def __init__(self,
style=None,
classSet=None,
featureSet=None,
gazetteerFileName=None):
global speculationWords
if classSet == None:
classSet = IdSet(1)
assert (classSet.getId("neg") == 1)
if featureSet == None:
featureSet = IdSet()
self.specWords, self.specWordStems = readWords(speculationWords)
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName != None:
self.gazetteer = Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from", gazetteerFileName
else:
self.gazetteer = None
self.styles = self.getParameters(style, {
"classification": "multiclass",
"speculation_words": True
}, {"classification": ("multiclass", "speculation", "negation")})
def __init__(self, style=["typed","directed","headsOnly"], length=None, types=[], featureSet=None, classSet=None, gazetteer=None, pathGazetteer=None, negFrac=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
if gazetteer != None:
print >> sys.stderr, "Loading gazetteer from", gazetteer
self.gazetteer=Gazetteer.loadGztr(gazetteer)
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer=None
self.pathGazetteer=None
self.pathGazetteerDependencies = None
self.pathGazetteerPairs = None
if pathGazetteer != None:
print >> sys.stderr, "Loading path gazetteer from", pathGazetteer
self.pathGazetteer=PathGazetteer.load(pathGazetteer)
self.pathGazetteerDependencies = PathGazetteer.getDependencies(self.pathGazetteer)
self.pathGazetteerPairs = PathGazetteer.getPairs(self.pathGazetteer)
else:
print >> sys.stderr, "No path gazetteer loaded"
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.negFrac = negFrac
print >> sys.stderr, "Downsampling negatives to", negFrac
self.negRand = random.Random()
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
if True:#"noAnnType" in self.styles:
self.multiEdgeFeatureBuilder.noAnnType = True
if "noMasking" in self.styles:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if "maxFeatures" in self.styles:
self.multiEdgeFeatureBuilder.maximum = True
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
#self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
#if "ontology" in self.styles:
# self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(self.featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
self.eventsByOrigId = {}
self.headTokensByOrigId = {}
self.interSentenceEvents = set()
self.examplesByEventOrigId = {}
self.skippedByType = {}
self.skippedByTypeAndReason = {}
self.builtByType = {}
self.gazMatchCache = {}
def __init__(self,
style=None,
classSet=None,
featureSet=None,
gazetteerFileName=None,
skiplist=None):
if classSet == None:
classSet = IdSet(1)
assert (classSet.getId("neg") == 1)
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName != None:
self.gazetteer = Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from", gazetteerFileName
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer = None
self.styles = self.getParameters(style, [
"rel_features", "wordnet", "bb_features", "giuliano",
"epi_merge_negated", "limit_merged_types", "genia_task1",
"build_for_nameless", "pos_only", "all_tokens", "names",
"pos_pairs", "linear_ngrams", "phospho"
])
# if "selftrain_group" in self.styles:
# self.selfTrainGroups = set()
# if "selftrain_group-1" in self.styles:
# self.selfTrainGroups.add("-1")
# if "selftrain_group0" in self.styles:
# self.selfTrainGroups.add("0")
# if "selftrain_group1" in self.styles:
# self.selfTrainGroups.add("1")
# if "selftrain_group2" in self.styles:
# self.selfTrainGroups.add("2")
# if "selftrain_group3" in self.styles:
# self.selfTrainGroups.add("3")
# print >> sys.stderr, "Self-train-groups:", self.selfTrainGroups
self.skiplist = set()
if skiplist != None:
f = open(skiplist, "rt")
for line in f.readlines():
self.skiplist.add(line.strip())
f.close()
if self.styles["rel_features"]:
self.relFeatureBuilder = RELFeatureBuilder(featureSet)
if self.styles["wordnet"]:
self.wordNetFeatureBuilder = WordNetFeatureBuilder(featureSet)
if self.styles["bb_features"]:
self.bacteriaTokens = PhraseTriggerExampleBuilder.getBacteriaTokens(
PhraseTriggerExampleBuilder.getBacteriaNames())
if self.styles["giuliano"]:
self.giulianoFeatureBuilder = GiulianoFeatureBuilder(featureSet)
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None):
if classSet == None:
classSet = IdSet(1)
assert( classSet.getId("neg") == 1 )
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
if gazetteerFileName!=None:
self.gazetteer=Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from",gazetteerFileName
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer=None
self.styles = style
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None, skiplist=None):
if classSet == None:
classSet = IdSet(1)
assert( classSet.getId("neg") == 1 )
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName!=None:
self.gazetteer=Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from",gazetteerFileName
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer=None
self.styles = self.getParameters(style, ["rel_features", "wordnet", "bb_features", "giuliano",
"epi_merge_negated", "limit_merged_types", "genia_task1",
"build_for_nameless", "pos_only", "all_tokens",
"names", "pos_pairs", "linear_ngrams", "phospho"])
# if "selftrain_group" in self.styles:
# self.selfTrainGroups = set()
# if "selftrain_group-1" in self.styles:
# self.selfTrainGroups.add("-1")
# if "selftrain_group0" in self.styles:
# self.selfTrainGroups.add("0")
# if "selftrain_group1" in self.styles:
# self.selfTrainGroups.add("1")
# if "selftrain_group2" in self.styles:
# self.selfTrainGroups.add("2")
# if "selftrain_group3" in self.styles:
# self.selfTrainGroups.add("3")
# print >> sys.stderr, "Self-train-groups:", self.selfTrainGroups
self.skiplist = set()
if skiplist != None:
f = open(skiplist, "rt")
for line in f.readlines():
self.skiplist.add(line.strip())
f.close()
if self.styles["rel_features"]:
self.relFeatureBuilder = RELFeatureBuilder(featureSet)
