for lex in verb_clause:
if lex not in senses:
missingFlowcharts.add(lex)
utils.caption(
0,
"\tNo flowchart for {} verbs, e.g. {}".format(
len(missingFlowcharts), ", ".join(sorted(missingFlowcharts)[0:10])),
)
# In[45]:
good = True
for lex in senses:
if lex not in verb_clause:
TF.error("No verb {} in enriched corpus".format(lex))
good = False
if good:
utils.caption(0, "\tAll flowcharts belong to a verb in the corpus")
# In[46]:
utils.caption(4, "Applying the flowcharts")
# In[47]:
outcome_lab = collections.Counter()
outcome_lab_l = collections.defaultdict(lambda: collections.Counter())
# we want an overview of the flowchart decisions per lexeme
# Per lexeme, per sense_label we store the clauses
def genTrees(version):
C = setVersion(version)
bhsa = C.bhsa
sp = C.sp
rela = C.rela
ptyp = C.ptyp
ctyp = C.ctyp
g_word_utf8 = C.g_word_utf8
tfDir = C.tfDir
TF = Fabric(locations=f"{GH}/{ORG}", modules=bhsa)
api = TF.load(f"{sp} {rela} {ptyp} {ctyp} {g_word_utf8} mother")
E = api.E
F = api.F
Fs = api.Fs
def getTag(node):
otype = F.otype.v(node)
tag = TYPE_TABLE[otype]
if tag == "P":
tag = Fs(ptyp).v(node)
elif tag == "C":
tag = ccrTable[Fs(rela).v(node)]
isWord = tag == ""
pos = POS_TABLE[Fs(sp).v(node)] if isWord else None
slot = node if isWord else None
text = f'"{Fs(g_word_utf8).v(node)}"' if isWord else None
return (tag, pos, slot, text, isWord)
def getTagN(node):
otype = F.otype.v(node)
tag = TYPE_TABLE[otype]
if tag == "P":
tag = Fs(ptyp).v(node)
elif tag == "C":
tag = ccrTable[Fs(rela).v(node)]
isWord = tag == ""
if not isWord:
tag += "{" + str(node) + "}"
pos = POS_TABLE[Fs(sp).v(node)] if isWord else None
slot = node if isWord else None
text = f'"{Fs(g_word_utf8).v(node)}"' if isWord else None
return (tag, pos, slot, text, isWord)
treeTypes = ("sentence", "clause", "phrase", "subphrase", "word")
(rootType, leafType, clauseType, phraseType) = (
treeTypes[0],
treeTypes[-1],
treeTypes[1],
treeTypes[2],
)
ccrTable = dict((c[0], c[1][1]) for c in CCR_INFO.items())
ccrClass = dict((c[0], c[1][0]) for c in CCR_INFO.items())
tree = Tree(
TF,
otypes=treeTypes,
phraseType=phraseType,
clauseType=clauseType,
ccrFeature=rela,
ptFeature=ptyp,
posFeature=sp,
motherFeature="mother",
)
tree.restructureClauses(ccrClass)
results = tree.relations()
TF.info("Ready for processing")
skip = set()
TF.info("Verifying whether all slots are preserved under restructuring")
TF.info(f"Expected mismatches: {EXPECTED_MISMATCHES.get(version, '??')}")
errors = []
# i = 10
for snode in F.otype.s(rootType):
declaredSlots = set(E.oslots.s(snode))
results = {}
thisgood = {}
for kind in ("e", "r"):
results[kind] = set(lt for lt in tree.getLeaves(snode, kind)
if F.otype.v(lt) == leafType)
thisgood[kind] = declaredSlots == results[kind]
# if not thisgood[kind]:
# print(f"{kind} D={declaredSlots}\n L={results[kind]}")
# i -= 1
# if i == 0: break
if False in thisgood.values():
errors.append((snode, thisgood["e"], thisgood["r"]))
nErrors = len(errors)
if nErrors:
TF.error(f"{len(errors)} mismatches:")
mine = min(20, len(errors))
skip |= {e[0] for e in errors}
for (s, e, r) in errors[0:mine]:
TF.error(
(f"{s} embedding: {'OK' if e else 'XX'};"
f" restructd: {'OK' if r else 'XX'}"),
tm=False,
)
else:
TF.info(f"{len(errors)} mismatches")
TF.info(f"Exporting {rootType} trees to TF")
s = 0
chunk = 10000
sc = 0
treeData = {}
treeDataN = {}
for node in F.otype.s(rootType):
if node in skip:
continue
(treeRep, wordsRep, bSlot) = tree.writeTree(node,
"r",
getTag,
rev=False,
leafNumbers=True)
(treeNRep, wordsNRep, bSlotN) = tree.writeTree(node,
"r",
getTagN,
rev=False,
leafNumbers=True)
treeData[node] = treeRep
treeDataN[node] = treeNRep
s += 1
sc += 1
if sc == chunk:
TF.info(f"{s} trees composed")
sc = 0
TF.info(f"{s} trees composed")
nodeFeatures = dict(tree=treeData, treen=treeDataN)
metaData = dict(
tree=dict(
valueType="str",
description="penn treebank represententation for sentences",
converter="Dirk Roorda",
convertor="trees.ipynb",
url="https://github.com/etcbc/trees/trees.ipynb",
coreData="BHSA",
coreVersion=version,
),
treen=dict(
valueType="str",
description=
"penn treebank represententation for sentences with node numbers included",
converter="Dirk Roorda",
convertor="trees.ipynb",
url="https://github.com/etcbc/trees/trees.ipynb",
coreData="BHSA",
coreVersion=version,
),
)
TF.info("Writing tree feature to TF")
TFw = Fabric(locations=tfDir, silent=True)
TFw.save(nodeFeatures=nodeFeatures, edgeFeatures={}, metaData=metaData)
TF.info("There are {} {}s".format(len(list(F.otype.s(rootType))), rootType))
# In[15]:
# 2
TF.info("Checking parents of {}s ... (expecting none)".format(rootType))
exceptions = set()
for node in F.otype.s(rootType):
if node in parent:
exceptions.add(node)
if len(exceptions) == 0:
TF.info("No {} has a parent".format(rootType))
else:
TF.error("{} {}s have a parent:".format(len(exceptions), rootType))
for n in sorted(exceptions):
p = parent[n]
TF.error(
"{} {} [{}] has {} parent {} [{}]".format(
rootType, n, tree.slotss(n), F.otype.v(p), p, tree.slotss(p)
)
)
# In[16]:
# 3 (again a check on #1)
TF.info("Checking the types of root nodes ... (should all be {}s)".format(rootType))
expectedTops = {
