{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Topic-Term shape: (20, 14567)\n",
"Doc-Topic shape: (2000, 20)\n"
]
}
],
"source": [
"import json\n",
"import numpy as np\n",
"\n",
"def load_R_model(filename):\n",
" with open(filename, 'r') as j:\n",
" data_input = json.load(j)\n",
" data = {'topic_term_dists': data_input['phi'], \n",
" 'doc_topic_dists': data_input['theta'],\n",
" 'doc_lengths': data_input['doc.length'],\n",
" 'vocab': data_input['vocab'],\n",
" 'term_frequency': data_input['term.frequency']}\n",
" return data\n",
"\n",
"movies_model_data = load_R_model('movie_reviews_input.json')\n",
"\n",
"print('Topic-Term shape: %s' % str(np.array(movies_model_data['topic_term_dists']).shape))\n",
"print('Doc-Topic shape: %s' % str(np.array(movies_model_data['doc_topic_dists']).shape))"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"import pyLDAvis\n",
"movies_vis_data = pyLDAvis.prepare(**movies_model_data)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"import warnings\n",
"warnings.filterwarnings(\"ignore\", category=DeprecationWarning)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"\n",
"\n",
"\n",
""
],
"text/plain": [
""
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pyLDAvis.display(movies_vis_data)"
]
}
],
"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": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}