bayesnetnode properties

Bayes Net node iconWith the Bayesian Network (Bayes Net) node, you can build a probability model by combining observed and recorded evidence with real-world knowledge to establish the likelihood of occurrences. The node focuses on Tree Augmented Naïve Bayes (TAN) and Markov Blanket networks that are primarily used for classification.


node = stream.create("bayesnet", "My node")
node.setPropertyValue("continue_training_existing_model", True)
node.setPropertyValue("structure_type", "MarkovBlanket")
node.setPropertyValue("use_feature_selection", True)
# Expert tab
node.setPropertyValue("mode", "Expert")
node.setPropertyValue("all_probabilities", True)
node.setPropertyValue("independence", "Pearson")
Table 1. bayesnetnode properties
bayesnetnode Properties Values Property description
inputs [field1 ... fieldN] Bayesian network models use a single target field, and one or more input fields. Continuous fields are automatically binned. See the topic Common modeling node properties for more information.
continue_training_existing_model flag  
structure_type TAN MarkovBlanket Select the structure to be used when building the Bayesian network.
use_feature_selection flag  
parameter_learning_method Likelihood Bayes Specifies the method used to estimate the conditional probability tables between nodes where the values of the parents are known.
mode Expert Simple  
missing_values flag  
all_probabilities flag  
independence Likelihood Pearson Specifies the method used to determine whether paired observations on two variables are independent of each other.
significance_level number Specifies the cutoff value for determining independence.
maximal_conditioning_set number Sets the maximal number of conditioning variables to be used for independence testing.
inputs_always_selected [field1 ... fieldN] Specifies which fields from the dataset are always to be used when building the Bayesian network.
Note: The target field is always selected.
maximum_number_inputs number Specifies the maximum number of input fields to be used in building the Bayesian network.
calculate_variable_importance flag  
calculate_raw_propensities flag  
calculate_adjusted_propensities flag  
adjusted_propensity_partition Test Validation