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._setDefaultParameters(
{
"classification": "multiclass",
"speculation_words": True
}, {"classification": ("multiclass", "speculation", "negation")})
self.styles = self.getParameters(style)
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=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=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._setDefaultParameters(["co_limits"])
self.styles = self.getParameters(style)
self.triggerFeatureBuilder = TriggerFeatureBuilder(self.featureSet)
self.triggerFeatureBuilder.useNonNameEntities = False
self.phraseTypeCounts = {}
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=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._setDefaultParameters({"classification":"multiclass", "speculation_words":True}, {"classification":("multiclass", "speculation", "negation")})
self.styles = self.getParameters(style)
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 = []
