def _updateDistribution_first(self):
if isinstance(self.baseline,
(pmml.PoissonDistribution, pmml.GaussianDistribution)):
self.baselinePartialSums = self.baseline.descendant(
pmml.X_ODG_PartialSums, exception=False, maxdepth=2)
if self.baselinePartialSums is None:
self.baselinePartialSums = pmml.X_ODG_PartialSums()
if not self.baseline.exists(pmml.Extension):
self.baseline.children.append(pmml.Extension())
self.baseline.child(pmml.Extension).children.append(
self.baselinePartialSums)
if isinstance(self.baseline, pmml.PoissonDistribution):
self.baselineUpdator = self.engine.producerUpdateScheme.updator(
SUM1, SUMX)
if self.updateExisting:
self.baselineUpdator.initialize({
COUNT:
self.baselinePartialSums.attrib.get("COUNT", 0),
SUM1:
self.baselinePartialSums.attrib.get("SUM1", 0.),
SUMX:
self.baselinePartialSums.attrib.get("SUMX", 0.)
})
if COUNT in self.baselineUpdator.counters:
self.baselinePartialSums.attrib[
"COUNT"] = self.baselineUpdator.counters[COUNT]
self.baselinePartialSums.attrib[
"SUM1"] = self.baselineUpdator.counters[SUM1]
self.baselinePartialSums.attrib[
"SUMX"] = self.baselineUpdator.counters[SUMX]
elif isinstance(self.baseline, pmml.GaussianDistribution):
self.baselineUpdator = self.engine.producerUpdateScheme.updator(
SUM1, SUMX, SUMXX)
if self.updateExisting:
self.baselineUpdator.initialize({
COUNT:
self.baselinePartialSums.attrib.get("COUNT", 0),
SUM1:
self.baselinePartialSums.attrib.get("SUM1", 0.),
SUMX:
self.baselinePartialSums.attrib.get("SUMX", 0.),
SUMXX:
self.baselinePartialSums.attrib.get("SUMXX", 0.)
})
if COUNT in self.baselineUpdator.counters:
self.baselinePartialSums.attrib[
"COUNT"] = self.baselineUpdator.counters[COUNT]
self.baselinePartialSums.attrib[
"SUM1"] = self.baselineUpdator.counters[SUM1]
self.baselinePartialSums.attrib[
"SUMX"] = self.baselineUpdator.counters[SUMX]
self.baselinePartialSums.attrib[
"SUMXX"] = self.baselineUpdator.counters[SUMXX]
elif isinstance(self.baseline, pmml.UniformDistribution):
self.baselineUpdator = self.engine.producerUpdateScheme.updator(
MIN, MAX)
if self.updateExisting:
self.baselineUpdator.initialize({
MIN:
self.baseline.attrib["lower"],
MAX:
self.baseline.attrib["upper"]
})
else:
raise NotImplementedError, "Only production of Gaussian, Poisson, and Uniform distributions has been implemented."
if self.alternateField is not None:
if not testDistributions.exists(pmml.Alternate):
raise RuntimeError, "alternateField requested but there is no <Alternate/> distribution in the PMML"
self.alternate = testDistributions.child(pmml.Alternate).child()
if isinstance(
self.alternate,
(pmml.PoissonDistribution, pmml.GaussianDistribution)):
self.alternatePartialSums = self.alternate.descendant(
pmml.X_ODG_PartialSums, exception=False, maxdepth=2)
if self.alternatePartialSums is None:
self.alternatePartialSums = pmml.X_ODG_PartialSums()
if not self.alternate.exists(pmml.Extension):
self.alternate.children.append(pmml.Extension())
self.alternate.child(pmml.Extension).children.append(
self.alternatePartialSums)
if isinstance(self.alternate, pmml.PoissonDistribution):
self.alternateUpdator = self.engine.producerUpdateScheme.updator(
SUM1, SUMX)
if self.updateExisting:
self.alternateUpdator.initialize({
COUNT:
self.alternatePartialSums.attrib.get("COUNT", 0),
SUM1:
self.alternatePartialSums.attrib.get("SUM1", 0.),
SUMX:
self.alternatePartialSums.attrib.get("SUMX", 0.)
})
if COUNT in self.alternateUpdator.counters:
self.alternatePartialSums.attrib[
"COUNT"] = self.alternateUpdator.counters[COUNT]
self.alternatePartialSums.attrib[
"SUM1"] = self.alternateUpdator.counters[SUM1]
self.alternatePartialSums.attrib[
"SUMX"] = self.alternateUpdator.counters[SUMX]
elif isinstance(self.alternate, pmml.GaussianDistribution):
self.alternateUpdator = self.engine.producerUpdateScheme.updator(
SUM1, SUMX, SUMXX)
if self.updateExisting:
self.alternateUpdator.initialize({
COUNT:
self.alternatePartialSums.attrib.get("COUNT", 0),
SUM1:
self.alternatePartialSums.attrib.get("SUM1", 0.),
SUMX:
self.alternatePartialSums.attrib.get("SUMX", 0.),
SUMXX:
self.alternatePartialSums.attrib.get("SUMXX", 0.)
