hydroPSO (version 0.2-0)

ReadPlot_params: Reading/Plotting the values of different parameter sets

Description

This function reads a file containing different parameter sets and their corresponding goodness-of-fit values The following values of file set default values for header, skip and param.cols: -) modelpara.out, created by the GLUE algorithm of SWAT-CUP, -) modelpara.beh, created by the GLUE algorithm of SWAT-CUP, -) goal.sf2, created by the SUFI-2 algorithm of SWAT-CUP -) goal.pso, created by the PSO algorithm of SWAT-CUP -) ParameterValues.log, created by Nimbus calibration tool (Lisflood model) header and skip are automatically set, in other case, they need to be provided

Usage

read_params(file, ...) 
## S3 method for class 'default':
read_params(file, header=TRUE, skip=0, param.cols, param.names,
     of.col=NULL, of.name="GoF", na.strings="-9999", plot=TRUE, 
     ptype=c("histogram", "dottyplot", "boxplot", "vioplot", "pairs"), 
     MinMax=NULL, beh.thr=NA, beh.col="red", beh.lty=1, beh.lwd=2, 
     nrows="auto", col="#00000030", ylab=of.name, main=NULL, pch=19, 
     cex=0.5, cex.main=1.5, cex.axis=1.5, cex.lab=1.5, 
     breaks="Scott", freq=TRUE, verbose=TRUE, ..., do.png=FALSE, 
     png.width=1500, png.height=900, png.res=90, png.fname="Parameters.png")
plot_params(params, ...)  
         
## S3 method for class 'default':
plot_params(params, gofs=NULL, 
     ptype=c("histogram", "dottyplot", "boxplot", "vioplot", "pairs"),  
     param.cols=1:ncol(params), param.names=colnames(params), of.name="GoF", 
     MinMax=NULL, beh.thr=NA,  beh.col="red", beh.lty=1, beh.lwd=2, 
     nrows="auto", col="#00000030", ylab=of.name, main=NULL, pch=19, cex=0.5, 
     cex.main=1.5, cex.axis=1.5, cex.lab=1.5, breaks="Scott", freq=TRUE,
     verbose=TRUE, ..., do.png=FALSE, png.width=1500, png.height=900,
     png.res=90, png.fname="Parameters.png")
     
## S3 method for class 'data.frame':
plot_params(params, gofs=NULL, 
     ptype=c("histogram", "dottyplot", "boxplot", "vioplot", "pairs"),  
     param.cols=1:ncol(params), param.names=colnames(params), of.name="GoF", 
     MinMax=NULL, beh.thr=NA,  beh.col="red", beh.lty=1, beh.lwd=2, 
     nrows="auto", col="#00000030", ylab=of.name, main=NULL, pch=19, cex=0.5, 
     cex.main=1.5, cex.axis=1.5, cex.lab=1.5, breaks="Scott", freq=TRUE,
     verbose=TRUE, ..., do.png=FALSE, png.width=1500, png.height=900,
     png.res=90, png.fname="Parameters.png")
     
## S3 method for class 'matrix':
plot_params(params, gofs=NULL, 
     ptype=c("histogram", "dottyplot", "boxplot", "vioplot", "pairs"),  
     param.cols=1:ncol(params), param.names=colnames(params), of.name="GoF", 
     MinMax=NULL, beh.thr=NA,  beh.col="red", beh.lty=1, beh.lwd=2, 
     nrows="auto", col="#00000030", ylab=of.name, main=NULL, pch=19, cex=0.5, 
     cex.main=1.5, cex.axis=1.5, cex.lab=1.5, breaks="Scott", freq=TRUE, 
     verbose=TRUE, ..., do.png=FALSE, png.width=1500, png.height=900,
     png.res=90, png.fname="Parameters.png")

Arguments

file

character, name (including path) of the file containing the results

params

data.frame whose rows represent the values of different parameter sets

gofs

OPTIONAL. numeric with the values of goodness-of-fit values for each one of the parameters in params (in the same order!)

header

logical, indicates whether the file contains the names of the variables as its first line If file is in c('modelpara.out', 'modelpara.beh', 'goal.sf2', 'goal.pso', 'ParameterValues.log') then header is automatically s

skip

numeric (integer), lines of the data file to skip before beginning to read data If file is in c('modelpara.out', 'modelpara.beh', 'goal.sf2', 'goal.pso', 'ParameterValues.log') then skip is automatically set

param.cols

numeric, number of the columns in file that store the values of each parameter

param.names

character, name of the parameters defined by param.cols

of.col

OPTIONAL. numeric, number of the column in file that store the values of objective function

of.name

OPTIONAL. Only used when of.col is provided. character, name that will be given to the column of.col

na.strings

character, string which is to be interpreted as NA values. read.table

plot

logical, indicates if a dotty-plot with the parameter values versus the objective function has to be produced

ptype

OPTIONAL. Only used when plot=TRUE character, indicating the type of plot to be done. It must be in: -) dottyplot: dotty plots for each parameter in params or file, with the value of the objective functi

