用python分析英文文章，画直方图

效果

image.png

读取文章：word.txt（内容截取片段）
VOLUME I

CHAPTER I

Emma Woodhouse, handsome, clever, and rich, with a comfortable home
and happy disposition, seemed to unite some of the best blessings
of existence; and had lived nearly twenty-one years in the world
with very little to distress or vex her.

The event had every promise of happiness for her friend. Mr. Weston
was a man of unexceptionable character, easy fortune, suitable age,
and pleasant manners; and there was some satisfaction in considering
with what self-denying, generous friendship she had always wished
and promoted the match; but it was a black morning's work for her.
The want of Miss Taylor would be felt every hour of every day.
She recalled her past kindness--the kindness, the affection of sixteen
years--how she had taught and how she had played with her from five
years old--how she had devoted all her powers to attach and amuse
her in health--and how nursed her through the various illnesses
of childhood.……

第一步：读取文件

  # 打开文件
        with open("word.txt") as f:
            # 读取每一行
            for line in f:

第二步：分析文件，把单词提炼出来

 # 按空格和符号分割
                words=[]
                for word in re.split(r'[^a-zA-Z]', line):
                    # 过滤空白字符
                    if (word.strip() != ''):
                        # 转换为小写
                        word = word.lower()
                        words.append(word)

第三步：利用字典统计词频

   # 存储单词出现次数字典
    dict_word ={}
   # 单词词典
   dict_word[word] = dict_word.get(word, 0) + 1

统计词频结果

{'volume': 3, 'i': 3192, 'chapter': 56, 'emma': 865,
 'woodhouse': 314, 'handsome': 38, 'clever': 27, 'and': 4897, 
……

第四步：获取单词频率前10名的单词

  # 获取排名前n个单词
  # 参数为单词字典，排名
  def get_topN(hist, num):
      l = []
      #迭代字典key,value
      for key,value in hist.items():
          #把单词，数量用元祖形式加入到列表中
          l.append((value,key))
      #按数量进行反向排序
      l.sort(reverse=True)
  #获得前num名
  return l[:num+1]

#第二种求取排序的方法
sorted(hist.items(), key=lambda x: x[1], reverse=True)[:num+1]

#排序结果
#[(5242, 'to'), (5205, 'the'), (4897, 'and'),
 (4295, 'of'), (3192, 'i'), (3130, 'a')]……

第五步：画图

# 导入画图
from matplotlib import pyplot as plt
# 导入字体库
from matplotlib.font_manager import FontProperties
# 获得字体
font_set = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=15)
# 获取topN
    data = get_topN(hist, 10)
    for d in data:
        #填充数据项y,x
        plt.bar((d[-1],), (d[0],))
        # 画图
    plt.xlabel(u'单词', fontproperties=font_set)
    plt.ylabel(u'出现次数', fontproperties=font_set)
    plt.title('单词直方图', fontproperties=font_set)
    plt.show()

代码:

#!/usr/bin/env python3 
# -*- coding: utf-8 -*-
# @Time    : 2018/1/22 15:23
# @Author  : hyang
# @File    : demo.py
# @Software: 获取单词直方图

import re
import string
# 导入画图
from matplotlib import pyplot as plt
# 导入字体
from matplotlib.font_manager import FontProperties
# 获得字体
font_set = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=15)


# 读取文件得到单词list
def deal_file(file_name):
    # 存储单词
    words = []
    # 存储单词出现次数字典
    dict_word ={}
    try:
        # 打开文件
        with open(file_name) as f:
            # 读取每一行
            for line in f:
                # 按空格和符号分割
                for word in re.split(r'[^a-zA-Z]', line):
                    # 过滤空白字符
                    if (word.strip() != ''):
                        # 转换为小写
                        word = word.lower()
                        words.append(word)
                        # 单词词典
                        dict_word[word] = dict_word.get(word, 0) + 1
    except Exception as e:
        print(e)
    return dict_word

# 获取前n个单词
def get_topN(hist, num):
  return sorted(hist.items(), key=lambda x: x[1], reverse=True)[:num+1]


def run():
    hist = deal_file('emma.txt')
    print(hist)
    # 获取topN
    data = get_topN(hist, 10)
    print(data)

    for d in data:
        plt.bar((d[0],), (d[-1],))
    # 画图
    plt.xlabel(u'单词', fontproperties=font_set)
    plt.ylabel(u'出现次数', fontproperties=font_set)
    plt.title('单词直方图', fontproperties=font_set)
    plt.show()
    pass

# 主函数
if __name__ == '__main__':
    run()