自然言語処理100本ノック00-09 http://www.cl.ecei.tohoku.ac.jp/nlp100/

NL100_0.ipynb

{
  "cells": [
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text0 = 'stressed'\nprint(text0[::-1])",
      "execution_count": null,
      "outputs": []
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text1 = 'パタトクカシーー'\nprint(text1[::2])",
      "execution_count": 20,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "パトカー\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text2_1 = 'パトカー'\ntext2_2 = 'タクシー'\nans2 =''\nfor (a, b) in zip(text2_1, text2_2):\n    ans2 += a\n    ans2 += b\nprint(ans2)",
      "execution_count": 3,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "パタトクカシーー\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text3 = \"Now I need a drink, alcoholic of course, after the heavy lectures involving quantum mechanics.\"\ntext3 = text3.replace('.', \"\")\ntext3 = text3.replace(',', \"\")\ntext3 = text3.split()\ncount = []\nfor str in text3:\n    count.append(len(str))\nprint(count)",
      "execution_count": 4,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "[3, 1, 4, 1, 5, 9, 2, 6, 5, 3, 5, 8, 9, 7, 9]\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text4 = \"Hi He Lied Because Boron Could Not Oxidize Fluorine. New Nations Might Also Sign Peace Security Clause. Arthur King Can.\"\ntext4 = text4.split()\nindex1 = [1, 5, 6, 7, 8, 9, 15, 16, 19]\ndict = {}\nfor element in text4:\n    if text4.index(element) + 1 in index1:\n        dict[element[:1]] = text4.index(element) + 1\n    else:\n        dict[element[:2]] = text4.index(element) + 1\nprint(dict)",
      "execution_count": 5,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "{'H': 1, 'He': 2, 'Li': 3, 'Be': 4, 'B': 5, 'C': 6, 'N': 7, 'O': 8, 'F': 9, 'Ne': 10, 'Na': 11, 'Mi': 12, 'Al': 13, 'Si': 14, 'P': 15, 'S': 16, 'Cl': 17, 'Ar': 18, 'K': 19, 'Ca': 20}\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "scrolled": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "st = \"I am an NLPer\"\ndef ngram(input, n):\n    ret = []\n    for i in range(len(input)-n+1):\n        ret.append(input[i:i+n])\n    return ret\nprint(ngram(st,2))\nst = st.split()\nprint(ngram(st,2))",
      "execution_count": 6,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "['I ', ' a', 'am', 'm ', ' a', 'an', 'n ', ' N', 'NL', 'LP', 'Pe', 'er']\n[['I', 'am'], ['am', 'an'], ['an', 'NLPer']]\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "text6_1 = \"paraparaparadise\"\ntext6_2 = \"paragraph\"\nX = set(ngram(text6_1,2))\nY = set(ngram(text6_2,2))\n\nprint(X|Y)\nprint(X&Y)\nprint(X-Y)\n\nprint(\"se\" in X)\nprint(\"se\" in Y)",
      "execution_count": 7,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "{'ra', 'se', 'ag', 'gr', 'ad', 'ap', 'di', 'is', 'ar', 'pa', 'ph'}\n{'pa', 'ar', 'ra', 'ap'}\n{'di', 'se', 'ad', 'is'}\nTrue\nFalse\n"
        }
      ]
    },
    {
      "metadata": {
        "code_folding": [],
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "x = 12\ny = u'気温'\nz = 22.4\n\ndef function(x, y, z):\n    return repr(x) + '時の' + repr(y) + u'は' + repr(z)\n\nprint(function(x, y, z))",
      "execution_count": 8,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "12時の'気温'は22.4\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "str = \"Atbash is a simple substitution cipher for the Hebrew alphabet.\"\n\ndef cipher(input):\n    ret = \"\"\n    for char in input:\n        ret += chr(219-ord(char)) if char.islower() else char\n    return ret\n\nstr = cipher(str)\nprint(str)\nstr = cipher(str)\nprint(str)\n",
      "execution_count": 9,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "Agyzhs rh z hrnkov hfyhgrgfgrlm xrksvi uli gsv Hvyivd zokszyvg.\nAtbash is a simple substitution cipher for the Hebrew alphabet.\n"
        }
      ]
    },
    {
      "metadata": {
        "collapsed": false,
        "trusted": true
      },
      "cell_type": "code",
      "source": "import random\n\n\ndef word_typoglycemia(word):\n    if len(word) <= 4:\n        return word\n\n    mid_list = list(word[1:-1])\n    while mid_list == list(word[1:-1]):\n        random.shuffle(mid_list)\n    return word[0] + \"\".join(mid_list) + word[-1]\n\n\ndef str_typoglycemia(str):\n    shuffled_list = []\n    for word in str.split():\n        shuffled_list.append(word_typoglycemia(word))\n    return \" \".join(shuffled_list)\n\n\nstr = \"I couldn't believe that I could actually understand \\\n what I was reading : the phenomenal power of the human mind .\"\n\nprint(str_typoglycemia(str))\n",
      "execution_count": 10,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "I clu'ondt beilvee that I cloud acullaty urtnandesd what I was rndeiag : the paneohmnel poewr of the huamn mind .\n"
        }
      ]
    }
  ],
  "metadata": {
    "_draft": {
      "nbviewer_url": "https://gist.github.com/5c60324b7f26cbf516f6c2c6fcac033e"
    },
    "gist": {
      "id": "5c60324b7f26cbf516f6c2c6fcac033e",
      "data": {
        "description": "自然言語処理100本ノック00-09 http://www.cl.ecei.tohoku.ac.jp/nlp100/",
        "public": true
      }
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.0",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "toc": {
      "threshold": 4,
      "number_sections": true,
      "toc_cell": false,
      "toc_window_display": false,
      "toc_section_display": "block",
      "sideBar": true,
      "navigate_menu": true,
      "moveMenuLeft": true,
      "widenNotebook": false,
      "colors": {
        "hover_highlight": "#DAA520",
        "selected_highlight": "#FFD700",
        "running_highlight": "#FF0000"
      },
      "nav_menu": {
        "height": "12px",
        "width": "252px"
      }
    },
    "varInspector": {
      "window_display": true,
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "library": "var_list.py",
          "delete_cmd_prefix": "del ",
          "delete_cmd_postfix": "",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "library": "var_list.r",
          "delete_cmd_prefix": "rm(",
          "delete_cmd_postfix": ") ",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ],
      "oldHeight": 122,
      "position": {
        "height": "144px",
        "left": "auto",
        "right": "20px",
        "top": "120px",
        "width": "350px"
      },
      "varInspector_section_display": "block"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}

NL100_1.ipynb