Seeking well-commented versions of mgcv source code [closed]

Question

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.

---

Questions asking us to recommend or find a tool, library or favorite off-site resource are off-topic for Stack Overflow as they tend to attract opinionated answers and spam. Instead, describe the problem and what has been done so far to solve it.

Closed 9 years ago.

Improve this question

Apologies for cross-posting (on R-help) but SO gets more views, and I hope someone who knows might find the question here.

I'm looking for well-commented versions of various functions comprising mgcv, so that I can modify a piece of it for a project I'm working on. In particular I'm looking for

• testStat
• summary.gam
• liu2
• simf

I know that I can find these by typing mgcv:::whatever. But there are a lot of nested if statements, making it difficult to follow. Comments in the code describing exactly what is happening at each step would make my life a lot easier.

Where can I find more-detailed versions of the code? Do such things exist?

EDIT: In response to the deleted comment: I didn't know that it could be found on github, not having used it before. FFR, it's here: https://github.com/cran/mgcv

Answer 1

Have you searched GitHub for any of the source code? There is commented code there. I found testStat in the mgcv.r file.

---

Here are a couple of suggestions that help me understand complex code:

(1) Write the source to a text file so you can space it out, move things around, etc.

> sink("testStat.txt")
> mgcv:::testStat
> sink()

(2) Break its body into a list of its parts

> x <- as.list(body(mgcv:::testStat))
> x
[[1]]
`{`

[[2]]
qrx <- qr(X, tol = 0)

 ...

[[19]]
if (nu > 0) {
    if (k1 == 1) 
        rank1 <- val <- 1
    else {
        val <- rep(1, k1)
        rp <- nu + 1
        val[k] <- (rp + sqrt(rp * (2 - rp)))/2
        val[k1] <- (rp - val[k])
    }
    if (res.df <= 0) 
        pval <- liu2(d, val)
    else pval <- simf(d, val, res.df)
} else {
    pval <- 2
}

 ...

[[21]]
list(stat = d, pval = min(1, pval), rank = rank)