def getIdSets(self, classIds=None, featureIds=None, allowNewIds=True):
# Class ids
#print classIds
#print featureIds
if classIds != None and os.path.exists(classIds):
print >> sys.stderr, "Using predefined class names from", classIds
classSet = IdSet(allowNewIds=allowNewIds)
classSet.load(classIds)
else:
print >> sys.stderr, "No predefined class names"
classSet = None
# Feature ids
if featureIds != None and os.path.exists(featureIds):
print >> sys.stderr, "Using predefined feature names from", featureIds
featureSet = IdSet(allowNewIds=allowNewIds)
featureSet.load(featureIds)
else:
print >> sys.stderr, "No predefined feature names"
featureSet = None
return classSet, featureSet
def getIdSets(self, classIds=None, featureIds=None, allowNewIds=True):
# Class ids
#print classIds
#print featureIds
if classIds != None and os.path.exists(classIds):
print >> sys.stderr, "Using predefined class names from", classIds
classSet = IdSet(allowNewIds=allowNewIds)
classSet.load(classIds)
else:
print >> sys.stderr, "No predefined class names"
classSet = None
# Feature ids
if featureIds != None and os.path.exists(featureIds):
print >> sys.stderr, "Using predefined feature names from", featureIds
featureSet = IdSet(allowNewIds=allowNewIds)
featureSet.load(featureIds)
else:
print >> sys.stderr, "No predefined feature names"
featureSet = None
return classSet, featureSet
psyco.full()
print >> sys.stderr, "Found Psyco, using"
except ImportError:
print >> sys.stderr, "Psyco not installed"
defaultAnalysisFilename = "/usr/share/biotext/ComplexPPI/BioInferForComplexPPIVisible.xml"
optparser = OptionParser(usage="%prog [options]\nCreate an html visualization for a corpus.")
optparser.add_option("-i", "--invariant", default=None, dest="invariant", help="Corpus in analysis format", metavar="FILE")
optparser.add_option("-v", "--variant", default=None, dest="variant", help="Corpus in analysis format", metavar="FILE")
(options, args) = optparser.parse_args()
#invariantExamples = ExampleUtils.readExamples(os.path.join(options.invariant, "examples.txt"))
variantExamples = ExampleUtils.readExamples(os.path.join(options.variant, "test-triggers.examples"))
invariantFeatureSet = IdSet()
invariantFeatureSet.load(os.path.join(options.invariant, "feature_names.txt"))
invariantClassSet = IdSet()
invariantClassSet.load(os.path.join(options.invariant, "class_names.txt"))
variantFeatureSet = IdSet()
variantFeatureSet.load(os.path.join(options.variant, "test-triggers.examples.feature_names"))
variantClassSet = IdSet()
variantClassSet.load(os.path.join(options.variant, "test-triggers.examples.class_names"))
counter = ProgressCounter(len(variantExamples))
for example in variantExamples:
counter.update()
example[1] = invariantClassSet.getId(variantClassSet.getName(example[1]))
newFeatures = {}
for k,v in example[2].iteritems():
newFeatures[ invariantFeatureSet.getId(variantFeatureSet.getName(k)) ] = v
# Optimize
optimizationSets = Example.divideExamples(exampleSets[0])
evaluationArgs = {"classSet":exampleBuilder.classSet}
if options.parameters != None:
paramDict = splitParameters(options.parameters)
bestResults = classifier.optimize([optimizationSets[0]], [optimizationSets[1]], paramDict, Evaluation, evaluationArgs)
else:
bestResults = classifier.optimize([optimizationSets[0]], [optimizationSets[1]], evaluationClass=Evaluation, evaluationArgs=evaluationArgs)
else:
print >> sys.stderr, "Using predefined model"
bestResults = [None,None,{}]
for k,v in classifierParamDict.iteritems():
bestResults[2][k] = v
featureSet = IdSet()
featureSet.load(os.path.join(classifierParamDict["predefined"][0], "feature_names.txt"))
classSet = None
if os.path.exists(os.path.join(classifierParamDict["predefined"][0], "class_names.txt")):
classSet = IdSet()
classSet.load(os.path.join(classifierParamDict["predefined"][0], "class_names.txt"))
exampleBuilder = ExampleBuilder(featureSet=featureSet, classSet=classSet, **splitParameters(options.exampleBuilderParameters))
# Save training sets
if options.output != None:
print >> sys.stderr, "Saving example sets to", options.output
Example.writeExamples(exampleSets[0], options.output + "/examplesTrain.txt")
if not classifierParamDict.has_key("predefined"):
Example.writeExamples(optimizationSets[0], options.output + "/examplesOptimizationTest.txt")
Example.writeExamples(optimizationSets[1], options.output + "/examplesOptimizationTrain.txt")
TableUtils.writeCSV(bestResults[2], options.output +"/best_parameters.csv")
# Optimize and train
bestResults = classifier.optimize([optimizationSets[0]],
[optimizationSets[1]], paramDict,
Evaluation, evaluationArgs)
else:
bestResults = classifier.optimize([optimizationSets[0]],
[optimizationSets[1]],
evaluationClass=Evaluation,
evaluationArgs=evaluationArgs)
else:
print >> sys.stderr, "Using predefined model"
bestResults = [None, None, {}]
for k, v in classifierParamDict.iteritems():
bestResults[2][k] = v
featureSet = IdSet()
featureSet.load(
os.path.join(classifierParamDict["predefined"][0],
"feature_names.txt"))
classSet = None
if os.path.exists(
os.path.join(classifierParamDict["predefined"][0],
"class_names.txt")):
classSet = IdSet()
classSet.load(
os.path.join(classifierParamDict["predefined"][0],
"class_names.txt"))
exampleBuilder = ExampleBuilder(featureSet=featureSet,
classSet=classSet,
**splitParameters(
options.exampleBuilderParameters))
# Save training sets
if options.output != None:
help="Corpus in analysis format",
metavar="FILE")
optparser.add_option("-v",
"--variant",
default=None,
dest="variant",
help="Corpus in analysis format",
metavar="FILE")
(options, args) = optparser.parse_args()
#invariantExamples = ExampleUtils.readExamples(os.path.join(options.invariant, "examples.txt"))
variantExamples = ExampleUtils.readExamples(
os.path.join(options.variant, "test-triggers.examples"))
invariantFeatureSet = IdSet()
invariantFeatureSet.load(
os.path.join(options.invariant, "feature_names.txt"))
invariantClassSet = IdSet()
invariantClassSet.load(os.path.join(options.invariant, "class_names.txt"))
variantFeatureSet = IdSet()
variantFeatureSet.load(
os.path.join(options.variant, "test-triggers.examples.feature_names"))
variantClassSet = IdSet()
variantClassSet.load(
os.path.join(options.variant, "test-triggers.examples.class_names"))
counter = ProgressCounter(len(variantExamples))
for example in variantExamples:
counter.update()
example[1] = invariantClassSet.getId(
variantClassSet.getName(example[1]))