def ckipnlp_cutwords(data: pd.DataFrame, ws, *args: str,
**kwargs) -> pd.DataFrame:
wg_dict = {}
for wordPackage in args:
wg_dict.update(txt_to_dict('頻道列表/' + wordPackage + '.txt'))
wg_dict = construct_dictionary(wg_dict)
data2 = data.copy()
cut = []
for text in data['textOriginal']:
comment_cut = ws([text], recommend_dictionary=wg_dict)[0]
cut.append(comment_cut)
print(comment_cut)
# cut.append(ws([text])[0])
data2['ckipnlp_cut'] = cut
year_month_cut(data2)
if kwargs.get('language'):
#若有給language這個keyword參數，就會回傳其value(True or False)，沒有給language這個參數將回傳None，等同於False
data2['traditional'] = [
1 if check.hasTraditional(s) else 0 for s in data2['textOriginal']
]
data2['simplified'] = [
1 if check.hasSimplified(s) else 0 for s in data2['textOriginal']
]
data2['english'] = [
1 if check.hasEnglish(s) else 0 for s in data2['textOriginal']
]
data2.reset_index(inplace=True, drop=True)
return data2
def jieba_cutwords(data: pd.DataFrame, *args: str, **kwargs) -> pd.DataFrame:
for wordPackage in args:
jieba.load_userdict('頻道列表/' + wordPackage + '.txt')
data2 = data.copy()
cut = []
for text in data['textOriginal']:
# print(text)
cut.append(list(jieba.cut(str(text))))
data2['jieba_cut'] = cut
year_month_cut(data2)
if (kwargs.get('language', -1) != -1):
if kwargs['language'] == True:
data2['traditional'] = [
1 if check.hasTraditional(s) else 0
for s in data2['textOriginal']
]
data2['simplified'] = [
1 if check.hasSimplified(s) else 0
for s in data2['textOriginal']
]
data2['english'] = [
1 if check.hasEnglish(s) else 0 for s in data2['textOriginal']
]
data2.reset_index(inplace=True, drop=True)
return data2
# 判斷文字是否包含繁體中文、簡體中文、英文
#-------------------------------------#
# 共有4個Function可使用
# check.hasTradional() : 判斷是否包含繁體中文
# check.hasSimplified()： 判斷是否包含簡體中文
# check.hasBoth()：判斷是否同時包含繁體、簡體中文
# check.hasEnglish()：判斷是否包含英文
import checkword as check
check.hasTraditional('ABC abc 国家 國家') #注意：家同時為繁體、簡體字
check.hasSimplified('ABC abc 国家 國家')
check.hasBoth('ABC abc 國家')
check.hasEnglish('ABC abc 國家')