def get_wordcloud_with_project(project_id=None):
"""
获取词云
:return:
"""
# 字体文件路径
font = CONF.TTF_PATH + 'msyh.ttc'
# 源数据处理(模块名称)
str_list = get_model_data_with_project(project_id)
# 分词
text = ""
for item in str_list:
text += item + " "
# 生成词云
pil_img = WordCloud(
font_path=font,
width=800,
height=300,
background_color="white",
prefer_horizontal=0.6,
collocations=False).generate(text=text).to_image()
# base64输出
img = io.BytesIO()
pil_img.save(img, "PNG")
img.seek(0)
img_base64 = base64.b64encode(img.getvalue()).decode()
return img_base64
def get_wordcloud(text):
pil_img = WordCloud(stopwords=stopwords).generate(text=text).to_image()
img = io.BytesIO()
pil_img.save(img, "PNG")
img.seek(0)
img_b64 = base64.b64encode(img.getvalue()).decode()
return img_b64
def get_wordcloud(text):
#text = text.decode("utf-8")
if langue == 'zh-CN':
pil_img = WordCloud(
font_path=font_path,
background_color="white",
max_words=2000,
max_font_size=100,
random_state=42,
width=1000,
height=860,
margin=2,
).generate(jieba_processing_txt(text))
else:
pil_img = WordCloud(width=1600,
height=800,
scale=20,
background_color='white',
mode="RGBA",
max_font_size=600).generate(
text=text) #mask = mask,
img = BytesIO(
) #mask = np.array(Image.open(mask).convert('RGB')) #image_colors = ImageColorGenerator(mask)
plt.figure(figsize=[7, 7])
pil_img = pil_img.to_image()
plt.axis("off") #no axis?
plt.tight_layout(pad=0)
img = BytesIO() #save it to a temporary buffer
pil_img.save(img, "PNG") #save this byte to a PNG
img.seek(0)
img_64 = base64.b64encode(img.getvalue()).decode('utf-8')
return img_64
def results():
# "if-the-internet-is-slow-so-local-items" tester
word_freq = [('hawk', 10), ('apple', 3), ('spoon', 2), ('red', 1),
('mine', 1)]
list_of_tokens = [
'hawk', 'hawk', 'hawk', 'hawk', 'hawk', 'hawk', 'hawk', 'hawk', 'hawk',
'hawk', 'apple', 'apple', 'apple', 'spoon', 'spoon', 'red', 'mine'
]
# url = request.form['url']
# word_freq, list_of_tokens = quick_prime(url)
text = " ".join(list_of_tokens)
cloud_PIL = WordCloud(background_color='white').generate(text).to_image()
# converts cloudPIL from PIL to bytes
output = BytesIO()
cloud_PIL.save(output, format='JPEG')
# converts bytes to base64 encoding minus the "b'"" prexif and "'" suffix
img = base64.b64encode(output.getvalue())
img = str(img)[2:-1]
return render_template('results.html', items=word_freq, img=img)
async def _generate_word_cloud_async(self, msg_id: str, reply_msg, to_chat,
search_chat, user, start: datetime,
end: datetime):
try:
import jieba
from wordcloud import WordCloud
except ImportError as e:
print(e)
return
words = defaultdict(int)
count = 0
initial_msg = reply_msg.text + '\n'
async for msg in self._client.iter_messages(search_chat,
from_user=user,
offset_date=end):
if start and msg.date < start:
break
if msg.text:
for word in jieba.cut(msg.text):
word = word.lower()
if not await self.redis.sismember(
f'{self.prefix}stop_words', word):
words[word] += 1
# words += [w for w in jieba.cut(msg.text) if not await self.redis.sismember(f'{self.prefix}stop_words', w)]
# if msg.sticker:
# words += [a.alt for a in msg.sticker.attributes if isinstance(a, DocumentAttributeSticker)]
count += 1
if count >= 1000:
p = math.floor(math.log(count, 10))
if count % int(math.pow(10, p)) == 0 and count // 1000:
try:
await reply_msg.edit(text=initial_msg + '.' *
(count // 1000))
