def featurize_windows(data, start, end, window_size=1):
"""Uses the input sequences in @data to construct new windowed data points."""
ret = []
for sentence, labels in data:
from util import window_iterator
sentence_ = []
for window in window_iterator(sentence, window_size, beg=start, end=end):
sentence_.append(sum(window, []))
ret.append((sentence_, labels))
return ret
def featurize_windows(data, start, end, window_size = 1):
"""Uses the input sequences in @data to construct new windowed data points.
"""
ret = []
for sentence, labels in data:
from util import window_iterator
sentence_ = []
for window in window_iterator(sentence, window_size, beg=start, end=end):
sentence_.append(sum(window, []))
ret.append((sentence_, labels))
return ret
def featurize_windows(data, start, end):
"""窗口取词，每个句子前后加<s>，</s>的编号，保证窗口长度统一
"""
ret = []
for sentence, labels in data: # 此时都是数字编号
sentence_ = []
for window in window_iterator(sentence,
window_size,
beg=start,
end=end):
sentence_.append(sum(window, []))
ret.append((sentence_, labels))
return ret
