Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://github.com/serkor1/SLmetrics/issues/8 below:

[BUG] NA handling in classification metrics · Issue #8 · serkor1/SLmetrics · GitHub

Great job on the package! it has good performance.

when looking at the package, i noticed that it isn't clearly documented behavior with regards to how missing values are handled. From the limited testing, i see that for regression metrics you get an NA if there NAs in the input, but they are ignored in classification settings.

I wasn't able to find if this is expected, according to the documentation or not.

library(SLmetrics)
#> Loading {SLmetrics} v0.1.0

fct1 <- factor(c("yes", "no"))
fct2 <- factor(c("yes", "no"))

accuracy(fct1, fct2)
#> [1] 1

fct1[1] <- NA

accuracy(fct1, fct2)
#> [1] 0.5

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4