This function computes K functions from point process data then converts it into PCs. Note, if there are replicates, i.e. multiple observations per unit, the K functions will be a weighted average based on the number of the first agents.
Usage
getKsPCAData(
data,
outcome = colnames(data)[1],
unit = colnames(data)[5],
replicate = NULL,
rCheckVals = NULL,
nPCs = 3,
agents_df = as.data.frame(expand.grid(unique(data[, 4]), unique(data[, 4]))),
xRange = NULL,
yRange = NULL,
edgeCorrection = "isotropic",
nbasis = 21,
silent = FALSE,
displayTVE = FALSE
)Arguments
- data
Data.frame with column titles for at least outcome, x, y, agents, and unit. For consistency (and avoiding errors), use that order. Additionally, replicate can be added.
- outcome
(Optional) String of the column name in data indicating the outcome or response. Default is the 1st column.
- unit
(Optional) String of the column name in data indicating a unit or base thing. Note this unit may have replicates. Default is the 4th column.
- replicate
(Optional) String of the column name in data indicating the replicate id. Default is NULL.
- rCheckVals
(Optional) Numeric vector indicating the radius to check. Note, if not specified, this could take a lot of memory, particularly with many units and replicates.
- nPCs
(Optional) Numeric indicating the number of principal components.
- agents_df
(Optional) Two-column data.frame. The first for agent 1 and the second for agent 2. Both should be in data agents column. This determines which K functions to compute. Default is to compute all, but may be misspecified if the data is in a different order.
- xRange, yRange
(Optional) Two value numeric vector indicating the min and max x/y values. Note this is re-used for all replicates. The default just takes the min and max x from each replicate. This allows different sized images, but the edges are defined by some agent location.
- edgeCorrection
(Optional) String indicating type of edgeCorrection(s) to apply when computing the K functions. Options include: "border", "bord.modif", "isotropic", "Ripley", "translate", "translation", "periodic", "none", "best" or "all" selects all options.
- nbasis
(Optional) Numeric indicating number of basis functions to fit K functions in order to compute PCA. Current implementation uses a b-spline basis.
- silent
(Optional) Boolean indicating if progress should be printed.
- displayTVE
(Optional) Boolean to indicate if total variance explained (TVE) should be displayed. Default is FALSE.
Examples
dataPCA_pheno <- getKsPCAData(
data = TNBC_pheno, unit = "Person",
agents_df = data.frame(rep("B", 2), c("Tumor", "Fake")),
nPCs = 3,
rCheckVals = seq(0, 50, 1),
displayTVE = TRUE
)
#> PCA Pairs (2): 1 (TVE: 0.997), 2