Thing for book thinging of stuff with the thing.

bookthing.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "0727e4f1-6539-45b0-8d05-5e1abb26ea28",
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('datasets/Book.txt', 'r') as file:\n",
    "    text = file.read()\n",
    "text = text.replace('\\n', ' ')\n",
    "sentences = text.split('.')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "59b268e1-f155-47ea-8a13-42d4d87903f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "new_sentences = []\n",
    "for sentence in sentences:\n",
    "    sentence = sentence.strip()\n",
    "    if len(sentence) > 80:\n",
    "        # Split on comma\n",
    "        parts = [part.strip() for part in sentence.split(',')]\n",
    "        if len(parts) > 1:  # If sentence could be split\n",
    "            new_sentences.extend(parts)\n",
    "    else:\n",
    "        new_sentences.append(sentence)\n",
    "\n",
    "sentences = new_sentences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fb84a662-4cd2-40f4-985b-31fba70ec7f4",
   "metadata": {},
   "outputs": [],
   "source": [
    "[print(x) for x in sentences[:10]]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "86f9ef96-b7eb-43e8-adf7-82620db375af",
   "metadata": {},
   "outputs": [],
   "source": [
    "import nltk\n",
    "nltk.download('punkt')\n",
    "nltk.download('averaged_perceptron_tagger')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "47bacb44-3279-4417-a94c-7e2435b72918",
   "metadata": {},
   "outputs": [],
   "source": [
    "def count_descriptive_words(sentence):\n",
    "    words = nltk.word_tokenize(sentence)\n",
    "    tagged = nltk.pos_tag(words)\n",
    "    descriptive_count = sum(1 for word, tag in tagged if tag in ('JJ', 'JJR', 'JJS', 'RB', 'RBR', 'RBS'))\n",
    "    return descriptive_count\n",
    "descriptive_counts = [(sentence, count_descriptive_words(sentence)) for sentence in sentences]\n",
    "descriptive_counts = sorted(descriptive_counts, key=lambda x: x[1], reverse=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "1b81d8c9-a640-4d39-98b7-fdea3b622e12",
   "metadata": {},
   "outputs": [],
   "source": [
    "top_100 = descriptive_counts[:100]\n",
    "items = [x.encode('ascii', 'ignore').decode() for x, y in top_100]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "18d88cd9-b289-49d5-9b42-0dedb16ab57e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "with open('descriptive_sentences.jsonl', 'w') as file:\n",
    "    for item in items:\n",
    "        line = json.dumps({\"text\": item})\n",
    "        file.write(line + '\\n')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}