NLP ML (Built-In)

3 Tokenization.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tokenization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>body_text</th>\n",
       "      <th>body_text_clean</th>\n",
       "      <th>body_text_tokenized</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ham</td>\n",
       "      <td>I've been searching for the right words to tha...</td>\n",
       "      <td>Ive been searching for the right words to than...</td>\n",
       "      <td>[ive, been, searching, for, the, right, words,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>spam</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "      <td>Free entry in 2 a wkly comp to win FA Cup fina...</td>\n",
       "      <td>[free, entry, in, 2, a, wkly, comp, to, win, f...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>ham</td>\n",
       "      <td>Nah I don't think he goes to usf, he lives aro...</td>\n",
       "      <td>Nah I dont think he goes to usf he lives aroun...</td>\n",
       "      <td>[nah, i, dont, think, he, goes, to, usf, he, l...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>ham</td>\n",
       "      <td>Even my brother is not like to speak with me. ...</td>\n",
       "      <td>Even my brother is not like to speak with me T...</td>\n",
       "      <td>[even, my, brother, is, not, like, to, speak, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>ham</td>\n",
       "      <td>I HAVE A DATE ON SUNDAY WITH WILL!!</td>\n",
       "      <td>I HAVE A DATE ON SUNDAY WITH WILL</td>\n",
       "      <td>[i, have, a, date, on, sunday, with, will]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  label                                          body_text  \\\n",
       "0   ham  I've been searching for the right words to tha...   \n",
       "1  spam  Free entry in 2 a wkly comp to win FA Cup fina...   \n",
       "2   ham  Nah I don't think he goes to usf, he lives aro...   \n",
       "3   ham  Even my brother is not like to speak with me. ...   \n",
       "4   ham                I HAVE A DATE ON SUNDAY WITH WILL!!   \n",
       "\n",
       "                                     body_text_clean  \\\n",
       "0  Ive been searching for the right words to than...   \n",
       "1  Free entry in 2 a wkly comp to win FA Cup fina...   \n",
       "2  Nah I dont think he goes to usf he lives aroun...   \n",
       "3  Even my brother is not like to speak with me T...   \n",
       "4                  I HAVE A DATE ON SUNDAY WITH WILL   \n",
       "\n",
       "                                 body_text_tokenized  \n",
       "0  [ive, been, searching, for, the, right, words,...  \n",
       "1  [free, entry, in, 2, a, wkly, comp, to, win, f...  \n",
       "2  [nah, i, dont, think, he, goes, to, usf, he, l...  \n",
       "3  [even, my, brother, is, not, like, to, speak, ...  \n",
       "4         [i, have, a, date, on, sunday, with, will]  "
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import re\n",
    "\n",
    "# Function to Tokenize words\n",
    "def tokenize(text):\n",
    "    tokens = re.split('\\W+', text) #W+ means that either a word character (A-Za-z0-9_) or a dash (-) can go there.\n",
    "    return tokens\n",
    "\n",
    "data['body_text_tokenized'] = data['body_text_clean'].apply(lambda x: tokenize(x.lower())) \n",
    "#We convert to lower as Python is case-sensitive. \n",
    "\n",
    "data.head()"
   ]
  }
 ],
 "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"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  },
  "varInspector": {
   "cols": {
    "lenName": 16,
    "lenType": 16,
    "lenVar": 40
   },
   "kernels_config": {
    "python": {
     "delete_cmd_postfix": "",
     "delete_cmd_prefix": "del ",
     "library": "var_list.py",
     "varRefreshCmd": "print(var_dic_list())"
    },
    "r": {
     "delete_cmd_postfix": ") ",
     "delete_cmd_prefix": "rm(",
     "library": "var_list.r",
     "varRefreshCmd": "cat(var_dic_list()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}