中文詞頻統計與詞雲生成

 本次作業的要求來自於：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/2822

初始化jieba環境：

 1. 下載一長篇中文小說。

 

2. 從文件讀取待分析文本。

3. 安裝並使用jieba進行中文分詞。

pip install jieba

import jieba

jieba.lcut(text)

 

4. 更新詞庫，加入所分析對象的專業詞彙。

jieba.add_word('天罡北斗陣')  #逐個添加

jieba.load_userdict(word_dict)  #詞庫文本文件

test=open(r"..\python1\threeCountry.txt", "r",encoding="utf-8").read()
File=open(r"..\python1\stops_chinese.txt", "r",encoding="utf-8")
jieba.load_userdict(r"..\python1\比較全的三國人名.txt")
#停詞表
stops = File.read().split('\n')
ch="《》\n：，。、-!?"

轉換代碼：scel_to_text

# -*- coding: utf-8 -*-
import struct
import os

# 拼音表偏移，
startPy = 0x1540;

# 漢語詞組表偏移
startChinese = 0x2628;

# 全局拼音表
GPy_Table = {}

# 解析結果
# 元組(詞頻,拼音,中文詞組)的列表


# 原始字節碼轉爲字符串
def byte2str(data):
pos = 0
str = ''
while pos < len(data):
c = chr(struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0])
if c != chr(0):
str += c
pos += 2
return str

# 獲取拼音表
def getPyTable(data):
data = data[4:]
pos = 0
while pos < len(data):
index = struct.unpack('H', bytes([data[pos],data[pos + 1]]))[0]
pos += 2
lenPy = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]
pos += 2
py = byte2str(data[pos:pos + lenPy])

GPy_Table[index] = py
pos += lenPy

# 獲取一個詞組的拼音
def getWordPy(data):
pos = 0
ret = ''
while pos < len(data):
index = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]
ret += GPy_Table[index]
pos += 2
return ret

# 讀取中文表
def getChinese(data):
GTable = []
pos = 0
while pos < len(data):
# 同音詞數量
same = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]

# 拼音索引表長度
pos += 2
py_table_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]

# 拼音索引表
pos += 2
py = getWordPy(data[pos: pos + py_table_len])

# 中文詞組
pos += py_table_len
for i in range(same):
# 中文詞組長度
c_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]
# 中文詞組
pos += 2
word = byte2str(data[pos: pos + c_len])
# 擴展數據長度
pos += c_len
ext_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]
# 詞頻
pos += 2
count = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]

# 保存
GTable.append((count, py, word))

# 到下個詞的偏移位置
pos += ext_len
return GTable


def scel2txt(file_name):
print('-' * 60)
with open(file_name, 'rb') as f:
data = f.read()

print("詞庫名：", byte2str(data[0x130:0x338])) # .encode('GB18030')
print("詞庫類型：", byte2str(data[0x338:0x540]))
print("描述信息：", byte2str(data[0x540:0xd40]))
print("詞庫示例：", byte2str(data[0xd40:startPy]))

getPyTable(data[startPy:startChinese])
getChinese(data[startChinese:])
return getChinese(data[startChinese:])

if __name__ == '__main__':
# scel所在文件夾路徑
in_path = r"F:\text" #修改爲你的詞庫文件存放文件夾
# 輸出詞典所在文件夾路徑
out_path = r"F:\text" # 轉換之後文件存放文件夾
fin = [fname for fname in os.listdir(in_path) if fname[-5:] == ".scel"]
for f in fin:
try:
for word in scel2txt(os.path.join(in_path, f)):
file_path=(os.path.join(out_path, str(f).split('.')[0] + '.txt'))
# 保存結果
with open(file_path,'a+',encoding='utf-8')as file:
file.write(word[2] + '\n')
os.remove(os.path.join(in_path, f))
except Exception as e:
print(e)
pass

5. 生成詞頻統計

for w in tokens:
    if len(w)==1:
        continue
    else:
        wordict[w] = wordict.get(w,0)+1

7. 排除語法型詞彙，代詞、冠詞、連詞等停用詞。

stops

tokens=[token for token in wordsls if token not in stops]

wordlist=jieba.lcut(test)
tokens=[token for token in wordlist if token not in stops]

8. 輸出詞頻最大TOP20，把結果存放到文件裏。

for i in range(20):
    print(wordsort[i])

9. 生成詞雲。

pd.DataFrame(wordsort).to_csv('three.csv', encoding='utf-8')
txt = open('three.csv','r',encoding='utf-8').read()
cut_text=''.join(txt)
from wordcloud import WordCloud
mywc=WordCloud().generate(cut_text)
import matplotlib.pyplot as plt
plt.imshow(mywc)
plt.axis("off")
plt.show()
mywc.to_file(r"F:\txt\threestory.png")

 

整體代碼：

# _*_ coding: utf-8 _*_
import jieba
import pandas as pd

test=open(r"..\python1\threeCountry.txt", "r",encoding="utf-8").read()
File=open(r"..\python1\stops_chinese.txt", "r",encoding="utf-8")
jieba.load_userdict(r"..\python1\比較全的三國人名.txt")
#停詞表
stops = File.read().split('\n')
ch="《》\n：，。、-!?"
for c in ch:
    test = test.replace(c,'')

    #更新詞庫，加入所分析對象的專業詞彙
jieba.add_word('哎喲不錯喲')
#中文切詞
wordlist=jieba.lcut(test)
tokens=[token for token in wordlist if token not in stops]
wordict={}
for w in tokens:
    if len(w)==1:
        continue
    else:
        wordict[w] = wordict.get(w,0)+1
wordsort=list(wordict.items())
wordsort.sort(key= lambda x:x[1],reverse=True)
#輸出詞頻最大TOP20
for i in range(20):
    print(wordsort[i])

pd.DataFrame(wordsort).to_csv('three.csv', encoding='utf-8')
txt = open('three.csv','r',encoding='utf-8').read()
cut_text=''.join(txt)
from wordcloud import WordCloud
mywc=WordCloud().generate(cut_text)
import matplotlib.pyplot as plt
plt.imshow(mywc)
plt.axis("off")
plt.show()
mywc.to_file(r"F:\txt\threestory.png")