def __init__(self):
# Initialize commons store with knowledge base.
start = time.time()
self.commons = sling.Store()
self.commons.lockgc()
self.commons.load(wikidir + "/kb.sling", snapshot=True)
self.n_item_member = self.commons['/w/item/member']
self.n_instance_of = self.commons['P31']
self.n_wikimedia_category = self.commons['Q4167836']
self.n_subject = self.commons['subject']
self.extractor = sling.FactExtractor(self.commons)
# Add category subject types.
self.subjects = {}
for subject, item in english_subject_types.iteritems():
self.subjects[subject] = self.commons[item]
# Add properties for subjects.
self.subject_properties = []
for p in subject_properties:
self.subject_properties.append(self.commons[p])
self.commons.freeze()
end = time.time()
print end - start, "secs loading commons"
# Load phrase table.
# TODO(ringgaard): Load language-dependent phrase table.
start = time.time()
self.phrasetab = sling.PhraseTable(self.commons,
wikidir + "/en/phrase-table.repo")
end = time.time()
print end - start, "secs loading phrase table"
# Open category member database.
self.member_db = sling.RecordDatabase(wikidir +
"/wikipedia-members.rec")
def init(self, task):
self.kb = load_kb(task)
self.extractor = sling.FactExtractor(self.kb)
self.matcher = FactMatcher(self.kb, self.extractor)
n_lei = kb["P1278"]
n_swift_bic_code = kb["P2627"]
n_subsidiary = kb["P355"]
n_parent = kb["P749"]
n_owned_by = kb["P127"]
n_owner_of = kb["P1830"]
n_starttime = kb["P580"]
n_endtime = kb["P582"]
n_legal_form = kb["P1454"]
n_coord_location = kb["P625"]
n_geo = kb["/w/geo"]
n_lat = kb["/w/lat"]
n_lng = kb["/w/lng"]
aliases = sling.PhraseTable(kb, "data/e/kb/en/phrase-table.repo")
factex = sling.FactExtractor(kb)
city_types = factex.taxonomy([
"Q486972", # human settlement
"Q56061", # administrative territorial entity
])
# Read registers.
bizregs = sling.dataset.bizreg.BusinessRegistries(kb)
regauth = bizregs.by_auth_code()
# Build country and region table.
countries = {}
regions = {}
for item in kb:
code = item[n_country_code]
def increment_key(dictionary, key, delta=1):
dictionary[key] = dictionary.get(key, 0) + delta
def fact_to_text(fact):
l = []
for f in fact:
l.append(str(f.name))
return ": ".join(l)
commons = sling.Store()
commons.lockgc()
commons.load(wikidir + "/kb.sling", snapshot=True)
n_is = commons["is"]
extractor = sling.FactExtractor(commons)
phrasetab = sling.PhraseTable(commons, wikidir + "/en/phrase-table.repo")
commons.freeze()
class Name:
def __init__(self, doc):
self.doc = doc
self.store = doc.frame.store()
self.covered = [False] * len(doc.tokens)
self.evokes = {}
self.matched = set()
self.skip = []
for t in self.doc.tokens:
self.skip.append(t.word in stop_words)
def index(self, i, j):
return i * self.size + j - 1 # second index is 1-based
def assign(self, i, j, span):
self.elements[self.index(i, j)] = span
def get(self, i, j):
return self.elements[self.index(i, j)]
commons = sling.Store()
commons.lockgc()
commons.load("data/e/wiki/kb.sling")
phrasetab = sling.PhraseTable(commons, "data/e/wiki/en/phrase-table.repo")
docschema = sling.DocumentSchema(commons)
factex = sling.FactExtractor(commons)
taxonomy = factex.taxonomy()
titles = [
commons['Q4164871'], # position
commons['Q12737077'], # occupation
commons['Q216353'], # title
]
commons.freeze()
documentids = [
#'Q5945076', 'Q23883660', 'Q43287478', 'Q2147524',
#'Q25048736', 'Q6525874', 'Q3851366', 'Q308735', 'Q2184354',
'Q5337174',
'Q6218080',
'Q1606412',
'Q7264446',