fClasP

Function for [Clas]s-specific [P]redictions

Source

https://github.com/FLFgit/ScaleP/blob/master/functions/fClasP.R

Parameter

• RU.DIR -> directory containing reference unit (RU) file
• RU.SHP -> name of reference unit shape file
• SAMPLE.DIR -> directory containing sample data set
• SAMPLE.SHP -> name of sample data set
• PART -> proportion of training and test data set [0...1]
• OUT.DIR -> directory containing resulting files
• EPSG -> EPSG code of all data
• T.CLASS -> column name of target class in SAMPLE.SHP
• PM -> prefix of explaning attributes, which should be considered
• UPTRAIN=TRUE -> option: UPTRAIN function for balancing of unequally distributed classes is TRUE
• EXPORT=FALSE -> option: export of shape file with explaining parameters and prediction result

Result

• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_part[PART*100]_train.shp -> shape file of training data set
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_part[PART*100]_test.shp -> shape file of test data set
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_BP.pdf -> barplot of target classes based on training and test data sets
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_VarImp.csv -> variable-specific variable importance
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_CV.csv -> global accuracy metrics based on cross validation representing internal model performance
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_CM.csv -> confusion matrix based on prediction to the training data set
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_AM.csv -> accuracy metrics based on prediction to the training data set by applying function fEvaluate.
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_BP.pdf -> barplot of predicted classes
• [RU.SHP]-[SAMPLE.SHP]_[T.PM]_MODEL-[M.TRAIN]_part[PART*100].shp -> optional: shape file with explaining parameters and prediction result (column [T.CLASS]_SIM)