Lemmatization_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=\"Tesla founder Elon Musk has launched tech startup Neuralink.\"\n",
    "\n",
    "# returns doc container with attributes \n",
    "doc=nlp(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# loop through doc\n",
    "# return tokens with lemmas_ (actual english language word)\n",
    "tokenized=[(token.text,token.lemma_) for token in doc]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[('Tesla', 'tesla'), ('founder', 'founder'), ('Elon', 'Elon'), ('Musk', 'Musk'), ('has', 'have'), ('launched', 'launch'), ('tech', 'tech'), ('startup', 'startup'), ('Neuralink', 'Neuralink'), ('.', '.')]\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
}