def feature_about():
# 获取特征列表
feature_dict = NewsUtil.get_feature()
# 获取新闻中出现特征后最近的5个词及其属性
logger.info("In Prepare Raw News...")
raw_news_data = CommonUtil.read_excel(RAW_NEWS_DEMO_PATH)
raw_news_table = raw_news_data.sheet_by_index(0)
raw_news_rows = raw_news_table.nrows
segmentor = Segmentor() # 初始化实例
segmentor.load_with_lexicon(cws_model_path,
CFETSFX_LEXICON_PATH) # 加载模型，第二个参数是您的外部词典文件路径
feature_about_list = list()
for rowN in range(0, raw_news_rows):
news_content = raw_news_table.cell_value(rowN, 2)
sentences = SentenceSplitter.split(news_content)
for sentence in sentences:
print(sentence)
# 分词
words = segmentor.segment(sentence)
print(list(words))
for word_index in range(0, len(words)):
word = words[word_index]
for feature_word in feature_dict.values():
if feature_word in word:
about_list = list()
count = 0
while word_index < len(words) and count < 6:
about_list.append(words[word_index])
count += 1
word_index += 1
feature_about_list.append(about_list)
print(about_list)
break
segmentor.release()
CommonUtil.write_csv(FEATURE_ABOUT_PATH, feature_about_list)
def prepare_feature():
logger.info("In Prepare Feature...")
# 获取sheet
feature_data = CommonUtil.read_excel(FEATURE_PATH)
feature_table = feature_data.sheet_by_index(0)
# 获取总行数
feature_rows = feature_table.nrows
# 获取总列数
# feature_cols = feature_table.ncols
for rowNum in range(1, feature_rows):
key = feature_table.cell_value(rowNum, 0)
value = feature_table.cell_value(rowNum, 1)
featureDict[key] = value
logger.info("Prepare Feature...Done!")
def get_feature():
# 特征字典[AAAA:黄金]
feature_dict = dict()
# 获取sheet
feature_data = CommonUtil.read_excel(FEATURE_PATH)
feature_table = feature_data.sheet_by_index(0)
# 获取总行数
feature_rows = feature_table.nrows
# 获取总列数
# feature_cols = feature_table.ncols
for rowNum in range(1, feature_rows):
key = feature_table.cell_value(rowNum, 0)
value = feature_table.cell_value(rowNum, 1)
feature_dict[key] = value
return feature_dict
def prepare_raw_news():
logger.info("In Prepare Raw News...")
raw_news_data = CommonUtil.read_excel(RAW_NEWS_PATH)
raw_news_table = raw_news_data.sheet_by_index(0)
raw_news_rows = raw_news_table.nrows
for rowN in range(0, raw_news_rows):
news_item = list()
news_index = int(raw_news_table.cell_value(rowN, 0))
news_time = CommonUtil.get_datetime_from_cell(
raw_news_table.cell_value(rowN, 1))
news_content = raw_news_table.cell_value(rowN, 2)
news_item.append(news_index)
news_item.append(news_time)
news_item.append(news_content)
newsList.append(news_item)
logger.info("Prepare Raw News...Done!")
