Teradata R Package Function Reference - DecisionForestEvaluator - Teradata R Package - Look here for syntax, methods and examples for the functions included in the Teradata R Package.

Description

The Forest Analyze function analyzes the model generated by the Forest Drive function and assigns weights to the model variables. The variable/attribute counts in each tree level help you understand the importance of different variables in the decision-making process.

Usage

  td_decision_forest_evaluator_mle (
    object = NULL,
      num.levels = 5,
      object.sequence.column = NULL
  )

Arguments

Value

Function returns an object of class "td_decision_forest_evaluator_mle" which is a named list containing Teradata tbl object.
Named list member can be referenced directly with the "$" operator using name: result

Examples

    # Get the current context/connection
    con <- td_get_context()$connection
    
    # Load the data to run the example
    loadExampleData("decisionforest_example","housing_train")
    
    # Create remote tibble objects.
    housing_train <- tbl(con, "housing_train")
    
    # First train the data, i.e., create a decision forest model
    td_decision_forest_out <- td_decision_forest_mle(data=housing_train,
                                      formula = (homestyle ~ bedrooms + lotsize + gashw + driveway +
                                          stories + recroom + price + garagepl + bathrms + fullbase + airco +
                                          prefarea),
                                      tree.type="classification",
                                      nodesize=1,
                                      variance=0,
                                      max.depth=12,
                                      maxnum.categorical=20,
                                      mtry = 100,
                                      seed = 100,
                                      ntree=50
                                      )
    
    # Analyze generated output.
    decision_forest_evaluator_out <- td_decision_forest_evaluator_mle(object=td_decision_forest_out,
                                         num.levels=5
                                         )