def setUp(self):
config.StringParameter('test.param0', 'a param', default='foo')
config.StringParameter('test.param1', 'a param', config.oneof('foo', 'bar'))
config.IntParameter('test.param2', 'a param', default=20)
config.IntParameter('test.param3', 'a param', config.atmost(100))
config.IntParameter('test.param4', 'a param', config.atleast(100))
config.IntParameter('test.param5', 'a param', config.between(10,100))
config.IntParameter('test.param6', 'a param', lambda x: x == 50)
config.FloatParameter('test.param7', 'a param', config.between(1.3, 2.7))
def setUp(self):
config.StringParameter('test.param0', 'a param', default='foo')
config.StringParameter('test.param1', 'a param',
config.oneof('foo', 'bar'))
config.IntParameter('test.param2', 'a param', default=20)
config.IntParameter('test.param3', 'a param', config.atmost(100))
config.IntParameter('test.param4', 'a param', config.atleast(100))
config.IntParameter('test.param5', 'a param', config.between(10, 100))
config.IntParameter('test.param6', 'a param', lambda x: x == 50)
config.FloatParameter('test.param7', 'a param',
config.between(1.3, 2.7))
class LearnerResult:
"""Class for storing any and all output of a learner.
This is a mutable container for networks and scores. In the future, it will
also be the place to collect statistics related to the learning task.
"""
#
# Parameters
#
_params = (
config.StringParameter(
'result.filename',
'The name of the result output file',
default='result.pebl'
),
config.StringParameter(
'result.format',
'The format for the pebl result file (pickle or html)',
config.oneof('pickle', 'html'),
default='pickle'
),
config.StringParameter(
'result.outdir',
'Directory for html report.',
default='result'
),
config.IntParameter(
'result.size',
"""Number of top-scoring networks to save. Specify 0 to indicate that
all scored networks should be saved.""",
default=1000
)
)
def __init__(self, learner_=None, size=None):
self.data = learner_.data if learner_ else None
self.nodes = self.data.variables if self.data else None
self.size = size or config.get('result.size')
self.networks = []
self.nethashes = {}
self.runs = []
def start_run(self):
"""Indicates that the learner is starting a new run."""
self.runs.append(LearnerRunStats(time.time()))
def stop_run(self):
"""Indicates that the learner is stopping a run."""
self.runs[-1].end = time.time()
def add_network(self, net, score):
"""Add a network and score to the results."""
nets = self.networks
nethashes = self.nethashes
nethash = hash(net.edges)
if self.size == 0 or len(nets) < self.size:
if nethash not in nethashes:
snet = _ScoredNetwork(copy(net.edges), score)
insort(nets, snet)
nethashes[nethash] = 1
elif score > nets[0].score and nethash not in nethashes:
nethashes.pop(hash(nets[0].edges))
nets.remove(nets[0])
snet = _ScoredNetwork(copy(net.edges), score)
insort(nets, snet)
nethashes[nethash] = 1
def tofile(self, filename=None):
"""Save the result to a python pickle file.
The result can be later read using the result.fromfile function.
"""
filename = filename or config.get('result.filename')
with open(filename, 'w') as fp:
cPickle.dump(self, fp)
def tohtml(self, outdir=None):
"""Create a html report of the result.
outdir is a directory to create html files inside.
"""
if _can_create_html:
HtmlFormatter().htmlreport(
self,
outdir or config.get('result.outdir')
)
else:
print "Cannot create html reports because some dependencies are missing."
@property
def posterior(self):
"""Returns a posterior object for this result."""
return posterior.from_sorted_scored_networks(
self.nodes,
list(reversed(self.networks))
)
#
# Parameters
#
_pmissingdatahandler = config.StringParameter(
'evaluator.missingdata_evaluator',
"""
Evaluator to use for handling missing data. Choices include:
* gibbs: Gibb's sampling
* maxentropy_gibbs: Gibbs's sampling over all completions of the
missing values that result in maximum entropy discretization for the
variables.
* exact: exact enumeration of all possible missing values (only
useable when there are few missing values)
""",
config.oneof('gibbs', 'exact', 'maxentropy_gibbs'),
default='gibbs'
)
_missingdata_evaluators = {
'gibbs': MissingDataNetworkEvaluator,
'exact': MissingDataExactNetworkEvaluator,
'maxentropy_gibbs': MissingDataMaximumEntropyNetworkEvaluator
}
def fromconfig(data_=None, network_=None, prior_=None):
"""Create an evaluator based on configuration parameters.
This function will return the correct evaluator based on the relevant
configuration parameters.
#
# Parameters
#
_pmissingdatahandler = config.StringParameter(
'evaluator.missingdata_evaluator',
"""
Evaluator to use for handling missing data. Choices include:
* gibbs: Gibb's sampling
* maxentropy_gibbs: Gibbs's sampling over all completions of the
missing values that result in maximum entropy discretization for the
variables.
* exact: exact enumeration of all possible missing values (only
useable when there are few missing values)
""",
config.oneof('gibbs', 'exact', 'maxentropy_gibbs'),
default='gibbs')
_missingdata_evaluators = {
'gibbs': MissingDataNetworkEvaluator,
'exact': MissingDataExactNetworkEvaluator,
'maxentropy_gibbs': MissingDataMaximumEntropyNetworkEvaluator
}
def fromconfig(data_=None, network_=None, prior_=None):
"""Create an evaluator based on configuration parameters.
This function will return the correct evaluator based on the relevant
configuration parameters.