MinMax

OPTIONAL character, indicates whether the optimum value in params corresponds to the minimum or maximum of the the objective function given in of.col. It is used to filter out model outputs with a non-acceptable performance Val

beh.thr

OPTIONAL numeric, threshold value used for selecting parameter sets that have to be used in the analysis (behavioural parameters, using the GLUE terminology) If MinMax='min', only parameter sets with a goodness-of-fit value

beh.col

OPTIONAL. Only used when plot=TRUE character, colour for drawing a horizontal line for separating behavioural from non behavioural parameter sets

beh.lty

OPTIONAL. Only used when plot=TRUE numeric, line type for drawing a horizontal line for separating behavioural from non behavioural parameter sets

beh.lwd

OPTIONAL. Only used when plot=TRUE numeric, width for drawing a horizontal line for separating behavioural from non behavioural parameter sets

nrows

OPTIONAL. Only used when plot=TRUE numeric, number of rows to be used in the plotting window If nrowsis set to auto, the number of rows is automatically computed depending on the number of columns of params

col

OPTIONAL. Only used when plot=TRUE character, colour to be used for drawing the points of the dotty plots

ylab

OPTIONAL. Only used when plot=TRUE character, label for the 'y' axis

main

chracter, title for the plot

pch

OPTIONAL. Only used when plot=TRUE numeric, type of symbol to be used for drawing the points of the dotty plots (e.g., 1: white circle)

cex

OPTIONAL. Only used when plot=TRUE numeric, values controlling the size of text and points with respect to the default

cex.main

OPTIONAL. Only used when plot=TRUE numeric, magnification for the main title relative to the current setting of cex

cex.axis

OPTIONAL. Only used when plot=TRUE numeric, magnification for axis annotation relative to the current setting of cex

cex.lab

OPTIONAL. Only used when plot=TRUE numeric, magnification for x and y labels relative to the current setting of cex

breaks

breaks used for plotting the histograms of the parameter sets. See hist

freq

logical, if TRUE, the histogram graphic is a representation of frequencies, the counts component of the result; if FALSE, probability densities, component density, are plotted (so that the histogram has a total area of one). See

verbose

logical, if TRUE, progress messages are printed

...

OPTIONAL. Only used when plot=TRUE further arguments passed to the plot command or from other methods

do.png

logical, indicates if the plot with the convergence measures has to be saved into a PNG file instead of the screen device

png.width

OPTIONAL. Only used when do.png=TRUE numeric, width of the device. See png

png.height

OPTIONAL. Only used when do.png=TRUE numeric, height of the device. See png

png.res

OPTIONAL. Only used when do.png=TRUE numeric, nominal resolution in ppi which will be recorded in the PNG file, if a positive integer of the device. See png

png.fname

OPTIONAL. Only used when do.png=TRUE character, name of the output PNG file. See png

Value

• A list with the following elements:
• params
  data.frame with the parameter sets tested during the optimisation
• gofs
  numeric with the fitness values computed during the optimisation (each element in 'gofs' corresponds to one row of 'params')

See Also

vioplot

Examples

# Number of dimensions to be optimised
nparam <- 4

# Setting the user home directory as working directory
setwd("~")

# Setting the seed
set.seed(100)

# Runing PSO with the 'sphere' test function, writing the results to text files
hydroPSO(
        fn= sphere, lower=rep(-100, nparam), upper=rep(100, nparam),
        control=list(npart=2*nparam, maxit=100, write2disk=TRUE, plot=TRUE)  
        ) 

# 1) reading ALL the parameter sets used in PSO, and histograms (by default)
params <- read_params(file="~/PSO.out/Particles.txt",  param.cols=4:7, of.col=3)

# 2) summary of the parameter sets and their goodness-
                    
# plotting the parameter sets as dotty plots
plot_params(params=params[["params"]], gofs=params[["gofs"]], 
            ptype="dottyplot", main=fn, MinMax="min", freq=TRUE)
                    
# plotting the parameter sets as boxplots                   
plot_params(params=params[["params"]], ptype="boxplot", MinMax="min")

# plotting the parameter sets as violing plots 
library(vioplot)
plot_params(params=params[["params"]], ptype="vioplot", MinMax="min")


# 2) reading only the parameter sets with a goodness-of-fit measure <= 'beh.thr', 
#    and dotty plots (by default)
params <- read_params(file="~/PSO.out/Particles.txt", param.cols=4:7, of.col=3, 
                      beh.thr=1000, MinMax="min")