except Exception as _:
traceback.print_exc()
wordcloud_msg = None
try:
image = WordCloud(
font_path="simsun.ttf", width=800,
height=400).generate_from_frequencies(words).to_image()
stream = BytesIO()
image.save(stream, 'PNG')
wordcloud_msg = await self._client.send_message(
to_chat,
'词云 for\n{}{}{}'.format(
f'{search_chat.title}',
f'\n{utils.get_display_name(user)}' if user else '',
'\n{}-{}'.format(
start.strftime('%Y/%m/%d') if start else 'Join',
end.strftime('%Y/%m/%d') if end else 'Now')
if start or end else ''),
reply_to=msg_id,
file=stream.getvalue())
except Exception as _:
traceback.print_exc()
finally:
await reply_msg.delete()
def wordcloud(text):
stopwords = set(STOPWORDS)
wordcloud = WordCloud(width=800,
height=800,
background_color='white',
stopwords=stopwords,
min_font_size=10).generate(text).to_image()
img = BytesIO()
wordcloud.save(img, "PNG")
img.seek(0)
img_b64 = base64.b64encode(img.getvalue()).decode()
return img_b64
def get_word_cloud(text):
# font = "./SimHei.ttf"
# pil_img = WordCloud(width=500, height=500, font_path=font).generate(text=text).to_image()
pil_img = WordCloud(
width=800, height=300,
background_color="white").generate(text=text).to_image()
img = io.BytesIO()
pil_img.save(img, "PNG")
img.seek(0)
img_base64 = base64.b64encode(img.getvalue()).decode()
return img_base64
def get_wordcloud(text):
"""
Convert text to a word cloud
"""
pillow_image = WordCloud().generate(text=text).to_image()
img = io.BytesIO()
pillow_image.save(img, "PNG")
img.seek(0)
# .decode -> returns base64 string instead of base64 byte string
# .b64encode -> returns base64 byte string
img_b64 = base64.b64encode(img.getvalue()).decode()
return img_b64
def wordcloud():
sentence = wordsentence()
stopwords = set(STOPWORDS)
wordcloud = WordCloud(width=800,
height=800,
background_color='white',
stopwords=stopwords,
min_font_size=10).generate(sentence)
wordcloud = wordcloud.to_image()
img = BytesIO()
wordcloud.save(img, format='PNG')
return 'data:image/png;base64,{}'.format(
base64.b64encode(img.getvalue()).decode())
async def _generate_word_cloud_async(self, chat, user, start, end):
try:
import jieba
from wordcloud import WordCloud
except ImportError as e:
print(e)
return
chat = await self._get_entity(chat)
if user is not None:
user = await self._get_entity(user)
if start is not None:
start = parser.parse(start).replace(tzinfo=timezone.utc)
if end is not None:
end = parser.parse(end)
words = []
async for msg in self._client.iter_messages(chat,
from_user=user,
offset_date=end):
if start and msg.date < start:
break
if msg.text:
print("[{}][{}] {}".format(
msg.date,
utils.get_display_name(await msg.get_sender()) if
user is None else utils.get_display_name(user), msg.text))
words += [
w for w in jieba.cut_for_search(msg.text)
if w not in stop_words
]
image = WordCloud(font_path="simsun.ttf", width=800,
height=400).generate(' '.join(words)).to_image()
stream = BytesIO()
image.save(stream, 'PNG')
await self._client.send_message(
'gua_mei_debug',
'{}{}{}'.format(
f'{chat.title}',
f'\n{utils.get_display_name(user)}' if user else '',
'\n{}-{}'.format(
start.strftime('%Y/%m/%d') if start else 'Join',
end.strftime('%Y/%m/%d') if end else 'Now')
if start or end else ''),
file=stream.getvalue())
def main(argv): #Given by Dr. Brown on Piazza
argc = len(argv)
if 2 > argc:
print("More arguments, please.")
