[R] screen

Thu Mar 16 15:56:43 CET 2017

Sorry. I focused on the table and not the record selection. Given the table this seems to be what you are looking for, but there may be an easier way:

> keep <- which(t(apply(DF2.tbl, 1, cumsum)) > .000001, arr.ind=TRUE)
> keep <- keep[order(keep[, 1], keep[, 2]), ]
> keep # These are the records you want to keep
  family time
A      1    2
A      1    3
A      1    4
B      2    1
B      2    2
B      2    3
B      2    4
C      3    4
# Now turn keep into a data.frame with factors: family and time
# so it matches DF2
> rownames(keep) <- NULL
> keep <- data.frame(keep)
> keep$family <- factor(keep$family, labels=levels(DF2$family))
> keep$time <- factor(keep$time, labels=levels(DF2$time))
> keep
  family  time
1      A WEEK2
2      A WEEK3
3      A WEEK4
4      B WEEK1
5      B WEEK2
6      B WEEK3
7      B WEEK4
8      C WEEK4
> DF2.new <- merge(DF2, keep)
> DF2.new
   family  time obs
1       A WEEK2   0
2       A WEEK2   1
3       A WEEK3   1
4       A WEEK3   0
5       B WEEK1   0
6       B WEEK1   1
7       B WEEK1   1
8       B WEEK2   0
9       B WEEK2   0
10      B WEEK3   1
11      B WEEK3   0
12      C WEEK4   1
13      C WEEK4   1

-------------------------------------
David L Carlson
Department of Anthropology
Texas A&M University
College Station, TX 77840-4352

-----Original Message-----
From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of David L Carlson
Sent: Thursday, March 16, 2017 9:01 AM
To: Val <valkremk at gmail.com>; r-help at R-project.org (r-help at r-project.org) <r-help at r-project.org>
Subject: Re: [R] screen

Something like this?

> DF2.agg <- aggregate(DF2$obs, DF2[, c("family", "time")], mean)
> DF2.tbl <- xtabs(x~family+time, DF2.agg)
> DF2.tbl      time
family WEEK1 WEEK2 WEEK3 WEEK4
     A  0.00  0.50  0.50  0.00
     B  0.67  0.00  0.50  0.00
     C  0.00  0.00  0.00  1.00

You can get closer to the output in your example with this

> suppressWarnings(as.table(formatC(DF2.tbl, digits=2, width=4, zero.print=".")))
      time
family WEEK1 WEEK2 WEEK3 WEEK4
     A    .   0.5   0.5     . 
     B 0.67     .   0.5     . 
     C    .     .     .     1

-------------------------------------
David L Carlson
Department of Anthropology
Texas A&M University
College Station, TX 77840-4352

-----Original Message-----
From: R-help [mailto:r-help-bounces at r-project.org] On Behalf Of Val
Sent: Wednesday, March 15, 2017 5:41 PM
To: r-help at R-project.org (r-help at r-project.org) <r-help at r-project.org>
Subject: [R] screen

HI all,

I have some data to be screened  based on the recording flag (obs).
Some family recorded properly (1) and others not (0).  Th 0 = improper
and 1 = proper

The recording  period starts week1.  All families may not start in the
same week in recording properly an observation,

  DF2 <- read.table(header=TRUE, text='family time obs
A  WEEK1 0
A  WEEK1 0
A  WEEK1 0
A  WEEK2 1
A  WEEK2 0
A  WEEK3 1
A  WEEK3 0
B  WEEK1 1
B  WEEK1 0
B  WEEK1 1
B  WEEK2 0
B  WEEK2 0
B  WEEK3 1
B  WEEK3 0
C  WEEK3 0
C  WEEK3 0
C  WEEK4 1
C  WEEK4 1')

Example, in week1  all records of family "A" are 0 (improper), but
starting the week2 they start recording proper (1) records as well.
Then I create a table that shows me the ratio of proper records to the
total records for each family within week. If the ratio is zero and
there is no prior proper recordings for that family then I want to
delete those records.

However,  once any family started showing proper records  as "1"  and
even if in the  the subsequent week the ratio is 0  then I want keep
that record for that family. Example records of week2 for family B

Here is the summary table

      WEEK1      WEEK2    WEEK3    WEEK4
A          0            0.5              0.5           .
B       0.33           0                0.5           .
C          .               .                 0            1

>From the above table
For A-  I want exclude all records of week1 and keep the rest. Because
they were not recording it propeller
For B-  Keep all records, as they stated recording properly from the beginning.
For C-  Keep only the week4 records because all records are  1's

Final and desired  result will be

A WEEK2 1
A WEEK2 0
A WEEK3 1
A WEEK3 0
B WEEK1 1
B WEEK1 0
B WEEK1 1
B WEEK2 0
B WEEK2 0
B WEEK3 1
B WEEK3 0
C WEEK4 1
C WEEK4 1

and the summary table looks like as follows

       WEEK1  WEEK2  WEEK3  WEEK4
A             .        0.5             0.5        .
B          0.33        0             0.5        .
C               .          .                 .        1

Thank you in advance

______________________________________________
R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.