Hardcoding

Let’s briefly revisit Week 5: Review of Weeks 1 - 4

View the script we used to guide our review:

cat https://github.com/jhustata/basic/raw/main/review.do

Run the script to see its output:

do https://github.com/jhustata/basic/raw/main/review.do

This script creates output into a .log file. But HW5 asks you to additionally direct output into a .xlsx file. How may we adapt the script to this purpose? Yes, this is the key question of HW5. Many of you may have missed a tip for HW3 that recommended “hardcoding” as a template – a starting place. You may then gradually replace the hardcoded stuff with appropriate macros.

Hardcoding as a firststep. In this example:

1. We use the ds command, not(type string) option, and levelsof. These were only briefly mentioned in class, but were further discussed in Lab 5 Section 2.2

2. Nested loops and conditional code-blocks (e.g. if r(r) == 2) can be very empowering!

3. Gradually update your .do file script to replace hardcoded stuff (e.g. catlab), or stuff that isn’t publication worthy (e.g. v, which in this example is a variable name) with more appropriate macros or variable labels

4. The HW5 solution will walk you through such a process

5. Copy and paste your .do file script into a program. And adapt it to a more general purpose, beyond any specific dataset or variables

qui {
	cls
	use ${repo}transplants, clear
    ds, not(type string)  
	global threshold 9  
	putexcel set levelsof, replace 
	local row=2
    foreach v of varlist `r(varlist)' {
	    levelsof `v', local(numlevels)
	    if r(r) == 2 {  
			putexcel A`row' = ("`v'") B`row' = ("per")
			local row = `row' + 1
	    }
	    else if inrange(`r(r)', 3, $threshold) {  
			putexcel A`row' = ("`v', %") B`row' = ("")
			foreach l of numlist `numlevels' {
				local row = `row' + 1
                putexcel A`row' = ("    catlab") B`row' = ("per")
			}	
	    }
	    else {  
			putexcel A`row' = ("`v'") B`row' = ("m_iqr")
			local row = `row' + 1
	    }
		
    }
	
}

GPT-4 Session:

User: help add comments/annotation [paste the above script into ChatGPTs prompt]

ChatGPT: Sure, I can help you add comments and annotations to your Stata code to make it more understandable. Here’s your code with comments explaining each part:

qui {  // Quietly execute the following block of code
    cls  // Clear the screen
    use ${repo}transplants, clear  // Load dataset from specified repository and clear any previous data in memory
    ds, not(type string)  // List all variables that are not of string type
    global threshold 9  // Set a global threshold value of 9
    putexcel set levelsof, replace  // Set the Excel file for output with the name 'levelsof', replace if exists
    local row=2  // Initialize row variable for Excel output starting at row 2

    foreach v of varlist `r(varlist)' {  // Loop over the variables listed by the previous 'ds' command
        levelsof `v', local(numlevels)  // Get the levels of each variable and store them in local 'numlevels'
        if r(r) == 2 {  // If there are exactly two levels for the variable
            putexcel A`row' = ("`v'") B`row' = ("per")  // Write variable name in column A and 'per' in column B of Excel
            local row = `row' + 1  // Increment the Excel row counter
        }
        else if inrange(`r(r)', 3, $threshold) {  // If the number of levels is between 3 and the threshold
            putexcel A`row' = ("`v', %") B`row' = ("")  // Write variable name with a percent sign in column A, leave column B empty
            foreach l of numlist `numlevels' {  // Loop through each level of the variable
                local row = `row' + 1  // Increment row before writing
                putexcel A`row' = ("    catlab") B`row' = ("per")  // Indent 'catlab' in column A, write 'per' in column B
            }   
        }
        else {  // If the number of levels exceeds the threshold
            putexcel A`row' = ("`v'") B`row' = ("m_iqr")  // Write variable name in column A and 'm_iqr' in column B
            local row = `row' + 1  // Increment the row counter
        }
    }
}

In this script, you’re using a combination of putexcel commands and conditional logic to format and export information about variable levels from Stata to an Excel file. This can be very useful for data review and verification processes.