return 1
frequency = WordFrequency()
for i in range(1, argc):
frequency.open(argv[i])
count = 23
stop_words = ['A', 'An', 'And', 'But', 'That', 'The', 'Which',
'a', 'an', 'and', 'but', 'that', 'the', 'which']
for count in [5, 20, 33, 50]:
cloud = WordCloud(count, frequency, stop_words)
cloud.save('cloud-{0}.txt'.format(count))
cloud = HtmlWordCloud(count, frequency, stop_words)
cloud.save('cloud-{0}.html'.format(count))
return 0
def index():
r = requests.get(
"http://loklak.org/api/search.json?q={0}&count=100".format(
request.args.get('q')))
data = r.json()
text = " "
for value in data["statuses"]:
value = re.sub(r"@", " ", value["text"])
value = re.sub(r"\#", " ", value)
value = re.sub(
r"https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{2,256}\.[a-z]{2,6}\b([-a-zA-Z0-9@:%_\+.~#?&//=]*)",
" ", value)
text += value
cloud = WordCloud(width=800, height=400,
stopwords=STOPWORDS).generate(text).to_image()
#tempFile = NamedTemporaryFile(mode='w+b',suffix='jpg')
#copyfileobj(cloud,tempFileObj)
buffer = cStringIO.StringIO()
cloud.save(buffer, format="PNG")
#cloud.close()
#tempFile.seek(0,0)
return base64.b64encode(buffer.getvalue())
async def group_word(context):
imported_1 = False
if len(context.parameter) >= 1:
imported_1 = True
if not imported:
try:
await context.edit("支持库 `jieba` 未安装...\n正在尝试自动安装...")
await execute(f'{executable} -m pip install jieba')
await sleep(10)
result = await execute(f'{executable} -m pip show jieba')
if len(result) > 0:
await context.edit('支持库 `jieba` 安装成功...\n正在尝试自动重启...')
await context.client.disconnect()
else:
await context.edit(f"自动安装失败..请尝试手动安装 `{executable} -m pip install jieba` 随后，请重启 PagerMaid-Modify 。")
return
except:
return
if not imported_ and imported_1:
try:
await context.edit("支持库 `paddlepaddle-tiny` 未安装...\n正在尝试自动安装...")
await execute(f'{executable} -m pip install paddlepaddle-tiny')
await sleep(10)
result = await execute(f'{executable} -m pip show paddlepaddle-tiny')
if len(result) > 0 and not 'WARNING' in result:
await context.edit('支持库 `paddlepaddle-tiny` 安装成功...\n正在尝试自动重启...')
await context.client.disconnect()
else:
await context.edit(f"自动安装失败，可能是系统不支持..\nAI 分词不可用，切换到基础分词。\n"
f"您可以尝试手动安装 `{executable} -m pip install paddlepaddle-tiny` 。")
await sleep(4)
except:
return
try:
await context.edit('正在生成中。。。')
except:
return
if not exists("plugins/groupword"):
makedirs("plugins/groupword")
if not exists("plugins/groupword/wqy-microhei.ttc"):
await context.edit('正在拉取中文字体文件。。。（等待时间请评估你的服务器）')
r = get('https://cdn.jsdelivr.net/gh/anthonyfok/fonts-wqy-microhei/wqy-microhei.ttc')
with open("plugins/groupword/wqy-microhei.ttc", "wb") as code:
code.write(r.content)
words = defaultdict(int)
count = 0
try:
if imported_ and imported_1:
try:
jieba.enable_paddle()
except:
imported_1 = False
async for msg in context.client.iter_messages(context.chat, limit=500):
if msg.id == context.id:
continue
if msg.text and not msg.text.startswith('/') and not msg.text.startswith('-') and not '//' in msg.text:
try:
if imported_ and imported_1:
for word in jieba.cut(msg.text.translate(punctuation), use_paddle=True):
word = word.lower()
words[word] += 1
else:
for word in jieba.cut(msg.text.translate(punctuation)):
word = word.lower()
words[word] += 1
count += 1
except:
pass
except:
if count == 0:
try:
await context.edit('您已被 TG 官方限制。')
return
except:
return
try:
image = WordCloud(font_path="plugins/groupword/wqy-microhei.ttc", width=800,
height=400).generate_from_frequencies(
words).to_image()
stream = BytesIO()
image.save(stream, 'PNG')
except:
await context.edit('词云生成失败。')
return
try:
await context.client.send_message(context.chat, f'对最近的 {count} 条消息进行了分析。', file=stream.getvalue())
await context.delete()
except:
return
