M388 suffixes and prefixes.ipynb

M388 suffixes and prefixes.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import re\nfrom nltk.util import bigrams\nfrom collections import Counter\nfrom beautifultable import BeautifulTable",
      "execution_count": 99,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "with open('protoElamTranslits20111120.txt') as f:\n    data = f.read().split('\\n')",
      "execution_count": 100,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "data[:15]",
      "execution_count": 101,
      "outputs": [
        {
          "data": {
            "text/plain": "['&P009331 = MDP 26S, 5233',\n '@obverse',\n '@column 1',\n '1. M010# , 2(N14)',\n '@reverse',\n '$ broken',\n '',\n '&P009342 = MDP 31, 003',\n '@obverse',\n '@column 1',\n '1. [...] ,',\n '2. x , 8(N14) 4(N01)',\n '3. M096~d , 4(N01) 2(N39B) 1(N24)#',\n '4. x , 5(N01)#',\n '@reverse']"
          },
          "execution_count": 101,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "line_re = re.compile(r\"\\d+\\.\")\ndamage_re = re.compile(r\"( x |\\[\\.\\.\\.\\])\")",
      "execution_count": 102,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# grab lines of text\nraw_lines = [line for line in data if line_re.match(line)]\n# reject lines with damage\ncomplete_lines = [line for line in raw_lines if not damage_re.search(line)]\n# remove line numerals\nlines = [line.split(' ', maxsplit=1)[1] for line in complete_lines if len(line.split(' ', maxsplit=1)) > 1]",
      "execution_count": 103,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "lines[:5]",
      "execution_count": 104,
      "outputs": [
        {
          "data": {
            "text/plain": "['M010# , 2(N14)',\n 'M096~d , 4(N01) 2(N39B) 1(N24)#',\n 'M388 , 9(N01)',\n 'M046 M254~b# , 1(N01)',\n 'M417~h , 3(N01)#']"
          },
          "execution_count": 104,
          "metadata": {},
          "output_type": "execute_result"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "# make one big line of signs\ncorpus = ' '.join(lines)\n# tokenize the line by spaces (naive)\nwords = corpus.split(' ')",
      "execution_count": 105,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "m388_re = re.compile(r\"M388\")\nm388_suffixes = Counter([word[1] for word in bigrams(words) if m388_re.search(word[0])])\nm388_prefixes = Counter([word[0] for word in bigrams(words) if m388_re.search(word[1])])",
      "execution_count": 106,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "t_m388 = BeautifulTable()\nt_m388.column_headers = [\"suffix\", \"count\", \"prefix\", \"count\"]\nfor row in zip(m388_suffixes.most_common(5), m388_prefixes.most_common(5)): \n    t_m388.append_row([item for duo in row for item in duo])\nt_m388.insert_column(2, ' ', [' ']*5)\nprint(t_m388)",
      "execution_count": 107,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": "+--------+-------+---+--------+-------+\n| suffix | count |   | prefix | count |\n+--------+-------+---+--------+-------+\n|   ,    |  93   |   | 1(N01) |  35   |\n+--------+-------+---+--------+-------+\n|  M218  |  13   |   |   ,    |  19   |\n+--------+-------+---+--------+-------+\n|  M066  |  11   |   |  M305  |  12   |\n+--------+-------+---+--------+-------+\n|  M387  |   7   |   | 2(N01) |  10   |\n+--------+-------+---+--------+-------+\n|  M347  |   7   |   |  M054  |  10   |\n+--------+-------+---+--------+-------+\n"
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.7",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "M388 suffixes and prefixes.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}