import re
import pandas as pd
from scipy.misc import imread
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
import matplotlib.pyplot as plt
import pkuseg
def wordCount(segment_list):
word_dict = {}
for item2 in segment_list:
if item2 not in word_dict:
word_dict[item2] = 1
else:
word_dict[item2] += 1
return word_dict
f = open(r"停用词2.txt",encoding='utf-8')
stopword_list = [line.strip() for line in f.readlines()]
path_txt = r'C:\Users\14167\Desktop\pbl\刘慈欣-三体.txt'
f2 = open(path_txt, 'r', encoding='UTF-8').read()
seg=pkuseg.pkuseg()
new = re.sub(r'[^\u4e00-\u9fa5]', '', f2) #去标点 https://github.com/fxsjy/jieba/issues/528
word_list = [word for word in seg.cut(''.join(new)) if word not in stopword_list]
back_color = imread(r"santi.jpg") # 解析该图片
wc = WordCloud(background_color='black', # 背景颜色
max_words=2000, # 最大词数
mask=back_color, # 以该参数值作图绘制词云,这个参数不为空时,width和height会被忽略
collocations=False,
#max_font_size=100, # 字体最大值
#min_font_size=20, # 字体最小值
font_path="C:/Windows/Fonts/SIMYOU.ttf", # 解决显示口字型乱码问题,可进入C:/Windows/Fonts/目录更换字体
# random_state=42, # 为每个词返回一个PIL颜色
)
wc.generate_from_text(" ".join(word_list))#根据文本绘制云图
# wc.generate_from_frequencies(wordCount(word_list)) #使用频率绘制云图
print(wordCount(word_list))#得到分词各个词频
# 基于彩色图像生成相应彩色
image_colors = ImageColorGenerator(back_color)
# 显示图片
#plt.imshow(wc)
# 关闭坐标轴
#plt.axis('off')
# 绘制词云
plt.figure()
# plt.imshow(wc, interpolation="bilinear")
plt.imshow(wc.recolor(color_func=image_colors))
plt.axis('off')
# 保存图片
#wc.to_file(r'img.jpg')
这是背景得图片,经过ps一波操作提取出来得形状比较好看的
最后的词云图做出来是这个样子,我试了几个背景颜色,还是黑色好。
看到“程心”这么大个字我就放心了