def test_optimalbinarize():
"""Verify that all optimal parsing complexities are lower than or
equal to the complexities of right-to-left binarizations."""
from discodop.treetransforms import optimalbinarize, complexityfanout
from discodop.treebank import NegraCorpusReader
corpus = NegraCorpusReader('alpinosample.export', punct='move')
total = violations = violationshd = 0
for n, (tree, sent) in enumerate(zip(list(
corpus.trees().values())[:-2000], corpus.sents().values())):
t = addbitsets(tree)
if all(fanout(x) == 1 for x in t.subtrees()):
continue
print(n, tree, '\n', ' '.join(sent))
total += 1
optbin = optimalbinarize(tree.copy(True), headdriven=False, h=None, v=1)
# undo head-ordering to get a normal right-to-left binarization
normbin = addbitsets(binarize(canonicalize(Tree.convert(tree))))
if (max(map(complexityfanout, optbin.subtrees()))
> max(map(complexityfanout, normbin.subtrees()))):
print('non-hd\n', tree)
print(max(map(complexityfanout, optbin.subtrees())), optbin)
print(max(map(complexityfanout, normbin.subtrees())), normbin, '\n')
violations += 1
optbin = optimalbinarize(tree.copy(True), headdriven=True, h=1, v=1)
normbin = addbitsets(binarize(Tree.convert(tree), horzmarkov=1))
if (max(map(complexityfanout, optbin.subtrees()))
> max(map(complexityfanout, normbin.subtrees()))):
print('hd\n', tree)
print(max(map(complexityfanout, optbin.subtrees())), optbin)
print(max(map(complexityfanout, normbin.subtrees())), normbin, '\n')
violationshd += 1
print('opt. bin. violations normal: %d / %d; hd: %d / %d' % (
violations, total, violationshd, total))
assert violations == violationshd == 0
def test_optimalbinarize():
"""Verify that all optimal parsing complexities are lower than or
equal to the complexities of right-to-left binarizations."""
from discodop.treetransforms import optimalbinarize, complexityfanout
from discodop.treebank import NegraCorpusReader
corpus = NegraCorpusReader('alpinosample.export', punct='move')
total = violations = violationshd = 0
for n, (tree, sent) in enumerate(zip(list(
corpus.trees().values())[:-2000], corpus.sents().values())):
t = addbitsets(tree)
if all(fanout(x) == 1 for x in t.subtrees()):
continue
print(n, tree, '\n', ' '.join(sent))
total += 1
optbin = optimalbinarize(tree.copy(True), headdriven=False, h=None, v=1)
# undo head-ordering to get a normal right-to-left binarization
normbin = addbitsets(binarize(canonicalize(Tree.convert(tree))))
if (max(map(complexityfanout, optbin.subtrees()))
> max(map(complexityfanout, normbin.subtrees()))):
print('non-hd\n', tree)
print(max(map(complexityfanout, optbin.subtrees())), optbin)
print(max(map(complexityfanout, normbin.subtrees())), normbin, '\n')
violations += 1
optbin = optimalbinarize(tree.copy(True), headdriven=True, h=1, v=1)
normbin = addbitsets(binarize(Tree.convert(tree), horzmarkov=1))
if (max(map(complexityfanout, optbin.subtrees()))
> max(map(complexityfanout, normbin.subtrees()))):
print('hd\n', tree)
print(max(map(complexityfanout, optbin.subtrees())), optbin)
print(max(map(complexityfanout, normbin.subtrees())), normbin, '\n')
violationshd += 1
print('opt. bin. violations normal: %d / %d; hd: %d / %d' % (
violations, total, violationshd, total))
assert violations == violationshd == 0
def dobinarization(trees, sents, binarization, relationalrealizational):
"""Apply binarization."""
