基于python生成词云图的代码示例

import codecs
def get_file_content(filePath):
  with codecs.open(filePath, 'r', 'utf-8') as f:
      txt = f.read()
  return txt

import jieba
from collections import Counter
def get_words(txt):
    # 先分词，得到词语数组
    seg_list = jieba.cut(txt)
    # 开始计数
    c = Counter()
    for x in seg_list:
        if len(x)>1 and x != '\r\n':
            c[x] += 1
    word_list = []
    print('常用词频度统计结果')
     # 统计前99个词
    for (k,v) in c.most_common(99):
        word_list.append(str(k))
    # 将词语生成文本文件
    file = open("./dist/out_words.txt", 'w').close()
    with open("./dist/out_words.txt",'a+',encoding='utf-8') as writeFile:
        for (k,v) in c.most_common(99):    # 统计前99个词
            writeFile.write(str(k))
            writeFile.write(str(v))
            writeFile.write('\n')
    print(word_list)
    # ['发展','平安']
    return word_list

import wordcloud;
def generate_cloud_image(file_path, shape_image_path):
  word_list = get_words(get_file_content(file_path))
  string = ' '.join(word_list)
  # 读取词云形状图片
  image = imageio.v2.imread(shape_image_path)
  # 先实例化一个词云对象
  wc = wordcloud.WordCloud(width=image.shape[0],     # 词云图宽度同原图片宽度
                          height=image.shape[1],
                          background_color='white',  # 背景颜色白色
                          font_path='Arial Unicode.ttf',    # 指定字体路径，微软雅黑，可从自带的字体库中找
                          mask=image,   # mask 指定词云形状图片，默认为矩形
                          scale=3)      # 默认为1，越大越清晰
  # 生成词云
  wc.generate(string)
  # 保存成文件,output_wordcloud.png，词云图
  wc.to_file('dist/output_wordcloud.png')
  # 弹出图片显示
  alert_image('dist/output_wordcloud.png')

#
# plt用于显示图片
import matplotlib.pyplot as plt
# mpimg 用于读取图片
import matplotlib.image as mpimg
def alert_image(image_path):
  # 这里是让词云图弹出来显示
  lena = mpimg.imread(image_path) # 读取和代码处于同一目录下的 lena.png
  # 此时 lena 就已经是一个 np.array 了，可以对它进行任意处理
  lena.shape #(512, 512, 3)
  plt.imshow(lena) # 显示图片
  plt.axis('off') # 不显示坐标轴
  plt.show()

import codecs
import jieba
import imageio
import wordcloud
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from collections import Counter
# def get_words(txt):...
# def get_file_content:...
# def alert_image(image_path):...
# def generate_cloud_image(file_path, shape_image_path):...
generate_cloud_image('input.txt', 'cloud.jpg')

import codecs
import jieba
import imageio
import wordcloud
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
from collections import Counter
#  get_words函数用于统计词频，生成out.txt，展示词语和词频 如发展218 坚持170
def get_words(txt):
    seg_list = jieba.cut(txt)
    c = Counter()
    for x in seg_list:
        if len(x)>1 and x != '\r\n':
            c[x] += 1
    word_list = []
    print('常用词频度统计结果')
     # 统计前99个词
    for (k,v) in c.most_common(99):
        word_list.append(str(k))

    file = open("./out_words.txt", 'w').close()
    with open("./out_words.txt",'a+',encoding='utf-8') as writeFile:
        for (k,v) in c.most_common(99):    # 统计前99个词
            writeFile.write(str(k))
            writeFile.write(str(v))
            writeFile.write('\n')
    print(word_list)
    # ['发展','平安']
    return word_list

def get_file_content(filePath):
    with codecs.open(filePath, 'r', 'utf-8') as f:
        txt = f.read()
    return txt
def alert_image(image_path):
    # 这里是让词云图弹出来显示
    lena = mpimg.imread(image_path) # 读取和代码处于同一目录下的 lena.png
    # 此时 lena 就已经是一个 np.array 了，可以对它进行任意处理
    lena.shape #(512, 512, 3)
    plt.imshow(lena) # 显示图片
    plt.axis('off') # 不显示坐标轴
    plt.show()

# 根据文件生成词云图，file_path是文本文件路径，shape_image_path是词云图的图片途径
def generate_cloud_image(file_path, shape_image_path):
    word_list = get_words(get_file_content(file_path))
    string = ' '.join(word_list)
    # 读取词云形状图片
    image = imageio.v2.imread(shape_image_path)
    # 生成词云图片，先实例化一个词云对象
    wc = wordcloud.WordCloud(width=image.shape[0],     # 词云图宽度同原图片宽度
                            height=image.shape[1],
                            background_color='white',  # 背景颜色白色
                            font_path='Arial Unicode.ttf',    # 指定字体路径，微软雅黑，可从win自带的字体库中找
                            mask=image,   # mask 指定词云形状图片，默认为矩形
                            scale=3)      # 默认为1，越大越清晰
    # 再给词云
    wc.generate(string)
    # 保存成文件,output_wordcloud.png，词云图
    wc.to_file('output_wordcloud.png')
    alert_image('output_wordcloud.png')

generate_cloud_image('input.txt', 'cloud.jpg')