TrainVectorRegression
Train a regression algorithm based on geometries with list of predictor to consider and a label (dependent variable).
Learning
QgsProcessingParameterMultipleLayers|io.vd|Input Vector Data|-1|None|False
QgsProcessingParameterFile|io.stats|Input XML image statistics file|QgsProcessingParameterFile.File|None|None|True
QgsProcessingParameterFileDestination|io.out|Output model|None|None|False
QgsProcessingParameterNumber|layer|Layer Index|QgsProcessingParameterNumber.Integer|0|True
QgsProcessingParameterField|feat|Field names for training features|None|io.vd|QgsProcessingParameterField.Numeric|True|True
QgsProcessingParameterMultipleLayers|valid.vd|Validation Vector Data|-1|None|True
QgsProcessingParameterNumber|valid.layer|Layer Index|QgsProcessingParameterNumber.Integer|0|True
QgsProcessingParameterField|cfield|Field containing the class integer label for supervision|None|io.vd|QgsProcessingParameterField.Any|False|True
QgsProcessingParameterBoolean|v|Verbose mode|true|True
OTBParameterChoice|classifier|Classifier to use for the training|libsvm;dt;ann;rf;knn;sharkrf|0|True
OTBParameterChoice|classifier.libsvm.k|SVM Kernel Type|linear;rbf;poly;sigmoid|0|True
OTBParameterChoice|classifier.libsvm.m|SVM Model Type|epssvr;nusvr|0|True
QgsProcessingParameterNumber|classifier.libsvm.c|Cost parameter C|QgsProcessingParameterNumber.Double|1|True
QgsProcessingParameterNumber|classifier.libsvm.gamma|Gamma parameter|QgsProcessingParameterNumber.Double|1|True
QgsProcessingParameterNumber|classifier.libsvm.coef0|Coefficient parameter|QgsProcessingParameterNumber.Double|0|True
QgsProcessingParameterNumber|classifier.libsvm.degree|Degree parameter|QgsProcessingParameterNumber.Integer|3|True
QgsProcessingParameterNumber|classifier.libsvm.nu|Cost parameter Nu|QgsProcessingParameterNumber.Double|0.5|True
QgsProcessingParameterBoolean|classifier.libsvm.opt|Parameters optimization|false|True
QgsProcessingParameterBoolean|classifier.libsvm.prob|Probability estimation|false|True
QgsProcessingParameterNumber|classifier.libsvm.eps|Epsilon|QgsProcessingParameterNumber.Double|0.001|True
QgsProcessingParameterNumber|classifier.dt.max|Maximum depth of the tree|QgsProcessingParameterNumber.Integer|10|True
QgsProcessingParameterNumber|classifier.dt.min|Minimum number of samples in each node|QgsProcessingParameterNumber.Integer|10|True
QgsProcessingParameterNumber|classifier.dt.ra|Termination criteria for regression tree|QgsProcessingParameterNumber.Double|0.01|True
QgsProcessingParameterNumber|classifier.dt.cat|Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split|QgsProcessingParameterNumber.Integer|10|True
QgsProcessingParameterBoolean|classifier.dt.r|Set Use1seRule flag to false|false|True
QgsProcessingParameterBoolean|classifier.dt.t|Set TruncatePrunedTree flag to false|false|True
OTBParameterChoice|classifier.ann.t|Train Method Type|back;reg|1|True
QgsProcessingParameterString|classifier.ann.sizes|Number of neurons in each intermediate layer|None|True|True
OTBParameterChoice|classifier.ann.f|Neuron activation function type|ident;sig;gau|1|True
QgsProcessingParameterNumber|classifier.ann.a|Alpha parameter of the activation function|QgsProcessingParameterNumber.Double|1|True
QgsProcessingParameterNumber|classifier.ann.b|Beta parameter of the activation function|QgsProcessingParameterNumber.Double|1|True
QgsProcessingParameterNumber|classifier.ann.bpdw|Strength of the weight gradient term in the BACKPROP method|QgsProcessingParameterNumber.Double|0.1|True
QgsProcessingParameterNumber|classifier.ann.bpms|Strength of the momentum term (the difference between weights on the 2 previous iterations)|QgsProcessingParameterNumber.Double|0.1|True
QgsProcessingParameterNumber|classifier.ann.rdw|Initial value Delta_0 of update-values Delta_{ij} in RPROP method|QgsProcessingParameterNumber.Double|0.1|True
QgsProcessingParameterNumber|classifier.ann.rdwm|Update-values lower limit Delta_{min} in RPROP method|QgsProcessingParameterNumber.Double|1e-07|True
OTBParameterChoice|classifier.ann.term|Termination criteria|iter;eps;all|2|True
QgsProcessingParameterNumber|classifier.ann.eps|Epsilon value used in the Termination criteria|QgsProcessingParameterNumber.Double|0.01|True
QgsProcessingParameterNumber|classifier.ann.iter|Maximum number of iterations used in the Termination criteria|QgsProcessingParameterNumber.Integer|1000|True
QgsProcessingParameterNumber|classifier.rf.max|Maximum depth of the tree|QgsProcessingParameterNumber.Integer|5|True
QgsProcessingParameterNumber|classifier.rf.min|Minimum number of samples in each node|QgsProcessingParameterNumber.Integer|10|True
QgsProcessingParameterNumber|classifier.rf.ra|Termination Criteria for regression tree|QgsProcessingParameterNumber.Double|0|True
QgsProcessingParameterNumber|classifier.rf.cat|Cluster possible values of a categorical variable into K <= cat clusters to find a suboptimal split|QgsProcessingParameterNumber.Integer|10|True
QgsProcessingParameterNumber|classifier.rf.var|Size of the randomly selected subset of features at each tree node|QgsProcessingParameterNumber.Integer|0|True
QgsProcessingParameterNumber|classifier.rf.nbtrees|Maximum number of trees in the forest|QgsProcessingParameterNumber.Integer|100|True
QgsProcessingParameterNumber|classifier.rf.acc|Sufficient accuracy (OOB error)|QgsProcessingParameterNumber.Double|0.01|True
QgsProcessingParameterNumber|classifier.knn.k|Number of Neighbors|QgsProcessingParameterNumber.Integer|32|True
OTBParameterChoice|classifier.knn.rule|Decision rule|mean;median|0|True
QgsProcessingParameterNumber|classifier.sharkrf.nbtrees|Maximum number of trees in the forest|QgsProcessingParameterNumber.Integer|100|True
QgsProcessingParameterNumber|classifier.sharkrf.nodesize|Min size of the node for a split|QgsProcessingParameterNumber.Integer|25|True
QgsProcessingParameterNumber|classifier.sharkrf.mtry|Number of features tested at each node|QgsProcessingParameterNumber.Integer|0|True
QgsProcessingParameterNumber|classifier.sharkrf.oobr|Out of bound ratio|QgsProcessingParameterNumber.Double|0.66|True
QgsProcessingParameterNumber|rand|Random seed|QgsProcessingParameterNumber.Integer|0|True
