An appropriate example case is water quality data that is measured at irregular time intervals. Regulatory compliance is often based on a statistical average measure or exceedance probability applied to all samples collected in the previous 7-years. tbrf can be used to display regulatory status at any sample point.
tbrf identifies the previous n measurements within the specified time window, applies the function, and outputs a variable with the result of the rolling statistical measure.
Installation
tbrf is available on CRAN:
The development version is maintained on github and can be installed as:
Available Functions
tbr_binom: Rolling binomial probability with confidence intervals.tbr_gmean: Rolling geometric mean with confidence intervals.tbr_mean: Rolling mean with confidence intervals.tbr_median: Rolling median with confidence intervals.tbr_misc: Accepts user specified function.tbr_sd: Rolling standard deviation.tbr_sum: Rolling sum.
Example
Plot a rolling 1-hour mean:
library(tbrf)
library(dplyr)
library(ggplot2)
library(ggalt)
y = 3 * sin(2 * seq(from = 0, to = 4*pi, length.out = 100)) + rnorm(100)
time = sample(seq(as.POSIXct(strptime("2017-01-01 00:01:00", "%Y-%m-%d %H:%M:%S")),
as.POSIXct(strptime("2017-01-01 23:00:00", "%Y-%m-%d %H:%M:%S")),
by = "min"), 100)
df <- tibble(y, time)
df %>%
tbr_mean(y, time, "hours", n = 1) %>%
ggplot() +
geom_point(aes(time, y)) +
geom_step(aes(time, mean))
Plot a rolling 3-hour mean:
df %>%
tbr_mean(y, time, "hours", n = 3) %>%
ggplot() +
geom_point(aes(time, y)) +
geom_step(aes(time, mean))
Contributing
Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
License
tbrf code is released under GPL-3 | LICENSE.md
binom_ci() is an implementation of code licensed under GPL (>=2) by Frank Harrell’s Hmisc package.
If you can cite the use of this software, please use citation("tbrf") 
Test Results
library(tbrf)
date()
## [1] "Mon May 18 19:33:59 2020"
devtools::test()
## ✔ | OK [31mF[39m [35mW[39m [34mS[39m | Context
## ⠏ | 0 | core functions work in piped workflow⠋ | 1 | core functions work in piped workflow⠹ | 3 | core functions work in piped workflow⠴ | 6 | core functions work in piped workflow[32m✔[39m | 6 | core functions work in piped workflow[36m [0.4 s][39m
## ⠏ | 0 | core functions return expected errors and messages⠼ | 5 | core functions return expected errors and messages[32m✔[39m | 7 | core functions return expected errors and messages[36m [0.1 s][39m
## ⠏ | 0 | core functions return expected structures and values⠋ | 0 1 | core functions return expected structures and values⠸ | 3 1 | core functions return expected structures and values⠴ | 5 1 | core functions return expected structures and values⠦ | 6 1 | core functions return expected structures and values[32m✔[39m | 6 1 | core functions return expected structures and values[36m [1.6 s][39m
## ────────────────────────────────────────────────────────────────────────────────
## [1mtest-expectedValues.R:26: [35mwarning[39m: tbr_mean provides same results as mean[22m
## Column `results` has different attributes on LHS and RHS of join
## ────────────────────────────────────────────────────────────────────────────────
## ⠏ | 0 | internal statistical functions return expected values⠙ | 2 | internal statistical functions return expected values⠹ | 3 | internal statistical functions return expected values⠼ | 5 | internal statistical functions return expected values⠇ | 9 | internal statistical functions return expected values⠦ | 17 | internal statistical functions return expected values[32m✔[39m | 17 | internal statistical functions return expected values[36m [0.9 s][39m
##
## ══ [1mResults[22m ═════════════════════════════════════════════════════════════════════
## [36mDuration: 3.1 s[39m
##
## OK: [32m36[39m
## Failed: [32m0[39m
## Warnings: [35m1[39m
## Skipped: [32m0[39m
