{"id":376,"date":"2013-08-11T23:57:00","date_gmt":"2013-08-11T14:57:00","guid":{"rendered":""},"modified":"2021-06-05T13:21:45","modified_gmt":"2021-06-05T04:21:45","slug":"blog-post-14","status":"publish","type":"post","link":"https:\/\/www.sigmadesign.co.jp\/minomonchan\/2013\/08\/blog-post-14.html","title":{"rendered":"\u5165\u9580\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\uff08\u30aa\u30e9\u30a4\u30ea\u30fc\uff09\u306e\u6f14\u7fd2\u554f\u984c \u89e3\u7b54Part1 [\u7b2c\uff11\u7ae0\uff11\u301c\uff18]"},"content":{"rendered":"

\u30aa\u30e9\u30a4\u30ea\u30fc\u304b\u3089\u51fa\u7248\u3055\u308c\u3066\u3044\u308b\u5165\u9580\u81ea\u7136\u8a00\u8a9e\u51e6\u7406<\/a>\u3092\u30b3\u30c4\u30b3\u30c4\u8aad\u3093\u3067\u3044\u308b\u3002<\/p>\n

\u3053\u308c\u304b\u3089\u3053\u306e\u5206\u91ce\u306f\u78ba\u5b9f\u306b\u4f38\u3073\u308b\u3060\u308d\u3046\u3057\u3001\u4f55\u3088\u308a\u5922\u304c\u3042\u308b\u3002\u5b8c\u5168\u306a\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u81ea\u52d5\u7ffb\u8a33\u3001\u5b8c\u5168\u306b\u4f1a\u8a71\u306e\u6210\u308a\u7acb\u3064\u4eba\u5de5\u77e5\u80fd\u3001\u81ea\u5206\u306e\u5fc3\u3092\u7652\u3057\u3066\u304f\u308c\u308b\u5fc3\u7406\u30ab\u30a6\u30f3\u30bb\u30e9\u30fc\u306e\u3088\u3046\u306a\u30ed\u30dc\u30c3\u30c8\u306a\u3069\u3002<\/p>\n

\u4eca\u3001\u81ea\u5206\u306b\u95a2\u4fc2\u306e\u3042\u308b\u9818\u57df\u3067\u8a00\u3048\u3070\u30b0\u30fc\u30b0\u30eb\u306e\u691c\u7d22\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u304c\u9032\u5316\u3059\u308b\u30ad\u30fc\u30dd\u30a4\u30f3\u30c8\u3068\u306a\u308b\u6280\u8853\u3082\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3060\u3068\u601d\u3046\u3002<\/p>\n

\u3082\u3057\u30b0\u30fc\u30b0\u30eb\u306e\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u304c\u3042\u308b\u30da\u30fc\u30b8\u306b\u66f8\u304b\u308c\u3066\u3044\u308b\u5185\u5bb9\u3092\u5b8c\u5168\u306b\u7406\u89e3\u3067\u304d\u308b\u3068\u3059\u308b\u3068\u3001\u4eca\u307f\u305f\u3044\u306b\u88ab\u30ea\u30f3\u30af\u306b\u983c\u308b\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u4f7f\u3046\u5fc5\u8981\u6027\u304c\u5168\u304f\u7121\u304f\u306a\u308b\u3002<\/p>\n

\u691c\u7d22\u30e6\u30fc\u30b6\u30fc\u306e\u610f\u56f3\u3092\u8aad\u307f\u53d6\u3063\u3066\u3001\u305d\u306e\u4eba\u306e\u6c42\u3081\u3066\u3044\u308b\u60c5\u5831\u304c\u63b2\u8f09\u3055\u308c\u3066\u3044\u308b\u30da\u30fc\u30b8\u3092\u691c\u7d22\u7d50\u679c\u306b\u8fd4\u305b\u3070\u3044\u3044\u3060\u3051\u3002<\/p>\n

\u305d\u306e\u30da\u30fc\u30b8\u304c\u3069\u3053\u304b\u3089\u30ea\u30f3\u30af\u3092\u8cb0\u3063\u3066\u3044\u308b\u3068\u304b\u3001\u3069\u308c\u3060\u3051\u306e\u6570\u306e\u30ea\u30f3\u30af\u3092\u8cb0\u3063\u3066\u3044\u308b\u304b\u306a\u3093\u3066\u5b8c\u5168\u306b\u4e8c\u6b21\u7684\u306a\u30b9\u30b3\u30a2\u4ed8\u3051\u306b\u904e\u304e\u306a\u304f\u306a\u308b\u3002<\/p>\n

