def processParses(xml, splitTarget="McCC"):
print >> sys.stderr, "Protein Name Splitting"
#ProteinNameSplitter.mainFunc(xml, None, splitTarget, splitTarget, "split-"+splitTarget, "split-"+splitTarget)
ProteinNameSplitter.mainFunc(xml, None, splitTarget, removeOld=True)
print >> sys.stderr, "Head Detection"
#xml = FindHeads.findHeads(xml, "split-"+splitTarget, tokenization=None, output=None, removeExisting=True)
xml = FindHeads.findHeads(xml, splitTarget, tokenization=None, output=None, removeExisting=True)
def processParses(xml, splitTarget="McCC"):
print >> sys.stderr, "---------------", "Protein Name Splitting", "---------------"
#ProteinNameSplitter.mainFunc(xml, None, splitTarget, splitTarget, "split-"+splitTarget, "split-"+splitTarget)
ProteinNameSplitter.mainFunc(xml, None, splitTarget, removeOld=True)
print >> sys.stderr, "---------------", "Head Detection", "---------------"
#xml = FindHeads.findHeads(xml, "split-"+splitTarget, tokenization=None, output=None, removeExisting=True)
xml = FindHeads.findHeads(xml, splitTarget, tokenization=None, output=None, removeExisting=True)
def convertDDI(outDir, downloadDir=None, redownload=False, makeIntermediateFiles=True, debug=False):
cwd = os.getcwd()
if not os.path.exists(outDir):
os.makedirs(outDir)
os.chdir(outDir)
logFileName = os.path.join(outDir, "DDI11-conversion-log.txt")
Stream.openLog(logFileName)
print >> sys.stderr, "=======================", "Converting DDI'11 corpus", "======================="
corpusDir = outDir + "/DDI11-original"
Utils.Download.downloadAndExtract(Settings.URL["DDI11_CORPUS"], corpusDir, downloadDir)
bigfileName = os.path.join(outDir, "DDI11")
#oldXML = ETUtils.ETFromObj(bigfileName+".xml")
trainUnified = corpusDir + "/train"
trainMTMX = corpusDir + "/train_MTMX"
testUnified = corpusDir + "/test"
testMTMX = corpusDir + "/test_MTMX"
# Load main documents
tempdir = tempfile.mkdtemp()
print >> sys.stderr, "Temporary files directory at", tempdir
documents, docById, docCounts = loadDocs(trainUnified)
# Divide training data into a train and devel set
sortedDocCounts = sorted(docCounts.iteritems(), key=lambda (k,v): (v,k), reverse=True)
datasetCounts = {"train":[0,0], "devel":[0,0], "test":[0,0]}
for i in range(0, len(sortedDocCounts)-3, 4):
for j in [0,1]:
docById[sortedDocCounts[i+j][0]].set("set", "train")
datasetCounts["train"][0] += sortedDocCounts[i+j][1][0]
datasetCounts["train"][1] += sortedDocCounts[i+j][1][1]
docById[sortedDocCounts[i+2][0]].set("set", "train") #docById[sortedDocCounts[i+2][0]].set("set", "devel")
docById[sortedDocCounts[i+3][0]].set("set", "devel") #docById[sortedDocCounts[i+3][0]].set("set", "test")
datasetCounts["train"][0] += sortedDocCounts[i+2][1][0] #datasetCounts["devel"][0] += sortedDocCounts[i+2][1][0]
datasetCounts["train"][1] += sortedDocCounts[i+2][1][1] #datasetCounts["devel"][1] += sortedDocCounts[i+2][1][1]
datasetCounts["devel"][0] += sortedDocCounts[i+3][1][0] #datasetCounts["test"][0] += sortedDocCounts[i+3][1][0]
datasetCounts["devel"][1] += sortedDocCounts[i+3][1][1] #datasetCounts["test"][1] += sortedDocCounts[i+3][1][1]
for document in documents: # epajaolliset jaa yli
if document.get("set") == None:
document.set("set", "train")
# Print division results
print >> sys.stderr, datasetCounts
for key in datasetCounts.keys():
if datasetCounts[key][1] != 0:
print key, datasetCounts[key][0] / float(datasetCounts[key][1])
else:
print key, datasetCounts[key][0], "/", float(datasetCounts[key][1])
