make-letter-frequency-treemap.ipynb

   1 {
   2  "cells": [
   3   {
   4    "cell_type": "code",
   5    "execution_count": 32,
   6    "metadata": {},
   7    "outputs": [],
   8    "source": [
   9     "# libraries\n",
  10     "import matplotlib.pyplot as plt\n",
  11     "%matplotlib inline\n",
  12     "\n",
  13     "import squarify    # pip install squarify (algorithm for treemap)\n",
  14     "\n",
  15     "from support.language_models import *\n",
  16     "from support.utilities import *"
  17    ]
  18   },
  19   {
  20    "cell_type": "code",
  21    "execution_count": 3,
  22    "metadata": {},
  23    "outputs": [
  24     {
  25      "data": {
  26       "text/plain": [
  27        "defaultdict(int,\n",
  28        "            {'a': 0.07822525209432887,\n",
  29        "             'b': 0.014829998223636929,\n",
  30        "             'c': 0.02251879345845122,\n",
  31        "             'd': 0.042759915992231244,\n",
  32        "             'e': 0.12099426536374505,\n",
  33        "             'f': 0.02159693603704411,\n",
  34        "             'g': 0.018815084434702378,\n",
  35        "             'h': 0.06645305621431015,\n",
  36        "             'i': 0.06723047441023709,\n",
  37        "             'j': 0.0010659774441790274,\n",
  38        "             'k': 0.00865805425839555,\n",
  39        "             'l': 0.04134042154867259,\n",
  40        "             'm': 0.027483193578407596,\n",
  41        "             'n': 0.06693265828344594,\n",
  42        "             'o': 0.08052207518149467,\n",
  43        "             'p': 0.016070260346516884,\n",
  44        "             'q': 0.0008776478463153873,\n",
  45        "             'r': 0.059626906298523796,\n",
  46        "             's': 0.06455443850567806,\n",
  47        "             't': 0.08946868868814231,\n",
  48        "             'u': 0.03036719004738724,\n",
  49        "             'v': 0.010421489620086533,\n",
  50        "             'w': 0.024603665947343364,\n",
  51        "             'x': 0.0011832844394584982,\n",
  52        "             'y': 0.022829377693572104,\n",
  53        "             'z': 0.0005708940436934243})"
  54       ]
  55      },
  56      "execution_count": 3,
  57      "metadata": {},
  58      "output_type": "execute_result"
  59     }
  60    ],
  61    "source": [
  62     "normalised_english_counts"
  63    ]
  64   },
  65   {
  66    "cell_type": "code",
  67    "execution_count": 11,
  68    "metadata": {
  69     "scrolled": true
  70    },
  71    "outputs": [
  72     {
  73      "data": {
  74       "text/plain": [
  75        "(['e',\n",
  76        "  't',\n",
  77        "  'o',\n",
  78        "  'a',\n",
  79        "  'i',\n",
  80        "  'n',\n",
  81        "  'h',\n",
  82        "  's',\n",
  83        "  'r',\n",
  84        "  'd',\n",
  85        "  'l',\n",
  86        "  'u',\n",
  87        "  'm',\n",
  88        "  'w',\n",
  89        "  'y',\n",
  90        "  'c',\n",
  91        "  'f',\n",
  92        "  'g',\n",
  93        "  'p',\n",
  94        "  'b',\n",
  95        "  'v',\n",
  96        "  'k',\n",
  97        "  'x',\n",
  98        "  'j',\n",
  99        "  'q',\n",
 100        "  'z'],\n",
 101        " [0.12099426536374505,\n",
 102        "  0.08946868868814231,\n",
 103        "  0.08052207518149467,\n",
 104        "  0.07822525209432887,\n",
 105        "  0.06723047441023709,\n",
 106        "  0.06693265828344594,\n",
 107        "  0.06645305621431015,\n",
