Merge pull request #107 from bleutner/dev

Dev

DESCRIPTION

@@ -41,5 +41,5 @@ Suggests:
 LinkingTo: Rcpp,
     RcppArmadillo
 License: GPL (>=3)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 LazyData: true

R/RStoolbox.R

@@ -62,7 +62,7 @@
 #' @importFrom grDevices hsv
 #' @useDynLib RStoolbox
 #' @importFrom Rcpp sourceCpp
-#' @docType package
+#' @docType _PACKAGE
 #' @name RStoolbox
 NULL
 
@@ -100,5 +100,17 @@ NULL
 #' @keywords datasets
 #' @name lsat
 #' @examples
-#' ggRGB(lsat, stretch = "lin")
+#' ggRGB(lsat, stretch = "sqrt")
+NULL
+
+#' Sentinel 2 MSI L2A Scene
+#'
+#' Contains all 13 bands in already converted spectral reflectances
+#'
+#' @usage sen2
+#' @docType data
+#' @keywords datasets
+#' @name sen2
+#' @examples
+#' ggRGB(sen2, r=4, g=3, b=2, stretch = "lin")
 NULL

R/classifyQA.R

@@ -2,7 +2,7 @@
 #' 
 #' extracts five classes from QA band: background, cloud, cirrus, snow and water.
 #' 
-#' @param img RasterLayer or SpatRaster. Landsat 8 OLI QA band.
+#' @param img SpatRaster. Landsat 8 OLI QA band.
 #' @param type Character. Classes which should be returned. One or more of c("background", "cloud", "cirrus","snow", "water").
 #' @param confLayers Logical. Return one layer per class classified by confidence levels, i.e. cloud:low, cloud:med, cloud:high.
 #' @param ... further arguments passed to \link[terra]{writeRaster}

R/cloudMask.R

@@ -4,7 +4,7 @@
 #' and thermal band for semi-automated creation of a cloud mask. Since it relies on thermal information it doesn't work well for sensors without
 #' thermal bands. 
 #' 
-#' @param x RasterBrick or RasterStack or SpatRaster with reflectance and brightness temperature OR the mask of a previous run of \code{cloudMask} with \code{returnDiffLayer=TRUE}.
+#' @param x SpatRaster with reflectance and brightness temperature OR the mask of a previous run of \code{cloudMask} with \code{returnDiffLayer=TRUE}.
 #' @param threshold Numeric. cloud detection threshold. If not provided it will be guessed. Everything *below* this threshold will be considered a cloud pixel (unless it is removed by filtering afterwards).
 #' @param blue Character or integer. Bandname or number for the blue band
 #' @param tir Character or integer. Bandname or number for the thermal band

R/coregisterImages.R

@@ -3,8 +3,8 @@
 #' Shifts an image to match a reference image. Matching is based on maximum
 #' mutual information. 
 #' 
-#' @param img SpatRaster or SpatRaster. Image to shift to match reference image. \code{img} and \code{ref} must have equal numbers of bands.
-#' @param ref SpatRaster or SpatRaster. Reference image. \code{img} and \code{ref} must have equal numbers of bands.
+#' @param img SpatRaster. Image to shift to match reference image. \code{img} and \code{ref} must have equal numbers of bands.
+#' @param ref SpatRaster. Reference image. \code{img} and \code{ref} must have equal numbers of bands.
 #' @param shift Numeric or matrix. If numeric, then shift is the maximal absolute radius (in pixels of \code{img} resolution) which \code{img} is shifted (\code{seq(-shift, shift, by=shiftInc)}). 
 #'  If shift is a matrix it must have two columns (x shift and y shift), then only these shift values will be tested.
 #' @param shiftInc Numeric. Shift increment (in pixels, but not restricted to integer). Ignored if \code{shift} is a matrix.

R/estimateHaze.R

@@ -2,7 +2,7 @@
 #' 
 #' estimates the digital number (DN) pixel value of *dark* objects for the visible wavelength range.
 #' 
-#' @param x RasterLayer or SpatRaster or a previous result from \code{estimateHaze} with \code{returnTables = TRUE} from which to estimate haze
+#' @param x SpatRaster or a previous result from \code{estimateHaze} with \code{returnTables = TRUE} from which to estimate haze
 #' @param hazeBands Integer or Character. Band number or bandname from which to estimate atmospheric haze (optional if x contains only one layer)
 #' @param darkProp Numeric. Proportion of pixels estimated to be dark.
 #' @param maxSlope Logical. Use \code{darkProp} only as an upper boundary and search for the DN of maximum slope in the histogram below this value.

