update documentation

R-package/man/model_opt_r.Rd

@@ -10,16 +10,15 @@ model_opt_r(
   sample_type,
   buffer,
   model,
-  area,
   seed,
   n,
   sample_size,
   n_channel,
   seed2,
   mtry,
+  mod.error,
   pbtn1,
-  pbtn2,
-  ras_vx,
+  rast,
   max_samples_per_class
 )
 }
@@ -34,8 +33,6 @@ model_opt_r(
 
 \item{model}{which machine learning classifier to use c("rf", "svm") for random forest or support vector machine implementation}
 
-\item{area}{extent where the the classification is happening}
-
 \item{seed}{set seed for reproducible results}
 
 \item{n}{number of iterations for model accuracy}
@@ -48,11 +45,11 @@ model_opt_r(
 
 \item{mtry}{number of predictor used at random forest splitting nodes (mtry << n predictors)}
 
-\item{pbtn1}{matrix for points}
+\item{mod.error}{threshold for model error until which iteration is being executed}
 
-\item{pbtn2}{matrix for points}
+\item{pbtn1}{matrix for points}
 
-\item{ras_vx}{velox raster}
+\item{rast}{raster}
 
 \item{max_samples_per_class}{maximum number of samples per class}
 }

R-package/man/multi_Class_Sampling.Rd

@@ -14,6 +14,7 @@ multi_Class_Sampling(
   reference,
   model = "rf",
   mtry = 10,
+  mod.error = 0.02,
   last = F,
   seed = 3,
   init.seed = "sample",
@@ -23,6 +24,7 @@ multi_Class_Sampling(
   n_classes,
   multiTest = 1,
   RGB = c(19, 20, 21),
+  in.memory = TRUE,
   color = c("lightgrey", "orange", "yellow", "limegreen", "forestgreen"),
   overwrite = TRUE,
   save_runs = TRUE,
@@ -50,6 +52,8 @@ multi_Class_Sampling(
 
 \item{mtry}{number of predictor used at random forest splitting nodes (mtry << n predictors)}
 
+\item{mod.error}{threshold for model error until which iteration is being executed}
+
 \item{last}{only true for one class classifier c("FALSE", TRUE")}
 
 \item{seed}{set seed for reproducible results}
@@ -68,7 +72,9 @@ multi_Class_Sampling(
 
 \item{RGB}{rgb channel numbers for image plot}
 
-\item{color}{color pallet}
+\item{in.memory}{boolean for raster processing (memory = "TRUE", from disk = "FALSE")}
+
+\item{color}{single colors for continuous color palette interpolation}
 
 \item{overwrite}{overwrite the KML and raster files from previous runs (default TRUE)}
 
@@ -85,7 +91,7 @@ multi_Class_Sampling(
 \enumerate{
 \item Habitat type probability map as geocoded *.kmz file (with a *.kml layer and *.png image output), and *.tif raster file
 \item A Habitat object (only if save_runs is set to TRUE) consisting of 7 slots: \cr
-run1@models - list of selcted classifiers \cr
+run1@models - list of selected classifiers \cr
 run1@ref_samples - list of SpatialPointsDataFrames with same length as run1@models holding reference labels \link{1,2} for each selected model \cr
 run1@switch - vector of lenght run1@models indicating if target class equals 2, if not NA the labels need to be switched \cr
 run1@layer - raster map of habitat type probability \cr

R-package/man/sample_nb.Rd

@@ -13,11 +13,12 @@ sample_nb(
   buffer,
   reference,
   model,
-  area,
   mtry,
+  mod.error,
   last,
   seed,
   init.seed,
+  in.memory,
   save_runs,
   parallel_mode,
   max_num_cores,
@@ -39,16 +40,18 @@ sample_nb(
 
 \item{model}{which machine learning classifier to use c("rf", "svm") for random forest or suppurt vector machine implementation}
 
-\item{area}{extent where the the classification is happening}
-
 \item{mtry}{number of predictor used at random forest splitting nodes (mtry << n predictors)}
 
+\item{mod.error}{threshold for model error until which iteration is being executed}
+
 \item{last}{only true for one class classifier c("FALSE", TRUE")}
 
 \item{seed}{set seed for reproducable results}
 
 \item{init.seed}{"sample" for new or use run1@seeds to reproduce previous steps}
 
+\item{in.memory}{boolean for raster processing (memory = "TRUE", from disk = "FALSE")}
+
 \item{save_runs}{if the user wants to save the runs, if TRUE the complete Habitat Class object is returned}
 
 \item{parallel_mode}{run loops in parallel}