def buildAdjacencyMatrix(tokenElements, dependencyElements, entityElements, metamapElements, pairElement, matrixSettings):
m = matrixSettings
#Punctuation dependencies are mostly junk
dependencyElements = removeDependencies(dependencyElements, m.removeDependencies)
parseGraph = ParseGraph.ParseGraph(tokenElements, dependencyElements, m.mergeDependencies)
parseGraph.shortestPathMethod = "dijkstra"
parseGraph.markNamedEntities(entityElements)
e1Id = pairElement.get("e1")
e2Id = pairElement.get("e2")
entity1TokenIds = parseGraph.getNamedEntityTokenIds( [e1Id] )
entity2TokenIds = parseGraph.getNamedEntityTokenIds( [e2Id] )
interactionWordTokenIds = parseGraph.getTokenIdsByText(m.interactionWords, False)
# Give dependencies base weights
parseGraph.setAllDependencyWeights(m.depBaseWeight)
# Set dependencies' weights based on paths
pathStyles = ParseGraph.splitPathStyles(m.paths)
for style in pathStyles:
paths = []
if style["type"] == "binary":
paths = parseGraph.buildBinaryPaths(entity1TokenIds, entity2TokenIds, style["length"], style["direction"]=="directed", m.pathTimeout)
elif style["type"].find("tertiary") != -1:
paths = parseGraph.buildTertiaryPaths(entity1TokenIds, interactionWordTokenIds, entity2TokenIds, style["type"]=="closest_tertiary", style["length"], style["direction"]=="directed", m.pathTimeout)
if m.markInteractionWords == MatrixSettings.markedInteractionWords.fromTertiaryPaths:
parseGraph.setPPIInteractionWords(paths)
for i in range(len(paths)):
paths[i] = paths[i][0]
if paths != None:
parseGraph.setDependencyWeightsByPath(paths, style["weight"])
# Reduce dependencies' weights by distance from threshold
if m.weightByDistance:
parseGraph.reduceWeightByDistance(m.depWeightReductionThreshold, m.depWeightReductionFactor)
# Set dependency prefixes
if m.depPrefixThreshold > 0.0:
parseGraph.setPPIPrefixForDependencies(m.depPrefix, m.depPrefixThreshold) # f.e. shortest path prefix
# Set token texts
if m.tokenPPIText == MatrixSettings.ppiTexts.full:
parseGraph.ppiTextFromOriginalText()
elif m.tokenPPIText == MatrixSettings.ppiTexts.stem:
parseGraph.ppiTextFromStems()
else:
print >> sys.stderr, "Illegal ppiText setting", m.tokenPPIText
sys.exit(1)
# Add metamap codes
if metamapElements != None:
metamapDict = {}
for metamapElement in metamapElements:
metamapDict[metamapElement.get("tokenid")] = metamapElement.get("basecodes").split(",")
parseGraph.addMetamapCodes(metamapDict)
if m.maskPPIText:
parseGraph.maskNames(e1Id, e2Id)
if m.tokenPositionTags:
parseGraph.addPositionTags(entity1TokenIds, entity2TokenIds)
if pairElement.get("interaction") == "True":
output = 1.
else:
output = -1.
adjMatrix, labels = parseGraph.buildAdjacencyMatrix(floattype, m.directed, m.linearOrderWeight)
return adjMatrix, labels, output
def buildAdjacencyMatrix(tokenElements, dependencyElements, entityElements,
metamapElements, pairElement, matrixSettings):
m = matrixSettings
#Punctuation dependencies are mostly junk
dependencyElements = removeDependencies(dependencyElements,
m.removeDependencies)
parseGraph = ParseGraph.ParseGraph(tokenElements, dependencyElements,
m.mergeDependencies)
parseGraph.shortestPathMethod = "dijkstra"
parseGraph.markNamedEntities(entityElements)
e1Id = pairElement.get("e1")
e2Id = pairElement.get("e2")
entity1TokenIds = parseGraph.getNamedEntityTokenIds([e1Id])
entity2TokenIds = parseGraph.getNamedEntityTokenIds([e2Id])
interactionWordTokenIds = parseGraph.getTokenIdsByText(
m.interactionWords, False)
# Give dependencies base weights
parseGraph.setAllDependencyWeights(m.depBaseWeight)
# Set dependencies' weights based on paths
pathStyles = ParseGraph.splitPathStyles(m.paths)
for style in pathStyles:
paths = []
if style["type"] == "binary":
paths = parseGraph.buildBinaryPaths(
entity1TokenIds, entity2TokenIds, style["length"],
style["direction"] == "directed", m.pathTimeout)
elif style["type"].find("tertiary") != -1:
paths = parseGraph.buildTertiaryPaths(
entity1TokenIds, interactionWordTokenIds, entity2TokenIds,
style["type"] == "closest_tertiary", style["length"],
style["direction"] == "directed", m.pathTimeout)
if m.markInteractionWords == MatrixSettings.markedInteractionWords.fromTertiaryPaths:
parseGraph.setPPIInteractionWords(paths)
for i in range(len(paths)):
paths[i] = paths[i][0]
if paths != None:
parseGraph.setDependencyWeightsByPath(paths, style["weight"])
# Reduce dependencies' weights by distance from threshold
if m.weightByDistance:
parseGraph.reduceWeightByDistance(m.depWeightReductionThreshold,
m.depWeightReductionFactor)
# Set dependency prefixes
if m.depPrefixThreshold > 0.0:
parseGraph.setPPIPrefixForDependencies(
m.depPrefix, m.depPrefixThreshold) # f.e. shortest path prefix
# Set token texts
if m.tokenPPIText == MatrixSettings.ppiTexts.full:
parseGraph.ppiTextFromOriginalText()
elif m.tokenPPIText == MatrixSettings.ppiTexts.stem:
parseGraph.ppiTextFromStems()
else:
print >> sys.stderr, "Illegal ppiText setting", m.tokenPPIText
sys.exit(1)
# Add metamap codes
if metamapElements != None:
metamapDict = {}
for metamapElement in metamapElements:
metamapDict[metamapElement.get("tokenid")] = metamapElement.get(
"basecodes").split(",")
parseGraph.addMetamapCodes(metamapDict)
if m.maskPPIText:
parseGraph.maskNames(e1Id, e2Id)
if m.tokenPositionTags:
parseGraph.addPositionTags(entity1TokenIds, entity2TokenIds)
if pairElement.get("interaction") == "True":
output = 1.
else:
output = -1.
adjMatrix, labels = parseGraph.buildAdjacencyMatrix(
floattype, m.directed, m.linearOrderWeight)
return adjMatrix, labels, output