Commit 38b12292 authored by Daniela Rabe's avatar Daniela Rabe
Browse files

update documentation

parent 50d3244f
......@@ -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}
}
......
......@@ -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
......
......@@ -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}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment