Post #1 of the NLP series

NLP_Post1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "425688a2-2705-464a-b770-6d2c9d3a4eab",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['My', 'name', 'is', 'John.', 'What', 'is', 'your', 'name?']\n"
     ]
    }
   ],
   "source": [
    "text = \"My name is John. What is your name?\"\n",
    "token = text.split()\n",
    "print(token)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6d5a6ec9-76cc-4974-838a-b102db531038",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['my', 'name', 'is', 'john', '.', 'what', 'is', 'your', 'name', '?']\n"
     ]
    }
   ],
   "source": [
    "import torchtext\n",
    "\n",
    "tokenizer = torchtext.data.utils.get_tokenizer(\"basic_english\")\n",
    "print(tokenizer(text))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "57219c34-6f7d-42f2-9743-4b17f8c69f8e",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['my', 'name', 'is', 'john', '.', 'what', 'your', '?']\n"
     ]
    }
   ],
   "source": [
    "import collections\n",
    "token = tokenizer(text)\n",
    "counter = collections.Counter(token)\n",
    "vocabulary = [t for t in counter.keys()]\n",
    "print(vocabulary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "12b58f2c-d5d8-474c-86a0-610ff0e4c71b",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[0, 1, 2, 3, 4, 5, 2, 6, 1, 7]\n"
     ]
    }
   ],
   "source": [
    "stois = dict()\n",
    "for idx, t in enumerate(vocabulary):\n",
    "    stois[t] = idx\n",
    "encoded_text = [stois[t] for t in token]\n",
    "print(encoded_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "99b6c8dd-df0b-4b9a-9914-0fc5f3b47837",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "my name is john . what is your name ?\n"
     ]
    }
   ],
   "source": [
    "decoded_text = \" \".join([vocabulary[idx] for idx in encoded_text])\n",
    "print(decoded_text)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "language": "python",
   "name": "venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}