gaussplotR (version 0.2.5)

predict_gaussian_2D: Predict values from a fitted 2D-Gaussian

Description

Predict values from a fitted 2D-Gaussian

Usage

predict_gaussian_2D(fit_object, X_values, Y_values, ...)

Arguments

fit_object

Either the output of gaussplotR::fit_gaussian_2D() or a list that contains coefficients and fit methods (see Details).

X_values

vector of numeric values for the x-axis

Y_values

vector of numeric values for the y-axis

...

Additional arguments

Value

A data.frame with the supplied X_values and Y_values along with the predicted values of the 2D-Gaussian (predicted_values)

Details

This function assumes Gaussian parameters have been fitted beforehand. No fitting of parameters is done within this function; these can be supplied via the object created by gaussplotR::fit_gaussian_2D().

If fit_object is not an object created by gaussplotR::fit_gaussian_2D(), predict_gaussian_2D() attempts to parse fit_object as a list of two items. The coefficients of the fit must be supplied as a one-row, named data.frame within fit_object$coefs, and details of the methods for fitting the Gaussian must be contained as a character vector in fit_object$fit_method. This character vector in fit_object$fit_method must be a named vector that provides information about the method, amplitude constraint choice, and orientation constraint choice, using the names method, amplitude, and orientation. method must be one of: "elliptical", "elliptical_log", or "circular". amplitude and orientation must each be either "unconstrained" or "constrained". For example, c(method = "elliptical", amplitude = "unconstrained", orientation = "unconstrained"). One exception to this is when method = "circular", in which case orientation must be NA, e.g.: c(method = "circular", amplitude = "unconstrained", orientation = NA).

Examples

# NOT RUN {
if (interactive()) {
  ## Load the sample data set
  data(gaussplot_sample_data)

  ## The raw data we'd like to use are in columns 1:3
  samp_dat <-
    gaussplot_sample_data[,1:3]


  #### Example 1: Unconstrained elliptical ####
  ## This fits an unconstrained elliptical by default
  gauss_fit <-
    fit_gaussian_2D(samp_dat)

  ## Generate a grid of x- and y- values on which to predict
  grid <-
    expand.grid(X_values = seq(from = -5, to = 0, by = 0.1),
                Y_values = seq(from = -1, to = 4, by = 0.1))

  ## Predict the values using predict_gaussian_2D
  gauss_data <-
    predict_gaussian_2D(
      fit_object = gauss_fit,
      X_values = grid$X_values,
      Y_values = grid$Y_values,
    )

  ## Plot via ggplot2 and metR
  library(ggplot2); library(metR)
  ggplot_gaussian_2D(gauss_data)

  ## Produce a 3D plot via rgl
  rgl_gaussian_2D(gauss_data)


  #### Example 2: Constrained elliptical_log ####
  ## This fits a constrained elliptical, as in Priebe et al. 2003
  gauss_fit <-
    fit_gaussian_2D(
      samp_dat,
      method = "elliptical_log",
      constrain_orientation = -1
    )

  ## Generate a grid of x- and y- values on which to predict
  grid <-
    expand.grid(X_values = seq(from = -5, to = 0, by = 0.1),
                Y_values = seq(from = -1, to = 4, by = 0.1))

  ## Predict the values using predict_gaussian_2D
  gauss_data <-
    predict_gaussian_2D(
      fit_object = gauss_fit,
      X_values = grid$X_values,
      Y_values = grid$Y_values,
    )

  ## Plot via ggplot2 and metR
  ggplot_gaussian_2D(gauss_data)

  ## Produce a 3D plot via rgl
  rgl_gaussian_2D(gauss_data)
}
# }