python詞云庫(kù)wordCloud使用方法詳解(解決中文亂碼)

import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud,STOPWORDS
from PIL import Image
from os import path
import matplotlib.pyplot as plt
#用來(lái)正常顯示中文
plt.rcParams["font.sans-serif"]=["SimHei"]
#用來(lái)正常顯示負(fù)號(hào)
plt.rcParams["axes.unicode_minus"]=False
import os
import random,jieba
 
'''
繪制單個(gè)詞一個(gè)圓形的詞云
'''
def single_wordColud():
  text = "第一 第二 第三 第四"
  #產(chǎn)生一個(gè)以(150,150)為圓心,半徑為130的圓形mask
  x,y = np.ogrid[:300,:300]
  mask = (x-150) ** 2 + (y-150) ** 2 > 130 ** 2
  mask = 255 * mask.astype(int)
  wc = WordCloud(background_color="white",repeat=True,mask=mask)
  wc.generate(text)
 
  #將x軸和y軸坐標(biāo)隱藏
  plt.axis("off")
  plt.imshow(wc,interpolation="bilinear")
  plt.show()

'''
中文分詞
'''
def segment_words(text):
  article_contents = ""
  #使用jieba進(jìn)行分詞
  words = jieba.cut(text,cut_all=False)
  for word in words:
    #使用空格來(lái)分割詞
    article_contents += word+" "
  return article_contents

'''
從文件中讀取停用詞
'''
def get_stopwords():
  dir_path = path.dirname(__file__) if "__file__" in locals() else os.getcwd()
  #獲取停用詞的路徑
  stopwords_path = os.path.join(dir_path,"txt/stopwords.txt")
  #創(chuàng)建set集合來(lái)保存停用詞
  stopwords = set()
  #讀取文件
  f = open(stopwords_path,"r",encoding="utf-8")
  line_contents = f.readline()
  while line_contents:
    #去掉回車(chē)
    line_contents = line_contents.replace("\n","").replace("\t","").replace("\u3000","")
    stopwords.add(line_contents)
    line_contents = f.readline()
  return stopwords

def drow_mask_wordColud():
  #獲取當(dāng)前文件的父目錄
  d = path.dirname(__file__) if "__file__" in locals() else os.getcwd()
  mask = np.array(Image.open(path.join(d,"img/test.jpg")))
  text = open(path.join(d,"txt/test.txt"),"r",encoding="utf-8").read().
      replace("\n","").replace("\t","").replace("\u3000","")
  #對(duì)文本進(jìn)行分詞
  text = segment_words(text)
  #獲取停用詞
  stopwords = get_stopwords()
  #創(chuàng)建詞云
  '''
  max_words:顯示詞的數(shù)量
  mask:背景
  stopwords:停用詞,是一個(gè)set集合
  margin:詞之間的間隔
  background_color:詞云圖片背景顏色
  '''
  wc = WordCloud(max_words=100,mask=mask,background_color="white",
          stopwords=stopwords,margin=10,random_state=1).generate(text)
  default_colors = wc.to_array()
  # #保存詞云圖片
  # wc.to_file("a_new_hope.png")
  plt.imshow(default_colors,interpolation="bilinear")
  plt.axis("off")
  plt.show()

from wordcloud import WordCloud,get_single_color_func
import matplotlib.pyplot as plt
 
'''
定義一個(gè)字體顏色設(shè)置類(lèi)
'''
class GroupedColorFunc(object):
  def __init__(self,color_to_words,default_color):
    self.color_func_to_words=[
      (get_single_color_func(color),set(words))
      for (color,words) in color_to_words.items()
    ]
    self.defalt_color_func=get_single_color_func(default_color)
  def get_color_func(self,word):
    try:
      #設(shè)置每個(gè)詞的顏色
      color_func = next(color_func for (color_func,words) in self.color_func_to_words
               if word in words)
    except StopIteration:
      #詞的默認(rèn)顏色
      color_func = self.defalt_color_func
    return color_func
  def __call__(self,word,**kwargs):
    return self.get_color_func(word)(word,**kwargs)
 
 
if __name__ == "__main__":
  text = "第一 第二 第三 第四 第五 第六"
  #創(chuàng)建詞云
  wc = WordCloud(collocations=False,background_color="white").generate(text)
  #設(shè)置詞的顏色
  color_to_words={
    #使用RGB來(lái)設(shè)置詞的顏色
    "#00ff00":["第一","第五"],
    "red":["第三","第六"],
    "yellow":["第二"]
  }
  #設(shè)置詞默認(rèn)的顏色
  default_color = "blue"
  grouped_color_func = GroupedColorFunc(color_to_words,default_color)
  #設(shè)置詞云的顏色
  wc.recolor(color_func=grouped_color_func)
  #顯示詞云圖
  plt.figure()
  plt.imshow(wc,interpolation="bilinear")
  plt.axis("off")
  plt.show()

from wordcloud import WordCloud
import matplotlib.pyplot as plt
import numpy as np
 
def get_mask():
  x,y = np.ogrid[:300,:300]
  mask = (x-150) ** 2 + (y-150) ** 2 > 130 ** 2
  mask = 255 * mask.astype(int)
  return mask
 
if __name__ == "__main__":
  #每個(gè)詞的權(quán)重
  text = {"第一":0.1,"第二":0.2,"第三":0.3,"第四":0.4,"第五":0.5}
  wc = WordCloud(background_color="white",mask=get_mask())
  wc.generate_from_frequencies(text)
  plt.axis("off")
  plt.imshow(wc,interpolation="bilinear")
  plt.show()

wc.to_file("test.png")