Friday, November 23, 2012

Stata tip: plotting the output of the tab function

UPDATE2: I updated this to allow for "if" and "in"

UPDATE: I updated this to preserve the value labels. So var2 (the second variable in your variable list) must have a value label attached to it.

Suppose you want to plot the output of the two-way tab function? Here is a program that will do it (see below). It is actually a wrapper for the tabout command. Some notes about the options:

using: put here the name of the filename that you want to save the tabout data to, in tab separated format. The graphs that this command produces will save graphs using the same filename but with different extension.

gc: this stands for graph command. You can use gc("graph bar"), gc("graph hbar")... and maybe others

go: this stands for graph options. These are the options that you would use for the graph command above (e.g. note, title, b1title, subtitle, etc)

ta: this stands for tabout options. These are the options you would use with the tabout command (e.g. c(), f(), etc.)


taboutgraph var1 var2 [aw=weight] using "filename_to_savedatato.csv", gc("graph bar") ta(cells(col) f(2 2 2 2)) replace go( note("Source: XXX") b1title("Quintile") title(`"Composition of Population"') ytitle("Percent of population in the quntile"))


program define taboutgraph

    // Written by Shafique Jamal (
    // This program requires that the second variable in varlist have a value label attached to it
    // It plots the column output of the tabout command

    syntax varlist(min=2 max=2) [if] [in] using/ [aweight], GCmd(string) GOptions(string asis) TAboutoptions(string asis) [replace overcategorysuboptions(string asis) overxsuboptions(string asis)]
    version 9.1
    marksample touse
    // di `"`0'"'
    cap drop _v*
    // cap ssc install lstrfun
    // first generate the table
    tabout `varlist' [`weight'`exp'] if `touse' using `using', `replace' `taboutoptions'
    di `"tabout [`weight'`exp'] `varlist' if `touse' using `using', `replace'"'
    local number_of_rows    = r(r)
    local number_of_columns = r(c)
    return list
    // get the filename
    di `"regexm:"'
    di regexm(`"`using'"',`"((.*)\.(.+))$"')
    if (regexm(`"`using'"',`"((.*)\.(.+))$"')) {
        local pathtofile_original            = regexs(1)
        local pathtofile_withoutextension    = regexs(2)
        local pathtofile_extension            = regexs(3)
    di `"pathtofile_original:`pathtofile_original'"'
    di `"pathtofile_withoutextension:`pathtofile_withoutextension'"'
    di `"pathtofile_extension:`pathtofile_extension'"'
    // open the file and process it.
    local count = 0
    tempname fhr
    tempname fhw
    tempfile tf
    file open `fhr' using `"`pathtofile_original'"', r
    // ---------------------------
    // file open `fhw' using `"$WHO_KG_reports/tempfile.csv"', t write all replace
    file open `fhw' using `"`tf'"', t write all replace
    local count = `count' + 1

    // First line is variable label.
    file read `fhr' line
    return list
    local count = 1
    while r(eof)==0 {
        local count = `count' + 1
        // di `"count = `count'"'
        file read `fhr' line
        if (`count'~=3) { // This line is units - we can throw this away
            file write `fhw' `"`line'"' _n
            // di `"`line'"'
    file close `fhr'
    file close `fhw'
    // We should save the value labels. Check to make sure that the label exists
    tempfile tfvaluelabels
    tempname nameofvaluelabel
    tempname variablenamewithlabel
    local `variablenamewithlabel' : word 2 of `varlist'
    local `nameofvaluelabel' : value label ``variablenamewithlabel''
    label save ``nameofvaluelabel'' using `"`tfvaluelabels'"', replace
    qui insheet using `"`tf'"', t clear names
    // I want to restore the value levels and value labels
    do `"`tfvaluelabels'"'
    // ssc install labellist
    // levelsof ``nameofvaluelabel'', local(levels)
    labellist ``nameofvaluelabel''
    local levels = r(``nameofvaluelabel''_values)
    local labels = r(``nameofvaluelabel''_labels)
    save `"`pathtofile_withoutextension'_short.dta"', replace

    drop total
    drop if _n == _N
    local count = 0
    local count_levels = 0
    foreach var of varlist * {
        local count = `count' + 1
        if (`count'==1) {
            qui rename `var' x
        else {
            local count_levels = `count_levels' + 1
            local level : word `count_levels' of `levels'
            qui rename `var' _v`level'
            // qui rename `var' _v`count'
            local v`level'_labelforfilename = `"`var'"'           // used for the filename for saving graphs of individual variables
            local v`level'_varlabel : variable label _v`level'    // used for the subtitle in the plot of individual variables.
    // graph each y var, then all y vars
    foreach level of local levels {
        `gcmd' (asis) _v`level', over(x, ) `goptions' subtitle(`"`v`level'_varlabel'"')
        graph export "`pathtofile_withoutextension'_`v`level'_labelforfilename'.pdf", replace
    forv x = 2/`count' {
        `gcmd' (asis) _v`x', over(x) `goptions' subtitle(`"`v`x'_varlabel'"')
        // di `"subtitle: subtitle(`"`v`x'_varlabel'"'), `v`x'_varlabel', v`x'_varlabel"'
        graph export "`pathtofile_withoutextension'_`v`x'_labelforfilename'.pdf", replace
    // graph all yvars
    qui reshape long _v, i(x) j(category)
    // cap tostring category, replace
    label values category ``nameofvaluelabel''

    forv x = 2/`count' {
    qui replace category = `"`v`x'_varlabel'"' if category == `"`x'"'
    `gcmd' (asis) _v, over(category, `overcategorysuboptions') over(x, `overxsuboptions') asyvars `goptions'
    graph export "`pathtofile_withoutextension'_allvars.pdf", replace
    save `"`pathtofile_withoutextension'_long.dta"', replace
end program

No comments: