EmbedDimension uses Simplex to evaluate
prediction accuracy as a function of embedding dimension.
EmbedDimension(dataFrame = NULL, columns, target, lib, pred, maxE = 10, Tp = 1,
tau = -1, exclusionRadius = 0, embedded = FALSE,
validLib = logical(0), noTime = FALSE, ignoreNan = TRUE,
numProcess = 4, pathIn = "./", dataFile = "", pathOut = "./",
predictFile = "", backend = "RANN",
parameterList = FALSE, showPlot = FALSE)A data.frame with columns E, rho.
A data.frame of input data. The first column must be a time
index or time values unless noTime = TRUE. The columns must be named.
Column name(s) to build the embedding: character vector or space-separated string.
Target column name to predict.
Library (training) index range as (start end) pairs.
Prediction index range as (start end) pairs.
Largest embedding dimension to evaluate.
Forecast interval (prediction horizon).
Embedding delay (negative selects past lags).
Temporal (Theiler) exclusion radius around each prediction point.
If TRUE, columns already form the embedding.
Logical vector marking admissible library rows (or length 0 for all).
If TRUE, synthesise a 1..N time index instead of using column 1.
Remove rows with NaN in the embedding from the library and prediction sets.
Number of worker processes for the parameter sweep or task grid.
File path for input dataFile.
Input dataFile, .csv format.
Output file path for predictFile
Output file name, .csv format.
Nearest-neighbour backend: "RANN" (default) or "brute".
Append named list of parameters/values to return.
If TRUE, draw a base-graphics plot of the result.
data(TentMap)
E.rho = EmbedDimension( dataFrame = TentMap, lib = "1 100", pred = "201 500",
columns = "TentMap", target = "TentMap", showPlot = FALSE )
Run the code above in your browser using DataLab