import sys
sys.path.append("../..")
from ArticutAPI import Articut
from pprint import pprint
import json
if __name__ == "__main__":
try:
#使用自己的斷詞額度。
with open("../../account.info", "r") as f:
userDICT = json.loads(f.read())
username = userDICT["email"]
apikey = userDICT["apikey"]
atc = Articut(username=userDICT["email"], apikey=userDICT["apikey"])
except:
#使用公用的斷詞額度。(每小時 2000 字)
atc = Articut()
downSample = '''台指選擇權盤後－年線保衛戰失利 外資續賣台股
台股期權盤後－華為拖累電子 台股摔破支撐
華為風暴持續擴大 三王領跌重挫148點 創波段新低
華為風暴 大跌退守10300點
美商禁令聲聲催，台股電子三王大跌，指數再破年線
跌148.85點
華為風暴擴大 一度破10300點
外資狂撤，台股欲振乏力
利空燒不盡，台股挫百點失年線
華為風暴！台股摜破前低，將往半年線測試
電子股恐慌殺盤出籠，可成慘破200元大關
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
from ArticutAPI import Articut
from pprint import pprint
username = ""
apikey = ""
articut = Articut(username=username, apikey=apikey)
def main(inputSTR):
resultDICT = articut.parse(inputSTR)
return resultDICT
def tfidf(resultDICT):
keywordLIST = articut.analyse.extractTags(resultDICT, topK=3)
return keywordLIST
def crime(resultDICT):
crimeLIST = articut.LawsToolkit.getCrime(resultDICT)
return crimeLIST
def penalty(resultDICT):
penaltyLIST = articut.LawsToolkit.getPenalty(resultDICT)
return penaltyLIST
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
from ArticutAPI import Articut
from pprint import pprint
from requests import post
username = ""
apikey = ""
articut = Articut(username=username, apikey=apikey)
def main(inputSTR):
resultDICT = articut.parse(inputSTR)
return resultDICT
if __name__ == "__main__":
inputSTR = inputSTR = """位於台南的50年老房子，
地址是台南市東區長榮路3段30巷3號。
這裡承載著曾經是學生宿舍的使命。
我們繼續把這樣的溫度傳遞，
讓往來的人都把這裡當做家，
用緩慢的步調體驗台南的在地生活。""".replace(" ", "").replace("\n", "")
resultDICT = main(inputSTR)
#pprint(resultDICT)
#取得完整地址
addTWLIST = articut.getAddTWLIST(resultDICT)
#pprint(addTWLIST)
from ArticutAPI import Articut
except:
from ArticutAPi import Articut
import json
from pprint import pprint
if __name__ == "__main__":
try:
#使用自己的斷詞額度。
with open("../../account.info", "r") as f:
userDICT = json.loads(f.read())
username = userDICT["email"]
apikey = userDICT["apikey"]
atc = Articut(username=userDICT["email"], apikey=userDICT["apikey"])
except:
#使用免費的斷詞額度。
#實體化 Articut()
atc = Articut()
#載入 Demo 用的文字
with open("./PengHu.txt", encoding="utf-8") as f:
contentLIST = [l.replace("\n", "") for l in f.readlines()]
resultLIST = []
for c in contentLIST:
print("Processing:{}/{} >> {}".format(
contentLIST.index(c) + 1, len(contentLIST), c))
resultDICT = atc.parse(c, openDataPlaceAccessBOOL=True)
locationLIST = atc.getLocationStemLIST(resultDICT)
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
from ArticutAPI import Articut
def main(inputSTR, nlptool):
resultDICT = articut.parse(inputSTR, level="lv3")
return resultDICT
if __name__ == "__main__":
inputSTR = "他關上大門，把窗戶也關上了。"
articut = Articut()
resultLIST = main(inputSTR, articut)
eventLIST = resultLIST["event"]
print(eventLIST)
import sys
sys.path.append("../..")
