def load_samples(self):
base_dir = common_path.get_task_data_dir('absa', is_original=True)
filepath = os.path.join(base_dir, 'MAMS-for-ABSA', 'MAMS-ACSA-mil',
'AMS-ACSA-mil.json')
samples = super()._load_samples_by_filepath(filepath)
return samples
def load_samples(self):
base_dir = common_path.get_task_data_dir('absa', is_original=True)
filepath = os.path.join(base_dir, 'SemEval-2014-Task-4-REST',
'SemEval-2014-Task-4-REST-mil',
'SemEval-2014-Task-4-REST-mil.json')
samples = super()._load_samples_by_filepath(filepath)
return samples
def load_samples(self):
base_dir = common_path.get_task_data_dir('absa', is_original=True)
filepath = os.path.join(base_dir, 'SemEval-2014-Task-4-REST',
'SemEval-2014-Task-4-REST-mil',
'SemEval-2014-Task-4-REST-mil.json')
samples = super()._load_samples_by_filepath(filepath)
filepath_hard = os.path.join(base_dir, 'SemEval-2014-Task-4-REST',
'SemEval-2014-Task-4-REST-mil',
'SemEval-2014-Task-4-REST-hard-mil.txt')
hard_sentences = set(file_utils.read_all_lines(filepath_hard))
result = [
sample for sample in samples
if sample.text.lower() in hard_sentences
]
return result
import pickle
import sys
from collections import defaultdict
from typing import List
import copy
import collections
from bs4 import BeautifulSoup
from bs4.element import Tag
from sklearn.model_selection import train_test_split
from nlp_tasks.common import common_path
from nlp_tasks.utils import file_utils
logger = logging.getLogger(__name__)
base_data_dir = common_path.get_task_data_dir('absa', is_original=True)
class AspectTerm:
"""
aspect term
"""
def __init__(self, term, polarity, from_index, to_index, category=None):
self.term = term
self.polarity = polarity
# inclusive
self.from_index = int(from_index)
# exclusive
self.to_index = int(to_index)
self.category = category
import os
import logging
import sys
import pickle
import numpy as np
from nlp_tasks.common import common_path
from nlp_tasks.utils import file_utils
from nlp_tasks.absa.data_adapter import data_object
from nlp_tasks.utils import word_processor
from nlp_tasks.utils import tokenizers
from nlp_tasks.utils import tokenizer_wrappers
task_dir = common_path.get_task_data_dir('absa')
class ModelTrainTemplate:
"""
1.
2.
3.
4.
5.
"""
def __init__(self, configuration: dict):
self.configuration = configuration
# 、、；，
#
if 'data_type' not in self.configuration:
import os
import logging
import sys
import pickle
import numpy as np
from nlp_tasks.common import common_path
from nlp_tasks.utils import file_utils
from nlp_tasks.text_segmentation.data_adapter import data_object
from nlp_tasks.utils import word_processor
from nlp_tasks.utils import tokenizers
from nlp_tasks.utils import tokenizer_wrappers
task_dir = common_path.get_task_data_dir('text_segmentation')
class ModelTrainTemplate:
"""
1.
2.
3.
4.
5.
"""
def __init__(self, configuration: dict):
self.configuration = configuration
self.base_data_dir = task_dir + ('{task_name}/{current_dataset}/{model_name_complete}/{timestamp}/'\
.format_map(self.configuration))