Python基于WordCloud制作词云图

import matplotlib.pyplot as plt
from scipy.misc import imread
from wordcloud import WordCloud,STOPWORDS
import xlrd

def set_background(picpath):
  back_coloring = imread(picpath)# 设置背景图片，png等图片格式
  return back_coloring

def create_word_cloud(txt_str, back_coloring): #txt_str表示导入的是字符串格式数据，#back_color表示的是背景图片位置
  print('---- 根据词频，开始生成词云! ----')
  font = r'C:\Windows\Fonts\simsun.ttc' #加载显示字体
  wc = WordCloud(
    font_path=font,
    collocations=False, # 去重，如果不加，词云图会显示相同的词
    stopwords=STOPWORDS, #加载停用词，如果不自己指定，则会加载默认的停用词
    max_words=100,
    width=2000,
    height=1200,
    # background_color='white',
    mask=back_coloring,
  )
  wordcloud = wc.generate(txt_str)
  # 写词云图片
  wordcloud.to_file(".\wordcloud_test.png")
  # 显示词云文件
  plt.imshow(wordcloud)
  plt.axis("off")
  plt.show()

if __name__ == '__main__': 
  picpath = r".\xxx.png" #背景图片路径
  back_coloring = set_background(picpath)
  
  with open(r".\jieba_分词数据.txt", "r",encoding='utf-8') as f:
    remove_stop_str = f.read()
  
  create_word_cloud(remove_stop_str, back_coloring)

def read_from_xls(filepath,index_sheet):
  #读取文件名，filepath是excel文件的路径，index_sheet是第几个sheet
  #读取表格#
  # 设置GBK编码
  xlrd.Book.encoding = "gbk"
  rb = xlrd.open_workbook(filepath)
  print(rb)

  sheet = rb.sheet_by_index(index_sheet)
  nrows = sheet.nrows
  data_tmp = []

  for i in range(nrows - 1):
    tt=i+1 #excel的第一行是标签
    tmp_char = [str(sheet.cell_value(tt,0))] #第一列是词
    tmp_num = int(sheet.cell_value(tt,1))  #第二列是词频
    data_tmp.extend(tmp_char*tmp_num)
  return data_tmp

if __name__ == '__main__': 
  picpath = r".\xxx.png"
  back_coloring = set_background(picpath)
  
  data_dic = read_from_xls(r'D:\Python_workspace\spyder_space\jieba分词表.xlsx',0)
  data_dic_str = '\n'.join(data_dic) #转成字符串格式
  
  create_word_cloud(data_dic_str, back_coloring)

# -*- coding: utf-8 -*-
"""
Created on Mon Aug 19 10:47:17 2019

@author: Administrator
"""
import matplotlib.pyplot as plt
from scipy.misc import imread
from wordcloud import WordCloud,STOPWORDS
import xlrd

def set_background(picpath):
  back_coloring = imread(picpath)# 设置背景图片
  return back_coloring

def create_word_cloud(txt_str, back_coloring):
  print('---- 根据词频，开始生成词云! ----')
  font = r'C:\Windows\Fonts\simsun.ttc'
  wc = WordCloud(
    font_path=font,
    collocations=False, # 去重
    stopwords=STOPWORDS,
    max_words=100,
    width=2000,
    height=1200,
    # background_color='white',
    mask=back_coloring,
  )
  wordcloud = wc.generate(txt_str)
  # 写词云图片
  wordcloud.to_file(".\wordcloud_test.png")
  # 显示词云文件
  plt.imshow(wordcloud)
  plt.axis("off")
  plt.show()

def read_from_xls(filepath,index_sheet):
  #读取文件名
  #读取表格#
  # 设置GBK编码
  xlrd.Book.encoding = "gbk"
  rb = xlrd.open_workbook(filepath)
  print(rb)

  sheet = rb.sheet_by_index(index_sheet)
  nrows = sheet.nrows
  data_tmp = []

  for i in range(nrows - 1):
    tt=i+1
    tmp_char = [str(sheet.cell_value(tt,0))]
    tmp_num = int(sheet.cell_value(tt,1))
    data_tmp.extend(tmp_char*tmp_num)
  return data_tmp

if __name__ == '__main__': 
  picpath = r".\xxx.png"
  back_coloring = set_background(picpath)
  data_dic = read_from_xls(r'D:\Python_workspace\spyder_space\jieba分词表.xlsx',0)
  data_dic_str = '\n'.join(data_dic)
  
#  with open(r".\jieba_分词数据.txt", "r",encoding='utf-8') as f: 
# 　　　remove_stop_str = f.read() 

　　create_word_cloud(data_dic_str, back_coloring)