def __init__(self, style=None, length=None, types=[], featureSet=None, classSet=None):
# reset style regardless of input
#style="trigger_features:typed:directed:no_linear:entities:genia_limits:noMasking:maxFeatures"
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
defaultNone = ["binary", "trigger_features","typed","directed","no_linear","entities","genia_limits",
"noAnnType", "noMasking", "maxFeatures", "no_merge", "disable_entity_features",
"disable_single_element_features", "disable_ngram_features", "disable_path_edge_features"]
defaultParameters = {}
for name in defaultNone:
defaultParameters[name] = None
defaultParameters["keep_intersentence"] = False
defaultParameters["keep_intersentence_gold"] = True
defaultParameters["no_arg_count_upper_limit"] = False
self.styles = self._setDefaultParameters(defaultParameters)
self.styles = self.getParameters(style)
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.multiEdgeFeatureBuilder.noAnnType = self.styles["noAnnType"]
self.multiEdgeFeatureBuilder.maskNamedEntities = not self.styles["noMasking"]
self.multiEdgeFeatureBuilder.maximum = self.styles["maxFeatures"]
#self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = True
def __init__(self,
style=["typed", "directed"],
length=None,
types=[],
featureSet=None,
classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert (classSet.getId("neg") == 1)
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
if style.find(",") != -1:
style = style.split(",")
self.styles = style
self.negFrac = None
self.posPairGaz = POSPairGazetteer()
for s in style:
if s.find("negFrac") != -1:
self.negFrac = float(s.split("_")[-1])
print >> sys.stderr, "Downsampling negatives to", self.negFrac
self.negRand = random.Random(15)
elif s.find("posPairGaz") != -1:
self.posPairGaz = POSPairGazetteer(
loadFrom=s.split("_", 1)[-1])
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder = TriggerFeatureBuilder(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.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
if "ontology" in self.styles:
self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(
self.featureSet)
if "nodalida" in self.styles:
self.nodalidaFeatureBuilder = NodalidaFeatureBuilder(
self.featureSet)
#IF LOCAL
if "bioinfer_limits" in self.styles:
self.bioinferOntologies = OntologyUtils.getBioInferTempOntology()
#self.bioinferOntologies = OntologyUtils.loadOntologies(OntologyUtils.g_bioInferFileName)
#ENDIF
self.pathLengths = length
assert (self.pathLengths == None)
self.types = types
if "random" in self.styles:
from FeatureBuilders.RandomFeatureBuilder import RandomFeatureBuilder
self.randomFeatureBuilder = RandomFeatureBuilder(self.featureSet)
def __init__(self, style):
ExampleBuilder.__init__(self)
self.featureBuilder = EdgeFeatureBuilder(self.featureSet)
self.style = style
if not "binary" in style:
self.classSet = IdSet(1)
assert (self.classSet.getId("neg") == 1)
def __init__(self, examples, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
self.classSet = classSet
# define class ids in alphabetical order
self.classSet = classSet
if classSet != None:
classNames = sorted(classSet.Ids.keys())
else:
classNames = []
# make an ordered list of class ids
self.classes = []
for className in classNames:
self.classes.append(classSet.getId(className))
# create data structures for per-class evaluation
self.dataByClass = {}
for cls in self.classes:
self.dataByClass[cls] = EvaluationData()
# hack for unnamed classes
if len(self.dataByClass) == 0:
self.dataByClass[1] = EvaluationData()
self.dataByClass[2] = EvaluationData()
#self.untypedUndirected = None
self.untypedCurrentMajorId = None
self.untypedPredictionQueue = []
self.untypedUndirected = EvaluationData()
#self.AUC = None
if predictions != None:
self._calculate(examples, predictions)
def __init__(self, style="trigger_features:typed:directed:no_linear:entities:genia_limits:noMasking:maxFeatures", length=None, types=[], featureSet=None, classSet=None):
# reset style regardless of input
style="trigger_features:typed:directed:no_linear:entities:genia_limits:noMasking:maxFeatures"
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = self.getParameters(style, ["trigger_features","typed","directed","no_linear","entities","genia_limits",
"noAnnType", "noMasking", "maxFeatures", "no_merge", "disable_entity_features",
"disable_single_element_features", "disable_ngram_features", "disable_path_edge_features"])
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.multiEdgeFeatureBuilder.noAnnType = self.styles["noAnnType"]
self.multiEdgeFeatureBuilder.maskNamedEntities = not self.styles["noMasking"]
self.multiEdgeFeatureBuilder.maximum = self.styles["maxFeatures"]
self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = True
def __init__(self, style=["typed", "directed", "headsOnly"], length=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert classSet.getId("neg") == 1
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(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.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
def __init__(self,
style=["typed", "directed", "headsOnly"],
length=None,
types=[],
featureSet=None,
classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert (classSet.getId("neg") == 1)
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(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.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
def __init__(self, examples, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
self.classSet = classSet
# define class ids in alphabetical order
self.classSet = classSet
if classSet != None:
classNames = sorted(classSet.Ids.keys())
else:
classNames = []
# make an ordered list of class ids
self.classes = []
for className in classNames:
self.classes.append(classSet.getId(className))
# create data structures for per-class evaluation
self.dataByClass = {}
for cls in self.classes:
self.dataByClass[cls] = EvaluationData()
# hack for unnamed classes
if len(self.dataByClass) == 0:
self.dataByClass[1] = EvaluationData()
self.dataByClass[2] = EvaluationData()
#self.untypedUndirected = None
self.untypedCurrentMajorId = None
self.untypedPredictionQueue = []
self.untypedUndirected = EvaluationData()
#self.AUC = None
if predictions != None:
self._calculate(examples, predictions)
def __init__(self, style=["typed","directed","headsOnly"], length=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(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.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
if "random" in self.styles:
from FeatureBuilders.RandomFeatureBuilder import RandomFeatureBuilder
self.randomFeatureBuilder = RandomFeatureBuilder(self.featureSet)
def devectorizePredictions(self, predictions):
"""
Converts a dense Numpy array of [examples][width][height][features] into
the corresponding Python list matrices where features are stored in a key-value
dictionary.
