Python中文分词、词频统计并制作词云图

中文分词、词频统计并制作词云图是统计数据常用的功能，这里用到了三个模块快速实现这个功能。

中文分词、词频统计

import jieba
from collections import Counter

# 1. 读取文本内容并进行分词
with open('demo.txt', mode='r', encoding='gbk') as f:
    report = f.read()
words = jieba.cut(report)

# 2. 按指定长度提取词
report_words = []
for word in words:
    if len(word) >= 4:
        report_words.append(word)
print(report_words)

# 3. 统计高频词汇
result = Counter(report_words).most_common(50)
print(result)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19

上面代码用jieba模块进行分词，用collections进行词频统计。
jieba是一个优秀的第三方中文词库，用于中文分词。中文分词指的是将一个汉字序列切分成一个一个单独的词。jieba可以帮助你快速高效地完成中文分词，支持三种分词模式：精确模式、全模式和搜索引擎模式。

collections是Python标准库中的一个模块，提供了一些额外的容器类型，以提供Python标准内建容器dict、list、set和tuple的替代选择。这些容器类型包括namedtuple、deque、Counter等。

简单词云图

import jieba.posseg as pseg
from collections import Counter
from wordcloud import WordCloud

# 1. 读取文本内容并进行分词
with open('demo.txt', mode='r', encoding='gbk') as f:
    report = f.read()
words = pseg.cut(report)

# 2. 按指定长度和词性提取词
report_words = []
for word, flag in words:
    if (len(word) >= 4) and ('n' in flag):
        report_words.append(word)
# print(report_words)

# 3. 统计高频词汇
result = Counter(report_words).most_common(50)
# print(result)

# 4. 绘制词云图
content = dict(result)
# print(content)
wc = WordCloud(font_path='PINGFANG MEDIUM.TTF', background_color='white', width=1000, height=600)
wc.generate_from_frequencies(content)
wc.to_file('词云图1.png')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

这里用到了wordcloud模块来生成词云图。

按照图片绘制词云图

import jieba.posseg as pseg
from collections import Counter
from PIL import Image
import numpy as np
from wordcloud import WordCloud

# 1. 读取文本内容并进行分词
with open('demo.txt', mode='r', encoding='gbk') as f:
    report = f.read()
words = pseg.cut(report)

# 2. 按指定长度和词性提取词
report_words = []
for word, flag in words:
    if (len(word) >= 4) and ('n' in flag):
        report_words.append(word)
# print(report_words)

# 3. 统计高频词汇
result = Counter(report_words).most_common(300)
# print(result)

# 4. 绘制词云图
mask_pic = Image.open('map.png')
mask_data = np.array(mask_pic)
print(mask_data)
content = dict(result)
wc = WordCloud(font_path='PINGFANG MEDIUM.TTF', background_color='white', mask=mask_data)
wc.generate_from_frequencies(content)
wc.to_file('词云图2.png')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31

这里给WordCloud加了mask遮罩参数。

按照图片绘制渐变词云图

import jieba.posseg as pseg
from collections import Counter
from PIL import Image
import numpy as np
from wordcloud import WordCloud, ImageColorGenerator

# 1. 读取文本内容并进行分词
with open('demo.txt', mode='r', encoding='gbk') as f:
    report = f.read()
words = pseg.cut(report)

# 2. 按指定长度和词性提取词
report_words = []
for word, flag in words:
    if (len(word) >= 4) and ('n' in flag):
        report_words.append(word)
# print(report_words)

# 3. 统计高频词汇
result = Counter(report_words).most_common(300)
# print(result)

# 4. 绘制词云图
mask_pic = Image.open('map.png')
mask_data = np.array(mask_pic)
content = dict(result)
wc = WordCloud(font_path='PINGFANG MEDIUM.TTF', background_color='white', mask=mask_data)
wc.generate_from_frequencies(content)
mask_colors = ImageColorGenerator(mask_data)
wc.recolor(color_func=mask_colors)
wc.to_file('词云图3.png')

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

这里用recolor重绘了颜色。