def ieer_headlines():
from nltk.corpus import ieer
from nltk import Tree
print "IEER: First 20 Headlines"
print "=" * 45
trees = [
doc.headline for file in ieer.files() for doc in ieer.parsed_docs(file)
]
for tree in trees[:20]:
print
print "%s:\n%s" % (doc.docno, tree)
def in_demo(trace=0):
from nltk.corpus import ieer
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
print
print "in(ORG, LOC) -- just the clauses:"
print "=" * 45
for file in ieer.files():
for doc in ieer.parsed_docs(file):
if trace:
print doc.docno
print "=" * 15
for rel in relextract('ORG', 'LOC', doc, pattern=IN):
print show_clause(rel, relsym='IN')
def roles_demo(trace=0):
from nltk.corpus import ieer
roles = """
(.*( # assorted roles
analyst|
chair(wo)?man|
commissioner|
counsel|
director|
economist|
editor|
executive|
foreman|
governor|
head|
lawyer|
leader|
librarian).*)|
manager|
partner|
president|
producer|
professor|
researcher|
spokes(wo)?man|
writer|
,\sof\sthe?\s* # "X, of (the) Y"
"""
ROLES = re.compile(roles, re.VERBOSE)
print
print "has_role(PER, ORG) -- raw rtuples:"
print "=" * 45
for file in ieer.files():
for doc in ieer.parsed_docs(file):
lcon = rcon = False
if trace:
print doc.docno
print "=" * 15
lcon = rcon = True
for rel in relextract('PER', 'ORG', doc, pattern=ROLES):
print show_raw_rtuple(rel, lcon=lcon, rcon=rcon)
def in_demo(trace=0, sql=True):
from nltk.corpus import ieer
if sql:
import sqlite3
connection = sqlite3.connect(":memory:")
connection.text_factory = sqlite3.OptimizedUnicode
cur = connection.cursor()
cur.execute("""create table Locations
(OrgName text, LocationName text, DocID text)""")
IN = re.compile(r'.*\bin\b(?!\b.+ing\b)')
print
print "IEER: in(ORG, LOC) -- just the clauses:"
print "=" * 45
for file in ieer.files():
for doc in ieer.parsed_docs(file):
if trace:
print doc.docno
print "=" * 15
for rel in extract_rels('ORG', 'LOC', doc, pattern=IN):
print show_clause(rel, relsym='IN')
if sql:
rtuple = (rel['subjtext'], rel['objtext'], doc.docno)
cur.execute(
"""insert into Locations
values (?, ?, ?)""", rtuple)
connection.commit()
if sql:
cur.execute("""select OrgName from Locations
where LocationName = 'Atlanta'""")
print
print "Extract data from SQL table: ORGs in Atlanta"
print "-" * 15
for row in cur:
print row