"""
targetIds = IdSet(filename=self.model.get(self.tag+"ids.classes"), locked=True)
dimMatrix = int(self.model.getStr("dimMatrix"))
dimLabels = int(self.model.getStr("dimLabels"))
predictions = reshape(predictions, (predictions.shape[0], dimMatrix, dimMatrix, dimLabels))
rangeMatrix = range(dimMatrix)
labels = np.argmax(predictions, axis=-1)
values = np.max(predictions, axis=-1)
minValue = np.min(values)
maxValue = np.max(values)
valRange = maxValue - minValue
print "MINMAX", minValue, maxValue
devectorized = []
for exampleIndex in range(predictions.shape[0]):
#print predictions[exampleIndex]
devectorized.append([])
for i in rangeMatrix:
devectorized[-1].append([])
for j in rangeMatrix:
features = {}
devectorized[-1][-1].append(features)
maxFeature = labels[exampleIndex][i][j]
predValue = predictions[exampleIndex][i][j][maxFeature]
features[targetIds.getName(maxFeature)] = float(predValue)
features["color"] = self.getColor((predValue - minValue) / valRange)
return devectorized
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=None, length=None, types=[], featureSet=None, classSet=None):
# reset style regardless of input
#style="trigger_features:typed:directed:no_linear:entities:genia_limits:noMasking:maxFeatures"
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
defaultNone = ["binary", "trigger_features","typed","directed","no_linear","entities","genia_limits",
"noAnnType", "noMasking", "maxFeatures", "no_merge", "disable_entity_features",
"disable_single_element_features", "disable_ngram_features", "disable_path_edge_features"]
defaultParameters = {}
for name in defaultNone:
defaultParameters[name] = None
defaultParameters["keep_intersentence"] = False
defaultParameters["keep_intersentence_gold"] = True
self.styles = self._setDefaultParameters(defaultParameters)
self.styles = self.getParameters(style)
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.multiEdgeFeatureBuilder.noAnnType = self.styles["noAnnType"]
self.multiEdgeFeatureBuilder.maskNamedEntities = not self.styles["noMasking"]
self.multiEdgeFeatureBuilder.maximum = self.styles["maxFeatures"]
#self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = True
def __init__(self, style=None, classSet=None, featureSet=None, gazetteerFileName=None, skiplist=None):
if classSet == None:
classSet = IdSet(1)
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
assert( classSet.getId("neg") == 1 )
#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._setDefaultParameters(["rel_features", "wordnet", "bb_features", "giuliano",
"epi_merge_negated", "limit_merged_types", "genia_task1",
"names", "build_for_nameless", "skip_for_nameless",
"pos_only", "all_tokens", "pos_pairs", "linear_ngrams",
"phospho", "drugbank_features", "ddi13_features", "metamap",
"only_types", "ontobiotope_features", "bb_spans", "w2v",
"no_context"])
self.styles = self.getParameters(style)
# 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()
#self.bacteriaTokens = PhraseTriggerExampleBuilder.getBacteriaTokens(PhraseTriggerExampleBuilder.getBacteriaNames())
if self.styles["giuliano"]:
self.giulianoFeatureBuilder = GiulianoFeatureBuilder(featureSet)
if self.styles["drugbank_features"]:
self.drugFeatureBuilder = DrugFeatureBuilder(featureSet)
if self.styles["ontobiotope_features"]:
self.ontobiotopeFeatureBuilder = OntoBiotopeFeatureBuilder(self.featureSet)
if self.styles["w2v"]:
self.wordVectorFeatureBuilder = WordVectorFeatureBuilder(featureSet)
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)
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
assert (classSet.getId("neg") == 1)
#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._setDefaultParameters([
"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"
])
self.styles = self.getParameters(style)
# 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(
)
#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)
self.styles = style
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = False
def addExamples(exampleFile, predictionFile, classFile, matrix):
classSet = IdSet(filename=classFile)
f = open(predictionFile, "rt")
for example in ExampleUtils.readExamples(exampleFile, False):
pred = int(f.readline().split()[0])
predClasses = classSet.getName(pred)
goldClasses = classSet.getName(example[1])
for predClass in predClasses.split("---"):
for goldClass in goldClasses.split("---"):
matrix[predClass][goldClass]
matrix[goldClass][predClass] += 1
f.close()
def addExamples(exampleFile, predictionFile, classFile, matrix):
classSet = IdSet(filename=classFile)
f = open(predictionFile, "rt")
for example in ExampleUtils.readExamples(exampleFile, False):
pred = int(f.readline().split()[0])
predClasses = classSet.getName(pred)
goldClasses = classSet.getName(example[1])
for predClass in predClasses.split("---"):
for goldClass in goldClasses.split("---"):
matrix[predClass][goldClass]
matrix[goldClass][predClass] += 1
f.close()
def run(EvaluatorClass,
inputCorpusFile,
goldCorpusFile,
parse,
tokenization=None,
target="both",
entityMatchFunction=compareEntitiesSimple,
removeIntersentenceInteractions=False,
errorMatrix=False,
verbose=False):
print >> sys.stderr, "##### EvaluateInteractionXML #####"
print >> sys.stderr, "Comparing input", inputCorpusFile, "to gold", goldCorpusFile
# Class sets are used to convert the types to ids that the evaluator can use
classSets = {}
if EvaluatorClass.type == "binary":
classSets["entity"] = IdSet(idDict={
"True": 1,
"False": -1
},
locked=True)
classSets["interaction"] = IdSet(idDict={
"True": 1,
"False": -1
},
locked=True)
negativeClassId = -1
elif EvaluatorClass.type == "multiclass":
classSets["entity"] = IdSet(idDict={"neg": 1}, locked=False)
classSets["interaction"] = IdSet(idDict={"neg": 1}, locked=False)
negativeClassId = 1
else:
sys.exit("Unknown evaluator type")
# Load corpus and make sentence graphs
goldCorpusElements = None
if goldCorpusFile != None:
goldCorpusElements = SentenceGraph.loadCorpus(
goldCorpusFile, parse, tokenization, False,
removeIntersentenceInteractions)
predictedCorpusElements = SentenceGraph.loadCorpus(
inputCorpusFile, parse, tokenization, False,
removeIntersentenceInteractions)
# Compare the corpora and print results on screen
return processCorpora(EvaluatorClass,
predictedCorpusElements,
goldCorpusElements,
target,
classSets,
negativeClassId,
entityMatchFunction,
errorMatrix=errorMatrix,
verbose=verbose)
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)
self._setDefaultParameters(["co_limits"])
self.styles = self.getParameters(style)
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = False
self.phraseTypeCounts = {}
def __init__(self, style=["typed","directed"], length=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
if style.find(",") != -1:
style = style.split(",")
self.styles = style
self.negFrac = None
self.posPairGaz = POSPairGazetteer()
for s in style:
if s.find("negFrac") != -1:
self.negFrac = float(s.split("_")[-1])
print >> sys.stderr, "Downsampling negatives to", self.negFrac
self.negRand = random.Random(15)
elif s.find("posPairGaz") != -1:
self.posPairGaz = POSPairGazetteer(loadFrom=s.split("_", 1)[-1])
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder = TriggerFeatureBuilder(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.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