# Some of the train and test ids overlap. Let's change the train set ids, because test set ones are needed
# for the final evaluation.
changeIdCount = 1000
for trainId in ['DrugDDI.d312', 'DrugDDI.d316', 'DrugDDI.d332', 'DrugDDI.d334', 'DrugDDI.d337',
'DrugDDI.d342', 'DrugDDI.d349', 'DrugDDI.d354', 'DrugDDI.d373', 'DrugDDI.d379',
'DrugDDI.d383', 'DrugDDI.d388', 'DrugDDI.d392', 'DrugDDI.d396', 'DrugDDI.d398',
'DrugDDI.d409', 'DrugDDI.d411', 'DrugDDI.d415', 'DrugDDI.d425', 'DrugDDI.d430',
'DrugDDI.d433', 'DrugDDI.d448', 'DrugDDI.d450', 'DrugDDI.d452', 'DrugDDI.d462',
'DrugDDI.d467', 'DrugDDI.d470', 'DrugDDI.d474', 'DrugDDI.d480', 'DrugDDI.d482',
'DrugDDI.d485', 'DrugDDI.d492', 'DrugDDI.d494', 'DrugDDI.d496', 'DrugDDI.d498',
'DrugDDI.d500', 'DrugDDI.d503', 'DrugDDI.d506', 'DrugDDI.d518', 'DrugDDI.d523',
'DrugDDI.d528', 'DrugDDI.d535', 'DrugDDI.d539', 'DrugDDI.d552', 'DrugDDI.d554',
'DrugDDI.d558', 'DrugDDI.d561', 'DrugDDI.d570', 'DrugDDI.d578']:
newId = "DrugDDI.d" + str(changeIdCount)
print >> sys.stderr, "Changing train/devel id", trainId, "to", newId
for element in docById[trainId].getiterator():
for attrName, attrValue in element.attrib.iteritems():
if trainId in attrValue:
element.set(attrName, attrValue.replace(trainId, newId))
docById[newId] = docById[trainId]
del docById[trainId]
changeIdCount += 1
# If test set exists, load it, too
if testUnified != None:
testDocuments, testDocById, testDocCounts = loadDocs(testUnified)
for document in testDocuments:
document.set("set", "test")
documents = documents + testDocuments
overlappingIds = []
for key in docById:
if key in testDocById:
overlappingIds.append(key)
for key in docById:
assert key not in testDocById, (key, docById[key].get("origId"), testDocById[key].get("origId"), sorted(docById.keys()), sorted(testDocById.keys()), sorted(overlappingIds))
docById.update(testDocById)
# Add all documents into one XML
xmlTree = ET.ElementTree(ET.Element("corpus"))
root = xmlTree.getroot()
root.set("source", "DDI11")
for document in documents:
root.append(document)
if makeIntermediateFiles:
ETUtils.write(root, bigfileName + "-documents-notfixed.xml")
xml = xmlTree
print >> sys.stderr, "Fixing DDI XML"
fixEntities(xml)
convertToInteractions(xml)
# Add MTMX
if trainMTMX != None:
inDir = Utils.Download.getTopDir(tempdir, Utils.Download.downloadAndExtract(trainMTMX, tempdir, outDir + "/DDI11-original"))
DDITools.addMTMX(xml, inDir)
if testMTMX != None:
inDir = Utils.Download.getTopDir(tempdir, Utils.Download.downloadAndExtract(testMTMX, tempdir, outDir + "/DDI11-original"))
DDITools.addMTMX(xml, inDir)
if makeIntermediateFiles:
ETUtils.write(root, bigfileName + "-documents.xml")
print >> sys.stderr, "---------------", "Inserting TEES-generated analyses", "---------------"
Utils.Download.downloadAndExtract(Settings.URL["TEES_PARSES"], os.path.join(Settings.DATAPATH, "TEES-parses"), downloadDir, redownload=redownload)
extractedFilename = os.path.join(Settings.DATAPATH, "TEES-parses") + "/DDI11"
print >> sys.stderr, "Making sentences"
Tools.SentenceSplitter.makeSentences(xml, extractedFilename, None)
print >> sys.stderr, "Inserting McCC parses"
Tools.BLLIPParser.insertParses(xml, extractedFilename, None, extraAttributes={"source":"TEES-preparsed"})
print >> sys.stderr, "Inserting Stanford conversions"
