def case_content_wordcloud():
content = ''
for case in Case.objects.all():
content += case.first_history.content
content += case.first_history.title
jieba.set_dictionary(str(settings.ROOT_DIR('static/dict.txt')))
pattern = re.compile(
'[\s+\.\!\/_,$%^*(+\"\']+|[+——！，。？“”、~@#￥%……&*（）(\d+)]+')
content = pattern.sub("", content)
words = [word for word in jieba.cut_for_search(content) if len(word) > 2]
counter = Counter(words)
data = [{
'name': word,
'weight': weight
} for word, weight in counter.most_common(20)]
chart = get_highchart_word_cloud(data=data)
return chart
def case_content_wordcloud():
content = ''
for case in Case.objects.all():
content += case.first_history.content
content += case.first_history.title
jieba.set_dictionary(str(settings.ROOT_DIR('static/jieba/dict.txt')))
stop = []
with open(str(settings.ROOT_DIR('static/jieba/stop.txt')),
'r',
encoding='UTF-8') as file:
for data in file.readlines():
data = data.strip()
stop.append(data)
pattern = re.compile(
'[\s+\.\!\/_,$%^*(+\"\']+|[+——！，。？“”、~@#￥%……&*（）(\d+)]+')
content = pattern.sub("", content)
words_2 = [
word for word in jieba.cut_for_search(content)
if len(word) == 2 and word not in stop
]
counter_2 = Counter(words_2)
words_3 = [
word for word in jieba.cut_for_search(content)
if len(word) > 2 and word not in stop
]
counter_3 = Counter(words_3)
data = [{'name': word, 'weight': weight} for word, weight in counter_2.most_common(50)] + \
[{'name': word, 'weight': weight} for word, weight in counter_3.most_common(50)]
chart = get_highchart_word_cloud(data=data)
return chart