def fromXML(self, input, parse, tokenization=None):
self.names = {}
if type(input) == types.StringType:
corpus = CorpusElements.loadCorpus(input, parse, tokenization)
else:
corpus = input
for sentence in corpus.sentences:
tokenTuples = self.prepareTokens(sentence.tokens)
for entity in sentence.entities:
if entity.get("isName") == "True":
tokens = self.getTokens(entity, tokenTuples)
assert len(tokens) > 0
self.addName(tokens)
self.addName(["".join(tokens)])
def fromXML(self, input, parse, tokenization=None):
self.names = {}
if type(input) == types.StringType:
corpus = CorpusElements.loadCorpus(input, parse, tokenization)
else:
corpus = input
for sentence in corpus.sentences:
tokenTuples = self.prepareTokens(sentence.tokens)
for entity in sentence.entities:
if entity.get("given") == "True":
tokens = self.getTokens(entity, tokenTuples)
assert len(tokens) > 0
self.addName(tokens)
self.addName(["".join(tokens)])
def run(EvaluatorClass, inputCorpusFile, goldCorpusFile, parse, tokenization=None, target="both", entityMatchFunction=compareEntitiesSimple, removeIntersentenceInteractions=False, errorMatrix=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 = CorpusElements.loadCorpus(goldCorpusFile, parse, tokenization, removeIntersentenceInteractions)
predictedCorpusElements = CorpusElements.loadCorpus(inputCorpusFile, parse, tokenization, removeIntersentenceInteractions)
# Compare the corpora and print results on screen
return processCorpora(EvaluatorClass, predictedCorpusElements, goldCorpusElements, target, classSets, negativeClassId, entityMatchFunction, errorMatrix=errorMatrix)
def run(EvaluatorClass, inputCorpusFile, goldCorpusFile, parse, tokenization=None, target="both", entityMatchFunction=compareEntitiesSimple, removeIntersentenceInteractions=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 = CorpusElements.loadCorpus(goldCorpusFile, parse, tokenization, removeIntersentenceInteractions)
predictedCorpusElements = CorpusElements.loadCorpus(inputCorpusFile, parse, tokenization, removeIntersentenceInteractions)
# Compare the corpora and print results on screen
return processCorpora(EvaluatorClass, predictedCorpusElements, goldCorpusElements, target, classSets, negativeClassId, entityMatchFunction)
import xml.etree.cElementTree as ET
except ImportError:
import cElementTree as ET
import Utils.ElementTreeUtils as ETUtils
import Utils.InteractionXML.CorpusElements as CorpusElements
if __name__=="__main__":
from optparse import OptionParser
optparser = OptionParser(usage="%prog [options]\n")
optparser.add_option("-i", "--input", default=None, dest="input", help="Corpus in analysis format", metavar="FILE")
optparser.add_option("-o", "--output", default=None, dest="output", help="Output directory")
optparser.add_option("-f", "--folds", type="int", default=10, dest="folds", help="X-fold cross validation")
(options, args) = optparser.parse_args()
# Load corpus and make sentence graphs
corpusElements = CorpusElements.loadCorpus(options.input)
outputTrees = []
for i in range(options.folds):
newRoot = ET.Element("corpus")
for key in corpusElements.rootElement.attrib.keys():
newRoot.attrib[key] = corpusElements.rootElement.attrib[key]
outputTrees.append(newRoot)
print >> sys.stderr, "Reading document ids"
documentIds = []
for document in corpusElements.documents:
docId = document.attrib["id"]
assert( not docId in documentIds )
documentIds.append(docId)
metavar="FILE")
optparser.add_option("-o",
"--output",
default=None,
dest="output",
help="Output directory")
optparser.add_option("-f",
"--folds",
type="int",
default=10,
dest="folds",
help="X-fold cross validation")
(options, args) = optparser.parse_args()
# Load corpus and make sentence graphs
corpusElements = CorpusElements.loadCorpus(options.input)
outputTrees = []
for i in range(options.folds):
newRoot = ET.Element("corpus")
for key in corpusElements.rootElement.attrib.keys():
newRoot.attrib[key] = corpusElements.rootElement.attrib[key]
outputTrees.append(newRoot)
print >> sys.stderr, "Reading document ids"
documentIds = []
for document in corpusElements.documents:
docId = document.attrib["id"]
assert (not docId in documentIds)
documentIds.append(docId)