})
if COUNT in self.alternateUpdator.counters:
self.alternatePartialSums.attrib[
"COUNT"] = self.alternateUpdator.counters[COUNT]
self.alternatePartialSums.attrib[
"SUM1"] = self.alternateUpdator.counters[SUM1]
self.alternatePartialSums.attrib[
"SUMX"] = self.alternateUpdator.counters[SUMX]
self.alternatePartialSums.attrib[
"SUMXX"] = self.alternateUpdator.counters[SUMXX]
elif isinstance(self.alternate, pmml.UniformDistribution):
self.alternateUpdator = self.engine.producerUpdateScheme.updator(
MIN, MAX)
if self.updateExisting:
self.alteranteUpdator.initialize({
MIN:
self.alterante.attrib["lower"],
MAX:
self.alterante.attrib["upper"]
})
else:
raise NotImplementedError, "Only production of Gaussian, Poisson, and Uniform distributions has been implemented."
else:
self.alternate = None
def initialize(self, **params):
"""Initialize a clustering model producer."""
if "resume" in params:
self.resume = pmml.boolCheck(params["resume"])
del params["resume"]
else:
self.resume = False
if "numberOfTrials" in params:
self.numberOfTrials = int(params["numberOfTrials"])
del params["numberOfTrials"]
else:
self.numberOfTrials = 10
if "numberToKeep" in params:
self.numberToKeep = int(params["numberToKeep"])
del params["numberToKeep"]
else:
self.numberToKeep = 3
if "maturityThreshold" in params:
self.maturityThreshold = int(params["maturityThreshold"])
del params["maturityThreshold"]
else:
self.maturityThreshold = 100
if "initialStability" in params:
self.initialStability = int(params["initialStability"])
del params["initialStability"]
else:
self.initialStability = 100
if "overrideSignificance" in params:
self.overrideSignificance = float(params["overrideSignificance"])
del params["overrideSignificance"]
if self.overrideSignificance == 0.:
self.overrideSignificance = None
else:
self.overrideSignificance = 5.
self.model = self.segmentRecord.pmmlModel
self.dataDistribution = self.engine.producerUpdateScheme.updator(COVARIANCE(self.model.numberOfFields))
self.distanceMeasure = (self.model.child(pmml.ComparisonMeasure).attrib["kind"] == "distance")
# put PartialSums in the model if they're not already there; pick up old values if you're resuming
extension = self.model.child(pmml.Extension, exception=False)
if extension is None:
extension = pmml.Extension()
self.model.children.append(extension)
if self.resume:
self.sumOfDistances = extension.child(lambda x: isinstance(x, pmml.X_ODG_PartialSums) and x.attrib.get("name", None) == "SumOfDistances", exception=False)
else:
index = extension.index(lambda x: isinstance(x, pmml.X_ODG_PartialSums) and x.attrib.get("name", None) == "SumOfDistances", exception=False)
if index is not None:
del extension[index]
self.sumOfDistances = None
if self.sumOfDistances is None:
self.sumOfDistances = pmml.X_ODG_PartialSums(name="SumOfDistances", COUNT=0, SUM1=0., SUMX=0., SUMXX=0.)
extension.children.append(self.sumOfDistances)
self.partialSums = {}
for theid, cluster in zip(self.model.ids, self.model.cluster):
for i, field in enumerate(self.model.fields):
fullname = "%s.%s" % (theid, field)
if self.resume:
partialSum = extension.child(lambda x: isinstance(x, pmml.X_ODG_PartialSums) and x.attrib.get("name", None) == fullname, exception=False)
else:
index = extension.index(lambda x: isinstance(x, pmml.X_ODG_PartialSums) and x.attrib.get("name", None) == fullname, exception=False)
if index is not None:
del extension[index]
partialSum = None
if partialSum is None:
partialSum = pmml.X_ODG_PartialSums(name=fullname, SUM1=1., SUMX=cluster.value[i])
extension.children.append(partialSum)
self.partialSums[fullname] = partialSum
# create the first trial using the values constructed above (they come from the PMML file if resume is True)
trialFromPmml = new.instance(TrialClusterSet)
trialFromPmml.updator = self.engine.producerUpdateScheme.updator(COUNT, SUM1, SUMX, SUMXX)
trialFromPmml.updator.initialize({COUNT: self.sumOfDistances.attrib["COUNT"], SUM1: self.sumOfDistances.attrib["SUM1"], SUMX: self.sumOfDistances.attrib["SUMX"], SUMXX: self.sumOfDistances.attrib["SUMXX"]})
trialFromPmml.clusters = []
for theid, cluster in zip(self.model.ids, self.model.cluster):
trialCluster = new.instance(TrialCluster)
trialCluster.fields = []
trialCluster.initialPosition = []
for field in self.model.fields:
partialSum = self.partialSums["%s.%s" % (theid, field)]
u = self.engine.producerUpdateScheme.updator(SUM1, SUMX)
u.initialize({SUM1: partialSum.attrib["SUM1"], SUMX: partialSum.attrib["SUMX"]})
trialCluster.fields.append(u)
trialCluster.initialPosition = list(cluster.value)
trialFromPmml.clusters.append(trialCluster)
self.trials = [trialFromPmml]
if len(params) > 0:
raise TypeError, "Unrecognized parameters %s" % params