if self.styles["wordnet"]:
self.wordNetFeatureBuilder = WordNetFeatureBuilder(featureSet)
if self.styles["bb_features"]:
self.bacteriaTokens = PhraseTriggerExampleBuilder.getBacteriaTokens(PhraseTriggerExampleBuilder.getBacteriaNames())
if self.styles["giuliano"]:
self.giulianoFeatureBuilder = GiulianoFeatureBuilder(featureSet)
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None, skiplist=None):
if classSet == None:
classSet = IdSet(1)
assert classSet.getId("neg") == 1
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
# gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName != None:
self.gazetteer = Gazetteer.loadGztr(gazetteerFileName)
print >>sys.stderr, "Loaded gazetteer from", gazetteerFileName
else:
print >>sys.stderr, "No gazetteer loaded"
self.gazetteer = None
self.styles = style
self.skiplist = set()
if skiplist != None:
f = open(skiplist, "rt")
for line in f.readlines():
self.skiplist.add(line.strip())
f.close()
self.styles = [
"trigger_features",
"typed",
"directed",
"no_linear",
"entities",
"genia_limits",
"noMasking",
"maxFeatures",
]
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
if "graph_kernel" in self.styles:
from FeatureBuilders.GraphKernelFeatureBuilder import GraphKernelFeatureBuilder
self.graphKernelFeatureBuilder = GraphKernelFeatureBuilder(self.featureSet)
if "noAnnType" in self.styles:
self.multiEdgeFeatureBuilder.noAnnType = True
if "noMasking" in self.styles:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if "maxFeatures" in self.styles:
self.multiEdgeFeatureBuilder.maximum = True
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
def __init__(self,
style=None,
classSet=None,
featureSet=None,
gazetteerFileName=None,
skiplist=None):
if classSet == None:
classSet = IdSet(1)
assert (classSet.getId("neg") == 1)
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName != None:
self.gazetteer = Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from", gazetteerFileName
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer = None
self.styles = style
self.skiplist = set()
if skiplist != None:
f = open(skiplist, "rt")
for line in f.readlines():
self.skiplist.add(line.strip())
f.close()
self.styles = [
"trigger_features", "typed", "directed", "no_linear", "entities",
"genia_limits", "noMasking", "maxFeatures"
]
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
if "graph_kernel" in self.styles:
from FeatureBuilders.GraphKernelFeatureBuilder import GraphKernelFeatureBuilder
self.graphKernelFeatureBuilder = GraphKernelFeatureBuilder(
self.featureSet)
if "noAnnType" in self.styles:
self.multiEdgeFeatureBuilder.noAnnType = True
if "noMasking" in self.styles:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if "maxFeatures" in self.styles:
self.multiEdgeFeatureBuilder.maximum = True
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None):
if classSet == None:
classSet = IdSet(1)
assert( classSet.getId("neg") == 1 )
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName!=None:
self.gazetteer=Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from",gazetteerFileName
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer=None
self.styles = style
self.excludedPOS = ["","(",")",",",".","CC","EX","FW","LS","MD","PDT","POS","PRP","PRP$","RBR","RBS","RP","WDT","WP","WP$","``"]
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None):
global speculationWords
if classSet == None:
classSet = IdSet(1)
assert( classSet.getId("neg") == 1 )
if featureSet == None:
featureSet = IdSet()
self.specWords, self.specWordStems = readWords(speculationWords)
ExampleBuilder.__init__(self, classSet, featureSet)
#gazetteerFileName="/usr/share/biotext/GeniaChallenge/SharedTaskTriggerTest/gazetteer-train"
if gazetteerFileName!=None:
self.gazetteer=Gazetteer.loadGztr(gazetteerFileName)
print >> sys.stderr, "Loaded gazetteer from",gazetteerFileName
else:
self.gazetteer=None
self.styles = self.getParameters(style, {"classification":"multiclass", "speculation_words":True}, {"classification":("multiclass", "speculation", "negation")})
def __init__(self,
style=["typed", "directed", "headsOnly"],
length=None,
types=[],
featureSet=None,
classSet=None,
gazetteer=None,
pathGazetteer=None,
negFrac=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert (classSet.getId("neg") == 1)
if gazetteer != None:
print >> sys.stderr, "Loading gazetteer from", gazetteer
self.gazetteer = Gazetteer.loadGztr(gazetteer)
else:
print >> sys.stderr, "No gazetteer loaded"
self.gazetteer = None
self.pathGazetteer = None
self.pathGazetteerDependencies = None
self.pathGazetteerPairs = None
if pathGazetteer != None:
print >> sys.stderr, "Loading path gazetteer from", pathGazetteer
self.pathGazetteer = PathGazetteer.load(pathGazetteer)
self.pathGazetteerDependencies = PathGazetteer.getDependencies(
self.pathGazetteer)
self.pathGazetteerPairs = PathGazetteer.getPairs(
self.pathGazetteer)
else:
print >> sys.stderr, "No path gazetteer loaded"
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.negFrac = negFrac
print >> sys.stderr, "Downsampling negatives to", negFrac
self.negRand = random.Random()
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
if True: #"noAnnType" in self.styles:
self.multiEdgeFeatureBuilder.noAnnType = True
if "noMasking" in self.styles:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if "maxFeatures" in self.styles:
self.multiEdgeFeatureBuilder.maximum = True
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
#self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
#if "ontology" in self.styles:
# self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(self.featureSet)
self.pathLengths = length
assert (self.pathLengths == None)
self.types = types
self.eventsByOrigId = {}
self.headTokensByOrigId = {}
self.interSentenceEvents = set()
self.examplesByEventOrigId = {}
self.skippedByType = {}
self.skippedByTypeAndReason = {}
self.builtByType = {}
self.gazMatchCache = {}
