做業來源:https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/2822python
1. 下載一長篇中文小說。git
2. 從文件讀取待分析文本。github
1 txt = open(r'G:\aa\三體.txt', 'r', encoding='utf8').read() # 打開三體小說文件 2 jieba.load_userdict(r'G:\aa\three.txt') # 讀取三體小說詞庫 3 4 Filess= open(r'G:\aa\stops_chinese.txt', 'r', encoding='utf8') # 打開中文停用詞表 5 stops = Filess.read().split('\n') # 以回車鍵做爲標識符把停用詞表放到stops列表中
3. 安裝並使用jieba進行中文分詞。app
4. 更新詞庫,加入所分析對象的專業詞彙。less
1 # -*- coding: utf-8 -*- 2 import struct 3 import os 4 5 # 拼音表偏移, 6 startPy = 0x1540; 7 8 # 漢語詞組表偏移 9 startChinese = 0x2628; 10 11 # 全局拼音表 12 GPy_Table = {} 13 14 # 解析結果 15 # 元組(詞頻,拼音,中文詞組)的列表 16 17 18 # 原始字節碼轉爲字符串 19 def byte2str(data): 20 pos = 0 21 str = '' 22 while pos < len(data): 23 c = chr(struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0]) 24 if c != chr(0): 25 str += c 26 pos += 2 27 return str 28 29 # 獲取拼音表 30 def getPyTable(data): 31 data = data[4:] 32 pos = 0 33 while pos < len(data): 34 index = struct.unpack('H', bytes([data[pos],data[pos + 1]]))[0] 35 pos += 2 36 lenPy = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 37 pos += 2 38 py = byte2str(data[pos:pos + lenPy]) 39 40 GPy_Table[index] = py 41 pos += lenPy 42 43 # 獲取一個詞組的拼音 44 def getWordPy(data): 45 pos = 0 46 ret = '' 47 while pos < len(data): 48 index = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 49 ret += GPy_Table[index] 50 pos += 2 51 return ret 52 53 # 讀取中文表 54 def getChinese(data): 55 GTable = [] 56 pos = 0 57 while pos < len(data): 58 # 同音詞數量 59 same = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 60 61 # 拼音索引表長度 62 pos += 2 63 py_table_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 64 65 # 拼音索引表 66 pos += 2 67 py = getWordPy(data[pos: pos + py_table_len]) 68 69 # 中文詞組 70 pos += py_table_len 71 for i in range(same): 72 # 中文詞組長度 73 c_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 74 # 中文詞組 75 pos += 2 76 word = byte2str(data[pos: pos + c_len]) 77 # 擴展數據長度 78 pos += c_len 79 ext_len = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 80 # 詞頻 81 pos += 2 82 count = struct.unpack('H', bytes([data[pos], data[pos + 1]]))[0] 83 84 # 保存 85 GTable.append((count, py, word)) 86 87 # 到下個詞的偏移位置 88 pos += ext_len 89 return GTable 90 91 92 def scel2txt(file_name): 93 print('-' * 60) 94 with open(file_name, 'rb') as f: 95 data = f.read() 96 97 print("詞庫名:", byte2str(data[0x130:0x338])) # .encode('GB18030') 98 print("詞庫類型:", byte2str(data[0x338:0x540])) 99 print("描述信息:", byte2str(data[0x540:0xd40])) 100 print("詞庫示例:", byte2str(data[0xd40:startPy])) 101 102 getPyTable(data[startPy:startChinese]) 103 getChinese(data[startChinese:]) 104 return getChinese(data[startChinese:]) 105 106 if __name__ == '__main__': 107 # scel所在文件夾路徑 108 in_path = r"C:\Users\Administrator\Downloads" #修改成你的詞庫文件存放文件夾 109 # 輸出詞典所在文件夾路徑 110 out_path = r"C:\Users\Administrator\Downloads\text" # 轉換以後文件存放文件夾 111 fin = [fname for fname in os.listdir(in_path) if fname[-5:] == ".scel"] 112 for f in fin: 113 try: 114 for word in scel2txt(os.path.join(in_path, f)): 115 file_path=(os.path.join(out_path, str(f).split('.')[0] + '.txt')) 116 # 保存結果 117 with open(file_path,'a+',encoding='utf-8')as file: 118 file.write(word[2] + '\n') 119 os.remove(os.path.join(in_path, f)) 120 except Exception as e: 121 print(e) 122 pass
5. 生成詞頻統計ide
1 # 統計詞頻次數 2 for word in tokens: 3 if len(word) == 1: 4 continue 5 else: 6 wcdict[word] = wcdict.get(word, 0) + 1
6. 排序spa
1 # 詞頻排序 2 wcls = list(wcdict.items()) 3 wcls.sort(key=lambda x: x[1], reverse=True)
7. 排除語法型詞彙,代詞、冠詞、連詞等停用詞。code
1 Filess= open(r'G:\aa\stops_chinese.txt', 'r', encoding='utf8') # 打開中文停用詞表 2 stops = Filess.read().split('\n') # 以回車鍵做爲標識符把停用詞表放到stops列表中 3 4 tokens=[token for token in wordsls if token not in stops] 5 print("過濾後中文內容對比:",len(tokens), len(wordsls))
8. 輸出詞頻最大TOP20,把結果存放到文件裏對象
1 # 打印前25詞頻最高的中文 2 for i in range(25): 3 print(wcls[i]) 4 5 # 存儲過濾後的文本 6 pd.DataFrame(wcls).to_csv('three.csv', encoding='utf-8') 7 8 # 讀取csv詞雲 9 txt = open('three.csv', 'r', encoding='utf-8').read()
9. 生成詞雲。blog
1 # 讀取csv詞雲 2 txt = open('three.csv', 'r', encoding='utf-8').read() 3 4 # 用空格鍵隔開文本並把它弄進列表中 5 cut_text = "".join(jieba.lcut(txt)) 6 mywc = WordCloud().generate(cut_text) 7 8 plt.imshow(mywc) 9 plt.axis("off") 10 plt.show()
默認形狀:
修改背景: