def load_data(input_file):
raw_data = open(input_file,'r')
doc_list = []
doc = Document()
for rline in raw_data.readlines():
if rline.strip():
entry = rline.split()
docID = entry[0]
if docID != doc.docID:
#import pdb
#if doc.docID!='':
# pdb.set_trace()
doc_list.append(doc)
doc = Document(docID)
first = Entity(entry[1],(entry[2],entry[3]),entry[4],entry[5])
second = Entity(entry[6],(entry[7],entry[8]),entry[9],entry[10])
pair = Pair(first,second)
if len(entry) == 12:
pair.set_label(entry[11])
doc.add_pair(pair)
else:
first = Entity(entry[1],(entry[2],entry[3]),entry[4],entry[5])
second = Entity(entry[6],(entry[7],entry[8]),entry[9],entry[10])
pair = Pair(first,second)
if len(entry) == 12:
pair.set_label(entry[11])
doc.add_pair(pair)
doc_list.append(doc)
return doc_list
def load_data(input_file):
raw_data = open(input_file,'r')
doc_list = []
doc = Document()
ne_dict = {}
for rline in raw_data.readlines():
if rline.strip():
i = 0
entry = rline.split()
if len(entry) == 14:
i = 1
docID = entry[i]
#new document
if docID != doc.docID:
#import pdb
#if doc.docID!='':
# pdb.set_trace()
#record the name entity dictionary we have created
doc.set_ne_dict(ne_dict)
doc_list.append(doc)
ne_dict = {}
doc = Document(docID)
first = Entity(entry[i+1],(entry[i+2],entry[i+3]),entry[i+4],entry[i+5],entry[i+6])
ne_dict[entry[i+5]] = (entry[i+1],entry[i+2])
second = Entity(entry[i+7],(entry[i+8],entry[i+9]),entry[i+10],entry[i+11],entry[i+12])
ne_dict[entry[i+11]] = (entry[i+7],entry[i+8])
pair = Pair(first,second)
if i:
pair.set_label(entry[0])
doc.add_pair(pair)
else:
first = Entity(entry[i+1],(entry[i+2],entry[i+3]),entry[i+4],entry[i+5],entry[i+6])
ne_dict[entry[i+5]] = (entry[i+1],entry[i+2])
second = Entity(entry[i+7],(entry[i+8],entry[i+9]),entry[i+10],entry[i+11],entry[i+12])
ne_dict[entry[i+11]] = (entry[i+7],entry[i+8])
pair = Pair(first,second)
if i:
pair.set_label(entry[0])
doc.add_pair(pair)
doc.set_ne_dict(ne_dict)
doc_list.append(doc)
return doc_list