if "ontology" in self.styles:
self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(self.featureSet)
if "nodalida" in self.styles:
self.nodalidaFeatureBuilder = NodalidaFeatureBuilder(self.featureSet)
#IF LOCAL
if "bioinfer_limits" in self.styles:
self.bioinferOntologies = OntologyUtils.getBioInferTempOntology()
#self.bioinferOntologies = OntologyUtils.loadOntologies(OntologyUtils.g_bioInferFileName)
#ENDIF
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
if "random" in self.styles:
from FeatureBuilders.RandomFeatureBuilder import RandomFeatureBuilder
self.randomFeatureBuilder = RandomFeatureBuilder(self.featureSet)
def __init__(self, style=None, classSet=None, featureSet=None):
if classSet == None:
classSet = IdSet(1)
assert( classSet.getId("neg") == 1 )
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
self.styles = style
self.timerBuildExamples = Timer(False)
self.timerCrawl = Timer(False)
self.timerCrawlPrecalc = Timer(False)
self.timerMatrix = Timer(False)
self.timerMatrixPrecalc = Timer(False)
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):
if classSet == None:
classSet = IdSet(1)
assert (classSet.getId("neg") == 1)
if featureSet == None:
featureSet = IdSet()
ExampleBuilder.__init__(self, classSet, featureSet)
self.styles = style
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = False
def __init__(self, examples=None, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
self.keep = set(["CPR:3", "CPR:4", "CPR:5", "CPR:6", "CPR:9"])
self.classSet = classSet
self.results = None
self.internal = None
if predictions != None:
for example in examples:
if example[3] != None:
print >> sys.stderr, "ChemProt Evaluator:"
self._calculateExamples(examples, predictions)
else:
print >> sys.stderr, "No example extra info, skipping ChemProt evaluation"
break
self.internal = AveragingMultiClassEvaluator(
examples, predictions, classSet)
print >> sys.stderr, "AveragingMultiClassEvaluator:"
print >> sys.stderr, self.internal.toStringConcise()
def __init__(self, examples, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
SharedTaskEvaluator.corpusElements = Core.SentenceGraph.loadCorpus(
SharedTaskEvaluator.corpusFilename, SharedTaskEvaluator.parse,
SharedTaskEvaluator.tokenization)
# Build interaction xml
xml = BioTextExampleWriter.write(
examples, predictions, SharedTaskEvaluator.corpusElements, None,
SharedTaskEvaluator.ids + ".class_names",
SharedTaskEvaluator.parse, SharedTaskEvaluator.tokenization)
#xml = ExampleUtils.writeToInteractionXML(examples, predictions, SharedTaskEvaluator.corpusElements, None, "genia-direct-event-ids.class_names", SharedTaskEvaluator.parse, SharedTaskEvaluator.tokenization)
# Convert to GENIA format
gifxmlToGenia(xml,
SharedTaskEvaluator.geniaDir,
task=SharedTaskEvaluator.task,
verbose=False)
# Use GENIA evaluation tool
self.results = evaluateSharedTask(SharedTaskEvaluator.geniaDir,
task=SharedTaskEvaluator.task,
evaluations=["approximate"],
verbose=False)
def __init__(self, style):
ExampleBuilder.__init__(self)
self.featureBuilder = EdgeFeatureBuilder(self.featureSet)
self.style = style
if not "binary" in style:
self.classSet = IdSet(1)
assert( self.classSet.getId("neg") == 1 )
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)
self._setDefaultParameters(["co_limits"])
self.styles = self.getParameters(style)
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = False
self.phraseTypeCounts = {}
def __init__(self, style=["typed","directed","headsOnly"], length=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.counts = {}
self.countsPerType = {}
self.untypedCounts = {}
self.tokenCounts = {}
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=None,
classSet=None,
featureSet=None,
gazetteerFileName=None,
skiplist=None):
if classSet == None:
classSet = IdSet(0)
if featureSet == None:
featureSet = IdSet(0)
ExampleBuilder.__init__(self, classSet, featureSet)
self.featureIds = self.featureSet
self.labelIds = self.classSet
self._setDefaultParameters([
"directed", "undirected", "cutoff", "annotated_only",
"all_positive", "wv", "epochs", "html", "autoencode", "lr",
"patience"
])
self.styles = self.getParameters(style)
if self.styles["cutoff"]:
self.styles["cutoff"] = int(self.styles["cutoff"])
self.wvIndices = None
self.embeddingMatrices = None
if self.styles.get("wv") != None:
indexPath = self.styles.get("wv") + "-indices.json.gz"
if not os.path.exists(indexPath):
indexPath = os.path.join(Settings.DATAPATH, "wv", indexPath)
print >> sys.stderr, "Loading word vector indices from", indexPath
with gzip.open(indexPath, "rt") as f:
self.wvIndices = json.load(f)["indices"]
self.embeddingMatrices = []
self.dimMatrix = 32
self.rangeMatrix = range(self.dimMatrix)
self.featureMatrices = []
self.labelMatrices = []
self.tokenLists = []
def __init__(self, style=["typed","directed","headsOnly"], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(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)
self.triggerFeatureBuilder.useNonNameEntities = False
def __init__(self, classSet=None, featureSet=None):
if(type(classSet) == types.StringType):
self.classSet = IdSet(filename=classSet)
else:
self.classSet = classSet
if(type(featureSet) == types.StringType):
self.featureSet = IdSet(filename=featureSet)
else:
self.featureSet = featureSet
self.featureTag = ""
self.exampleStats = ExampleStats()
self.parse = None
self.tokenization = None
#self.idFileTag = None
self.classIdFilename = None
self.featureIdFilename = None
self.styles = None
self._defaultParameters = None
self._parameterValueLimits = None
self._setDefaultParameters(["sentenceLimit"])
def __init__(self,
style=["typed", "directed", "headsOnly"],
length=None,
types=[],
featureSet=None,
classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert (classSet.getId("neg") == 1)
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = style
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
self.counts = {}
self.countsPerType = {}
self.untypedCounts = {}
self.tokenCounts = {}
def __init__(self, classSet=None, featureSet=None):
if (type(classSet) == types.StringType):
self.classSet = IdSet(filename=classSet)
else:
self.classSet = classSet
if (type(featureSet) == types.StringType):
self.featureSet = IdSet(filename=featureSet)
else:
self.featureSet = featureSet
self.featureTag = ""
self.exampleStats = ExampleStats()
self.parse = None
self.tokenization = None
#self.idFileTag = None
self.classIdFilename = None
self.featureIdFilename = None
self.styles = {}
self._defaultParameters = None
self._parameterValueLimits = None
self._setDefaultParameters(["sentenceLimit"])
self.debug = False
def __init__(self, examples, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
self.classSet = classSet
self.dataByClass = defaultdict(EvaluationData)
#self.untypedUndirected = None
self.untypedCurrentMajorId = None
self.untypedPredictionQueue = []
self.untypedUndirected = EvaluationData()
#self.AUC = None
if predictions != None:
self._calculate(examples, predictions)
def getClassSet(rows, classSet=None):
from Core.IdSet import IdSet
classNames = set()
for row in rows:
classNames.add(row["class"])
classNames.add(row["prediction"])
# In the case of multiclass, give integer id:s for the classes
if classSet == None:
classSet = IdSet()
assert(not ("1" in classNames and "neg" in classNames))
assert("1" in classNames or "neg" in classNames)