R/fCover.R

@@ -3,8 +3,8 @@
 #' fCover takes a classified high resolution image, e.g. vegetation and non-vegetation based on Landsat and calculates cover fractions for
 #' pixels of a coarser resolution, e.g. MODIS.
 #' 
-#' @param classImage high resolution RasterLayer or SpatRaster containing a landcover classification, e.g. as obtained by \link{superClass}.
-#' @param predImage coarse resolution RasterLayer or SpatRaster for which fractional cover will be estimated.
+#' @param classImage high resolution SpatRaster containing a landcover classification, e.g. as obtained by \link{superClass}.
+#' @param predImage coarse resolution SpatRaster for which fractional cover will be estimated.
 #' @param nSamples Integer. Number of pixels to sample from predImage to train the regression model
 #' @param classes Integer. Classes for which fractional cover should be estimated (one or more). 
 #' @param model Character. Which model to fit for image regression. See \link[caret]{train} for options. Defaults to randomForest ('rf')

R/getValidation.R

@@ -11,7 +11,7 @@
 #' @examples
 #' library(pls)
 #' ## Fit classifier (splitting training into 70\% training data, 30\% validation data)
-#' train <- readRDS(system.file("external/trainingPoints.rds", package="RStoolbox"))
+#' train <- readRDS(system.file("external/trainingPoints_lsat.rds", package="RStoolbox"))
 #' SC   <- superClass(rlogo, trainData = train, responseCol = "class",
 #'                     model="pls", trainPartition = 0.7)
 #' ## Independent testset-validation

R/ggR.R

@@ -2,7 +2,7 @@
 #' 
 #' Plot single layer imagery in grey-scale. Can be used with a SpatRaster.
 #' 
-#' @param img raster
+#' @param img SpatRaster
 #' @param layer Character or numeric. Layername or number. Can be more than one layer, in which case each layer is plotted in a subplot.
 #' @param maxpixels Integer. Maximal number of pixels to sample.
 #' @param ext Extent object to crop the image

R/ggRGB.R

@@ -4,7 +4,7 @@
 #' 
 #' Functionality is based on \code{\link[terra]{plotRGB}} from the raster package.
 #' 
-#' @param img RasterStack or RasterBrick
+#' @param img SpatRaster
 #' @param r Integer or character. Red layer in x. Can be set to \code{NULL}, in which case the red channel will be set to zero.
 #' @param g Integer or character. Green layer in x. Can be set to \code{NULL}, in which case the green channel will be set to zero.
 #' @param b Integer or character. Blue layer in x. Can be set to \code{NULL}, in which case the blue channel will be set to zero.

R/histMatch.R

@@ -3,8 +3,8 @@
 #' Performs image to image contrast adjustments based on histogram matching using empirical cumulative
 #'  distribution functions from both images.
 #' 
-#' @param x RasterLayer or SpatRaster. Source raster which is to be modified.
-#' @param ref RasterLayer or SpatRaster. Reference raster, to which x will be matched.
+#' @param x SpatRaster. Source raster which is to be modified.
+#' @param ref SpatRaster. Reference raster, to which x will be matched.
 #' @param xmask RasterLayer or SpatRaster. Mask layer for \code{x} to exclude pixels which might distort the histogram, i.e. are not present in \code{ref}. Any NA pixel in \code{xmask} will be ignored (\code{maskvalue = NA}).
 #' @param refmask RasterLayer or SpatRaster. Mask layer for \code{ref}. Any NA pixel in \code{refmask} will be ignored (\code{maskvalue = NA}).
 #' @param nSamples Integer. Number of random samples from each image to build the histograms.

