This is an old revision of the document!
In the background mode GMDH Shell performs modeling simulation without any interaction. The easiest way to launch the program in the background mode is to use the command line key /auto
Use of the key /auto
executes the project located in the current directory. So, the usual way for background processing is to configure a project visually and then run it from the command line. Example: ““GMDH Shell.exe” /auto
” No other settings required.
If the project is located in another directory, you'll need to run ““GMDH Shell.exe” /auto:C\MyData
”. Of course, there should be a configured project (gmdh_shell.ini
) in that directory.
/auto | Runs the project located in the current directory. Example: “GMDH Shell.exe /auto ” |
/auto:ProjectPath | Runs a project located in ProjectPath . Example:“ GMDH Shell.exe /auto:C:\MyData ” |
/save:FileName.model | Saves a binary simulation file. Example: “ GMDH Shell.exe /save:C:\MyData\TimeSeries.model ” |
/semiauto /semiauto:ProjPath | Semi-automatic mode. Same as /auto , but does not forbid interaction with user. |
gmdh_shell.ini
file. All plug-ins' settings are kept there. Find a section with appropriate name.step
to 10, write /pr.step:10
./im
— importer/pr
— preprocessor/ca
— solver/po
— postprocessor/ex
— exporter
The plug-in may have some extra options that aren't stored in gmdh_shell.ini
.
/noexport | Prevents the export plug-in from exporting simulation results. |
/ex.file:FPath | Saves result to FPath. Example: “ GMDH Shell.exe /auto /ex.file:C:\MyData\example.txt ” |
/im.file:FPath | import file from path FPath. Example: “ GMDH Shell.exe /auto /im.file:C:\MyData\example.xls ” |
/pr.calc:n | Number of forecasts to simulate = n . |
/pr.skip:n | Skip observations = n . |
/pr:unk:n | Number of unknown values = n . |
/pr:limit:n | Calculate only (0=all ) = n . |
/ca.ncpu:n | Number of parallel threads |
/ca.ncpu:n | Number of parallel tasks. |
/ca.reserve:b | Reserve cluster, Yes: b = 1 ; No: b = 0 . |