def from_file(cls, filepath, synonyms_filepaths, stemmer, debug=False):
"""
filepath: string or list
single filepath or list of filepaths.
"""
assert (isinstance(filepath, unicode) or isinstance(filepath, list))
assert (isinstance(stemmer, Stemmer))
if isinstance(synonyms_filepaths, unicode):
synonyms = SynonymsCollection.from_file(synonyms_filepaths,
stemmer=stemmer,
debug=debug)
elif isinstance(synonyms_filepaths, list):
synonyms = SynonymsCollection.from_files(synonyms_filepaths,
stemmer=stemmer,
debug=debug)
else:
raise Exception("Unsupported type for 'synonyms_filepaths'")
opinions = []
filepaths = []
if (isinstance(filepath, unicode)):
filepaths.append(filepath)
elif (isinstance(filepath, unicode)):
filepaths = filepath
for fp in filepaths:
with io.open(fp, "r", encoding='utf-8') as f:
for i, line in enumerate(f.readlines()):
if line == '\n':
continue
args = line.strip().split(',')
if len(args) < 3:
print "should be at least 3 arguments: {}, '{}'".format(
i, line.encode('utf-8'))
continue
entity_left = args[0].strip()
entity_right = args[1].strip()
sentiment = Label.from_str(args[2].strip())
o = Opinion(entity_left, entity_right, sentiment, stemmer)
opinions.append(o)
return cls(opinions, synonyms, stemmer, debug)
def from_file(cls, filepath, synonyms):
assert (isinstance(synonyms, SynonymsCollection))
opinions = []
with io.open(filepath, "r", encoding='utf-8') as f:
for i, line in enumerate(f.readlines()):
if line == '\n':
continue
args = line.strip().split(',')
assert (len(args) >= 3)
entity_left = args[0].strip()
entity_right = args[1].strip()
sentiment = Label.from_str(args[2].strip())
o = Opinion(entity_left, entity_right, sentiment)
opinions.append(o)
return cls(opinions, synonyms)
def from_file(cls, filepath):
""" Read the vectors from *.vectors.txt file
"""
vectors = {}
with io.open(filepath, 'r', encoding='utf-8') as f:
for line in f.readlines():
args = line.split(',')
opinion_value_left = args[0].strip()
opinion_value_right = args[1].strip()
label = Label.from_str(args[len(args) - 1].strip())
vector = np.array(
[float(args[i]) for i in range(2,
len(args) - 1)])
key = cls.___create_key(opinion_value_left,
opinion_value_right)
vectors[key] = OpinionVector(opinion_value_left,
opinion_value_right, vector,
label)
return cls(vectors)
def __frame_polarity_from_args(args):
return FramePolarity(src=args[0],
dest=args[1],
label=Label.from_str(args[2]),
prob=args[3])