def main(treeFile):
dump = set(['4 -> 1 3',
'0 -> 1 3'])
prods = {}
pe = evaluate_productions.ProdEvaluator(True, ma_util.GRANULARITY_FINE)
for tree in ma_util.readPenn(treeFile):
for subTree in ma_util.walkTree(tree):
l = pe.getInterestingLabel(subTree)
if l:
if not l in prods:
prods[l] = set()
prod = '%s -> %s %s' % (subTree.node, subTree[0].node,
subTree[1].node)
prods[l].add(prod)
if prod in dump:
print "DESIRED: %s" % l
print subTree.pprint().encode('utf-8')
# don't print everything
if len(subTree.leaves()) < 5:
print "L: %s" % l
print subTree.pprint().encode('utf-8')
print "-" * 8
for rule in prods:
print "RULE: %s" % rule
for prod in prods[rule]:
print prod
print "=" * 8
def getMappingFromNodeIDToSentiment(tigerSentence, pennSentence):
"""Extracts sentiment values for node IDs.
Given a parse tree in TigerXML format and a sentiment-annotated
parse tree in Penn Treebank format, this methods extracts
the sentiment values for each node and matches it
to the node ID obtained from the TigerXML file.
Both trees must be isomorphic.
@param tigerSentence TigerGraph object containing a sentence parse tree
@param pennSentence NLTK Tree containing a sentence parse tree
@returns Mapping from node IDs to sentiment values
"""
res = {}
for (tigerNode, pennNode) in itertools.izip_longest(
ma_util.walkTree(tigerToTree(tigerSentence)), ma_util.walkTree(pennSentence),
fillvalue="LIST_LENGTH_NOT_EQUAL"):
tigerID = tigerNode.node
pennSentiment = pennNode.node
res[tigerID] = pennSentiment
return res
def walkTree(tree):
return ma_util.walkTree(tree)