Tools.StanfordParser.insertParses(xml, extractedFilename, None, extraAttributes={"stanfordSource":"TEES-preparsed"})
print >> sys.stderr, "Protein Name Splitting"
splitTarget = "McCC"
#ProteinNameSplitter.mainFunc(xml, None, splitTarget, splitTarget, "split-"+splitTarget, "split-"+splitTarget)
ProteinNameSplitter.mainFunc(xml, None, splitTarget, removeOld=True)
print >> sys.stderr, "Head Detection"
#xml = FindHeads.findHeads(xml, "split-"+splitTarget, tokenization=None, output=None, removeExisting=True)
xml = FindHeads.findHeads(xml, splitTarget, tokenization=None, output=None, removeExisting=True)
print >> sys.stderr, "Dividing into sets"
Utils.InteractionXML.DivideSets.processCorpus(xml, outDir, "DDI11", ".xml")
Stream.closeLog(logFileName)
if not debug:
print >> sys.stderr, "Removing temporary directory", tempdir
shutil.rmtree(tempdir)
os.chdir(cwd)
def convertDDI(outDir,
downloadDir=None,
redownload=False,
makeIntermediateFiles=True,
debug=False):
cwd = os.getcwd()
if not os.path.exists(outDir):
os.makedirs(outDir)
os.chdir(outDir)
logFileName = os.path.join(outDir, "DDI11-conversion-log.txt")
Stream.openLog(logFileName)
print >> sys.stderr, "=======================", "Converting DDI'11 corpus", "======================="
corpusDir = outDir + "/DDI11-original"
Utils.Download.downloadAndExtract(Settings.URL["DDI11_CORPUS"], corpusDir,
downloadDir)
bigfileName = os.path.join(outDir, "DDI11")
#oldXML = ETUtils.ETFromObj(bigfileName+".xml")
trainUnified = corpusDir + "/train"
trainMTMX = corpusDir + "/train_MTMX"
testUnified = corpusDir + "/test"
testMTMX = corpusDir + "/test_MTMX"
# Load main documents
tempdir = tempfile.mkdtemp()
print >> sys.stderr, "Temporary files directory at", tempdir
documents, docById, docCounts = loadDocs(trainUnified)
# Divide training data into a train and devel set
sortedDocCounts = sorted(docCounts.iteritems(),
key=lambda (k, v): (v, k),
reverse=True)
datasetCounts = {"train": [0, 0], "devel": [0, 0], "test": [0, 0]}
for i in range(0, len(sortedDocCounts) - 3, 4):
for j in [0, 1]:
docById[sortedDocCounts[i + j][0]].set("set", "train")
datasetCounts["train"][0] += sortedDocCounts[i + j][1][0]
datasetCounts["train"][1] += sortedDocCounts[i + j][1][1]
docById[sortedDocCounts[i + 2][0]].set(
"set",
"train") #docById[sortedDocCounts[i+2][0]].set("set", "devel")
docById[sortedDocCounts[i + 3][0]].set(
"set",
"devel") #docById[sortedDocCounts[i+3][0]].set("set", "test")
datasetCounts["train"][0] += sortedDocCounts[i + 2][1][
0] #datasetCounts["devel"][0] += sortedDocCounts[i+2][1][0]
datasetCounts["train"][1] += sortedDocCounts[i + 2][1][
1] #datasetCounts["devel"][1] += sortedDocCounts[i+2][1][1]
datasetCounts["devel"][0] += sortedDocCounts[i + 3][1][
0] #datasetCounts["test"][0] += sortedDocCounts[i+3][1][0]
datasetCounts["devel"][1] += sortedDocCounts[i + 3][1][
1] #datasetCounts["test"][1] += sortedDocCounts[i+3][1][1]
for document in documents: # epajaolliset jaa yli
if document.get("set") == None:
document.set("set", "train")
# Print division results
print >> sys.stderr, datasetCounts
for key in datasetCounts.keys():
if datasetCounts[key][1] != 0:
print key, datasetCounts[key][0] / float(datasetCounts[key][1])
else:
print key, datasetCounts[key][0], "/", float(datasetCounts[key][1])
