def merge_syntactic_units(original_units, filtered_units, tags=None):
"""Process given sentences and its filtered (tokenized) copies into
:class:`~gensim.summarization.syntactic_unit.SyntacticUnit`. Also adds tags if they are provided to produced units.
Parameters
----------
original_units : list
List of original sentences.
filtered_units : list
List of tokenized sentences.
tags : list of str, optional
List of strings used as tags for each unit. None as deafault.
Returns
-------
list of :class:~gensim.summarization.syntactic_unit.SyntacticUnit
List of syntactic units (sentences).
"""
units = []
for i in range(len(original_units)):
if filtered_units[i] == '':
continue
text = original_units[i]
token = filtered_units[i]
tag = tags[i][1] if tags else None
sentence = SyntacticUnit(text, token, tag)
sentence.index = i
units.append(sentence)
return units
def merge_syntactic_units(original_units, filtered_units, tags=None):
units = []
for i in xrange(len(original_units)):
if filtered_units[i] == '':
continue
text = original_units[i]
token = filtered_units[i]
if tags:
try:
tag = tags[i][1]
except:
tag = None
else:
tag = None
#tag = tags[i][1] if tags else None
sentence = SyntacticUnit(text, token, tag)
sentence.index = i
units.append(sentence)
return units
def merge_syntactic_units(original_units, filtered_units, tags=None):
"""Process given sentences and its filtered (tokenized) copies into
:class:`~gensim.summarization.syntactic_unit.SyntacticUnit`. Also adds tags if they are provided to produced units.
Parameters
----------
original_units : list
List of original sentences.
filtered_units : list
List of tokenized sentences.
tags : list of str, optional
List of strings used as tags for each unit. None as deafault.
Returns
-------
list of :class:~gensim.summarization.syntactic_unit.SyntacticUnit
List of syntactic units (sentences).
"""
units = []
for i in xrange(len(original_units)):
if filtered_units[i] == '':
continue
text = original_units[i]
token = filtered_units[i]
tag = tags[i][1] if tags else None
sentence = SyntacticUnit(text, token, tag)
sentence.index = i
units.append(sentence)
return units
def merge_syntactic_units(original_units, filtered_units, tags=None):
units = []
for i in xrange(len(original_units)):
if filtered_units[i] == '':
continue
text = original_units[i]
token = filtered_units[i]
tag = tags[i][1] if tags else None
sentence = SyntacticUnit(text, token, tag)
sentence.index = i
units.append(sentence)
return units