cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
JMP is taking Discovery online, April 16 and 18. Register today and join us for interactive sessions featuring popular presentation topics, networking, and discussions with the experts.
Choose Language Hide Translation Bar

Col>modelling utilities> explore outlier scripting

HI All,

I have a question. Is it possible to have jsl script for" Col>modelling utilities> explore outlier" ?

Thanks

Ram

15 REPLIES 15

Re: Col>modelling utilities> explore outlier scripting

Hello, Wendy. thanks for response.

Will be looking forward to see the full script functionality for this.

Rgds

Ram

johnm
Level III

Re: Col>modelling utilities> explore outlier scripting

Hello,

 

I very much like this outlier feature.

I understand there is limited scripting to this point in time.

In looking at the tree structure, I understand how to 'click' on a selection box.

But is there a way to select (click) a variable listed in the Column in the "OutlineBox(4): Robust Estimates and Outliers" ?

 

Thanks,
John

Re: Col>modelling utilities> explore outlier scripting

Hi, John.

JMP 13 introduced more JSL support for Explore Outliers.  See the Scripting Index (Help > Scripting Index) for details.  However if you have not yet updated to JMP 13, you can still select rows by navigating to the TableBox.  Below is an example to demonstrate:

 

Names Default To Here( 1 );
dt = Open( "$SAMPLE_DATA/Water Treatment.jmp" );
dt << Select Column Group( "Sensor Measurements" );
obj = dt << Explore Outliers( Quantile Range Outliers( 1 ) );

Report( obj )[Table Box( 1 )] << Set Selected Rows( [1, 2] );

Hope that helps!

 

Wendy
johnm
Level III

Re: Col>modelling utilities> explore outlier scripting

Hi Wendy,



Yes, this is exactly what I was wanting to know how to do.



Thanks very much,

John


ghartel
Level III

Re: Col>modelling utilities> explore outlier scripting

So, how owuld you do this in version 13? When I say reort(obj) << change to missing(); it says 'select a column...'. I could do the table box thing you showed, but I don't know how many columns will have missing values, or what their names would be.  What the best way of scripting that in 13?

thanks

ghartel
Level III

Re: Col>modelling utilities> explore outlier scripting

I did the following but hoped something more elgant was available:

EO = Explore Outliers(
        Y( Eval( VariableList ) ),
        Show only columns with outliers( 1 ),
        Quantile Range Outliers
) << journal;
n = n items(Report( EO )[Table Box( 1 )][1] << get );
If( n,
        Report( EO )[Table Box( 1 )] << Set Selected Rows( 1 :: n );
        EO << Change to Missing();
);