# fixme: this n should correspond to sentence id
tbfanout, n = treebank.treebankfanout(trees)
logging.info('treebank fan-out before binarization: %d #%d\n%s\n%s',
tbfanout, n, trees[n], ' '.join(sents[n]))
# binarization
begin = time.clock()
msg = 'binarization: %s' % binarization.method
if binarization.fanout_marks_before_bin:
trees = [treetransforms.addfanoutmarkers(t) for t in trees]
if binarization.method is None:
pass
elif binarization.method == 'default':
msg += ' %s h=%d v=%d %s' % (
binarization.factor, binarization.h, binarization.v,
'tailmarker' if binarization.tailmarker else '')
for a in trees:
treetransforms.binarize(a, factor=binarization.factor,
tailmarker=binarization.tailmarker,
horzmarkov=binarization.h, vertmarkov=binarization.v,
leftmostunary=binarization.leftmostunary,
rightmostunary=binarization.rightmostunary,
reverse=binarization.revmarkov,
headidx=-1 if binarization.markhead else None,
filterfuncs=(relationalrealizational['ignorefunctions']
+ (relationalrealizational['adjunctionlabel'], ))
if relationalrealizational else (),
labelfun=binarization.labelfun)
elif binarization.method == 'optimal':
trees = [Tree.convert(treetransforms.optimalbinarize(tree))
for n, tree in enumerate(trees)]
elif binarization.method == 'optimalhead':
msg += ' h=%d v=%d' % (
binarization.h, binarization.v)
trees = [Tree.convert(treetransforms.optimalbinarize(
tree, headdriven=True, h=binarization.h, v=binarization.v))
for n, tree in enumerate(trees)]
trees = [treetransforms.addfanoutmarkers(t) for t in trees]
logging.info('%s; cpu time elapsed: %gs',
msg, time.clock() - begin)
trees = [treetransforms.canonicalize(a).freeze() for a in trees]
return trees
def getgrammars(trees, sents, stages, bintype, horzmarkov, vertmarkov, factor,
tailmarker, revmarkov, leftmostunary, rightmostunary, pospa, markhead,
fanout_marks_before_bin, testmaxwords, resultdir, numproc,
lexmodel, simplelexsmooth, top, relationalrealizational):
""" Apply binarization and read off the requested grammars. """
# fixme: this n should correspond to sentence id
tbfanout, n = treebankfanout(trees)
logging.info('treebank fan-out before binarization: %d #%d\n%s\n%s',
tbfanout, n, trees[n], ' '.join(sents[n]))
# binarization
begin = time.clock()
if fanout_marks_before_bin:
trees = [addfanoutmarkers(t) for t in trees]
if bintype == 'binarize':
bintype += ' %s h=%d v=%d %s' % (factor, horzmarkov, vertmarkov,
'tailmarker' if tailmarker else '')
for a in trees:
binarize(a, factor=factor, tailmarker=tailmarker,
horzmarkov=horzmarkov, vertmarkov=vertmarkov,
leftmostunary=leftmostunary, rightmostunary=rightmostunary,
reverse=revmarkov, pospa=pospa,
headidx=-1 if markhead else None,
filterfuncs=(relationalrealizational['ignorefunctions']
+ (relationalrealizational['adjunctionlabel'], ))
if relationalrealizational else ())
elif bintype == 'optimal':
trees = [Tree.convert(optimalbinarize(tree))
for n, tree in enumerate(trees)]
elif bintype == 'optimalhead':
trees = [Tree.convert(optimalbinarize(tree, headdriven=True,
h=horzmarkov, v=vertmarkov)) for n, tree in enumerate(trees)]
trees = [addfanoutmarkers(t) for t in trees]
logging.info('binarized %s cpu time elapsed: %gs',
bintype, time.clock() - begin)
logging.info('binarized treebank fan-out: %d #%d', *treebankfanout(trees))
trees = [canonicalize(a).freeze() for a in trees]
for n, stage in enumerate(stages):
if stage.split:
traintrees = [binarize(splitdiscnodes(Tree.convert(a),
stage.markorigin), childchar=':').freeze() for a in trees]
logging.info('splitted discontinuous nodes')
else:
traintrees = trees
if stage.mode.startswith('pcfg'):
assert tbfanout == 1 or stage.split
backtransform = None
if stage.dop:
if stage.usedoubledop:
# find recurring fragments in treebank,
# as well as depth 1 'cover' fragments
fragments = getfragments(traintrees, sents, numproc,
iterate=stage.iterate, complement=stage.complement)
xgrammar, backtransform, altweights = doubledop(
traintrees, fragments)
else: # DOP reduction
xgrammar, altweights = dopreduction(
traintrees, sents, packedgraph=stage.packedgraph)
nodes = sum(len(list(a.subtrees())) for a in traintrees)
if lexmodel and simplelexsmooth:
newrules = simplesmoothlexicon(lexmodel)
xgrammar.extend(newrules)
for weights in altweights.values():
weights.extend(w for _, w in newrules)
elif lexmodel:
xgrammar = smoothlexicon(xgrammar, lexmodel)
msg = grammarinfo(xgrammar)
rules, lexicon = write_lcfrs_grammar(
xgrammar, bitpar=stage.mode.startswith('pcfg'))
grammar = Grammar(rules, lexicon, start=top,
bitpar=stage.mode.startswith('pcfg'))