\u3068\u3044\u3046\u3053\u3068\u3067\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3068\u3044\u3046\u6280\u8853\u306b\u3059\u3054\u304f\u8208\u5473\u304c\u3042\u308b\u3002<\/p>\n

\u5165\u9580\u81ea\u7136\u8a00\u8a9e\u51e6\u7406<\/a>\u304c\u3044\u3044\u306e\u306f\u3001\u5404\u7ae0\u306e\u7d42\u308f\u308a\u306b\u6f14\u7fd2\u554f\u984c\u304c\u4ed8\u3044\u3066\u3044\u308b\u3053\u3068\u3060\u3068\u601d\u3046\u3002\u672c\u3092\u8aad\u3093\u3067\u77e5\u8b58\u3092\u5165\u308c\u308b\u3060\u3051\u3067\u3082\u672c\u5f53\u306e\u7406\u89e3\u306b\u306f\u81f3\u3089\u305a\u3001\u81ea\u5206\u3067\u8003\u3048\u3066\u624b\u3092\u52d5\u304b\u3057\u305f\u308a\u3057\u3066\u51fa\u529b\uff08\u30a2\u30a6\u30c8\u30d7\u30c3\u30c8\uff09\u3057\u3066\u306f\u3058\u3081\u3066\u7406\u89e3\u304c\u6df1\u307e\u308b\u3002<\/p>\n

\u305f\u3060\u3001\u7b54\u3048\u304c\u3069\u3053\u306b\u3082\u66f8\u304b\u308c\u3066\u306a\u3044\u3002\u4ed5\u65b9\u306a\u3044\u304b\u3089\u4ed6\u306e\u4eba\u304c\u30d6\u30ed\u30b0\u306a\u3093\u304b\u306b\u66f8\u3044\u3066\u305f\u308a\u3059\u308b\u306e\u3092\u53c2\u8003\u306b\u3057\u306a\u304c\u3089\u3084\u3063\u3066\u3044\u307e\u3059\u3002<\/p>\n

\u4ed6\u306b\u3082\u540c\u3058\u3088\u3046\u306a\u4eba\u304c\u3044\u308b\u304b\u3082\u3057\u308c\u306a\u3044\u306e\u3067\u3001\u50d5\u3082\u81ea\u5206\u306e\u89e3\u3044\u305f\u7b54\u3048\u3092\u30d6\u30ed\u30b0\u306b\u8f09\u305b\u308b\u3053\u3068\u306b\u3059\u308b\u3002\u5408\u3063\u3066\u3044\u308b\u304b\u3069\u3046\u304b\u306f\u5168\u304f\u5206\u304b\u3089\u306a\u3044\u3057\u81ea\u4fe1\u3082\u3042\u308a\u307e\u305b\u3093\u3002\u3042\u304f\u307e\u3067\u3082\u53c2\u8003\u3068\u3044\u3046\u4e8b\u306b\u3057\u3066\u3044\u305f\u3060\u3044\u3066\u9593\u9055\u3044\u306a\u3069\u304c\u3042\u308c\u3070\u30b3\u30e1\u30f3\u30c8\u8cb0\u3048\u308b\u3068\u5b09\u3057\u3044\u3067\u3059\u3002<\/p>\n

