Colab WordCount

# -*- coding: utf-8 -*-
"""tf_GUP.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1crfzBEkEzf5Y8oGyDepR1PGem5CITnk2
"""

import tensorflow as tf
device_name = tf.test.gpu_device_name()
if device_name != '/device:GPU:0':
  raise SystemError('GPU device not found')
print('Found GPU at: {}'.format(device_name))

!pip install wordcloud matplotlib jieba

# 授权绑定代码
!apt-get install -y -qq software-properties-common python-software-properties module-init-tools
!add-apt-repository -y ppa:alessandro-strada/ppa 2>&1 > /dev/null
!apt-get update -qq 2>&1 > /dev/null
!apt-get -y install -qq google-drive-ocamlfuse fuse
from google.colab import auth
auth.authenticate_user()
from oauth2client.client import GoogleCredentials
creds = GoogleCredentials.get_application_default()
import getpass
!google-drive-ocamlfuse -headless -id={creds.client_id} -secret={creds.client_secret} < /dev/null 2>&1 | grep URL
vcode = getpass.getpass()
!echo {vcode} | google-drive-ocamlfuse -headless -id={creds.client_id} -secret={creds.client_secret}

# 指定Google Drive云端硬盘的根目录，名为drive
!mkdir -p drive
!google-drive-ocamlfuse drive

# 指定当前的工作文件夹
import os

# 此处为google drive中的文件路径,drive为之前指定的工作根目录，要加上
os.chdir("drive/Colab Notebooks")

!ls

# -*- coding: utf-8 -*-

# %matplotlib inline
from wordcloud import WordCloud
import matplotlib.pyplot as plt
import jieba

# 打开文本
text = open('xyj.txt').read()

# 中文分词
text = ' '.join(jieba.cut(text))
print(text[:100])

# 生成对象
wc = WordCloud(font_path='Hiragino.ttf', width=800, height=600, mode='RGBA', background_color=None).generate(text)

# 显示词云
plt.imshow(wc, interpolation='bilinear')
plt.axis('off')
plt.show()

# 保存到文件
wc.to_file('wordcloud.png')