JSL Syntax Reference • JSL Functions • Platform Scripting Notes
Previous
 • 
Next
Platform Scripting Notes
Fit Model
Fit Group ( model1, model2, ...);
Fit Group ( model1; model2; ...);
Description
Groups separate Fit Models (for example, least squares, nonlinear, neural, gaussian processing, and mixed) in the same output window with a shared Profiler.
Arguments
model1, model2
Specifies the profiled fit model and its arguments.
Scripting Options for All Platforms
The following messages are available for any platform object only in JSL:
object <<Get Script
object <<Get Script With Data Table
object <<Get Data Table
object <<Get Timing
object <<Report
object <<Top Report
object <<Title
object <<SendToReport( Dispatch(...) )
object <<SendToByGroup( ... )
object <<Action
object <<Ignore Platform Preferences( 0|1 )
Individual Platform Options
Each platform has preferences configurable using File > Preferences > Platforms. Each platform’s options are scriptable. For detailed information about scripting platform preferences, refer to the JMP Scripting Index. In JMP, select Help > Scripting Index for details.
Distribution
The following message for a Distribution object is available only in JSL:
dist_object <<(Fit Handle[n] << ...)
The following JSL option for Fit Distribution() is equivalent to the Make into Data Table option on the right-click menu for the Parameter Estimates table:
Fit Distribution(
<distribution>( "Make Parms Table" )
);
Bivariate
To turn off specific fits for a Bivariate object, set the fit to 0:
Bivariate(
Y( :height ),
X( :weight ),
fit mean(1), // enables fit
Density Ellipse( 0 ), // disables fit
Fit Orthogonal( 0 ),
Fit Line( 0 ),
Fit Polynomial( 0 ),
Fit spline( 0 ),
fit robust(0),
fit each value(0),
histogram borders(0),
nonpar density(0)
);
The following message for a Bivariate object is available only in JSL:
biv_object <<Fit Where( WHERE_clause )
Fit Model
The following messages for a Fit Model object are available only in JSL:
fit_model_object <<Get Variance Components( );
fit_model_object <<Get Effect Names( );
fit_model_object <<Get Effect PValues( );
fit_model_object <<Get Estimates( );
fit_model_object <<Get Parameter Names( );
fit_model_object <<Get Random Effect Names( );
fit_model_object <<Get Std Errors( );
fit_model_object <<Get X Matrix( );
fit_model_object <<Get XPX Inverse( );
fit_model_object <<Get Y Matrix( );
Fit Model: Standard Least Squares
Saving Prediction Formulas as SQL Expressions
In Standard Least Squares, save prediction formulas as SQL expressions using Get SQL Prediction Expression(). For an example, see the JMP Scripting Index on the Help menu.
Fitting Models that Have Missing Y Values and Only Fixed Effects
In models that contain a random effect, Y values are fit separately by default. However, suppose that your model contains only fixed effects. You enter more than one Y response, some of which have missing values.
•
In a script, the Y responses are fit together by default. The model fits each Y using only those rows that are nonmissing for all of the Y variables. For example, a row that includes one or more missing Y values is excluded from the model. You can explicitly include Run( "Fit Together" ) in a script to get the same result.
•
If you include the Run( "Fit Separately" ) option, the model fits each Y using all rows that are nonmissing for that particular Y. For example, a row that includes one or more missing Y values is included in the model.
The following script fits the Y responses together:
dt << Fit Model(
Y( :height, :weight ),
Effects( :sex ),
Personality( "Standard Least Squares" ),
Emphasis( "Minimal Report" ),
Run // or Run( "Fit Together" )
);
The following script fits the Y responses separately:
dt << Fit Model(
Y( :height, :weight ),
Effects( :sex ),
Personality( "Standard Least Squares" ),
Emphasis( "Minimal Report" ),
Run( "Fit Separately" )
);
In JMP, the user is prompted to select Fit Together or Fit Separately when running the model. See the Standard Least Squares chapter in Fitting Linear Models for details about how missing Y values are handled.
Fit Model: MANOVA
The following message for a Fit Model object is available only in JSL:
fit_model_object << (Response[1] << (Effect[1] << ... ) );
Fit Model: Generalized Linear Models
The following message for a Fit Model object is available only in JSL:
Parametric Formula( )
Fit Model: Nominal Logistic
The following messages for a Fit Model Nominal Logistic object are available only in JSL:
fit_model_object << Get SAS Data Step
fit_model_object << Get MM SAS Data Step
Fit Model: Ordinal Logistic
The following messages for a Fit Model Ordinal Logistic object are available only in JSL:
fit_model_object << Get SAS Data Step
fit_model_object << Get MM SAS Data Step
Neural
The Neural platform replaces Neural Net. Scripts that use Neural Net are deprecated and might not work in the future. We recommend that you use the Neural platform for new scripts and change your old scripts that use Neural Net to Neural.
