Word_Tokenization_spaCy.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# spacy import convention\n",
    "import spacy\n",
    "\n",
    "# load the english model into nlp object.\n",
    "nlp=spacy.load('en_core_web_sm') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Sample text\n",
    "text=\"\"\"Success isn't easy, and that's a good thing - at least in business. \\\n",
    "If it was easy, everybody would be doing it and your competition would be outrageous!\"\"\"\n",
    "\n",
    "# returns doc container with many attributes.\n",
    "doc=nlp(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# loop through doc and return tokens with .text attribute\n",
    "# using list comprehension\n",
    "tokenized=[token.text for token in doc]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Success', 'is', \"n't\", 'easy', ',', 'and', 'that', \"'s\", 'a', 'good', 'thing', '-', 'at', 'least', 'in', 'business', '.', 'If', 'it', 'was', 'easy', ',', 'everybody', 'would', 'be', 'doing', 'it', 'and', 'your', 'competition', 'would', 'be', 'outrageous', '!']\n"
     ]
    }
   ],
   "source": [
    "# print result.\n",
    "print(tokenized)"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}