if "1" in classNames:
classSet.defineId("1",1)
else:
classSet.defineId("neg",1)
for i in sorted(list(classNames)):
if i != "1" and i != "neg":
classSet.getId(i)
return classSet
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 __init__(self, examples=None, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
#self.examples = examples
#self.predictions = predictions
self.truePositives = 0
self.falsePositives = 0
self.trueNegatives = 0
self.falseNegatives = 0
self.precision = None
self.recall = None
self.fScore = None
self.AUC = None
self.type = "binary"
if predictions != None:
self._calculate(examples, predictions)
def __init__(self, examples, predictions=None, classSet=None):
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
if type(predictions) == types.StringType: # predictions are in file
predictions = ExampleUtils.loadPredictions(predictions)
if type(examples) == types.StringType: # examples are in file
examples = ExampleUtils.readExamples(examples, False)
corpusElements = Core.SentenceGraph.loadCorpus(BXEvaluator.corpusFilename, BXEvaluator.parse, BXEvaluator.tokenization)
# Build interaction xml
xml = BioTextExampleWriter.write(examples, predictions, corpusElements, None, BXEvaluator.ids+".class_names", BXEvaluator.parse, BXEvaluator.tokenization)
xml = ix.splitMergedElements(xml, None)
xml = ix.recalculateIds(xml, None, True)
#xml = ExampleUtils.writeToInteractionXML(examples, predictions, SharedTaskEvaluator.corpusElements, None, "genia-direct-event-ids.class_names", SharedTaskEvaluator.parse, SharedTaskEvaluator.tokenization)
# Convert to GENIA format
STFormat.ConvertXML.toSTFormat(xml, BXEvaluator.geniaDir, outputTag="a2")
#gifxmlToGenia(xml, BXEvaluator.geniaDir, task=SharedTaskEvaluator.task, verbose=False)
# Use GENIA evaluation tool
self.results = BioNLP11GeniaTools.evaluateBX(BXEvaluator.geniaDir, corpusName=BXEvaluator.corpusTag)
corpusElements = None
def getClassSet(rows, classSet=None):
from Core.IdSet import IdSet
classNames = set()
for row in rows:
classNames.add(row["class"])
classNames.add(row["prediction"])
# In the case of multiclass, give integer id:s for the classes
if classSet == None:
classSet = IdSet()
assert(not ("1" in classNames and "neg" in classNames))
assert("1" in classNames or "neg" in classNames)
if "1" in classNames:
classSet.defineId("1",1)
else:
classSet.defineId("neg",1)
for i in sorted(list(classNames)):
if i != "1" and i != "neg":
classSet.getId(i)
return classSet
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 compareExamples(examples1, examples2, features1, features2=None):
ExampleUtils.readExamples(examples1)
exampleIter1 = ExampleUtils.readExamples(examples1)
exampleIter2 = ExampleUtils.readExamples(examples2)
features1 = IdSet(filename=features1)
if features2 != None:
features2 = IdSet(filename=features2)
else:
features2 = features1
# Compare feature sets
if set(features1.Ids.keys()) != set(features2.Ids.keys()):
print "Feature sets differ"
# Compare examples
counter = ProgressCounter(step=1)
for e1, e2 in itertools.izip(exampleIter1, exampleIter2):
counter.update()
assert e1[0] == e2[0], (removeFeatures(e1), removeFeatures(e2))
if e1[1] != e2[1]:
print "Class differs"
print " E1", removeFeatures(e1)
print " E2", removeFeatures(e2)
f1 = getFeatureNames(e1, features1)
f2 = getFeatureNames(e2, features2)
f1Set = set(f1)
f2Set = set(f2)
f1Only = f1Set.difference(f2Set)
f2Only = f2Set.difference(f1Set)
if len(f1Only) > 0 or len(f2Only) > 0:
print "Features differ"
print " E1", removeFeatures(e1)
print " E2", removeFeatures(e2)
if len(f1Only) > 0:
print " E1-only features:", f1Only
if len(f2Only) > 0:
print " E2-only features:", f2Only
else:
assert len(f1) == len(f2)
fCount = 0
differ = False
for feature1, feature2 in zip(f1, f2):
#f1Id = features1.getId(feature1, createIfNotExist=False)
#if f1Id == 454 or feature1 == "e1_strength_Positive_regulation":
# print "!!!!!!!!!!!", 454, feature1, e1[2][f1Id]
if feature1 != feature2:
if not differ:
print "Feature order differs for example", e1[0]
differ = True
print "[" + feature1 + "/" + feature2 + "](" + str(fCount) + ") ",
else:
f1Id = features1.getId(feature1, createIfNotExist=False)
f2Id = features2.getId(feature2, createIfNotExist=False)
f1Value = e1[2][f1Id]
f2Value = e2[2][f2Id]
if f1Value != f2Value:
if not differ:
print "Feature values differ", e1[0]
differ = True
print "[" + feature1 + "/" + str(f1Id) + "]" + "[" + str(f1Value) + "/" + str(f2Value) + "]" + "(" + str(fCount) + ") ",
fCount += 1
if differ:
print
counter.endUpdate()
def writeXML(self,
examples,
predictions,
corpus,
outputFile,
classSet=None,
parse=None,
tokenization=None,
goldCorpus=None,
exampleStyle=None,
structureAnalyzer=None):
"""
Writes task 3 examples to interaction XML. Assumes task 3 classification
is done with SVMMulticlass Classifier, used for two classes.
"""
print >> sys.stderr, "Adding task 3 to Interaction XML"
examples, predictions = self.loadExamples(examples, predictions)
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
classIds = None
if classSet != None:
classIds = classSet.getIds()
corpusTree = ETUtils.ETFromObj(corpus)
corpusRoot = corpusTree.getroot()
# Determine subtask
task3Type = None
for example in examples:
assert example[3].has_key("t3type")
task3Type = example[3]["t3type"]
break
if task3Type == None:
if outputFile != None:
print >> sys.stderr, "Writing corpus to", outputFile
ETUtils.write(corpusRoot, outputFile)
return corpusTree
assert task3Type in ["multiclass", "speculation", "negation"]
# Remove the task 3 subtask information if it already exists
for entity in corpusRoot.getiterator("entity"):
if task3Type == "multiclass":
entity.set("speculation", "False")
entity.set("negation", "False")
elif task3Type == "speculation":
entity.set("speculation", "False")
else: # task3Type == "negation"
entity.set("negation", "False")
specMap = {}
negMap = {}
for example, prediction in itertools.izip(examples, predictions):
assert example[3]["xtype"] == "task3"
if example[3]["t3type"] == "multiclass":
if isinstance(prediction, dict):
encoded = prediction["prediction"]
predictedModifiers = [
classSet.getName(i) for i in range(len(encoded))
if encoded[i] == 1
]
else:
predictedClassName = classSet.getName(prediction[0])
predictedModifiers = ""
if predictedClassName != "neg":
predictedModifiers = predictedClassName.split("---")
if "negation" in predictedModifiers:
assert not negMap.has_key(example[3]["entity"])
negMap[example[3]["entity"]] = (True, prediction)
if "speculation" in predictedModifiers:
assert not specMap.has_key(example[3]["entity"])
specMap[example[3]["entity"]] = (True, prediction)
else:
if example[3]["t3type"] == "speculation":
map = specMap
else:
map = negMap
if prediction[0] != 1:
assert not map.has_key(example[3]["entity"])
map[example[3]["entity"]] = (True, prediction)
else:
assert not map.has_key(example[3]["entity"])
map[example[3]["entity"]] = (False, prediction)
for entity in corpusRoot.getiterator("entity"):
eId = entity.get("id")
if task3Type == "multiclass":
if specMap.has_key(eId):
entity.set("speculation", str(specMap[eId][0]))
entity.set(
"modConf",
self.getPredictionStrengthString(
specMap[eId][1], classSet, classIds))
if negMap.has_key(eId):
entity.set("negation", str(negMap[eId][0]))
entity.set(
"modConf",
self.getPredictionStrengthString(