from ArticutAPI import Articut
import json
from pprint import pprint
if __name__ == "__main__":
try:
#使用自己的斷詞額度。
with open("../../account.info", "r") as f:
userDICT = json.loads(f.read())
username = userDICT["email"]
apikey = userDICT["apikey"]
atc = Articut(username=userDICT["email"], apikey=userDICT["apikey"])
except:
#使用免費的斷詞額度。
#實體化 Articut()
atc = Articut()
#Demo 用的文字：載入政府機構名稱前。
inputSTR = "國軍退除役官兵輔導委員會簡稱退輔會。 "
resultDICT = atc.parse(inputSTR)
print("1. 政府機構名稱直接「斷詞」處理：")
pprint(resultDICT["result_pos"])
print("=====================")
inputSTR = "國軍退除役官兵輔導委員會簡稱退輔會。 "
resultDICT = atc.parse(inputSTR, userDefinedDictFILE="../../Public_UserDefinedDict/KNOWLEDGE_govTW.json")
print("2. 政府機構名稱用「自定字典」處理：")
# Installed via git clone
import sys
sys.path.append("../..")
from ArticutAPI import Articut
import json
if __name__ == "__main__":
try:
#使用自己的斷詞額度。
with open("../../account.info", "r") as f:
userDICT = json.loads(f.read())
username = userDICT["email"]
apikey = userDICT["apikey"]
atc = Articut(username=userDICT["email"], apikey=userDICT["apikey"])
except:
#使用免費的斷詞額度。
#實體化 Articut()
atc = Articut()
# 載入 Demo 用的文字
text = open("./InputString.txt", "r").read()
sentLIST = text.split("\n")
print("ArticutAPI Term Extraction Demo")
for sentence in sentLIST:
if "" == sentence.strip():
continue
result = atc.parse(sentence)
def jsonTextReader(jsonFilePath):
with open(jsonFilePath, encoding = "utf-8") as f:
Content = f.read()
return Content
def jsonFileWriter(jsonDICT, jsonFileName):
with open(jsonFileName, mode="w") as f:
json.dump(jsonDICT, f, ensure_ascii=False)
return None
def EventAnalysis(inputSTR, nlptool):
resultDICT = articut.parse(inputSTR, level="lv3")
return resultDICT
if __name__== "__main__":
articut = Articut(username = "******", apikey="yfYwawQRAvuCkPR#W2uug+bpZoN7cEwyfYwawQRAvuCkPR#W2uug+bpZoN7cEw")
fileTUPLE = ("../example/text.txt", "./A. forsteri.txt")
MouseSTR = jsonTextReader(fileTUPLE[0])
#print(MouseSTR)
PenguinSTR = jsonTextReader(fileTUPLE[1])
#print(PenguinSTR)
MouseDICT_lv3 = EventAnalysis(MouseSTR, articut)
MouseLIST = MouseDICT_lv3["event"]
MouseDICT_lv2 = articut.parse(MouseSTR, level = "lv2")
MouseLIST_lv2 = articut.getVerbStemLIST(MouseDICT_lv2)
#for item in MouseLIST_lv2:
# if item != '\n' and item != []:
# print(item)
args str[],
resultDICT dict
Output:
resultDICT dict
"""
from ArticutAPI import Articut
import json
try:
accountDICT = json.loads(open("./account.info", encoding="utf-8").read())
except:
accountDICT = {"username":"", "apikey":""}
articut = Articut(username=accountDICT["username"], apikey=accountDICT["apikey"])
DEBUG_Cashier = True
userDefinedDICT = {"硬幣": ["銅板"]}
class CreditCard:
def __init__(self):
self.balance = 87
self.owner = "Peter"
def callToRaiseCredit(self, amount):
self.balance = self.balance + amount
# 將符合句型的參數列表印出。這是 debug 或是開發用的。
def debugInfo(inputSTR, utterance):
if DEBUG_Cashier:
print("[Cashier] {} ===> {}".format(inputSTR, utterance))
def main(inputSTR):
articut = Articut(username=username, apikey=apikey)
resultDICT = articut.parse(inputSTR)
return resultDICT