def estimate_cpd(self, node):
"""
Method to estimate the CPD for a given variable.
Parameters
----------
node: int, string (any hashable python object)
The name of the variable for which the CPD is to be estimated.
Returns
-------
CPD: TabularCPD
Examples
--------
>>> import pandas as pd
>>> from pgm.models import BayesianModel
>>> from pgm.estimators import MaximumLikelihoodEstimator
>>> data = pd.DataFrame(data={'A': [0, 0, 1], 'B': [0, 1, 0], 'C': [1, 1, 0]})
>>> model = BayesianModel([('A', 'C'), ('B', 'C')])
>>> cpd_A = MaximumLikelihoodEstimator(model, data).estimate_cpd('A')
>>> print(cpd_A)
╒══════╤══════════╕
│ A(0) │ 0.666667 │
├──────┼──────────┤
│ A(1) │ 0.333333 │
╘══════╧══════════╛
>>> cpd_C = MaximumLikelihoodEstimator(model, data).estimate_cpd('C')
>>> print(cpd_C)
╒══════╤══════╤══════╤══════╤══════╕
│ A │ A(0) │ A(0) │ A(1) │ A(1) │
├──────┼──────┼──────┼──────┼──────┤
│ B │ B(0) │ B(1) │ B(0) │ B(1) │
├──────┼──────┼──────┼──────┼──────┤
│ C(0) │ 0.0 │ 0.0 │ 1.0 │ 0.5 │
├──────┼──────┼──────┼──────┼──────┤
│ C(1) │ 1.0 │ 1.0 │ 0.0 │ 0.5 │
╘══════╧══════╧══════╧══════╧══════╛
"""
state_counts = self.state_counts(node)
# if a column contains only `0`s (no states observed for some configuration
# of parents' states) fill that column uniformly instead
state_counts.ix[:, (state_counts == 0).all()] = 1
parents = sorted(self.model.get_parents(node))
parents_cardinalities = [len(self.state_names[parent]) for parent in parents]
node_cardinality = len(self.state_names[node])
cpd = TabularCPD(node, node_cardinality, np.array(state_counts),
evidence=parents,
evidence_card=parents_cardinalities,
state_names=self.state_names)
cpd.normalize()
return cpd
def estimate_cpd(self, node, prior_type='BDeu', pseudo_counts=[], equivalent_sample_size=5):
"""
Method to estimate the CPD for a given variable.
Parameters
----------
node: int, string (any hashable python object)
The name of the variable for which the CPD is to be estimated.
prior_type: 'dirichlet', 'BDeu', 'K2',
string indicting which type of prior to use for the model parameters.
- If 'prior_type' is 'dirichlet', the following must be provided:
'pseudo_counts' = dirichlet hyperparameters; a list or dict
with a "virtual" count for each variable state.
The virtual counts are added to the actual state counts found in the data.
(if a list is provided, a lexicographic ordering of states is assumed)
- If 'prior_type' is 'BDeu', then an 'equivalent_sample_size'
must be specified instead of 'pseudo_counts'. This is equivalent to
'prior_type=dirichlet' and using uniform 'pseudo_counts' of
`equivalent_sample_size/(node_cardinality*np.prod(parents_cardinalities))`.
- A prior_type of 'K2' is a shorthand for 'dirichlet' + setting every pseudo_count to 1,
regardless of the cardinality of the variable.
Returns
-------
CPD: TabularCPD
Examples
--------
>>> import pandas as pd
>>> from pgm.models import BayesianModel
>>> from pgm.estimators import BayesianEstimator
>>> data = pd.DataFrame(data={'A': [0, 0, 1], 'B': [0, 1, 0], 'C': [1, 1, 0]})
>>> model = BayesianModel([('A', 'C'), ('B', 'C')])
>>> estimator = BayesianEstimator(model, data)
>>> cpd_C = estimator.estimate_cpd('C', prior_type="dirichlet", pseudo_counts=[1, 2])
>>> print(cpd_C)
╒══════╤══════╤══════╤══════╤════════════════════╕
│ A │ A(0) │ A(0) │ A(1) │ A(1) │
├──────┼──────┼──────┼──────┼────────────────────┤
│ B │ B(0) │ B(1) │ B(0) │ B(1) │
├──────┼──────┼──────┼──────┼────────────────────┤
│ C(0) │ 0.25 │ 0.25 │ 0.5 │ 0.3333333333333333 │
├──────┼──────┼──────┼──────┼────────────────────┤
│ C(1) │ 0.75 │ 0.75 │ 0.5 │ 0.6666666666666666 │
╘══════╧══════╧══════╧══════╧════════════════════╛
"""
node_cardinality = len(self.state_names[node])
parents = sorted(self.model.get_parents(node))
parents_cardinalities = [len(self.state_names[parent]) for parent in parents]
if prior_type == 'K2':
pseudo_counts = [1] * node_cardinality
elif prior_type == 'BDeu':
alpha = float(equivalent_sample_size) / (node_cardinality * np.prod(parents_cardinalities))
pseudo_counts = [alpha] * node_cardinality
elif prior_type == 'dirichlet':
if not len(pseudo_counts) == node_cardinality:
raise ValueError("'pseudo_counts' should have length {0}".format(node_cardinality))
if isinstance(pseudo_counts, dict):
pseudo_counts = sorted(pseudo_counts.values())
else:
raise ValueError("'prior_type' not specified")
state_counts = self.state_counts(node)
bayesian_counts = (state_counts.T + pseudo_counts).T
cpd = TabularCPD(node, node_cardinality, np.array(bayesian_counts),
evidence=parents,
evidence_card=parents_cardinalities,
state_names=self.state_names)
cpd.normalize()
return cpd