R/internalFunctions.R

@@ -57,7 +57,7 @@
 }
 
 #' Run raster functions
-#' @param SpatRaster Object
+#' @param raster SpatRaster
 #' @param rasterFun function. E.g. predict, calc, overlay 
 #' @param args list. arguments to be passed to rasterFun.
 #' @param wrArgs arguments to be passed to rasterFun, typically to writeRaster

R/mesma.R

@@ -2,7 +2,7 @@
 #' 
 #' \code{mesma} performs a multiple endmember spectral mixture analysis on a multiband raster image.
 #' 
-#' @param img RasterLayer or RasterBrick or SpatRaster. Remote sensing imagery (usually hyperspectral).
+#' @param img SpatRaster. Remote sensing imagery (usually hyperspectral).
 #' @param em Matrix or data.frame with spectral endmembers. Rows represent a single endmember of a class, columns represent the spectral bands (i.e. columns correspond to number of bands in \code{img}). Number of rows needs to be > 1.
 #' @param method Character. Select an unmixing method. Currently, only "NNLS" is implemented. Default is "NNLS".
 #' \itemize{

R/oneHotEncode.R

@@ -2,7 +2,7 @@
 #' 
 #' Splits a categorical raster layer (or a vector) into a multilayer raster (or matrix).
 #' 
-#' @param img RasterLayer or SpatRaster or integer/numeric vector containing multiple classes
+#' @param img SpatRaster or integer/numeric vector containing multiple classes
 #' @param classes integer: vector of classes which should be extracted
 #' @param background integer: background value (default = 0)
 #' @param foreground integer: foreground value (default = 1)

R/panSharpen.R

@@ -3,8 +3,8 @@
 #' provides different methods for pan sharpening a coarse resolution (typically multispectral) image with 
 #' a higher reolution panchromatic image. Values of the pan-chromatic and multispectral images must be of the same scale, (e.g. from 0:1, or all DNs from 0:255)
 #' 
-#' @param img RasterLayer or SpatRaster. Coarse resolution multispectral image
-#' @param pan RasterLayer or SpatRaster. High resolution image, typically panchromatic.
+#' @param img SpatRaster. Coarse resolution multispectral image
+#' @param pan SpatRaster. High resolution image, typically panchromatic.
 #' @param method Character. Choose method from c("pca", "ihs", "brovey").
 #' @param r Character or Integer. Red band in \code{img}. Only relevant if \code{method!='pca'}
 #' @param g Character or Integer. Green band in \code{img}. Only relevant if \code{method!='pca'}

R/pifMatch.R

@@ -2,8 +2,8 @@
 #' 
 #' Match one scene to another based on linear regression of pseudo-invariant features (PIF).
 #' 
-#' @param img RasterStack or RasterBrick or SpatRaster. Image to be adjusted.
-#' @param ref RasterStack or RasterBrick or SpatRaster. Reference image.
+#' @param img SpatRaster. Image to be adjusted.
+#' @param ref SpatRaster. Reference image.
 #' @param method Method to calculate pixel similarity. Options: euclidean distance ('ed'), spectral angle ('sam') or pearson correlation coefficient ('cor').
 #' @param quantile Numeric. Threshold quantile used to identify PIFs
 #' @param returnPifMap Logical. Return a binary raster map ot pixels which were identified as pesudo-invariant features.

R/rasterCVA.R

@@ -3,8 +3,8 @@
 #' Calculates angle and magnitude of change vectors. 
 #' Dimensionality is limited to two bands per image. 
 #' 
-#' @param x RasterBrick or RasterStack or SpatRaster with two layers. This will be the reference/origin for the change calculations. Both rasters (y and y) need to correspond to each other, i.e. same resolution, extent and origin.
-#' @param y RasterBrick or RasterStack or SpatRaster with two layers. Both rasters (y and y) need to correspond to each other, i.e. same resolution, extent and origin.
+#' @param x SpatRaster with two layers. This will be the reference/origin for the change calculations. Both rasters (y and y) need to correspond to each other, i.e. same resolution, extent and origin.
+#' @param y SpatRaster with two layers. Both rasters (y and y) need to correspond to each other, i.e. same resolution, extent and origin.
 #' @param tmf Numeric. Threshold median factor (optional). Used to calculate a threshold magnitude for which pixels are considered stable, i.e. no change. Calculated as \code{tmf * mean(magnitude[magnitude > 0])}.
 #' @param nct Numeric. No-change threshold (optional). Alternative to \code{tmf}. Sets an absolute threshold. Change magnitudes below \code{nct} are considered stable and set to NA.
 #' @param ... further arguments passed to writeRaster

