VariableElimination

class pgmpy.inference.VariableElimination(model)

Bases: Inference

induced_graph(elimination_order)

Returns the induced graph formed by running Variable Elimination on the network.

Parameters:

elimination_order: list, array like

List of variables in the order in which they are to be eliminated.

Examples

>>> import numpy as np
>>> import pandas as pd
>>> from pgmpy.models import DiscreteBayesianNetwork
>>> from pgmpy.inference import VariableElimination
>>> values = pd.DataFrame(
...     np.random.randint(low=0, high=2, size=(1000, 5)),
...     columns=["A", "B", "C", "D", "E"],
... )
>>> model = DiscreteBayesianNetwork(
...     [("A", "B"), ("C", "B"), ("C", "D"), ("B", "E")]
... )
>>> model.fit(values)
<pgmpy.models...DiscreteBayesianNetwork object at 0x...>
>>> inference = VariableElimination(model)
>>> inference.induced_graph(["C", "D", "A", "B", "E"])
<networkx.classes.graph.Graph object at 0x...>

induced_width(elimination_order)

Returns the width (integer) of the induced graph formed by running Variable Elimination on the network. The width is the defined as the number of nodes in the largest clique in the graph minus 1.

Parameters:

elimination_order: list, array like

List of variables in the order in which they are to be eliminated.

Examples

>>> import numpy as np
>>> import pandas as pd
>>> from pgmpy.models import DiscreteBayesianNetwork
>>> from pgmpy.inference import VariableElimination
>>> values = pd.DataFrame(
...     np.random.randint(low=0, high=2, size=(1000, 5)),
...     columns=["A", "B", "C", "D", "E"],
... )
>>> model = DiscreteBayesianNetwork(
...     [("A", "B"), ("C", "B"), ("C", "D"), ("B", "E")]
... )
>>> model.fit(values)
<pgmpy.models...DiscreteBayesianNetwork object at 0x...>
>>> inference = VariableElimination(model)
>>> inference.induced_width(["C", "D", "A", "B", "E"])
3

map_query(variables=None, evidence=None, virtual_evidence=None, elimination_order='MinFill', show_progress=True)

Computes the MAP Query over the variables given the evidence. Returns the highest probable state in the joint distribution of variables.

Parameters:

variables: list

list of variables over which we want to compute the max-marginal.

evidence: dict

a dict key, value pair as {var: state_of_var_observed} None if no evidence

virtual_evidence: list (default:None)

A list of pgmpy.factors.discrete.TabularCPD representing the virtual evidences.

elimination_order: list

order of variable eliminations (if nothing is provided) order is computed automatically

show_progress: boolean

If True, shows a progress bar.

Examples

>>> from pgmpy.inference import VariableElimination
>>> from pgmpy.models import DiscreteBayesianNetwork
>>> import numpy as np
>>> import pandas as pd
>>> values = pd.DataFrame(
...     np.random.randint(low=0, high=2, size=(1000, 5)),
...     columns=["A", "B", "C", "D", "E"],
... )
>>> model = DiscreteBayesianNetwork(
...     [("A", "B"), ("C", "B"), ("C", "D"), ("B", "E")]
... )
>>> model.fit(values)
<pgmpy.models...DiscreteBayesianNetwork object at 0x...>
>>> inference = VariableElimination(model)
>>> phi_query = inference.map_query(["A", "B"])

max_marginal(variables=None, evidence=None, elimination_order='MinFill', show_progress=True)

Computes the max-marginal over the variables given the evidence.

Parameters:

variables: list

list of variables over which we want to compute the max-marginal.

evidence: dict

a dict key, value pair as {var: state_of_var_observed} None if no evidence

elimination_order: list

order of variable eliminations (if nothing is provided) order is computed automatically

Examples

>>> import numpy as np
>>> import pandas as pd
>>> from pgmpy.models import DiscreteBayesianNetwork
>>> from pgmpy.inference import VariableElimination
>>> values = pd.DataFrame(
...     np.random.randint(low=0, high=2, size=(1000, 5)),
...     columns=["A", "B", "C", "D", "E"],
... )
>>> model = DiscreteBayesianNetwork(
...     [("A", "B"), ("C", "B"), ("C", "D"), ("B", "E")]
... )
>>> model.fit(values)
<pgmpy.models...DiscreteBayesianNetwork object at 0x...>
>>> inference = VariableElimination(model)
>>> phi_query = inference.max_marginal(["A", "B"])

query(variables: list[Hashable], evidence: dict[Hashable, int] | None = None, virtual_evidence: list | None = None, elimination_order='greedy', joint=True, show_progress=True)

Parameters:

variables: list

list of variables for which you want to compute the probability

evidence: dict

a dict key, value pair as {var: state_of_var_observed} None if no evidence

virtual_evidence: list (default:None)

A list of pgmpy.factors.discrete.TabularCPD representing the virtual evidences.

elimination_order: str or list (default=’greedy’)

Order in which to eliminate the variables in the algorithm. If list is provided, should contain all variables in the model except the ones in variables. str options are: greedy, WeightedMinFill, MinNeighbors, MinWeight, MinFill. Please refer https://pgmpy.org/exact_infer/ve.html#module-pgmpy.inference.EliminationOrder for details.

joint: boolean (default: True)

If True, returns a Joint Distribution over variables. If False, returns a dict of distributions over each of the variables.

show_progress: boolean

If True, shows a progress bar.

Examples

>>> from pgmpy.inference import VariableElimination
>>> from pgmpy.models import DiscreteBayesianNetwork
>>> import numpy as np
>>> import pandas as pd
>>> values = pd.DataFrame(
...     np.random.randint(low=0, high=2, size=(1000, 5)),
...     columns=["A", "B", "C", "D", "E"],
... )
>>> model = DiscreteBayesianNetwork(
...     [("A", "B"), ("C", "B"), ("C", "D"), ("B", "E")]
... )
>>> model.fit(values)
<pgmpy.models...DiscreteBayesianNetwork object at 0x...>
>>> inference = VariableElimination(model)
>>> phi_query = inference.query(["A", "B"])