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
def writeXML(self, examples, predictions, corpus, outputFile, classSet=None, parse=None, tokenization=None, goldCorpus=None, exampleStyle=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":
predictedClassName = classSet.getName(prediction[0])
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("modPred", self.getPredictionStrengthString(specMap[eId][1], classSet, classIds))
if negMap.has_key(eId):
entity.set("negation", str(negMap[eId][0]))
entity.set("modPred", 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("specPred", self.getPredictionStrengthString(specMap[eId][1], classSet, classIds, [""]))
elif task3Type == "negation":
if negMap.has_key(eId):
entity.set("negation", str(negMap[eId][0]))
entity.set("negPred", 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
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 writeXML(self,
examples,
predictions,
corpus,
outputFile,
classSet=None,
parse=None,
tokenization=None,
goldCorpus=None,
exampleStyle=None,
structureAnalyzer=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
if count > 0:
progress = ProgressCounter(count, "Write Examples")
else:
predCount = 0
for prediction in predictions:
predCount += 1
assert predCount == 0
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,
exampleStyle=exampleStyle,
structureAnalyzer=structureAnalyzer) # 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,
exampleStyle=exampleStyle,
structureAnalyzer=structureAnalyzer) # 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,
exampleStyle=exampleStyle,
structureAnalyzer=structureAnalyzer)
# 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
