本文整理匯總了Python中philologic.OHCOVector.Record.attrib['bytes']方法的典型用法代碼示例。如果您正苦於以下問題：Python Record.attrib['bytes']方法的具體用法？Python Record.attrib['bytes']怎麽用？Python Record.attrib['bytes']使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類philologic.OHCOVector.Record的用法示例。
在下文中一共展示了Record.attrib['bytes']方法的2個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: inner_word_frequencies_per_obj
# 需要導入模塊: from philologic.OHCOVector import Record [as 別名]
# 或者: from philologic.OHCOVector.Record import attrib['bytes'] [as 別名]
def inner_word_frequencies_per_obj(loader_obj,text):
files_path = loader_obj.destination + '/WORK/'
try:
os.mkdir(files_path)
except OSError:
## Path was already created
pass
for obj, d in obj_types.iteritems():
file = text['name'] + '.%s.freq_counts' % obj
output = open(files_path + file, 'w')
old_philo_id = []
old_word = ''
records = {}
for line in open(text['words']):
type, word, id, attrib = line.split('\t')
attrib = eval(attrib)
## Dismiss all irrelevant fields while making sure we still have 9 fields in the end
philo_id = id.split()[:d] + [0 for i in range(7-d)] + [0,0]
record = Record(type, word, philo_id)
count_key = obj + '_token_count'
byte = attrib['byte_start']
del attrib['byte_start']
record.attrib = {'token_count': attrib[count_key]}
if philo_id[:d] != old_philo_id[:d] or word != old_word:
if records and old_word:
for w in records:
print >> output, records[w]
records = {}
if word not in records:
record.attrib['bytes'] = []
record.attrib['bytes']= str(byte)
records[word] = record
else:
records[word].attrib['bytes'] += ' ' + str(byte)
old_philo_id = philo_id
old_word = word
for w in records:
print >> output, records[w]
output.close()示例2: word_frequencies_per_obj
# 需要導入模塊: from philologic.OHCOVector import Record [as 別名]
# 或者: from philologic.OHCOVector.Record import attrib['bytes'] [as 別名]
def word_frequencies_per_obj(loader_obj, text, depth=1):
object_types = ['doc', 'div1', 'div2', 'div3', 'para', 'sent', 'word'][:depth]
files_path = loader_obj.destination + '/WORK/'
try:
os.mkdir(files_path)
except OSError:
## Path was already created
pass
for d, obj in enumerate(object_types):
file = text['name'] + '.%s.sorted' % obj
output = open(files_path + file, 'w')
d = d + 1
old_philo_id = []
records = {}
for line in open(text['words']):
type, word, id, attrib = line.split('\t')
attrib = eval(attrib)
philo_id = id.split()
record = Record(type, word, philo_id)
count_key = obj + '_token_count'
byte = attrib['byte_start']
del attrib['byte_start']
record.attrib = {count_key: attrib[count_key]}
if philo_id[:d] != old_philo_id[:d]:
if records:
for w in records:
print >> output, records[w]
records = {}
if word not in records:
record.attrib['bytes'] = []
record.attrib['bytes']= str(byte)
records[word] = record
else:
records[word].attrib['bytes'] += ' ' + str(byte)
old_philo_id = philo_id
for w in records:
print >> output, records[w]
output.close()