From d3834a1fa329763062b2885391e962cb111fc44a Mon Sep 17 00:00:00 2001 From: Andreas Madsen Date: Sat, 27 Aug 2016 13:27:02 +0200 Subject: benchmark: ignore significance when using --runs 1 Because the standard deviation can't be calculated when there is only one observation the R scripts raises an error. However it may still be useful to run them for non-statistical purposes. This changes the behaviour such when there is only one observation, the values that depends on the standard deviation becomes Not Applicable (NA). Fixes: https://github.com/nodejs/node/issues/8288 PR-URL: https://github.com/nodejs/node/pull/8299 Reviewed-By: Anna Henningsen --- benchmark/scatter.R | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'benchmark/scatter.R') diff --git a/benchmark/scatter.R b/benchmark/scatter.R index 7b98611482..10e099e430 100644 --- a/benchmark/scatter.R +++ b/benchmark/scatter.R @@ -51,13 +51,17 @@ if (length(aggregate) > 0) { stats = ddply(dat, c(x.axis.name, category.name), function(subdat) { rate = subdat$rate; - # calculate standard error of the mean - se = sqrt(var(rate)/length(rate)); + # calculate confidence interval of the mean + ci = NA; + if (length(rate) > 1) { + se = sqrt(var(rate)/length(rate)); + ci = se * qt(0.975, length(rate) - 1) + } # calculate mean and 95 % confidence interval r = list( rate = mean(rate), - confidence.interval = se * qt(0.975, length(rate) - 1) + confidence.interval = ci ); return(data.frame(r)); @@ -66,11 +70,14 @@ stats = ddply(dat, c(x.axis.name, category.name), function(subdat) { print(stats, row.names=F); if (!is.null(plot.filename)) { - p = ggplot(stats, aes_string(x=x.axis.name, y='mean', colour=category.name)); + p = ggplot(stats, aes_string(x=x.axis.name, y='rate', colour=category.name)); if (use.log2) { p = p + scale_x_continuous(trans='log2'); } - p = p + geom_errorbar(aes(ymin=mean-confidence.interval, ymax=mean+confidence.interval), width=.1); + p = p + geom_errorbar( + aes(ymin=rate-confidence.interval, ymax=rate+confidence.interval), + width=.1, na.rm=TRUE + ); p = p + geom_point(); p = p + ylab("rate of operations (higher is better)"); p = p + ggtitle(dat[1, 1]); -- cgit v1.2.3