def find_keyword(word_list,lentext=3):
'''
:param list word_list: a list of thai text
:param int lentext: a number of keyword
:return: dict
'''
filtered_words = [word for word in word_list if word not in set(stopwords.words('thai'))]
word_list=rank(filtered_words)
return {k:v for k, v in word_list.items() if v>=lentext}
def find_keyword(word_list, lentext=3):
'''
:param list word_list: a list of thai text
:param int lentext: a number of keyword
:return: dict
'''
filtered_words = [
word for word in word_list if word not in set(stopwords.words('thai'))
]
word_list = rank(filtered_words)
return {k: v for k, v in word_list.items() if v >= lentext}
def find_keyword(word_list,lentext=3):
'''
ระบบค้นหาคำสำคัญ
หลักการ ลบ stopword ออกแล้ว นับจำนวนคำที่ส่งค่าออกมา
find_keyword(word_list,lentext=3)
word_list คือ คำที่อยู่ใน list
lentext คือ จำนวนคำที่มีอยู่ใน list สำหรับใช้กำหนดค่าหา keyword ค่าเริ่มต้นคือ 3
'''
filtered_words = [word for word in word_list if word not in set(stopwords.words('thai'))]
word_list=rank(filtered_words)
return {k:v for k, v in word_list.items() if v>=lentext}
def wordcloud():
if DEVELOPMENT_MODE:
with open('wordcloud.json') as f:
return jsonify(json.load(f))
else:
graph = facebook.GraphAPI(access_token=FACEBOOK_USER_ACCESS_TOKEN,
version='2.7')
query_string = f'fields=feed.since({SINCE})' \
'{comments{comments{message,created_time,like_count},' \
'message,created_time,like_count,reactions},' \
'message,created_time,updated_time,reactions}'
endpoint_url = f'{FACEBOOK_GROUP_ID}?{query_string}'
feed = graph.request(endpoint_url).get('feed')
text = ''
for each in feed.get('data'):
message = each.get('message')
if message:
text += message
comments = each.get('comments')
if comments:
for comment in comments.get('data'):
text += comment.get('message')
comments_in_comment = comment.get('comments')
if comments_in_comment:
for comment_in_comment in comments_in_comment.get(
'data'):
text += comment_in_comment.get('message')
from pythainlp.rank import rank
from pythainlp.tokenize import word_tokenize
word_list = word_tokenize(text, engine='newmm')
word_count = rank(word_list)
from toolz.dicttoolz import dissoc
new_word_count = dissoc(word_count, ' ')
words = []
for each in new_word_count:
d = {'word': each, 'value': new_word_count[each]}
words.append(d)
return jsonify(words)
def testRank(self):
self.assertEqual(rank(["แมว","คน","แมว"]),Counter({'แมว': 2, 'คน': 1}))
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(b)
print(aa)
from pythainlp.romanization import romanization
b=romanization("แมว")
print(b)
from pythainlp.change import *
a="l;ylfu8iy["
a=texttothai(a)
b="นามรสนอำันี"
b=texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ปีคริสต์ศักราช'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))
from pythainlp.postaggers import tag
from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(a)
print(aa)
from pythainlp.romanization import romanization
b=romanization("ต้นกก")
print(b)
from pythainlp.change import *
a="l;ylfu8iy["
a=texttothai(a)
b="นามรสนอำันี"
b=texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ฉันรักคุณ'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from pythainlp.segment import segment
a = 'ฉันรักภาษาไทยเพราะฉันเป็นคนไทย'
b = segment(a)
print(b)
from pythainlp.segment.dict import segment
print(segment(a))
print(type(b))
from pythainlp.rank import rank
aa = rank(b)
print(aa)
from pythainlp.romanization import romanization
b = romanization("แมว")
print(b)
from pythainlp.change import *
a = "l;ylfu8iy["
a = texttothai(a)
b = "นามรสนอำันี"
b = texttoeng(b)
print(a)
print(b)
from pythainlp.segment.dict import segment
print(segment('ปีคริสต์ศักราช'))
from pythainlp.number import numtowords
print("5611116.50")
print(numtowords(5611116.50))
from pythainlp.postaggers import tag
word_all_mix.append(word)
#print(pos_tag(word_all_thai,engine='old'))
def preprocessingByList(beforeList,afterList):
for word in beforeList:
if (word not in stopwords and (word not in word_preposition) and (word not in double_char) and (len(word) > 1)):
afterList.append(word)
preprocessingByList(word_all_thai_unfiltered,word_all_thai_filtered)
for word in word_all_thai_unfiltered:
if(word in negative_adjective or word in positive_adjective):
adjective_word.append(word)
tag_counter = []
print(rank(word_all_thai_unfiltered))
print(rank(word_all_thai_filtered))
item = rank(word_all_thai_filtered)
with open('document/general_data/data.json','w',encoding="utf-8") as fp:
json.dump(item,fp,indent=4,ensure_ascii=False,sort_keys=True)
json.dump(rank(word_all_thai_filtered),fp,indent=4,ensure_ascii=False,sort_keys=True)
######################################################
########use adjective list for polarity train#########
######################################################
# pos tagger part
# for (word,tag) in pos_tag(word_all_thai_filtered,engine="old"):
# tag_counter.append(tag)
# if(tag is not None and tag[0] == 'V'):
def test_rank(self):
self.assertEqual(rank(["แมว","คน","แมว"]),Counter({'แมว': 2, 'คน': 1}))