negMap[eId][1], classSet, classIds))
else:
if task3Type == "speculation":
if specMap.has_key(eId):
entity.set("speculation", str(specMap[eId][0]))
entity.set(
"specConf",
self.getPredictionStrengthString(
specMap[eId][1], classSet, classIds, [""]))
elif task3Type == "negation":
if negMap.has_key(eId):
entity.set("negation", str(negMap[eId][0]))
entity.set(
"negConf",
self.getPredictionStrengthString(
negMap[eId][1], classSet, classIds,
["", "speculation"]))
# Write corpus
if outputFile != None:
print >> sys.stderr, "Writing corpus to", outputFile
ETUtils.write(corpusRoot, outputFile)
return corpusTree
import psyco
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():
def writeXML(self, examples, predictions, corpus, outputFile, classSet=None, parse=None, tokenization=None, goldCorpus=None):
#print >> sys.stderr, "Writing output to Interaction XML"
corpus = self.loadCorpus(corpus, parse, tokenization)
if goldCorpus != None:
goldCorpus = self.loadCorpus(corpus, parse, tokenization)
examples, predictions = self.loadExamples(examples, predictions)
if type(classSet) == types.StringType: # class names are in file
classSet = IdSet(filename=classSet)
classIds = None
if classSet != None:
classIds = classSet.getIds()
#counter = ProgressCounter(len(corpus.sentences), "Write Examples")
exampleQueue = [] # One sentence's examples
predictionsByExample = {}
currentMajorId = None
prevMajorIds = set()
processedSentenceIds = set()
xType = None
count = 0
for example in examples:
count += 1
assert count > 0
progress = ProgressCounter(count, "Write Examples")
for example, prediction in itertools.izip_longest(examples, predictions):
assert example != None
assert prediction != None
majorId, minorId = example[0].rsplit(".x", 1)
#if currentMajorId == "GENIA.d114.s9": print "Start"
if majorId != currentMajorId: # new sentence
if currentMajorId != None:
#if currentMajorId == "GENIA.d114.s9": print "JAA"
processedSentenceIds.add(currentMajorId)
sentenceObject = corpus.sentencesById[currentMajorId]
goldSentence = None
if goldCorpus != None:
goldSentence = goldCorpus.sentencesById[currentMajorId]
self.writeXMLSentence(exampleQueue, predictionsByExample, sentenceObject, classSet, classIds, goldSentence=goldSentence) # process queue
progress.update(len(exampleQueue), "Writing examples ("+exampleQueue[-1][0]+"): ")
exampleQueue = []
predictionsByExample = {}
prevMajorIds.add(currentMajorId)
assert majorId not in prevMajorIds, majorId
currentMajorId = majorId
exampleQueue.append(example) # queue example
predictionsByExample[example[0]] = prediction
assert example[3]["xtype"] == self.xType, str(example[3]["xtype"]) + "/" + str(self.xType)
# Process what is still in queue
if currentMajorId != None:
processedSentenceIds.add(currentMajorId)
sentenceObject = corpus.sentencesById[currentMajorId]
goldSentence = None
if goldCorpus != None:
goldSentence = goldCorpus.sentencesById[currentMajorId]
self.writeXMLSentence(exampleQueue, predictionsByExample, sentenceObject, classSet, classIds, goldSentence=goldSentence) # process queue
progress.update(len(exampleQueue), "Writing examples ("+exampleQueue[-1][0]+"): ")
exampleQueue = []
predictionsByExample = {}
# Process sentences with no examples (e.g. to clear interactions)
for sentenceId in sorted(corpus.sentencesById.keys()):
if sentenceId not in processedSentenceIds:
sentenceObject = corpus.sentencesById[sentenceId]
goldSentence = None
if goldCorpus != None:
goldSentence = goldCorpus.sentencesById[currentMajorId]
self.writeXMLSentence([], {}, sentenceObject, classSet, classIds, goldSentence=goldSentence)
# Print statistics
if len(self.counts) > 0:
print >> sys.stderr, self.counts
self.counts = defaultdict(int)
# Write corpus
if outputFile != None:
print >> sys.stderr, "Writing corpus to", outputFile
ETUtils.write(corpus.rootElement, outputFile)
return corpus.tree
def readARFF(filename):
featureSet = IdSet(1)
classSet = IdSet(0)
f = open(filename,"rt")
inData = False
lines = f.readlines()
counter = ProgressCounter(len(lines),"ARFFLine")
examples = []
for line in lines:
counter.update(string="Processing line " + str(counter.current + 1) + ": ")
line = line.strip()
if len(line) == 0 or line[0] == "%":
continue
elif line[0] == "@":
#print line
category = line.split()[0].lower()
if category == "@attribute":
category, name, type = line.split()
assert(not inData)
if name.lower() == "class":
name = name.lower()
classNames = type[1:-1].split(",")
assert(len(classNames)==2)
classSet.defineId(classNames[0].strip(),1)
classSet.defineId(classNames[1].strip(),-1)
featureSet.getId(name)
elif category.lower() == "@relation":
assert(not inData)
elif category == "@data":
inData = True
else:
assert(inData)
count = 1
features = {}
for column in line.split(","):
if featureSet.getName(count) != "class":
features[count] = float(column)
else:
classId = classSet.getId(column, False)
assert(classId != None)
count += 1
exampleCount = str(len(examples))
exampleId = "BreastCancer.d" + exampleCount + ".s0.x0"
examples.append([exampleId,classId,features,{}])
return examples
def __init__(self, style=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
assert( classSet.getId("neg") == 1 or (len(classSet.Ids)== 2 and classSet.getId("neg") == -1) )
# Basic style = trigger_features:typed:directed:no_linear:entities:auto_limits:noMasking:maxFeatures
self._setDefaultParameters([
"directed", "undirected", "headsOnly", "graph_kernel", "noAnnType", "mask_nodes", "limit_features",
"no_auto_limits", "co_features", "genia_features", "bi_features", #"genia_limits", "epi_limits", "id_limits", "rel_limits", "bb_limits", "bi_limits", "co_limits",
"genia_task1", "ontology", "nodalida", "bacteria_renaming", "no_trigger_features", "rel_features",
"drugbank_features", "ddi_mtmx", "evex", "giuliano", "random", "themeOnly", "causeOnly", "no_path", "token_nodes",
"skip_extra_triggers", "headsOnly", "graph_kernel", "no_task", "no_dependency",
"disable_entity_features", "disable_terminus_features", "disable_single_element_features",
"disable_ngram_features", "disable_path_edge_features", "linear_features", "subset", "binary", "pos_only",
"entity_type", "filter_shortest_path", "maskTypeAsProtein", "keep_neg", "metamap",
"sdb_merge", "sdb_features", "ontobiotope_features", "no_self_loops", "full_entities",
"no_features", "wordnet", "wordvector", "se10t8_undirected", "filter_types", "doc_extra",
"entity_extra"])
self.styles = self.getParameters(style)
#if style == None: # no parameters given
# style["typed"] = style["directed"] = style["headsOnly"] = True
self.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet, self.styles)
# NOTE Temporarily re-enabling predicted range
#self.multiEdgeFeatureBuilder.definePredictedValueRange([], None)
if self.styles["graph_kernel"]:
from FeatureBuilders.GraphKernelFeatureBuilder import GraphKernelFeatureBuilder
self.graphKernelFeatureBuilder = GraphKernelFeatureBuilder(self.featureSet)
if self.styles["noAnnType"]:
self.multiEdgeFeatureBuilder.noAnnType = True
if self.styles["mask_nodes"]:
self.multiEdgeFeatureBuilder.maskNamedEntities = True
else:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if not self.styles["limit_features"]:
self.multiEdgeFeatureBuilder.maximum = True
if self.styles["genia_task1"]:
self.multiEdgeFeatureBuilder.filterAnnTypes.add("Entity")