\u3010\u7b2c\uff11\u7ae0\u6f14\u7fd2\u554f\u984c\u3011<\/p>\n

\u7b2c\uff11\u554f<\/p>\n

\n
#!\/usr\/bin\/env python\r\n#-*- coding: utf-8 -*-\r\n\r\nfrom __future__ import division\r\n\r\ndef main():\r\n    print 12 \/ (4 + 1)\r\n\r\nif __name__ == '__main__':\r\n    main()<\/code><\/pre>\n<\/div>\n
\u7b2c\uff12\u554f<\/p>\n
\n
print 26 ** 100<\/code><\/pre>\n<\/div>\n
\u7b2c\uff13\u554f<\/p>\n
\n
>>> ['Monty', 'Python'] * 20\r\n['Monty', 'Python'] * 20\r\n['Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python', 'Monty', 'Python']<\/code><\/pre>\n<\/div>\n
\u7b2c\uff14\u554f<\/p>\n
\n
#!\/usr\/bin\/env python\r\n#-*- coding: utf-8 -*-\r\n\r\nfrom nltk.book import *\r\n\r\ndef main():\r\n    print len(text2)\r\n    print len(set(text2))\r\n\r\nif __name__ == '__main__':\r\n    main()\r\n<\/code><\/pre>\n<\/div>\n
\u7d50\u679c\u3068\u3057\u3066\u306ftext2\u306b\u542b\u307e\u308c\u3066\u3044\u308b\u5358\u8a9e\u306e\u6570\u306f141,576\u500b\u3002\u91cd\u8907\u3092\u7701\u304f\u30686,833\u500b\u3002<\/p>\n
\u7b2c\uff15\u554f<\/p>\n
\n
---------------------------------------------------------------------------------\r\n|\u30b8\u30e3\u30f3\u30eb                 | \u30c8\u30fc\u30af\u30f3\u6570 | \u7570\u306a\u308a\u30a2\u30a4\u30c6\u30e0\u6570 | \u8a9e\u5f59\u306e\u591a\u69d8\u6027 |\r\n---------------------------------------------------------------------------------\r\n|\u30e6\u30fc\u30e2\u30a2(humor)    |     21,695|                  5,017|                 4.3|\r\n---------------------------------------------------------------------------------\r\n|\u30ed\u30de\u30f3\u30b9(romance) |     70,022|                  8,452|                8.3|\r\n---------------------------------------------------------------------------------<\/code><\/pre>\n<\/div>\n
\u30c8\u30fc\u30af\u30f3\u6570\/\u7570\u306a\u308a\u30a2\u30a4\u30c6\u30e0\u6570=\u8a9e\u5f59\u306e\u591a\u69d8\u6027\u3068\u3044\u3046\u8a08\u7b97\u5f0f\u3060\u304b\u3089\u30b9\u30b3\u30a2\u304c\u4f4e\u3044\u65b9\u304c\u8a9e\u5f59\u306f\u591a\u69d8\u6027\u306b\u5bcc\u3093\u3067\u3044\u308b\u3068\u3044\u3046\u4e8b\u3002<\/p>\n
\u3082\u3057\u30c8\u30fc\u30af\u30f3\u6570\u304c100\u3067\u3001\u73fe\u5b9f\u7684\u306b\u306f\u4e0d\u53ef\u80fd\u3060\u308d\u3046\u3051\u3069\u5168\u3066\u7570\u306a\u308b\u8a9e\u5f59\u3092\u4f7f\u3048\u3070\u7570\u306a\u308a\u30a2\u30a4\u30c6\u30e0\u6570\u3082100\u306b\u306a\u308a\u8a9e\u5f59\u306e\u591a\u69d8\u6027\u306f1\u306b\u306a\u308b\u304b\u3089\u3002<\/p>\n
\u3057\u305f\u304c\u3063\u3066\u3001\u30e6\u30fc\u30e2\u30a2\u306e\u65b9\u304c\u8a9e\u5f59\u306e\u591a\u69d8\u6027\u306b\u5bcc\u3093\u3067\u3044\u308b\u3002<\/p>\n
\u7b2c\uff16\u554f<\/p>\n