R/rasterEntropy.R

@@ -5,7 +5,7 @@
 #' 
 #' Entropy is calculated as -sum(p log(p)); p being the class frequency per pixel.
 #' 
-#' @param img RasterStack or RasterBrick or SpatRaster
+#' @param img SpatRaster
 #' @param ... additional arguments passed to writeRaster
 #' @return
 #' SpatRaster "entropy"

R/rasterPCA.R

@@ -1,6 +1,6 @@
 #' Principal Component Analysis for Rasters
 #' 
-#' Calculates R-mode PCA for RasterBricks or RasterStacks and returns a RasterBrick with multiple layers of PCA scores. 
+#' Calculates R-mode PCA for SpatRasters and returns a SpatRaster with multiple layers of PCA scores.
 #' 
 #' Internally rasterPCA relies on the use of \link[stats]{princomp} (R-mode PCA). If nSamples is given the PCA will be calculated
 #' based on a random sample of pixels and then predicted for the full raster. If nSamples is NULL then the covariance matrix will be calculated
@@ -14,7 +14,7 @@
 #' Standardised PCA (SPCA) can be useful if imagery or bands of different dynamic ranges are combined. SPC uses the correlation matrix instead of the covariance matrix, which
 #' has the same effect as using normalised bands of unit variance. 
 #' 
-#' @param img RasterLayer or SpatRaster.
+#' @param img SpatRaster.
 #' @param nSamples Integer or NULL. Number of pixels to sample for PCA fitting. If NULL, all pixels will be used.
 #' @param nComp Integer. Number of PCA components to return.
 #' @param spca Logical. If \code{TRUE}, perform standardized PCA. Corresponds to centered and scaled input image. This is usually beneficial for equal weighting of all layers. (\code{FALSE} by default)

R/rescaleImage.R

@@ -8,7 +8,7 @@
 #' By providing `xmin = -1` and `xmax = 1` the values can be rescaled to any other range,
 #' e.g. 1 to 100 while comparability to other rescaled NDVI scenes is retained. 
 #' 
-#' @param x patRaster or numeric vector. Image to normalise.
+#' @param x SpatRaster or numeric vector. Image to normalise.
 #' @param y SpatRaster or numeric vector. Reference image. Optional. Used to extract min and max values if ymin or ymax are missing.
 #' @param xmin Numeric. Min value of x. Either a single value or one value per layer in x. If xmin is not provided it will be extracted from x.
 #' @param xmax Numeric. Max value of x. Either a single value or one value per layer in x. If xmax is not provided it will be extracted from x.

R/sam.R

@@ -2,7 +2,7 @@
 #' 
 #' Calculates the angle in spectral space between pixels and a set of reference spectra (endmembers) for image classification based on spectral similarity.
 #' 
-#' @param img RasterBrick or RasterStack or SpatRaster. Remote sensing imagery.
+#' @param img SpatRaster. Remote sensing imagery.
 #' @param em Matrix or data.frame with endmembers. Each row should contain the endmember spectrum of a class, i.e. columns correspond to bands in \code{img}. It is reccomended to set the rownames to class names.
 #' @param angles Logical. If \code{TRUE} a RasterBrick containing each one layer per endmember will be returned containing the spectral angles.
 #' @param ... further arguments to be passed to \code{\link[terra]{writeRaster}}

R/spectralIndices.R

@@ -2,7 +2,7 @@
 #' 
 #' Calculate a suite of multispectral indices such as NDVI, SAVI etc. in an efficient way.
 #' 
-#' @param img SpatRaster, Typically remote sensing imagery, which is to be classified.
+#' @param img SpatRaster. Typically remote sensing imagery, which is to be classified.
 #' @param blue Character or integer. Blue band. 
 #' @param green Character or integer. Green band. 
 #' @param red Character or integer. Red band. 

