Autotune Action Set

This section contains Lua code for the analysis in the CASL version of this example, which contains details about the results.

Note: In order to run this code, the data that are described in the CASL version need to be accessible to the CAS server. One way to do this is to convert the iris data to the comma-separated-value (CSV) file iris.csv and then use the following code to load the CSV file into CAS:

s:loadtable{casLib="casuser", path="iris.csv"}

For more information about coding in Lua, see Getting Started with SAS Viya for Lua and SAS Viya: System Programming Guide.

The following Lua code uses the tuneGradientBoostTree action to automatically tune the hyperparameters of a gradient boosting tree model that is trained on the iris data table. The data and the parameters are the same as in the PROC CAS version of this example. Note that the syntax of the trainOptions parameter here is the same as the syntax of the gbtreeTrain action. For more information about the gbtreeTrain action, see "Decision Tree Action Set," SAS Visual Analytics: Programming Guide.

   result = s:autotune_tuneGradientBoostTree{
        trainOptions = {
           table     = {name="iris"},
           inputs    = {"SepalLength",
                        "SepalWidth",
                        "PetalLength",
                        "PetalWidth"
                       },
           target    = "Species",
           nominal   = {"Species"},
           casout    = {name = "gradboost_iris_model",
                        replace=true
                       }
       },
       tunerOptions={seed=12345}

       --[[ Tuning Parameters

       You do not need to specify any tuning parameters for the default
       tuning process. If you want to make adjustments to the default
       tuning process, uncomment the following block of code and change
       any of the tuning parameters' attributes.

       , tuningParameters={
          {name="nTree",         lb=20,   ub=150,  initValue=100,  exclude=false},
          {name="m",             lb=1,    ub=4,    initValue=4,    exclude=false},
          {name="learningRate",  lb=0.01, ub=1.0,  initValue=0.1,  exclude=false},
          {name="subSampleRate", lb=0.1,  ub=1.0,  initValue=0.5,  exclude=false},
          {name="lasso",         lb=0.0,  ub=10.0, initValue=0.0,  exclude=false},
          {name="ridge",         lb=0.0,  ub=10.0, initValue=1.0,  exclude=false},
          {name="nBins",         lb=20,   ub=100,  initValue=50,   exclude=false},
          {name="maxLevel",      lb=2,    ub=7,    initValue=5,    exclude=false},
          {name="leafSize",      valueList={1, 5, 10, 20, 40, 80, 160, 320},
                                                   initValue=5,    exclude=true }
       }

       --]]

   }

The following commands display the tables that are produced by this action call:

print(result.TunerInfo)
print(result.TunerResults)
print(result.IterationHistory)
print(result.EvaluationHistory)
print(result.BestConfiguration)
print(result.TunerSummary)
print(result.TunerTiming)
print(result.TunerCasOutputTables)
print(result.HyperparameterImportance)

For details about the results of this analysis, see the PROC CAS version of this example.

This section contains Python code for the analysis in the CASL version of this example, which contains details about the results.

Note: In order to run this code, the data that are described in the CASL version need to be accessible to the CAS server. One way to do this is to convert the iris data to the comma-separated-value (CSV) file iris.csv and then use the following code to load the CSV file into CAS:

s.upload_file('iris.csv')

For more information about coding in Python, see Getting Started with SAS Viya for Python and SAS Viya: System Programming Guide.

The following Python code uses the tuneGradientBoostTree action to automatically tune the hyperparameters of a gradient boosting tree model that is trained on the iris data table. The data and the parameters are the same as in the PROC CAS version of this example. Note that the syntax of the trainOptions parameter here is the same as the syntax of the gbtreeTrain action. For more information about the gbtreeTrain action, see "Decision Tree Action Set," SAS Visual Analytics: Programming Guide.

   result = s.autotune.tuneGradientBoostTree(
        trainOptions = {
           "table"   : {"name":"iris"},
           "inputs"  : {"SepalLength",
                        "SepalWidth",
                        "PetalLength",
                        "PetalWidth"
                       },
           "target"  : "Species",
           "nominal" : {"Species"},
           "casout"  : {"name":"gradboost_iris_model"}
        },
        tunerOptions={"seed":12345}

   # Tuning Parameters

   # You do not need to specify any tuning parameters for the default
   # tuning process. If you want to make adjustments to the default
   # tuning process, uncomment the following block of code and change
   # any of the tuning parameters' attributes.

   # , tuningParameters=[
   #    {"name":"nTree",
   #         "lb":20,   "ub":150,  "initValue":100,  "exclude":"false"},
   #    {"name":"m",
   #         "lb":1,    "ub":4,    "initValue":4,    "exclude":"false"},
   #    {"name":"learningRate",
   #         "lb":0.01, "ub":1.0,  "initValue":0.1,  "exclude":"false"},
   #    {"name":"subSampleRate",
   #         "lb":0.1,  "ub":1.0,  "initValue":0.5,  "exclude":"false"},
   #    {"name":"lasso",
   #         "lb":0.0,  "ub":10.0, "initValue":0.0,  "exclude":"false"},
   #    {"name":"ridge",
   #         "lb":0.0,  "ub":10.0, "initValue":1.0,  "exclude":"false"},
   #    {"name":"nBins",
   #         "lb":20,   "ub":100,  "initValue":50,   "exclude":"false"},
   #    {"name":"maxLevel",
   #         "lb":2,    "ub":7,    "initValue":5,    "exclude":"false"},
   #    {"name":"leafSize",
   #        "valueList":{1, 5, 10, 20, 40, 80, 160, 320},
   #                                   "initValue":5, "exclude":"true"}
   #  ]

   )

The following commands display the tables that are produced by this action call:

print(result.TunerInfo)
print(result.TunerResults)
print(result.IterationHistory)
print(result.IterationHistory)
print(result.EvaluationHistory)
print(result.BestConfiguration)
print(result.TunerSummary)
print(result.TunerTiming)
print(result.TunerCasOutputTables)
print(result.HyperparameterImportance)

For details about the results of this analysis, see the PROC CAS version of this example.

This example is not available for the R programming language.