for name in altweights:
grammar.register(u'%s' % name, altweights[name])
with gzip.open('%s/%s.rules.gz' % (
resultdir, stage.name), 'wb') as rulesfile:
rulesfile.write(rules)
with codecs.getwriter('utf-8')(gzip.open('%s/%s.lex.gz' % (
resultdir, stage.name), 'wb')) as lexiconfile:
lexiconfile.write(lexicon)
logging.info('DOP model based on %d sentences, %d nodes, '
'%d nonterminals', len(traintrees), nodes, len(grammar.toid))
logging.info(msg)
if stage.estimator != 'dop1':
grammar.switch(u'%s' % stage.estimator)
_sumsto1 = grammar.testgrammar()
if stage.usedoubledop:
# backtransform keys are line numbers to rules file;
# to see them together do:
# $ paste <(zcat dop.rules.gz) <(zcat dop.backtransform.gz)
with codecs.getwriter('ascii')(gzip.open(
'%s/%s.backtransform.gz' % (resultdir, stage.name),
'w')) as out:
out.writelines('%s\n' % a for a in backtransform)
if n and stage.prune:
msg = grammar.getmapping(stages[n - 1].grammar,
striplabelre=None if stages[n - 1].dop
else re.compile(b'@.+$'),
neverblockre=re.compile(b'.+}<'),
splitprune=stage.splitprune and stages[n - 1].split,
markorigin=stages[n - 1].markorigin)
else:
# recoverfragments() relies on this mapping to identify
# binarization nodes
msg = grammar.getmapping(None,
striplabelre=None,
neverblockre=re.compile(b'.+}<'),
splitprune=False, markorigin=False)
logging.info(msg)
elif n and stage.prune: # dop reduction
msg = grammar.getmapping(stages[n - 1].grammar,
striplabelre=None if stages[n - 1].dop
and not stages[n - 1].usedoubledop
else re.compile(b'@[-0-9]+$'),
neverblockre=re.compile(stage.neverblockre)
if stage.neverblockre else None,
splitprune=stage.splitprune and stages[n - 1].split,
markorigin=stages[n - 1].markorigin)
if stage.mode == 'dop-rerank':
grammar.getrulemapping(stages[n - 1].grammar)
logging.info(msg)
# write prob models
np.savez_compressed('%s/%s.probs.npz' % (resultdir, stage.name),
**{name: mod for name, mod
in zip(grammar.modelnames, grammar.models)})
else: # not stage.dop
xgrammar = treebankgrammar(traintrees, sents)
logging.info('induced %s based on %d sentences',
('PCFG' if tbfanout == 1 or stage.split else 'PLCFRS'),
len(traintrees))
if stage.split or os.path.exists('%s/pcdist.txt' % resultdir):
logging.info(grammarinfo(xgrammar))
else:
logging.info(grammarinfo(xgrammar,
dump='%s/pcdist.txt' % resultdir))
if lexmodel and simplelexsmooth:
newrules = simplesmoothlexicon(lexmodel)
xgrammar.extend(newrules)
elif lexmodel:
xgrammar = smoothlexicon(xgrammar, lexmodel)
rules, lexicon = write_lcfrs_grammar(
xgrammar, bitpar=stage.mode.startswith('pcfg'))
grammar = Grammar(rules, lexicon, start=top,
bitpar=stage.mode.startswith('pcfg'))
with gzip.open('%s/%s.rules.gz' % (
resultdir, stage.name), 'wb') as rulesfile:
rulesfile.write(rules)
with codecs.getwriter('utf-8')(gzip.open('%s/%s.lex.gz' % (
resultdir, stage.name), 'wb')) as lexiconfile:
lexiconfile.write(lexicon)
_sumsto1 = grammar.testgrammar()
if n and stage.prune:
msg = grammar.getmapping(stages[n - 1].grammar,
striplabelre=None,
neverblockre=re.compile(stage.neverblockre)
if stage.neverblockre else None,
splitprune=stage.splitprune and stages[n - 1].split,
markorigin=stages[n - 1].markorigin)
logging.info(msg)
logging.info('wrote grammar to %s/%s.{rules,lex%s}.gz', resultdir,
stage.name, ',backtransform' if stage.usedoubledop else '')
outside = None
if stage.getestimates == 'SX':
assert tbfanout == 1 or stage.split, 'SX estimate requires PCFG.'
logging.info('computing PCFG estimates')
begin = time.clock()
outside = getpcfgestimates(grammar, testmaxwords,
grammar.toid[trees[0].label])
logging.info('estimates done. cpu time elapsed: %gs',
time.clock() - begin)
np.savez('pcfgoutside.npz', outside=outside)
logging.info('saved PCFG estimates')
elif stage.useestimates == 'SX':
assert tbfanout == 1 or stage.split, 'SX estimate requires PCFG.'
assert stage.mode != 'pcfg', (
'estimates require agenda-based parser.')
outside = np.load('pcfgoutside.npz')['outside']
logging.info('loaded PCFG estimates')
if stage.getestimates == 'SXlrgaps':
logging.info('computing PLCFRS estimates')
begin = time.clock()
outside = getestimates(grammar, testmaxwords,
grammar.toid[trees[0].label])
logging.info('estimates done. cpu time elapsed: %gs',
time.clock() - begin)
np.savez('outside.npz', outside=outside)
logging.info('saved estimates')
elif stage.useestimates == 'SXlrgaps':
outside = np.load('outside.npz')['outside']
logging.info('loaded PLCFRS estimates')
stage.update(grammar=grammar, backtransform=backtransform,
outside=outside)