Learn more about Model-Based Calibration

Properties (for models) - View and edit model properties

Syntax

properties=M.Properties M.Properties.PropertyName = NewValue properties(M.Properties) f=M.Properties.properties

Description

"Properties" is a property of mbcmodel.model.

properties=M.Properties returns a mbcmodel.modelproperties object.

To edit a property, use the syntax M.Properties.PropertyName = NewValue

"properties" is a method of mbcmodel.fitalgorithm and mbcmodel.modelproperties which returns a list of properties.

properties(M.Properties) lists the property names, types and allowed values.

f=M.Properties.properties returns the property names as a cell array.

The model Type determines which properties you can set. For more information, see Type (for models).

To get a mbcmodel.modelproperties object from a model:

>> M = mbcmodel.CreateModel('Polynomial', 4);
>> disp(M)
mbcmodel.linearmodel:Polynomial

>>modelproperties=M.Properties
 
modelproperties = 
Polynomial Properties
                  Order: [3 3 3 3]
       InteractionOrder: 3
    TransformInputRange: 1
         ParameterNames: {35x1 cell}
         StepwiseStatus: {35x1 cell}
                 BoxCox: 1

To create a model and list the properties:

>> M = mbcmodel.CreateModel('RBF',2)
 
M =
 
   A radial basis function network using a multiquadric kernel
	    with 0 centers
   and a global width of 2.                                                  
   The regularization parameter, lambda, is 0.0001.                          
   InputData: [0x2 double]
   OutputData: [0x1 double]
   Status: Not fitted
   Linked to Response: <not linked>

>> properties(M.Properties)
RBF Properties
     Kernel: RBF kernel (enum: {'multiquadric',...
'recmultiquadric','gaussian','thinplate','logisticrbf',...
'wendland', 'linearrbf','cubicrbf'})
     Continuity: Continuity for Wendland kernel...
 (0,2,4,6) (int: [0,6])
     ParameterNames: List of parameter names (read-only)
     StepwiseStatus: Stepwise status {'Always','Never',...
'Step'} (cell)
     BoxCox: Box-Cox transform (power) (numeric: [-3,3])

The following syntax returns the properties as a cell array:

>> f=M.Properties.properties

f = 

    'Kernel'
    'Continuity'
    'ParameterNames'
    'StepwiseStatus'
    'BoxCox'

Change a property as follows:

>>M.Properties.Kernel = 'thinplate';

The model changes state to ‘Being Edited'. The settings are not applied until you call Fit on the model object.

The following sections list the properties available for each model type.

Linear Models — Polynomial Properties

mbcmodel.linearmodel:Polynomial

Order: Polynomial order (vector int: {[0,Inf],NumberOfInputs})

InteractionOrder: Maximum order of interaction terms (int: [0,Inf])

TransformInputRange: Transform inputs (Boolean)

ParameterNames: List of parameter names (read-only)

StepwiseStatus: Stepwise status {'Always','Never','Step'} (cell)

BoxCox: Box-Cox transform (power) (numeric: [-3,3])

Linear Models — Hybrid Spline Properties

mbcmodel.linearmodel:Hybrid Spline

Order: Spline and polynomial order (vector int: {[0,3],NumberOfInputs})

SplineVariable: Spline variable

SplineInteraction: Order of interaction between spline and polynomial (int: [0,3])

Knots: Position of knots (vector real)

ParameterNames: List of parameter names (read-only)

StepwiseStatus: Stepwise status {'Always','Never','Step'} (cell)

BoxCox: Box-Cox transform (power) (numeric: [-3,3])

Linear Models — RBF Properties

mbcmodel.linearmodel:RBF

Kernel: RBF kernel (enum: {'multiquadric','recmultiquadric','gaussian','thinplate','logisticrbf','wendland',

'linearrbf','cubicrbf'})

Continuity: Continuity for Wendland kernel (0,2,4,6) (int: [0,6])

ParameterNames: List of parameter names (read-only)

StepwiseStatus: Stepwise status {'Always','Never','Step'} (cell)

BoxCox: Box-Cox transform (power) (numeric: [-3,3])

Linear Models — Polynomial-RBF Properties

mbcmodel.linearmodel:Polynomial-RBF

Order: Polynomial order (vector int: {[0,Inf],NumberOfInputs})

InteractionOrder: Maximum order of interaction terms (int: [0,Inf])

Kernel: RBF kernel (enum:

{'multiquadric','recmultiquadric','gaussian','thinplate','logisticrbf','wendland',

'linearrbf','cubicrbf'})

Continuity: Continuity for Wendland kernel (0,2,4,6) (int: [0,6])

ParameterNames: List of parameter names (read-only)

StepwiseStatus: Stepwise status {'Always','Never','Step'} (cell)

BoxCox: Box-Cox transform (power) (numeric: [-3,3])

Linear Models — Hybrid Spline-RBF Properties

mbcmodel.linearmodel:Hybrid Spline-RBF

Order: Spline and polynomial order (vector int: {[0,3],NumberOfInputs})

SplineVariable: Spline variable

SplineInteraction: Order of interaction between spline and polynomial (int: [0,3])

Knots: Position of knots (vector real)

Kernel: RBF kernel (enum: {'multiquadric','recmultiquadric','gaussian','thinplate','logisticrbf','wendland',

'linearrbf','cubicrbf'})

Continuity: Continuity for Wendland kernel (0,2,4,6) (int: [0,6])

ParameterNames: List of parameter names (read-only)

StepwiseStatus: Stepwise status {'Always','Never','Step'} (cell)

BoxCox: Box-Cox transform (power) (numeric: [-3,3])

Nonlinear Models — Free Knot Spline Properties

mbcmodel.model:Free Knot Spline

Order: Spline order (int: [0,3])

NumKnots: Number of knots (int: 'Positive')

Nonlinear Models — Neural Network Properties

mbcmodel.model:Neural Network

HiddenLayers: Number of hidden layers (int: [1,2])

Neurons: Number of Neurons in each hidden layer (vector int: 'Positive')

Examples

>> properties=M.Properties
 
properties = 
Polynomial Properties
                  Order: [3 3 3 3]
       InteractionOrder: 3
    TransformInputRange: 1
         ParameterNames: {35x1 cell}
         StepwiseStatus: {35x1 cell}
                 BoxCox: 1

 
>> M.Properties.Order = [3 2 2 3]
 
M =
 
   1 + 2*X1 + 10*X4 + 15*X2 + 18*X3 + 3*X1^2 + 6*X1*X4 
...+ 8*X1*X2 + 9*X1*X3 +
   11*X4^2 + 13*X4*X2 + 14*X4*X3 + 16*X2^2 + 17*X2*X3 
...+ 19*X3^2 + 4*X1^3 +  
   5*X1^2*X4 + 7*X1*X4^2 + 12*X4^3                                          
   InputData: [0x4 double]
   OutputData: [0x1 double]
   Status: Being Edited
   Linked to Response: <not linked>

Properties (for models) - View and edit model properties

Syntax

Description

Linear Models — Polynomial Properties

Linear Models — Hybrid Spline Properties

Linear Models — RBF Properties

Linear Models — Polynomial-RBF Properties

Linear Models — Hybrid Spline-RBF Properties

Nonlinear Models — Free Knot Spline Properties

Nonlinear Models — Neural Network Properties

Examples

See Also

Recommended Products