Skip to main content

Parameter learning in Python

This example makes use of the Python code in Data Frame Utils.

# __author__ = 'Bayes Server'
# __version__= '0.4'

import pandas as pd
import jpype # pip install jpype1 (version 1.2.1 or later)
import jpype.imports
from jpype.types import *

classpath = "lib/bayesserver-10.8.jar" # TODO download the Bayes Server Java API, and adjust the path

# Launch the JVM

import data_frame_utils as dfu

# import the Java modules
from com.bayesserver import *
from com.bayesserver.inference import *
from com.bayesserver.learning.parameters import *
from import *
from jpype import java, JImplements, JOverride

# Uncomment the following line and change the license key, if you are using a licensed version
# License.validate("xxx")

class ConsoleParameterLearningProgress(object):

def update(self, info):
See ParameterLearningProgress in the Bayes Server .NET or Java API docs for details.
print('Iterations: ', info.getIterationCount(), ', log-likelihood: ', info.getLogLikelihood())

def getDistributionMonitoring(self):
See ParameterLearningProgress in the Bayes Server .NET or Java API docs for details.
return DistributionMonitoring.NONE

def train_network():
Example code that learns the parameters of a Bayesian network from data.
network = create_network_structure() # we manually construct the network here, but it could be loaded from a file
x = network.getVariables().get('X', True)
y = network.getVariables().get('Y', True)

# now learn the parameters from the data in Tutorial 2 - Mixture model

df = pd.read_csv('data/mixture_model.csv') # Note: Saved as csv from the Tutorial data installed with Bayes Server
dt = dfu.to_data_table(df)

# We will use the RelevanceTree algorithm here, as it is optimized for parameter learning
learning = ParameterLearning(network, RelevanceTreeInferenceFactory())
learning_options = ParameterLearningOptions()

progress = ConsoleParameterLearningProgress()

data_reader_command = DataTableDataReaderCommand(dt)

reader_options = ReaderOptions(None, None) # we do not have a case column or weight column in this example

# here we map variables to database columns
# in this case the variables and database columns have the same name
variable_references = [
VariableReference(x, ColumnValueType.VALUE, x.getName()),
VariableReference(y, ColumnValueType.VALUE, y.getName())

# note that although this example only has non temporal data
# we could have included additional temporal variables and data

evidence_reader_command = DefaultEvidenceReaderCommand(

result = learning.learn(evidence_reader_command, learning_options)

print('Log likelihood = ' + str(result.getLogLikelihood()))

def create_network_structure():
network = Network()

node_cluster = Node('Cluster', ['Cluster1', 'Cluster2', 'Cluster3'])

x = Variable('X', VariableValueType.CONTINUOUS)
y = Variable('Y', VariableValueType.CONTINUOUS)

node_position = Node('Position', JArray(Variable)([x, y]))

network.getLinks().add(Link(node_cluster, node_position))

# at this point the Bayesian network structure is fully specified

return network