self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
if self.styles["ontology"]:
self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(self.featureSet)
if self.styles["ontobiotope_features"]:
self.ontobiotopeFeatureBuilder = OntoBiotopeFeatureBuilder(self.featureSet)
if self.styles["nodalida"]:
self.nodalidaFeatureBuilder = NodalidaFeatureBuilder(self.featureSet)
if self.styles["bacteria_renaming"]:
self.bacteriaRenamingFeatureBuilder = BacteriaRenamingFeatureBuilder(self.featureSet)
if not self.styles["no_trigger_features"]:
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet, self.styles)
self.triggerFeatureBuilder.useNonNameEntities = True
if self.styles["noAnnType"]:
self.triggerFeatureBuilder.noAnnType = True
if self.styles["genia_task1"]:
self.triggerFeatureBuilder.filterAnnTypes.add("Entity")
#self.bioinferOntologies = OntologyUtils.loadOntologies(OntologyUtils.g_bioInferFileName)
if self.styles["rel_features"]:
self.relFeatureBuilder = RELFeatureBuilder(featureSet)
if self.styles["drugbank_features"]:
self.drugFeatureBuilder = DrugFeatureBuilder(featureSet)
if self.styles["evex"]:
self.evexFeatureBuilder = EVEXFeatureBuilder(featureSet)
if self.styles["wordnet"]:
self.wordNetFeatureBuilder = WordNetFeatureBuilder(featureSet)
if self.styles["wordvector"]:
self.wordVectorFeatureBuilder = WordVectorFeatureBuilder(featureSet, self.styles)
if self.styles["giuliano"]:
self.giulianoFeatureBuilder = GiulianoFeatureBuilder(featureSet)
self.types = types
if self.styles["random"]:
from FeatureBuilders.RandomFeatureBuilder import RandomFeatureBuilder
self.randomFeatureBuilder = RandomFeatureBuilder(self.featureSet)
ExampleUtils.appendExamples(exampleCache, outFile)
exampleCache = []
ExampleUtils.appendExamples(exampleCache, outFile)
outFile.close()
print "Added", addCount, "polynomial features"
if __name__=="__main__":
# Import Psyco if available
try:
import psyco
psyco.full()
print >> sys.stderr, "Found Psyco, using"
except ImportError:
print >> sys.stderr, "Psyco not installed"
from optparse import OptionParser # For using command line options
optparser = OptionParser()
optparser.add_option("-i", "--ids", default=None, dest="ids", help="")
optparser.add_option("-e", "--examples", default=None, dest="examples", help="")
optparser.add_option("-j", "--idOutput", default=None, dest="idOutput", help="")
optparser.add_option("-o", "--output", default=None, dest="output", help="")
optparser.add_option("-w", "--weights", default=None, dest="weights", help="")
optparser.add_option("-c", "--cutoff", type="float", default=10.0, dest="cutoff", help="")
(options, args) = optparser.parse_args()
#classIds = IdSet(filename="/usr/share/biotext/GeniaChallenge/extension-data/genia/edge-examples/genia-edge-ids.class_names")
featureIds = IdSet(filename=options.ids)
weightFeatures = readWeights(options.weights, options.cutoff)
polynomizeExamples(options.examples, options.output, weightFeatures, featureIds)
featureIds.write(options.idOutput)
class ExampleBuilder:
structureAnalyzer = None
"""
ExampleBuilder is the abstract base class for specialized example builders.
Example builders take some data and convert it to examples usable by e.g. SVMs.
An example builder writes three files, an example-file (in extended Joachim's
SVM format) and .class_names and .feature_names files, which contain the names
for the class and feature id-numbers. An example builder can also be given
pre-existing sets of class and feature ids (optionally in files) so that the
generated examples are consistent with other, previously generated examples.
"""
def __init__(self, classSet=None, featureSet=None):
if (type(classSet) == types.StringType):
self.classSet = IdSet(filename=classSet)
else:
self.classSet = classSet
if (type(featureSet) == types.StringType):
self.featureSet = IdSet(filename=featureSet)
else:
self.featureSet = featureSet
self.featureTag = ""
self.exampleStats = ExampleStats()
self.parse = None
self.tokenization = None
#self.idFileTag = None
self.classIdFilename = None
self.featureIdFilename = None
self.styles = {}
self._defaultParameters = None
self._parameterValueLimits = None
self._setDefaultParameters(["sentenceLimit"])
self.debug = False
def hasStyle(self, style):
return style in self.styles and not self.styles[style]
def _setDefaultParameters(self, defaults=None, valueLimits=None):
# Initialize
if self._defaultParameters == None:
self._defaultParameters = {}
if self._parameterValueLimits == None:
self._parameterValueLimits = {}
newParameters = Utils.Parameters.get({},
defaults,
valueLimits=valueLimits)
self._defaultParameters.update(newParameters)
if valueLimits != None:
self._parameterValueLimits.update(valueLimits)
def getParameters(self, parameters):
return Utils.Parameters.get(parameters,
defaults=self._defaultParameters,
valueLimits=self._parameterValueLimits)
def setFeature(self, name, value):
self.features[self.featureSet.getId(self.featureTag + name)] = value
def getElementCounts(self, filename):
print >> sys.stderr, "Counting elements:",
if filename.endswith(".gz"):
f = gzip.open(filename, "rt")
else:
f = open(filename, "rt")
counts = {"documents": 0, "sentences": 0}
for line in f:
if "<document" in line:
counts["documents"] += 1
elif "<sentence" in line:
counts["sentences"] += 1
f.close()
print >> sys.stderr, counts
return counts
def saveIds(self):
if self.classIdFilename != None:
print >> sys.stderr, "Saving class names to", self.classIdFilename
self.classSet.write(self.classIdFilename)
else:
print >> sys.stderr, "Class names not saved"
if self.featureIdFilename != None:
print >> sys.stderr, "Saving feature names to", self.featureIdFilename
self.featureSet.write(self.featureIdFilename)
else:
print >> sys.stderr, "Feature names not saved"
def processCorpus(self,
input,
output,
gold=None,
append=False,
allowNewIds=True,
structureAnalyzer=None):
# Create intermediate paths if needed
if os.path.dirname(output) != "" and not os.path.exists(
os.path.dirname(output)):
os.makedirs(os.path.dirname(output))
# Open output file
openStyle = "wt"
if append:
#print "Appending examples"
openStyle = "at"
if output.endswith(".gz"):
outfile = gzip.open(output, openStyle)
else:
outfile = open(output, openStyle)
# Build examples
self.exampleCount = 0
if type(input) in types.StringTypes: # Entered here - Mu
self.elementCounts = self.getElementCounts(input)
if self.elementCounts["sentences"] > 0: # Entered here, 1448 - Mu
self.progress = ProgressCounter(
self.elementCounts["sentences"], "Build examples")
else:
self.elementCounts = None
self.progress = ProgressCounter(None, "Build examples")
else:
self.elementCounts = None
self.progress = ProgressCounter(None, "Build examples")
# pdb.set_trace()
# This line generates log below:(getSentences function generates the first 2 lines)
# Making sentence graphs (GE09.d149.s5): 100.00 % (0:0:1.113)
# Skipped 381 duplicate interaction edges in SentenceGraphs
# Defining predicted value range: None - Mu
self.calculatePredictedRange(
self.getSentences(input, self.parse, self.tokenization)
) # self.parse: mccc; self.tokenization: None
removeIntersentenceInteractions = True
if "keep_intersentence" in self.styles and self.styles[
"keep_intersentence"]:
print >> sys.stderr, "Keeping intersentence interactions for input corpus"
removeIntersentenceInteractions = False # this is True - Mu
