{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"inputHidden": false,
"outputHidden": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Hello World!\n",
"Hello Again\n",
"I like typing this.\n",
"This is fun.\n",
"Yay! Printing.\n",
"I'd much rather you 'not'.\n",
"I \"said\" do not touch this.\n"
]
}
],
"source": [
"print(\"Hello World!\")\n",
"print(\"Hello Again\")\n",
"print(\"I like typing this.\")\n",
"print(\"This is fun.\")\n",
"print('Yay! Printing.')\n",
"print(\"I'd much rather you 'not'.\")\n",
"print('I \"said\" do not touch this.')"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"inputHidden": false,
"outputHidden": false
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"\n",
"\n",
""
],
"text/plain": [
""
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import requests\n",
"import re\n",
"from gensim.parsing.preprocessing import remove_stopwords\n",
"from gensim.corpora.dictionary import Dictionary\n",
"from gensim.models.ldamodel import LdaModel\n",
"import pyLDAvis\n",
"import pyLDAvis.gensim\n",
"\n",
"pride_and_prejudice = requests.get(\"http://www.gutenberg.org/cache/epub/42671/pg42671.txt\").text\n",
"paragraphs = [re.split(r\"\\W+\",remove_stopwords(paragraph)) for paragraph in re.split(r\"\\r\\n\\r\\n\",re.sub(r\"CHAPTER [XIV]+\\.\",\"\",pride_and_prejudice[pride_and_prejudice.index(\"CHAPTER I.\"):pride_and_prejudice.index(\"*** END OF THE PROJECT GUTENBERG EBOOK PRIDE AND PREJUDICE ***\")]))]\n",
"d = Dictionary(paragraphs)\n",
"c = [d.doc2bow(paragraph) for paragraph in paragraphs]\n",
"m = LdaModel(c,num_topics = 15, alpha='auto')\n",
"pyLDAvis.display(pyLDAvis.gensim.prepare(m,c,d))\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"inputHidden": false,
"outputHidden": false
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernel_info": {
"name": "python3"
},
"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": "3.6.6"
},
"nteract": {
"version": "0.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 4
}