# Some of the train and test ids overlap. Let's change the train set ids, because test set ones are needed
# for the final evaluation.
changeIdCount = 1000
for trainId in [
'DrugDDI.d312', 'DrugDDI.d316', 'DrugDDI.d332', 'DrugDDI.d334',
'DrugDDI.d337', 'DrugDDI.d342', 'DrugDDI.d349', 'DrugDDI.d354',
'DrugDDI.d373', 'DrugDDI.d379', 'DrugDDI.d383', 'DrugDDI.d388',
'DrugDDI.d392', 'DrugDDI.d396', 'DrugDDI.d398', 'DrugDDI.d409',
'DrugDDI.d411', 'DrugDDI.d415', 'DrugDDI.d425', 'DrugDDI.d430',
'DrugDDI.d433', 'DrugDDI.d448', 'DrugDDI.d450', 'DrugDDI.d452',
'DrugDDI.d462', 'DrugDDI.d467', 'DrugDDI.d470', 'DrugDDI.d474',
'DrugDDI.d480', 'DrugDDI.d482', 'DrugDDI.d485', 'DrugDDI.d492',
'DrugDDI.d494', 'DrugDDI.d496', 'DrugDDI.d498', 'DrugDDI.d500',
'DrugDDI.d503', 'DrugDDI.d506', 'DrugDDI.d518', 'DrugDDI.d523',
'DrugDDI.d528', 'DrugDDI.d535', 'DrugDDI.d539', 'DrugDDI.d552',
'DrugDDI.d554', 'DrugDDI.d558', 'DrugDDI.d561', 'DrugDDI.d570',
'DrugDDI.d578'
]:
newId = "DrugDDI.d" + str(changeIdCount)
print >> sys.stderr, "Changing train/devel id", trainId, "to", newId
for element in docById[trainId].getiterator():
for attrName, attrValue in element.attrib.iteritems():
if trainId in attrValue:
element.set(attrName, attrValue.replace(trainId, newId))
docById[newId] = docById[trainId]
del docById[trainId]
changeIdCount += 1
# If test set exists, load it, too
if testUnified != None:
testDocuments, testDocById, testDocCounts = loadDocs(testUnified)
for document in testDocuments:
document.set("set", "test")
documents = documents + testDocuments
overlappingIds = []
for key in docById:
if key in testDocById:
overlappingIds.append(key)
for key in docById:
assert key not in testDocById, (key, docById[key].get("origId"),
testDocById[key].get("origId"),
sorted(docById.keys()),
sorted(testDocById.keys()),
sorted(overlappingIds))
docById.update(testDocById)
# Add all documents into one XML
xmlTree = ET.ElementTree(ET.Element("corpus"))
root = xmlTree.getroot()
root.set("source", "DDI11")
for document in documents:
root.append(document)
if makeIntermediateFiles:
ETUtils.write(root, bigfileName + "-documents-notfixed.xml")
xml = xmlTree
print >> sys.stderr, "Fixing DDI XML"
fixEntities(xml)
convertToInteractions(xml)
# Add MTMX
if trainMTMX != None:
inDir = Utils.Download.getTopDir(
tempdir,
Utils.Download.downloadAndExtract(trainMTMX, tempdir,
outDir + "/DDI11-original"))
DDITools.addMTMX(xml, inDir)
if testMTMX != None:
inDir = Utils.Download.getTopDir(
tempdir,
Utils.Download.downloadAndExtract(testMTMX, tempdir,
outDir + "/DDI11-original"))
DDITools.addMTMX(xml, inDir)
if makeIntermediateFiles:
ETUtils.write(root, bigfileName + "-documents.xml")
print >> sys.stderr, "---------------", "Inserting TEES-generated analyses", "---------------"
Utils.Download.downloadAndExtract(Settings.URL["TEES_PARSES"],
os.path.join(Settings.DATAPATH,
"TEES-parses"),
downloadDir,
redownload=redownload)
extractedFilename = os.path.join(Settings.DATAPATH,
"TEES-parses") + "/DDI11"
print >> sys.stderr, "Making sentences"
Tools.SentenceSplitter.makeSentences(xml, extractedFilename, None)
print >> sys.stderr, "Inserting McCC parses"
Tools.BLLIPParser.insertParses(
xml,
extractedFilename,
None,
extraAttributes={"source": "TEES-preparsed"})
print >> sys.stderr, "Inserting Stanford conversions"
Tools.StanfordParser.insertParses(
xml,
extractedFilename,
None,
extraAttributes={"stanfordSource": "TEES-preparsed"})
print >> sys.stderr, "Protein Name Splitting"
splitTarget = "McCC"
#ProteinNameSplitter.mainFunc(xml, None, splitTarget, splitTarget, "split-"+splitTarget, "split-"+splitTarget)
ProteinNameSplitter.mainFunc(xml, None, splitTarget, removeOld=True)
print >> sys.stderr, "Head Detection"
#xml = FindHeads.findHeads(xml, "split-"+splitTarget, tokenization=None, output=None, removeExisting=True)
xml = FindHeads.findHeads(xml,
splitTarget,
tokenization=None,
output=None,
removeExisting=True)
print >> sys.stderr, "Dividing into sets"
Utils.InteractionXML.DivideSets.processCorpus(xml, outDir, "DDI11", ".xml")
Stream.closeLog(logFileName)
if not debug:
print >> sys.stderr, "Removing temporary directory", tempdir
shutil.rmtree(tempdir)
os.chdir(cwd)