 108        "  0.06455443850567806,\n",
 109        "  0.059626906298523796,\n",
 110        "  0.042759915992231244,\n",
 111        "  0.04134042154867259,\n",
 112        "  0.03036719004738724,\n",
 113        "  0.027483193578407596,\n",
 114        "  0.024603665947343364,\n",
 115        "  0.022829377693572104,\n",
 116        "  0.02251879345845122,\n",
 117        "  0.02159693603704411,\n",
 118        "  0.018815084434702378,\n",
 119        "  0.016070260346516884,\n",
 120        "  0.014829998223636929,\n",
 121        "  0.010421489620086533,\n",
 122        "  0.00865805425839555,\n",
 123        "  0.0011832844394584982,\n",
 124        "  0.0010659774441790274,\n",
 125        "  0.0008776478463153873,\n",
 126        "  0.0005708940436934243])"
 127       ]
 128      },
 129      "execution_count": 11,
 130      "metadata": {},
 131      "output_type": "execute_result"
 132     }
 133    ],
 134    "source": [
 135     "ls = sorted(normalised_english_counts, key=normalised_english_counts.get, reverse=True)\n",
 136     "cs = [normalised_english_counts[l] for l in ls]\n",
 137     "ls, cs"
 138    ]
 139   },
 140   {
 141    "cell_type": "code",
 142    "execution_count": 29,
 143    "metadata": {},
 144    "outputs": [
 145     {
 146      "data": {
 147       "image/png": "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\n",
 148       "text/plain": [
 149        "<matplotlib.figure.Figure at 0x7f1224d9be10>"
 150       ]
 151      },
 152      "metadata": {},
 153      "output_type": "display_data"
 154     }
 155    ],
 156    "source": [
 157     "# If you have 2 lists\n",
 158     "plt.rcParams[\"figure.figsize\"] = (4,4)\n",
 159     "squarify.plot(sizes=cs, label=ls, alpha=.7 )\n",
 160     "plt.axis('off')\n",
 161     "plt.savefig('letter-treemap.png', bbox_inches='tight')\n",
 162     "plt.show()"
 163    ]
 164   },
 165   {
 166    "cell_type": "code",
 167    "execution_count": 42,
 168    "metadata": {},
 169    "outputs": [
 170     {
 171      "data": {
 172       "text/plain": [
 173        "'treattlpis'"
 174       ]
 175      },
 176      "execution_count": 42,
 177      "metadata": {},
 178      "output_type": "execute_result"
 179     }
 180    ],
 181    "source": [
 182     "cat(random_english_letter() for _ in range(10))"
 183    ]
 184   },
 185   {
 186    "cell_type": "code",
 187    "execution_count": 46,
 188    "metadata": {},
 189    "outputs": [
 190     {
 191      "data": {
 192       "text/plain": [
 193        "'lbycjleuqz'"
 194       ]
 195      },
 196      "execution_count": 46,
 197      "metadata": {},
 198      "output_type": "execute_result"
 199     }
 200    ],
 201    "source": [
 202     "import random\n",
 203     "import string\n",
 204     "\n",
 205     "cat(random.choices(string.ascii_lowercase, k=10))"
 206    ]
 207   },
 208   {
 209    "cell_type": "code",
 210    "execution_count": null,
 211    "metadata": {},
 212    "outputs": [],
 213    "source": []
 214   }
 215  ],
 216  "metadata": {
 217   "kernelspec": {
 218    "display_name": "Python 3",
 219    "language": "python",
 220    "name": "python3"
 221   },
 222   "language_info": {
 223    "codemirror_mode": {
 224     "name": "ipython",
 225     "version": 3
 226    },
 227    "file_extension": ".py",
 228    "mimetype": "text/x-python",
 229    "name": "python",
 230    "nbconvert_exporter": "python",
 231    "pygments_lexer": "ipython3",
 232    "version": "3.6.3"
 233   }
 234  },
 235  "nbformat": 4,
 236  "nbformat_minor": 2
 237 }