SANNDataSelection Members

These members are related to Statistica Neural Networks Data Selection Dialog.

Functions

Name Description
Cancel
OK Return value: Integer.

Properties

Name Description
Application Returns application object. Return value: Object. This property is read only.
AutomaticNetworkSearch Select this option to create neural networks using the Automated Neural Search (ANS). Return/assignment value: Integer.
CasewiseDeletionOfMD Select this option to excludes cases with missing values. This is preferable, unless you are severely restricted in the number of cases available. In that case, you may select mean substitution (see MeanSubstitutionOfMD). Return/assignment value: Integer.
CustomNetworkBuilding Select this option to create neural networks using the Statistica Custom Neural Network (CNN). Return/assignment value: Integer.
MeanSubstitutionOfMD Select this option to substitute missing case values with their means. Return/assignment value: Integer.
Name Return value: String. This property is read only.
NoMissingDataTreatment Functions is obsolete. Return/assignment value: Integer.
NumberOfSubsamples Use this option to specify the number of subsamples to generate in the analysis. This will also be the number of networks to train since each network is created using one subsample. Return/assignment value: Integer.
Parent Returns the parent of the object. Return value: Object. This property is read only.
ResultsCodes Assignment value: Variant.
ResultsOption Assignment value: Integer.
ResultsOutputFields Assignment value: Variant.
ResultsSaveFileName Assignment value: String.
ResultsSelection Assignment value: Variant.
ResultsSelectionOption Assignment value: Variant.
ResultsValues Assignment value: Variant.
ResultsVariables Assignment value: Variant.
SamplingSeed Use this option to specify the seed for random number generator used to create the training, testing and validation samples. Return/assignment value: Integer.
SizeOfTestSample Specifies the percentage of the valid cases in the data set that will be used to create the test sample. Must be larger than 0 and less than 100. Return/assignment value: Double.
SizeOfTestSubsample Specifies the percentage of the valid cases in the data set that will be used to create the test subsample. Must be larger than 0 and less than 100. Return/assignment value: Double.
SizeOfTrainingSample Specifies the percentage of the valid cases in the data set that will be used to create the training sample. Must be larger than 0 and less or equal 100. Return/assignment value: Double.
SizeOfTrainingSubsample Specifies the percentage of the valid cases in the data set that will be used to create the training subsample. Must be larger than 0 and less or equal 100. Return/assignment value: Double.
SizeOfValidationSample Specifies the percentage of the valid cases in the data set that will be used to form the validation sample. Must be larger than 0 and less than 100. Return/assignment value: Double.
SizeOfValidationSubsample Specifies the percentage of the valid cases in the data set that will be used to form the validation subsample. Must be larger than 0 and less than 100. Return/assignment value: Double.
StepsAhead Specify how many steps ahead to predict. Return/assignment value: Integer.
StepsUsedToPredict Specify how many steps should be used to make predictions. Return/assignment value: Integer.
SubsampleNetworkBuilding Select this option to create neural networks using subsampling. Return/assignment value: Integer.
SubsamplingSeed Use this option to specify the seed for random number generator used to create the training, testing and validation subsamples. Return/assignment value: Integer.
TestSample Call this option to specify the testing sample. Return/assignment value: String.
TrainSample Call this option to specify the training sample. Return/assignment value: String.
UseBootstrapSubsampling Select this option to create the training, testing and validation subsamples using the bootstrap method. Return/assignment value: Integer.
UseRandomSampling Select this option to randomly create the training, testing and validation samples. Return/assignment value: Integer.
UseRandomSubsampling Select this option to randomly create the training, testing and validation subsamples. Return/assignment value: Integer.
UseSubsetVariable Select this option to control the sampling of cases for training, testing and validation using a sampling variable. A sampling variable is a categorical variable in the dataset that can be used to indicate the case samples. Return/assignment value: Integer.
UseTestSample Functions is obsolete. Return/assignment value: Integer.
UseValidationSample Functions is obsolete. Return/assignment value: Integer.
ValidationSample Call this option to specify the validation sample. Return/assignment value: String.
Variables Select variables for the analysis. You need to select at least one input and one target variable for regression and classification analysis. Select at least one input for cluster analysis. For time series analysis inputs are optional. Return/assignment value: String.