GaussianSmooth: Calculate rolling Gaussian smooth of pollutant values

Description

This is a utility function designed to calculate rolling Gaussian smooth (kernel smoothing). The function will try and fill in missing time gaps to get a full time sequence but return a data frame with the same number of rows supplied.

Usage

GaussianSmooth(
  mydata,
  pollutant = "o3",
  sigma = 24L,
  type = "default",
  data.thresh = 0,
  new.name = NULL,
  date.pad = FALSE,
  ...
)

Value

A tibble with two new columns for the Gaussian smooth value.

Arguments

mydata: A data frame containing a date field. mydata must contain a date field in Date or POSIXct format. The input time series must be regular, e.g., hourly, daily.
pollutant: The name of a pollutant, e.g., pollutant = "o3". More than one pollutant can be supplied as a vector, e.g., pollutant = c("o3", "nox").
sigma: The value of sigma to use in the Gaussian.
type: Used for splitting the data further. Passed to cutData().
data.thresh: The % data capture threshold. No values are calculated if data capture over the period of interest is less than this value.
new.name: The name given to the new column(s). If not supplied it will create a name based on the name of the pollutant and the averaging period used.
date.pad: Should missing dates be padded? Default is FALSE.
...: Passed to cutData() for use with type.

Author

David Carslaw

Details

The function provides centre-aligned smoothing out to 3 sigma, which captures 99.7% of the data.

Examples

Run this code

# Gaussian smoother with sigma = 24
mydata <- GaussianSmooth(mydata,
  pollutant = "o3", sigma = 24, data.thresh = 75)

Run the code above in your browser using DataLab