Skip to contents

Apply Smoothing Kernel in Parallel

Source: R/future_kernapply.R
future_kernapply.Rd

future_kernapply() is a futurized version of stats::kernapply(), i.e. it computes, in parallel, the convolution between an input sequence and a specific kernel. Parallelization takes place over columns when x is a matrix, including a ts matrix.

Usage

future_kernapply(x, ...)

# Default S3 method
future_kernapply(x, k, circular = FALSE, ...)

# S3 method for class 'ts'
future_kernapply(x, k, circular = FALSE, ...)

Arguments

x

an input vector, matrix, time series or kernel to be smoothed.

...

arguments passed to or from other methods.

k

smoothing "tskernel" object.

circular

a logical indicating whether the input sequence to be smoothed is treated as circular, i.e., periodic.

Value

See stats::kernapply() for details.

Examples

library(datasets)
library(stats)

X <- EuStockMarkets[, 1:2]
k <- kernel("daniell", 50)  # a long moving average
X_smooth <- future_kernapply(X, k = k)