Sense and Sensibility\uff08\u5206\u5225\u3068\u591a\u611f\uff09\u3068\u3044\u3046\u672c\u306ftext2\u306e\u4e8b\u306a\u306e\u3060\u304c\u30de\u30ea\u30a2\u30f3\u306e\u30b9\u30da\u30eb\u304c\u5206\u304b\u3089\u306a\u3044\u306e\u3067\u691c\u7d22\u3057\u305f\u3002<\/p>\n
\n
print [w for w in set(text2) if w.startswith('M')]<\/code><\/pre>\n<\/div>\n
\u3053\u308c\u3089\u304c\u62bd\u51fa\u3055\u308c\u305f\u3051\u3069\u3001\u5f53\u3066\u306f\u307e\u308a\u305d\u3046\u306a\u306e\u306fMarianne\u3060\u3051\u304b\u306a\u3002<\/p>\n
[‘Mansion’, ‘Magna’, ‘Me’, ‘Ma’, ‘Mr’, ‘My’, ‘ME’, ‘MY’, ‘Michaelmas’, ‘Midsummer’, ‘Monday’, ‘May’, ‘M’, ‘Many’, ‘MADAM’, ‘Madam’, ‘MIND’, ‘MAY’, ‘Mind’, ‘Mine’, ‘Misses’, ‘Mary’, ‘Marlborough’, ‘Mama’, ‘Most’, ‘Mrs’, ‘MUST’, ‘Music’, ‘MONTH’, ‘Must’, ‘Middletons’, ‘Misery’, ‘Margaret’, ‘Men’, ‘Mab’, ‘Mistress’, ‘Middleton’, ‘Mamma’, ‘Much’, ‘Martha’, ‘Marianne’, ‘Mid’, ‘Morton’, ‘Master’, ‘March’, ‘More’, ‘Mall’, ‘Miss’, ‘Months’]<\/p>\n
\u3053\u308c\u3089\uff14\u4eba\u306e\u540d\u524d\u3092\u914d\u5217\u306b\u5165\u308c\u3066dispersion_plot\u30e1\u30bd\u30c3\u30c9\u306b\u6e21\u3059\u3002<\/p>\n
\n
print text2.dispersion_plot(['Elinor', 'Marianne', 'Edward', 'Willoughby'])<\/code><\/pre>\n<\/div>\n
\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30d7\u30ed\u30c3\u30c8\u304c\u8868\u793a\u3055\u308c\u305f\u3002<\/p>\n
<\/div>\n
\u3053\u306e\u5c0f\u8aac\u306e\u4e2d\u3067\u7537\u6027\u3068\u5973\u6027\u306e\u6f14\u3058\u308b\u5f79\u5272\u306e\u9055\u3044\u3092\u4f55\u304b\u767a\u898b\u3067\u304d\u308b\u304b\uff1f\u3068\u3044\u3046\u554f\u3044\u304c\u3042\u308b\u3093\u3060\u3051\u3069\u3001\u7537\u6027\u306f\u30a8\u30c9\u30ef\u30fc\u30c9\u3060\u3051\u3063\u307d\u3044\u3002<\/p>\n
\u30a8\u30ea\u30ca\u3068\u30de\u30ea\u30a2\u30f3\u304c\u4e3b\u4eba\u516c\u7684\u306a\u5f79\u5272\u3067\u30a8\u30c9\u30ef\u30fc\u30c9\u3068\u30a6\u30a3\u30ed\u30d3\u30fc\u304c\u5c11\u3057\u8107\u5f79\u7684\u306a\u5f79\u5272\u3068\u3044\u3046\u306e\u306f\u3059\u3050\u306b\u5206\u304b\u308b\u3002\u3059\u3050\u306b\u601d\u3044\u3064\u304f\u306e\u306f\u3053\u308c\u304f\u3089\u3044\u306a\u306e\u3067\u5973\u6027\u304c\u4e2d\u5fc3\u7684\u306a\u5f79\u5272\u3067\u7537\u6027\u304c\u5973\u6027\u3092\u5f15\u304d\u7acb\u3066\u308b\u305f\u3081\u306e\u8107\u5f79\u3068\u3057\u3066\u306e\u5f79\u5272\u3092\u679c\u305f\u3057\u3066\u3044\u308b\u3068\u3044\u3046\u4e8b\u306b\u3057\u3066\u304a\u3053\u3046\u3002<\/p>\n
\u3055\u3089\u306b\u3001\u3053\u306e\u60c5\u5831\u304b\u3089\u300c\u30ab\u30c3\u30d7\u30eb\u3092\u7279\u5b9a\u305b\u3088\uff01\u300d\u3068\u306e\u8cea\u554f\u304c\u3042\u308b\u3002<\/p>\n
\u4e00\u822c\u7684\u306b\u8003\u3048\u3066\u7570\u6027\u306e\u30ab\u30c3\u30d7\u30eb\u3068\u3059\u308b\u3068\u30a8\u30c9\u30ef\u30fc\u30c9\u3092\u4e2d\u5fc3\u306b\u6b8b\u308a\u306e\uff13\u4eba\u3092\u8003\u3048\u308b\u4e8b\u306b\u306a\u308b\u3002<\/p>\n
