从 R 中的包中编辑函数？

Question

我正在使用 R 中的 referenceIntervals 包进行一些数据分析。

特别是我正在使用计算参考和置信区间的 refLimit 函数。我想对其进行编辑以删除某些功能（例如，它运行 shapiro normalitiy 测试，如果数据大于 5000，它将停止整个代码，它不允许您对小于 120 的样本进行参数测试）。为此，我一直在终端中输入 refLimit - 复制函数定义，然后将其保存为单独的文件（以下是函数的完整原始定义）。

 singleRefLimit = 
function (data, dname = "default", out.method = "horn", out.rm = FALSE, 
    RI = "p", CI = "p", refConf = 0.95, limitConf = 0.9) 
{
    if (out.method == "dixon") {
        output = dixon.outliers(data)
    }
    else if (out.method == "cook") {
        output = cook.outliers(data)
    }
    else if (out.method == "vanderLoo") {
        output = vanderLoo.outliers(data)
    }
    else {
        output = horn.outliers(data)
    }
    if (out.rm == TRUE) {
        data = output$subset
    }
    outliers = output$outliers
    n = length(data)
    mean = mean(data, na.rm = TRUE)
    sd = sd(data, na.rm = TRUE)
    norm = NULL
    if (RI == "n") {
        methodRI = "Reference Interval calculated nonparametrically"
        data = sort(data)
        holder = nonparRI(data, indices = 1:length(data), refConf)
        lowerRefLimit = holder[1]
        upperRefLimit = holder[2]
        if (CI == "p") {
            CI = "n"
        }
    }
    if (RI == "r") {
        methodRI = "Reference Interval calculated using Robust algorithm"
        holder = robust(data, 1:length(data), refConf)
        lowerRefLimit = holder[1]
        upperRefLimit = holder[2]
        CI = "boot"
    }
    if (RI == "p") {
        methodRI = "Reference Interval calculated parametrically"
        methodCI = "Confidence Intervals calculated parametrically"
        refZ = qnorm(1 - ((1 - refConf)/2))
        limitZ = qnorm(1 - ((1 - limitConf)/2))
        lowerRefLimit = mean - refZ * sd
        upperRefLimit = mean + refZ * sd
        se = sqrt(((sd^2)/n) + (((refZ^2) * (sd^2))/(2 * n)))
        lowerRefLowLimit = lowerRefLimit - limitZ * se
        lowerRefUpperLimit = lowerRefLimit + limitZ * se
        upperRefLowLimit = upperRefLimit - limitZ * se
        upperRefUpperLimit = upperRefLimit + limitZ * se
        shap_normalcy = shapiro.test(data)
        shap_output = paste(c("Shapiro-Wilk: W = ", format(shap_normalcy$statistic, 
            digits = 6), ", p-value = ", format(shap_normalcy$p.value, 
            digits = 6)), collapse = "")
        ks_normalcy = suppressWarnings(ks.test(data, "pnorm", 
            m = mean, sd = sd))
        ks_output = paste(c("Kolmorgorov-Smirnov: D = ", format(ks_normalcy$statistic, 
            digits = 6), ", p-value = ", format(ks_normalcy$p.value, 
            digits = 6)), collapse = "")
        if (shap_normalcy$p.value < 0.05 | ks_normalcy$p.value < 
            0.05) {
            norm = list(shap_output, ks_output)
        }
        else {
            norm = list(shap_output, ks_output)
        }
    }
    if (CI == "n") {
        if (n < 120) {
            cat("\nSample size too small for non-parametric confidence intervals, \n    \t\tbootstrapping instead\n")
            CI = "boot"
        }
        else {
            methodCI = "Confidence Intervals calculated nonparametrically"
            ranks = nonparRanks[which(nonparRanks$SampleSize == 
                n), ]
            lowerRefLowLimit = data[ranks$Lower]
            lowerRefUpperLimit = data[ranks$Upper]
            upperRefLowLimit = data[(n + 1) - ranks$Upper]
            upperRefUpperLimit = data[(n + 1) - ranks$Lower]
        }
    }
    if (CI == "boot" & (RI == "n" | RI == "r")) {
        methodCI = "Confidence Intervals calculated by bootstrapping, R = 5000"
        if (RI == "n") {
            bootresult = boot::boot(data = data, statistic = nonparRI, 
                refConf = refConf, R = 5000)
        }
        if (RI == "r") {
            bootresult = boot::boot(data = data, statistic = robust, 
                refConf = refConf, R = 5000)
        }
        bootresultlower = boot::boot.ci(bootresult, conf = limitConf, 
            type = "basic", index = 1)
        bootresultupper = boot::boot.ci(bootresult, conf = limitConf, 
            type = "basic", index = 2)
        lowerRefLowLimit = bootresultlower$basic[4]
        lowerRefUpperLimit = bootresultlower$basic[5]
        upperRefLowLimit = bootresultupper$basic[4]
        upperRefUpperLimit = bootresultupper$basic[5]
    }
    RVAL = list(size = n, dname = dname, out.method = out.method, 
        out.rm = out.rm, outliers = outliers, methodRI = methodRI, 
        methodCI = methodCI, norm = norm, refConf = refConf, 
        limitConf = limitConf, Ref_Int = c(lowerRefLimit = lowerRefLimit, 
            upperRefLimit = upperRefLimit), Conf_Int = c(lowerRefLowLimit = lowerRefLowLimit, 
            lowerRefUpperLimit = lowerRefUpperLimit, upperRefLowLimit = upperRefLowLimit, 
            upperRefUpperLimit = upperRefUpperLimit))
    class(RVAL) = "interval"
    return(RVAL)
}

但是，当我随后执行此文件时，大量术语最终未定义，例如，当我使用函数时，我得到“找不到对象'nonparRanks'”。

如何编辑包中的函数？我已经研究过尝试重视包命名空间和环境，但这并没有帮助。我也尝试在我的目录中的包文件中找到实际功能，但无法找到。

我在 R 方面的经验相当丰富，但我以前从未编辑过包。我显然遗漏了一些关于如何在包中定义函数的内容，但我不确定是什么。

Answer 1

在package的开头有一行

data(sysdata, envir=environment())

请看这里：https://github.com/cran/referenceIntervals/tree/master/data/sysdata.rda

我怀疑“nonparRanks”是在那里定义的，因为我没有看到它在其他任何地方定义。所以也许你可以下载那个文件，编写你自己的函数，然后在运行你的函数之前运行同一行，它可能会工作。

编辑： 下载文件然后运行：

load("C:/sysdata.rda")

使用您的文件路径，然后您的功能将起作用。

Answer 2

nonparRanks 是referenceIntervals 包中的一个函数：

Table that dictate the ranks for the confidence intervals around thecalculated reference interval

您保存和编辑函数的方法很好，但请确保您也加载了所有必要的底层函数来运行它。

最简单的方法可能是：

1. 将复制和粘贴的 R 函数另存为其他名称，例如singleRefLimit2，然后
2. 调用library("referenceIntervals")，它将加载您需要的所有底层函数，然后
3. 加载你的函数source("singelRefLimit2.R")，无论你选择做什么编辑。