inputIterator = getCorpusIterator(
input,
None,
self.parse,
self.tokenization,
removeIntersentenceInteractions=removeIntersentenceInteractions)
# pdb.set_trace()
#goldIterator = []
if gold != None: # Entered here - Mu
removeGoldIntersentenceInteractions = True
if "keep_intersentence_gold" in self.styles and self.styles[
"keep_intersentence_gold"]:
print >> sys.stderr, "Keeping intersentence interactions for gold corpus"
removeGoldIntersentenceInteractions = False # this is False - Mu
goldIterator = getCorpusIterator(
gold,
None,
self.parse,
self.tokenization,
removeIntersentenceInteractions=
removeGoldIntersentenceInteractions)
for inputSentences, goldSentences in itertools.izip_longest(
inputIterator, goldIterator, fillvalue=None):
assert inputSentences != None
assert goldSentences != None
# pdb.set_trace()
# see the documentation of function processSentence() in this script
# inputSentences[1].sentence is the unmerged version
# inputSentences[1].sentenceGraph is the merged version, meaning that when generating sentenceGraph,
# duplicated intereactions are removed(actually skipped, not added to the graph, but not really removed) - Mu
self.processDocument(inputSentences,
goldSentences,
outfile,
structureAnalyzer=structureAnalyzer)
else:
for inputSentences in inputIterator:
self.processDocument(inputSentences,
None,
outfile,
structureAnalyzer=structureAnalyzer)
outfile.close()
self.progress.endUpdate()
# Show statistics
print >> sys.stderr, "Examples built:", self.exampleCount
print >> sys.stderr, "Features:", len(self.featureSet.getNames())
print >> sys.stderr, "Classes:", len(self.classSet.getNames())
print >> sys.stderr, "Style:", Utils.Parameters.toString(
self.getParameters(self.styles))
if self.exampleStats.getExampleCount() > 0:
self.exampleStats.printStats()
# Save Ids
if allowNewIds:
self.saveIds()
def processDocument(self,
sentences,
goldSentences,
outfile,
structureAnalyzer=None):
#calculatePredictedRange(self, sentences)
for i in range(len(sentences)):
sentence = sentences[i]
goldSentence = None
if goldSentences != None:
goldSentence = goldSentences[i]
self.progress.update(
1, "Building examples (" + sentence.sentence.get("id") + "): ")
self.processSentence(sentence,
outfile,
goldSentence,
structureAnalyzer=structureAnalyzer)
def processSentence(self,
sentence,
outfile,
goldSentence=None,
structureAnalyzer=None):
'''
sentence: Utils.InteractionXML.SentenceElements.SentenceElements instance
sentence.sentence: Element 'sentence' in the xml file
'''
# pdb.set_trace()
# Process filtering rules
# does NOT entered here since self.styles["sentenceLimit"] is None - Mu
if "sentenceLimit" in self.styles and self.styles[
"sentenceLimit"]: # Rules for limiting which sentences to process
# Get the rule list
limitRules = self.styles["sentenceLimit"]
if type(limitRules) in types.StringTypes:
limitRules = [limitRules]
# Get the list of sentence element attribute names
sentenceElement = sentence.sentence
sentenceAttributes = sorted(sentenceElement.attrib.keys())
# Filter sentences based on matching rules to their attribute values
for rule in limitRules:
for sentAttr in sentenceAttributes:
# Rule are of the form "attr.value" where "attr" is the name
# of the attribute to match, and "value" a substring within
# that attribute
if rule.startswith(sentAttr +
"."): # rule matches the attribute
value = rule.split(
".", 1)[-1] # get the value part of the rule
if value not in sentenceElement.get(
sentAttr
): # rule value must be a substring of the attribute value
return # discard all sentences that do not match all rules
# Process the sentence
if sentence.sentenceGraph != None:
goldGraph = None
if goldSentence != None:
goldGraph = goldSentence.sentenceGraph
# c, sentenceGraph_return, argCombinations_return = self.buildExamplesFromGraph(sentence.sentenceGraph, outfile, goldGraph, structureAnalyzer=structureAnalyzer)
# self.exampleCount += c
self.exampleCount += self.buildExamplesFromGraph(
sentence.sentenceGraph,
outfile,
goldGraph,
structureAnalyzer=structureAnalyzer)
# return sentenceGraph_return, argCombinations_return
@classmethod
def run(cls,
input,
output,
parse,
tokenization,
style,
classIds=None,
featureIds=None,
gold=None,
append=False,
allowNewIds=True,
structureAnalyzer=None,
debug=False):
print >> sys.stderr, "Running", cls.__name__
print >> sys.stderr, " input:", input
if gold != None:
print >> sys.stderr, " gold:", gold
print >> sys.stderr, " output:", output, "(append:", str(append) + ")"
print >> sys.stderr, " add new class/feature ids:", allowNewIds
if not isinstance(style, types.StringTypes):
style = Utils.Parameters.toString(style)
print >> sys.stderr, " style:", style
if tokenization == None:
print >> sys.stderr, " parse:", parse
else:
print >> sys.stderr, " parse:", parse + ", tokenization:", tokenization
classSet, featureSet = cls.getIdSets(
classIds, featureIds, allowNewIds) #cls.getIdSets(idFileTag)
builder = cls(style=style, classSet=classSet, featureSet=featureSet)
builder.debug = debug
#builder.idFileTag = idFileTag
builder.classIdFilename = classIds
builder.featureIdFilename = featureIds
builder.parse = parse
builder.tokenization = tokenization
builder.processCorpus(input,
output,
gold,
append=append,
allowNewIds=allowNewIds,
structureAnalyzer=structureAnalyzer)
return builder
def buildExamplesFromGraph(self, sentenceGraph, outfile, goldGraph=None):
raise NotImplementedError
def definePredictedValueRange(self, sentences, elementName):
pass
def getPredictedValueRange(self):
return None
@classmethod
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
# if idFileTag != None and os.path.exists(idFileTag + ".feature_names.gz") and os.path.exists(idFileTag + ".class_names"):
# print >> sys.stderr, "Using predefined class and feature names"
# featureSet = IdSet()
# featureSet.load(idFileTag + ".feature_names.gz")
# classSet = IdSet()
# classSet.load(idFileTag + ".class_names")
# return classSet, featureSet
# else:
# print >> sys.stderr, "No predefined class or feature-names"
# if idFileTag != None:
# assert(not os.path.exists(idFileTag + ".feature_names.gz")), idFileTag
# assert(not os.path.exists(idFileTag + ".class_names")), idFileTag
# return None, None
def getSentences(self, input, parse, tokenization, removeNameInfo=False):
# pdb.set_trace()
# input is the path to the corpus xml file
if type(input) != types.ListType: # Program entered here - Mu
# Load corpus and make sentence graphs
# pdb.set_trace()
corpusElements = Core.SentenceGraph.loadCorpus(
input, parse, tokenization, removeNameInfo=removeNameInfo)
sentences = []
for sentence in corpusElements.sentences:
if sentence.sentenceGraph != None: # required for event detection
sentences.append([sentence.sentenceGraph, None])
return sentences
else: # assume input is already a list of sentences
assert (removeNameInfo == False)
return input
def calculatePredictedRange(self, sentences):
print >> sys.stderr, "Defining predicted value range:",
sentenceElements = []
for sentence in sentences:
sentenceElements.append(sentence[0].sentenceElement)
self.definePredictedValueRange(sentenceElements, "entity")
print >> sys.stderr, self.getPredictedValueRange()
def test(cls, examples, modelPath, output=None, parameters=None, forceInternal=False, classIds=None): # , timeout=None):
"""
Classify examples with a pre-trained model.
