WordCloud词云制作以及美化

练习代码

import wordcloud
import pandas as pd
import jieba
import matplotlib.pyplot as plt
from nltk.corpus import brown
font_path = \'C:\Windows\Fonts\msyh.ttc\'
text = \'this is shanghai, 李帅, 郭靖, 成龙, 哀牢山 三十六剑\'

\'\'\'
wc = wordcloud.WordCloud(
    font_path=font_path,
    max_font_size=300,
    width=360,
    height=180,
    mode=\'RGBA\',
    background_color=None, #透明的词云
)

cloudobj = wc.generate(text)

# cloudobj.show()
print(cloudobj)

#     展示词云图
plt.imshow(cloudobj)
# 关闭坐标轴，否则很丑
plt.axis(\'off\')
plt.show()
# 保存高清图片
cloudobj.to_file(\'词云.png\')
\'\'\'
raw = pd.read_table(\'./金庸-射雕英雄传txt精校版.txt\',names=[\'txt\'],encoding=\'GBK\')
# print(raw)

# 加入章节标识
# 章节判断用变量预处理
def m_head(tmpstr):
    return tmpstr[:1]  #取第一个字

def m_mid(tmpstr):
    return tmpstr.find("回 ")

# 用apply函数将下面的属性加入到对应列
raw[\'head\'] = raw.txt.apply(m_head)
raw[\'mid\'] = raw.txt.apply(m_mid)
raw[\'len\'] = raw.txt.apply(len)


# 章节判断
chapnum = 0
for i in range(len(raw)):
    if raw[\'head\'][i] == "第" and raw[\'mid\'][i] >0 and raw[\'len\'][i]<30:
        chapnum += 1
    if chapnum >= 40 and raw[\'txt\'][i] == "附录一：成吉思汗家族":
        chapnum=0
    raw.loc[i,\'chap\'] = chapnum


# 删除临时变量
del raw[\'head\']
del raw[\'mid\']
del raw[\'len\']

# 段落聚合  根据章节聚合
rawgrp = raw.groupby(\'chap\')

chapter = rawgrp.agg(sum)

chapter = chapter[chapter.index != 0]

t = chapter.txt[1]
print("*"*100)
print(t)
print("*"*100)
\'\'\'
生成射雕英雄传第一章的词云
\'\'\'


# 把停用词.txt的内容读入数据框
stoplist = list(pd.read_csv(\'./停用词.txt\',names=[\'w\'],sep=\'aaa\',encoding=\'utf-8\',engine=\'python\').w)


# print(stoplist)
# print(\' \'.join(stoplist))

def m_cut(intxt):
    return [w for w in jieba.cut(intxt) if w not in stoplist]


cloudobj = wordcloud.WordCloud(
    font_path=font_path,
    width=1200,
    height=800,
    mode=\'RGBA\',
    background_color=None,
    stopwords=stoplist,
).generate(\' \'.join(jieba.lcut(chapter.txt[1])))

plt.imshow(cloudobj)
plt.axis(\'off\')
plt.show()



\'\'\'
基于分词频数绘制词云
\'\'\'

txt_freq = {\'张三\':100,\'李四\':90,\'王二麻子\':50}

cloudobj = wordcloud.WordCloud(
    font_path=font_path,

).fit_words(txt_freq)

plt.imshow(cloudobj)
plt.axis("off")
plt.show()


\'\'\'
基于分词频数绘制射雕英雄传的词云
\'\'\'
import nltk
from nltk import FreqDist

# 去停用词
tokens = m_cut(chapter.txt[1])
# 生成完备的词条频数词典
fdist = FreqDist(tokens)

print(type(fdist))
# <class \'nltk.probability.FreqDist\'>

cloudobj = wordcloud.WordCloud(
    font_path=font_path,
    background_color=None,
    width=1600,
    height=1000,

).fit_words(fdist)

plt.imshow(cloudobj)
plt.axis("off")
plt.show()



\'\'\'
词云的美化：
1，设置背景图片
    Mask/遮罩
    用于控制词频的整体形状
    指定mask后，设置的高和宽江北忽略，遮罩形状被指定图形的形状取代。除全白的部分仍然被保留外，
    其余部分会用于绘制词云。因此背景图片的画布一定要设置为白色
    字体的大小，布局和颜色也会基于mask生成
    必要时需要调整颜色以增强可视效果

    # 基本调用方式
    from scipy.misc import imread
    mask = imread(\'背景图片\')
\'\'\'


from imageio import imread

def m_cut2(intxt):
    return [w for w in jieba.cut(intxt) if w not in stoplist and len(w)>1]

cloudobj = wordcloud.WordCloud(
    font_path=font_path,
    mask=imread(\'射雕背景1.png\'),
    mode=\'RGBA\',
    background_color=None,

).generate(\' \'.join(m_cut2(chapter.txt[1])))


plt.imshow(cloudobj)
plt.axis("off")
plt.show()
相关截图

练习代码