\u30a8\u30c9\u30ef\u30fc\u30c9\u3068\u30a6\u30a3\u30ed\u30d3\u30fc\u306f\u307b\u3068\u3093\u3069\u540c\u3058\u6642\u9593\u306b\u767b\u5834\u3057\u3066\u3044\u306a\u3044\u306e\u3067\u304a\u305d\u3089\u304f\u9055\u3046\u3060\u308d\u3046\u3002<\/p>\n
\u30a8\u30ea\u30ca\u304b\u30de\u30ea\u30a2\u30f3\u304b\u306f\u3053\u306e\u60c5\u5831\u3060\u3051\u3067\u306f\u7279\u5b9a\u3067\u304d\u306a\u3044\u3088\u306d\u3002<\/p>\n
\u3082\u3057\u540c\u6027\u306e\u30ab\u30c3\u30d7\u30eb\u3068\u3044\u3046\u4e8b\u3067\u3042\u308c\u3070\u4e07\u904d\u306a\u304f\u767b\u5834\u3057\u3066\u3044\u308b\u30a8\u30ea\u30ca\u3068\u30de\u30ea\u30a2\u30f3\u3060\u308d\u3046\u3002<\/p>\n
\u30a8\u30ea\u30ca\u3068\u30de\u30ea\u30a2\u30f3\u304c\u30a8\u30c9\u30ef\u30fc\u30c9\u3092\u5de1\u3063\u3066\u604b\u6575\u306e\u72b6\u614b\u306b\u306a\u3063\u3066\u3044\u3066\u3001\u3067\u3082\u5b9f\u306f\u30a8\u30c9\u30ef\u30fc\u30c9\u306b\u306f\u30a6\u30a3\u30ed\u30d3\u30fc\u3068\u3044\u3046\u604b\u4eba\u304c\u3044\u308b\u3068\u3044\u3046\u8a2d\u5b9a\u3082\u3042\u308a\u5f97\u308b\u3002<\/p>\n
\u7d50\u8ad6\u3068\u3057\u3066\u306f\u3053\u308c\u3060\u3051\u3067\u306f\u306f\u3063\u304d\u308a\u3068\u306f\u5206\u304b\u3089\u306a\u3044\u3002<\/p>\n
\u3010\u8ffd\u8a18\u3011Wikipedia\u3067\u3053\u306e\u5c0f\u8aac\u306e\u4e8b\u3092\u8abf\u3079\u3066\u30a8\u30ea\u30ca\u3068\u30a8\u30c9\u30ef\u30fc\u30c9\u304c\u604b\u4eba\u3060\u3068\u3044\u3046\u4e8b\u304c\u5206\u304b\u308a\u307e\u3057\u305f\u3002\u3061\u306a\u307f\u306b\u30a8\u30ea\u30ca\u3068\u30de\u30ea\u30a2\u30f3\u304c\u59c9\u59b9\u3067\u30a6\u30a3\u30ed\u30d3\u30fc\u3082\u7537\u6027\u3060\u305d\u3046\u3067\u3059\u3002Willoughby\u3067\u753b\u50cf\u691c\u7d22\u3059\u308b\u3068\u5727\u5012\u7684\u306b\u5973\u6027\u304c\u591a\u304f\u51fa\u3066\u304d\u305f\u3093\u3067\u3059\u3051\u3069\u306d\u3002<\/p>\n
\u7b2c\uff17\u554f<\/p>\n
\u3053\u308c\u306f\u4f55\u3082\u96e3\u3057\u304f\u306a\u3044\u3002<\/p>\n
\n
print text5.collocations()<\/code><\/pre>\n<\/div>\n
\u7b2c\uff18\u554f<\/p>\n
len(set(text4))\u3068\u3044\u3046\u5f0f\u306e\u76ee\u7684\u3068\u610f\u5473\u306f\uff1f<\/p>\n
\u76ee\u7684\u306f\u3001text4\u306e\u4e2d\u306b\u542b\u307e\u308c\u3066\u3044\u308b\u5358\u8a9e\u306e\u7a2e\u985e\u306e\u6570\u3092\u8abf\u3079\u308b\u4e8b\u3002<\/p>\n
set\u95a2\u6570\u3067\uff12\u56de\u4ee5\u4e0a\u767b\u5834\u3059\u308b\u5358\u8a9e\u3092\uff11\u3064\u306b\u307e\u3068\u3081\u3066len\u95a2\u6570\u3067\u5358\u8a9e\u306e\u6570\u3092\u6570\u3048\u308b\u3002<\/p>\n
\u3010\u5165\u9580\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u89e3\u7b54\uff08\u7b2c\uff11\u7ae0\uff09\u3011<\/p>\n