I'm trying to explore a continuous target variable in SPSS Modeler v. 18.2, using a split variable ("Cohort"). In other models that have a nominal target variable, I'm able to use the auto-classifier to generate models on each split---but in this model when I use the auto-numeric node it ignores the splits entirely. Here is the stream:
In the data file, I have "Cohort" set to Split:
In the node, in the Fields tab, I have added Cohort to the splits...
...and in the Model tab I have checked the build model for each split box:
The nugget doesn't include the splits---in the Summary tab it doesn't look like it's in the model at all:
My work-around is to use Select nodes for each split but that has disadvantages---thank you in advance for any help/corrections.
I am currently using IBM SPSS Modeler 18.0 but I am seeing the exact same behavior when using one of the demo data sets supplied with Modeler. I would consider this to be a defect and something that would need to be addressed by IBM's development team.
I suggest that you replicate the issue with one of the data sets from the "Demos" folder such as the "car_insurance_claims.sav" and then open a support ticket with the IBM SPSS technical support to have this resolved.
Related
I am creating a data dictionary and I am supposed to track the location of any used field in a workbook. For example (superstore sample data), I need to specify which sheets/dashboards have the [sub-category] field.
My dataset has hundreds of measures/dimensions/calc fields, so it's incredibly time exhaustive to click into every single sheet/dashboard just to see if a field exists in there, so is there a quicker way to do this?
One robust, but not free, approach is to use Tableau's Data Catalog which is part of the Tableau Server Data Management Add-On
Another option is to build your own cross reference - You could start with Chris Gerrard's ruby libraries described in the article http://tableaufriction.blogspot.com/2018/09/documenting-dashboards-and-their.html
According to IBM's online help:
Optionally, for CHAID, QUEST, and C&R Tree models, an additional field can be added that indicates the ID for the node to which each record is assigned.
I cannot find that option. I am using an (exhaustive) CHAID which adds the $R- (prediction field) variable but there is no $RI- (node identifier field) variable. Just in case IBM was being literal I checked running a regular CHAID (not exhaustive) but still without getting the $RI-variable I need.
I know that in SPSS v. 25 this is easily configured so is IBM just confused in their online help for modeler, or am I missing something obvious? Thanks in advance for any help.
The get the rule identifier added to the data set, you need to first train the model to generate the model nugget.
You can then edit (or open) the model nugget and select the "Settings" tab. Here you will find the option "Rule identifier" which must be checked to include the ID of node the each record is assigned.
It is important to realize that this is a setting in the generated mudel nugget and not in the modeling node. This also means that this setting must be checked (and rechecked) each time the model is retrained and the nugget is regenerated.
Is there any possibility to filter data source based on the selected item in another data source?
If it is possible please share some directions. Thanks.
This feature is planned to be released in the next major version of Code Effects rules engine.
I've written a NetLogo model to model agent movement in a landscape. I'd like to run this model from the command prompt, using AWs/Google Compute. The model uses about 500MB worth of input rasters and shapefiles and writes rasters and csv files. It also uses the extensions gis, rnd, cf, table and csv.
Would this be possible using the Controlling API? (https://github.com/NetLogo/NetLogo/wiki/Controlling-API). Can I just use the steps listed in the link? I have not tried running NetLogo from the command prompt before.
Also, I do not want to run BehaviourSpace as it is not relevant to this model.
A BehaviorSpace experiment can consist of only a single run, so BehaviorSpace may actually be relevant to you here. You only need to write one short XML file (or no new files at all, if the experiment setup you want is already part of the model) to do it this way.
Whereas if you go through the controlling API, you will have to write and compile Java (or Scala) code, which is a substantially more complex task.
But if you decide to go the controlling API route: yes, that works too, and it is documented, as you've already noticed.
I would like to change the properties of multiple diagrams together rather than clicking on them one by one. Does anyone know how this can be achieved?
You can use the scripting facility of Enterprise Architect to loop the diagrams you would like to change and update them.
See this section of the manual to get help.
There is a bunch of example scripts included with EA, either from the local scripts, or from the EAScriptLib MDG.
Another source of examples is my Github repository: https://github.com/GeertBellekens/Enterprise-Architect-VBScript-Library
You could write a SQL to manipulate your database. t_diagram.PDATA holds a long cryptic string where one part is ScalePI=0; (which is the default for no scaling). You can alter that to be ScalePI=1; (meaning scale to one page).
String manipulations vary from database to database. So you need to write your own which you can execute in a script using
Repository.Execute("UPDATE t_diagram ...")
Note that you should test this in a sandbox first since invalid SQLs can easily disrupt your whole repository.