soundex-nlp.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "def soundex(name, len=4):\n",
    "    \"\"\" soundex module conforming to Knuth's algorithm\n",
    "        implementation 2000-12-24 by Gregory Jorgensen\n",
    "        public domain\n",
    "    \"\"\"\n",
    "\n",
    "    # digits holds the soundex values for the alphabet\n",
    "    digits = '01230120022455012623010202'\n",
    "    sndx = ''\n",
    "    fc = ''\n",
    "\n",
    "    # translate alpha chars in name to soundex digits\n",
    "    for c in name.upper():\n",
    "        if c.isalpha():\n",
    "            if not fc: fc = c   # remember first letter\n",
    "            d = digits[ord(c)-ord('A')]\n",
    "            # duplicate consecutive soundex digits are skipped\n",
    "            if not sndx or (d != sndx[-1]):\n",
    "                sndx += d\n",
    "\n",
    "    # replace first digit with first alpha character\n",
    "    sndx = fc + sndx[1:]\n",
    "\n",
    "    # remove all 0s from the soundex code\n",
    "    sndx = sndx.replace('0','')\n",
    "\n",
    "    # return soundex code padded to len characters\n",
    "    return (sndx + (len * '0'))[:len]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'F460'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "soundex('flower')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'F460'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "soundex('flour')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}