@type examples: string (filename) or list (or iterator) of examples
@param examples: a list or file containing examples in SVM-format
@type modelPath: string
@param modelPath: filename of the pre-trained model file
@type parameters: a dictionary or string
@param parameters: parameters for the classifier
@type output: string
@param output: the name of the predictions file to be written
@type forceInternal: Boolean
@param forceInternal: Use python classifier even if SVM Multiclass binary is defined in Settings.py
"""
if type(parameters) == types.StringType:
parameters = splitParameters(parameters)
timer = Timer()
if type(examples) == types.ListType:
print >> sys.stderr, "Classifying", len(examples), "with SVM-MultiClass model", modelPath
examples, predictions = self.filterClassificationSet(examples, False)
testPath = self.tempDir+"/test.dat"
Example.writeExamples(examples, testPath)
else:
print >> sys.stderr, "Classifying file", examples, "with SVM-MultiClass model", modelPath
testPath = examples
examples = Example.readExamples(examples,False)
if parameters != None:
parameters = copy.copy(parameters)
if parameters.has_key("c"):
del parameters["c"]
if parameters.has_key("predefined"):
parameters = copy.copy(parameters)
modelPath = os.path.join(parameters["predefined"][0],"classifier/model")
del parameters["predefined"]
# Read model
if modelPath == None:
modelPath = "model-multilabel"
classModels = {}
if modelPath.endswith(".gz"):
f = gzip.open(modelPath, "rt")
else:
f = open(modelPath, "rt")
thresholds = {}
for line in f:
key, value, threshold = line.split()
classModels[key] = value
if threshold != "None":
thresholds[key] = float(threshold)
else:
thresholds[key] = 0.0
f.close()
mergedPredictions = []
if type(classIds) == types.StringType:
classIds = IdSet(filename=classIds)
#print classModels
print "Thresholds", thresholds
classifierBin = Settings.SVMMultiClassDir+"/svm_multiclass_classify"
print parameters
if "classifier" in parameters and "svmperf" in parameters["classifier"]:
classifierBin = Settings.SVMPerfDir+"/svm_perf_classify"
parameters = copy.copy(parameters)
del parameters["classifier"]
for className in classIds.getNames():
if className != "neg" and not "---" in className:
classId = classIds.getId(className)
if thresholds[str(className)] != 0.0:
print >> sys.stderr, "Classifying", className, "with threshold", thresholds[str(className)]
else:
print >> sys.stderr, "Classifying", className
args = [classifierBin]
#self.__addParametersToSubprocessCall(args, parameters)
classOutput = "predictions" + ".cls-" + className
logFile = open("svmmulticlass" + ".cls-" + className + ".log","at")
args += [testPath, classModels[str(className)], classOutput]
print args
subprocess.call(args, stdout = logFile, stderr = logFile)
cls.addPredictions(classOutput, mergedPredictions, classId, len(classIds.Ids), threshold=thresholds[str(className)])
print >> sys.stderr, timer.toString()
predFileName = output
f = open(predFileName, "wt")
for mergedPred in mergedPredictions:
if len(mergedPred[0]) > 1 and "1" in mergedPred[0]:
mergedPred[0].remove("1")
mergedPred[1] = str(mergedPred[1])
mergedPred[0] = ",".join(sorted(list(mergedPred[0])))
f.write(" ".join(mergedPred) + "\n")
f.close()
return mergedPredictions
def __init__(self, style=None, length=None, types=[], featureSet=None, classSet=None):
if featureSet == None:
featureSet = IdSet()
if classSet == None:
classSet = IdSet(1)
else:
classSet = classSet
assert( classSet.getId("neg") == 1 or (len(classSet.Ids)== 2 and classSet.getId("neg") == -1) )
ExampleBuilder.__init__(self, classSet=classSet, featureSet=featureSet)
self.styles = self.getParameters(style, [
"typed", "directed", "headsOnly", "graph_kernel", "noAnnType", "noMasking", "maxFeatures",
"genia_limits", "epi_limits", "id_limits", "rel_limits", "bb_limits", "bi_limits", "co_limits",
"genia_task1", "ontology", "nodalida", "bacteria_renaming", "trigger_features", "rel_features",
"ddi_features", "evex", "giuliano", "random", "themeOnly", "causeOnly", "no_path", "entities",
"skip_extra_triggers", "headsOnly", "graph_kernel", "trigger_features", "no_task", "no_dependency",
"disable_entity_features", "disable_terminus_features", "disable_single_element_features",
"disable_ngram_features", "disable_path_edge_features", "no_linear", "subset", "binary", "pos_only",
"entity_type"
])
if style == None: # no parameters given
style["typed"] = style["directed"] = style["headsOnly"] = True
# self.styles = style
# 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.multiEdgeFeatureBuilder = MultiEdgeFeatureBuilder(self.featureSet)
# NOTE Temporarily re-enabling predicted range
#self.multiEdgeFeatureBuilder.definePredictedValueRange([], None)
if self.styles["graph_kernel"]:
from FeatureBuilders.GraphKernelFeatureBuilder import GraphKernelFeatureBuilder
self.graphKernelFeatureBuilder = GraphKernelFeatureBuilder(self.featureSet)
if self.styles["noAnnType"]:
self.multiEdgeFeatureBuilder.noAnnType = True
if self.styles["noMasking"]:
self.multiEdgeFeatureBuilder.maskNamedEntities = False
if self.styles["maxFeatures"]:
self.multiEdgeFeatureBuilder.maximum = True
if self.styles["genia_task1"]:
self.multiEdgeFeatureBuilder.filterAnnTypes.add("Entity")
self.tokenFeatureBuilder = TokenFeatureBuilder(self.featureSet)
if self.styles["ontology"]:
self.multiEdgeFeatureBuilder.ontologyFeatureBuilder = BioInferOntologyFeatureBuilder(self.featureSet)
if self.styles["nodalida"]:
self.nodalidaFeatureBuilder = NodalidaFeatureBuilder(self.featureSet)
if self.styles["bacteria_renaming"]:
self.bacteriaRenamingFeatureBuilder = BacteriaRenamingFeatureBuilder(self.featureSet)
if self.styles["trigger_features"]:
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = True
if self.styles["genia_task1"]:
self.triggerFeatureBuilder.filterAnnTypes.add("Entity")
#self.bioinferOntologies = OntologyUtils.loadOntologies(OntologyUtils.g_bioInferFileName)
if self.styles["rel_features"]:
self.relFeatureBuilder = RELFeatureBuilder(featureSet)
if self.styles["ddi_features"]:
self.drugFeatureBuilder = DrugFeatureBuilder(featureSet)
if self.styles["evex"]:
self.evexFeatureBuilder = EVEXFeatureBuilder(featureSet)
if self.styles["giuliano"]:
self.giulianoFeatureBuilder = GiulianoFeatureBuilder(featureSet)
self.pathLengths = length
assert(self.pathLengths == None)
self.types = types
if self.styles["random"]:
from FeatureBuilders.RandomFeatureBuilder import RandomFeatureBuilder
self.randomFeatureBuilder = RandomFeatureBuilder(self.featureSet)