{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from spacy import displacy"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Prepared 22 documents.\n",
"They can be accessed using or_texts[n], being n an integer from 0 to 21.\n",
"Distribution of documents by language after translation: {'en': 22}\n",
"Unique terms found: 3538\n",
"Named entities found: 176\n",
"Vectors created.\n",
"Test: [4 5 0 0 0 2 0 0 0 1 4 4 2 2 1 0 2 4 1 1 1 3]\n",
"Reference: [0, 5, 2, 2, 2, 3, 2, 2, 2, 4, 0, 0, 3, 3, 4, 2, 3, 0, 4, 4, 4, 1]\n",
"Adjusted Rand Index: 1.0\n"
]
}
],
"source": [
"%run ./Practica1ObligatoriaRIMT_1819.py"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Rendering named entities visualization of original texts"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"The \n",
"\n",
" British\n",
" NORP\n",
"\n",
" photographer \n",
"\n",
" John Cantlie\n",
" PERSON\n",
"\n",
", hostage of the \n",
"\n",
" Islamic\n",
" NORP\n",
"\n",
" \n",
"\n",
" State\n",
" ORG\n",
"\n",
" since \n",
"\n",
" November 2012\n",
" DATE\n",
"\n",
" could be alive and be in \n",
"\n",
" Syria\n",
" GPE\n",
"\n",
", specifically the last stronghold of the jihadist organization that is being attacked by \n",
"\n",
" the Syrian Democratic Forces (SDF\n",
" ORG\n",
"\n",
"), formed mostly by militias \n",
"\n",
" Kurdish\n",
" NORP\n",
"\n",
" \n",
"\n",
" YPG\n",
" ORG\n",
"\n",
".
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"displacy.render(nlp(or_texts[3])[0:50], style = 'ent', jupyter = True)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"The \n",
"\n",
" British\n",
" NORP\n",
"\n",
" journalist \n",
"\n",
" John Cantlie\n",
" PERSON\n",
"\n",
", kidnapped \n",
"\n",
" seven years ago\n",
" DATE\n",
"\n",
" in \n",
"\n",
" Syria\n",
" GPE\n",
"\n",
" by \n",
"\n",
" the Islamic State\n",
" ORG\n",
"\n",
" (IS), could remain alive, according to the Secretary of \n",
"\n",
" State for Security of the United Kingdom\n",
" ORG\n",
"\n",
", \n",
"\n",
" Ben Wallace\n",
" PERSON\n",
"\n",
". Speaking to the media at \n",
"\n",
" the Interior Ministry\n",
" ORG\n",
"\n",
", \n",
"\n",
" Wallace\n",
" PERSON\n",
"\n",
"
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"displacy.render(nlp(or_texts[4])[0:50], style = 'ent', jupyter = True)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"Based on facts observed and verified firsthand by the journalist, or reported by reliable and well-informed sources. The \n",
"\n",
" American\n",
" NORP\n",
"\n",
" retires at \n",
"\n",
" 34 years\n",
" DATE\n",
"\n",
" after the conquest of an unexpected bronze medal in the descent of \n",
"\n",
" the World Cup\n",
" EVENT\n",
"\n",
" AreThe ski said goodbye to \n",
"\n",
" Lindsey Vonn\n",
" PERSON\n",
"\n",
" with
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"displacy.render(nlp(or_texts[0])[0:50], style = 'ent', jupyter = True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"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": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 2
}