R/superClass.R

@@ -70,7 +70,7 @@
 #' library(randomForest)
 #' library(e1071)
 #' library(terra)
-#' train <- readRDS(system.file("external/trainingPoints.rds", package="RStoolbox"))
+#' train <- readRDS(system.file("external/trainingPoints_lsat.rds", package="RStoolbox"))
 #' 
 #' ## Plot training data
 #' olpar <- par(no.readonly = TRUE) # back-up par
@@ -498,7 +498,7 @@ superClass <- function(img, trainData, valData = NULL, responseCol = NULL,
 #' @export 
 #' @examples 
 #' ## Load training data
-#' train <- readRDS(system.file("external/trainingPoints.rds", package="RStoolbox"))
+#' train <- readRDS(system.file("external/trainingPoints_lsat.rds", package="RStoolbox"))
 #' 
 #' ## Fit classifier 
 #' SC       <- superClass(rlogo, trainData = train, responseCol = "class",
@@ -527,7 +527,6 @@ predict.superClass <- function(object, img, predType = "raw", filename = NULL, d
 
     wrArgs          <- c(list(...), list(filename = filename, datatype = datatype))
     wrArgs$filename <- filename ## remove filename from args if is.null(filename) --> standard writeRaster handling applies
-    print(img)
     .paraRasterFun(img, rasterFun=terra::predict, args = list(model=model, type = predType, index = probInd, na.rm = TRUE), wrArgs = wrArgs)
 
 }

R/tasseledCap.R

@@ -3,7 +3,7 @@
 #' Calculates brightness, greenness and wetness from multispectral imagery.
 #' Currently implemented Landsat 4 TM, Landsat 5 TM, Landsat 7ETM+, Landsat 8 OLI, MODIS, QuickBird, Spot5 and RapidEye.
 #' 
-#' @param img RasterBrick or RasterStack or SpatRaster. Input image. Band order must correspond to sensor specifications (see Details and Examples)
+#' @param img SpatRaster. Input image. Band order must correspond to sensor specifications (see Details and Examples)
 #' @param sat Character. Sensor; one of: c("Landsat4TM", "Landsat5TM", "Landsat7ETM", "Landsat8OLI", "MODIS", "QuickBird", "Spot5", "RapidEye"). Case is irrelevant.
 #' @param ... Further arguments passed to writeRaster.
 #' @export 

R/validateMap.R

@@ -3,7 +3,7 @@
 #'
 #' validate a map from a classification or regression model. This can be useful to update the accuracy assessment after filtering, e.g. for a minimum mapping unit.
 #'  
-#' @param map RasterLayer or SpatRaster. The classified map.
+#' @param map SpatRaster. The classified map.
 #' @param valData sf object with validation data (POLYGONs or POINTs).
 #' @param nSamplesV Integer. Number of pixels to sample for validation (only applies to polygons).
 #' @param responseCol Character. Column containing the validation data in attribute table of \code{valData}.
@@ -17,7 +17,7 @@
 #' library(terra)
 #' 
 #' ## Training data
-#' poly     <- readRDS(system.file("external/trainingPolygons.rds", package="RStoolbox"))
+#' poly     <- readRDS(system.file("external/trainingPolygons_lsat.rds", package="RStoolbox"))
 #' 
 #' ## Split training data in training and validation set (50%-50%)
 #' splitIn   <- createDataPartition(poly$class, p = .5)[[1]]

R/zzz.R

@@ -12,10 +12,16 @@
   lsat_rs <- terra::readRDS(system.file("external", "lsat.rds", package = pkgname))
   assign("lsat", lsat_rs, envir=as.environment("package:RStoolbox"))
 
+  srtml_rs <- terra::readRDS(system.file("external", "srtm_lsat.rds", package = pkgname))
+  assign("srtm", srtml_rs, envir=as.environment("package:RStoolbox"))
+
   rlogo_rs <- terra::readRDS(system.file("external", "rlogo.rds", package = pkgname))
   assign("rlogo", rlogo_rs, envir=as.environment("package:RStoolbox"))
 
-  srtm_rs <- terra::readRDS(system.file("external", "srtm.rds", package = pkgname))
-  assign("srtm", srtm_rs, envir=as.environment("package:RStoolbox"))
+  sen2_rs <- terra::readRDS(system.file("external", "sen2.rds", package = pkgname))
+  assign("sen2", sen2_rs, envir=as.environment("package:RStoolbox"))
+
+  srtms_rs <- terra::readRDS(system.file("external", "srtm_sen2.rds", package = pkgname))
+  assign("srtm_sen2", srtms_rs, envir=as.environment("package:RStoolbox"))
 
 }