   2011-03-09  9     0.15            0
#76 76          6     11   2011-04-11 10    -0.45            1


 head(fun2(dat.bru)[[2]],3)
# Mean_Middle0 Mean_1
#2         0.90  -0.80
#5         0.00  -1.20
#6         0.15  -0.45

res1<- fun2(dat.bru)[[1]]

lapply(res1,function(x) tail(x,-1))[1:3]
#$`2`
 #   X patient_id number responsed_at  t basdai_d evnmt_brutal
#14 14          2     13   2011-08-07 13      0.9            0
#15 15          2     14   2011-09-11 14     -0.8            1
#
#$`5`
 #   X patient_id number responsed_at t basdai_d evnmt_brutal
#53 53          5      9   2011-02-13 8      0.0            0
#54 54          5     10   2011-03-19 9     -1.2            1
#
#$`6`
 #   X patient_id number responsed_at  t basdai_d evnmt_brutal
#75 75          6     10   2011-03-09  9     0.15            0
#76 76          6     11   2011-04-11 10    -0.45            1

#or
res11<-do.call(rbind,lapply(res1,function(x) tail(x,-1)))
row.names(res11)<-1:nrow(res11)

A.K.
________________________________
From: GUANGUAN LUO <guanguanluo at gmail.com>
To: arun <smartpink111 at yahoo.com> 
Sent: Tuesday, June 4, 2013 2:10 PM
Subject: choose the lines2



13 2 12 2011/7/5 12 -1 0 
14 2 13 2011/8/7 13 0.9 0 
15 2 14 2011/9/11 14 -0.8 1 
52 5 8 2011/1/11 7 -2.8 0 
53 5 9 2011/2/13 8 0 0 
54 5 10 2011/3/19 9 -1.2 1 
74 6 9 2011/2/5 8 0.8 0 
75 6 10 2011/3/9 9 0.15 0 
76 6 11 2011/4/11 10 -0.45 1 

those are the result which i want, and then i want to choose like this










14 2 13 2011/8/7 13 0.9 0 
15 2 14 2011/9/11 14 -0.8 1 








53 5 9 2011/2/13 8 0 0 
54 5 10 2011/3/19 9 -1.2 1 








75 6 10 2011/3/9 9 0.15 0 
76 6 11 2011/4/11 10 -0.45 1






















so that i can calculate the mean of the lines with evnmt_brutal ==0 and compare with the lines with evnmt_brutal==1