The following options for Neural() are available only in JSL:
Multithreading( Boolean )
Set Random Seed( n )
The following message for a Neural object is available only in JSL:
neural_object <<Get NBoost
The following messages for a Neural Fit object are available only in JSL:
neural_object <<(Fit[n] <<Get RSquare Training)
neural_object <<(Fit[n] <<Get RSquare Validation)
neural_object <<(Fit[n] <<Get RSquare Test)
neural_object <<(Fit[n] <<Get Gen RSquare Training)
neural_object <<(Fit[n] <<Get Gen RSquare Validation)
neural_object <<(Fit[n] <<Get Gen RSquare Test)
neural_object <<(Fit[n] <<Get Misclassification Rate Training)
neural_object <<(Fit[n] <<Get Misclassification Rate Validation)
neural_object <<(Fit[n] <<Get Misclassification Rate Test)
neural_object <<(Fit[n] <<Get Average Log Error Training)
neural_object <<(Fit[n] <<Get Average Log Error Validation)
neural_object <<(Fit[n] <<Get Average Log Error Test)
neural_object <<(Fit[n] <<Get RMS Error Training)
neural_object <<(Fit[n] <<Get RMS Error Validation)
neural_object <<(Fit[n] <<Get RMS Error Test)
neural_object <<(Fit[n] <<Get Average Absolute Error Training)
neural_object <<(Fit[n] <<Get Average Absolute Error Validation)
neural_object <<(Fit[n] <<Get Average Absolute Error Test)
neural_object <<(Fit[n] <<Get ROC Area Training)
neural_object <<(Fit[n] <<Get ROC Area Validation)
neural_object <<(Fit[n] <<Get ROC Area Test)
neural_object <<(Fit[n] <<Get Confusion Matrix Training)
neural_object <<(Fit[n] <<Get Confusion Matrix Validation)
neural_object <<(Fit[n] <<Get Confusion Matrix Test)
neural_object <<(Fit[n] <<Get Confusion Rates Training)
neural_object <<(Fit[n] <<Get Confusion Rates Validation)
neural_object <<(Fit[n] <<Get Confusion Rates Test)
neural_object <<(Fit[n] <<Get Seconds)
Partition
The following options for Partition() are available only in JSL:
Missing Value Categories( Boolean )
Set Random Seed( n )
Multithreading( Boolean )
Time Limit ( n )
The following messages for a Partition object are available only in JSL:
partition_object <<Get RSquare Training
partition_object <<Get RSquare Validation
partition_object <<Get RSquare Test
partition_object <<Get Gen RSquare Training
partition_object <<Get Gen RSquare Validation
partition_object <<Get Gen RSquare Test
partition_object <<Get Misclassification Rate Training
partition_object <<Get Misclassification Rate Validation
partition_object <<Get Misclassification Rate Test
partition_object <<Get ROC Area Training
partition_object <<Get ROC Area Validation
partition_object <<Get ROC Area Test
partition_object <<Get Average Log Error Training
partition_object <<Get Average Log Error Validation
partition_object <<Get Average Log Error Test
partition_object <<Get RMS Error Training
partition_object <<Get RMS Error Validation
partition_object <<Get RMS Error Test
partition_object <<Get Average Absolute Error Training
partition_object <<Get Average Absolute Error Validation
partition_object <<Get Average Absolute Error Test
partition_object <<Get Seconds
partition_object <<Get SAS Data Step
partition_object <<Get Tolerant SAS Data Step
partition_object <<Get MM SAS Data Step
partition_object <<Get MM Tolerant SAS Data Step
Time Series
The following options for Time Series() are available only in JSL:
Autocorrelation Lags( n )
Forecast Periods( n )
The following messages for a Time Series object are available only in JSL:
time_series_object <<Maximum Iterations( n )
time_series_object <<Get Models
time_series_object <<Get Model Specs
Choice
The following option for Choice() is available only in JSL:
Convergence Criterion( fraction )
Multivariate
The following message for a Multivariate object is available only in JSL:
multivariate_object << Create SAS Job( )
Hierarchical Clustering
The following messages for a Hierarchical cluster object are available only in JSL:
hier_cluster_object <<Get Column Names
hier_cluster_object <<Get Clusters
hier_cluster_object <<GetDisplayOrder
hier_cluster_object <<GetColumnDisplayOrder
hier_cluster_object <<Get Distance Matrix
KMeans Clustering
The following message for a KMeans cluster object is available only in JSL:
kmeans_cluster_object <<Get Statistics
Life Distribution
The following messages for a Life Distribution object are available only in JSL:
life_dist_object <<Suppress Plot(plot_name)
life_dist_object <<Get Results
life_dist_object <<Get Estimates
life_dist_object <<Get Formula
Fit Life by X
The following messages for a Fit Life by X object are available only in JSL:
fit_life_object <<Set Scriptables( ... )
fit_life_object <<Get Results
Fit Parametric Survival
The following messages for a Fit Parametric Survival object are available only in JSL:
survival_object <<Get Parameter Names
survival_object <<Get Estimates
survival_object <<Get Std Errors
survival_object <<Get Effect Names
survival_object <<Get Effect PValues
Control Chart
The following option for Control Chart() is available only in JSL:
Use Excluded Points on MR( Boolean )
Variability Chart
The following message for a Variability Chart object is available only in JSL:
variability_object <<Show Box Plot Whisker Bars( Boolean )
Pareto Plot
The following message for a Pareto Plot object is available only in JSL:
No Plot(Boolean)
Partial Least Squares
The Partial Least Squares (PLS) platform has replaced PLS. Scripts that use PLS might not work in the future. We recommend that you update your old scripts to use Partial Least Squares instead of PLS and use Partial Least Squares in the future.
Profiler
The following messages for a Profiler object are available only in JSL:
profiler_object <<Get Objective
profiler_object <<Objective Formula
profiler_object <<Get Objective Formula
Surface Plot
The following messages for a Surface Plot object are available only in JSL:
surface_plot_object <<Mode( "Isosurface" | "Sheet" )
surface_plot_object <<Set Z Axis( col, Current Value( n ) )
surface_plot_object <<Set Variable Axis( col, Current Value( n ) )
surface_plot_object <<Response( ... )
surface_plot_object <<Formula( ... )