File size: 2,937 Bytes
bcffb9c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Entity: L V | Type: ('Let', 'VB')\n",
"Entity: ' P | Type: (\"'s\", 'POS')\n",
"Entity: m N | Type: ('meet', 'NN')\n",
"Entity: f I | Type: ('for', 'IN')\n",
"Entity: l N | Type: ('lunch', 'NN')\n",
"Entity: t N | Type: ('tomorrow', 'NN')\n",
"Entity: a I | Type: ('at', 'IN')\n",
"Entity: 1 C | Type: ('12', 'CD')\n",
"Entity: P N | Type: ('PM', 'NNP')\n",
"Entity: a I | Type: ('at', 'IN')\n",
"Entity: t D | Type: ('the', 'DT')\n",
"Entity: Italian | Type: (GPE Italian/JJ)\n",
"Entity: r N | Type: ('restaurant', 'NN')\n",
"Entity: o I | Type: ('on', 'IN')\n",
"Entity: Main Street | Type: (FACILITY Main/NNP Street/NNP)\n",
"Entity: . . | Type: ('.', '.')\n"
]
}
],
"source": [
"\n",
"from nltk import ne_chunk, pos_tag\n",
"from nltk.tokenize import word_tokenize\n",
"\n",
"# Sample text for demonstration\n",
"text = \"Let's meet for lunch tomorrow at 12 PM at the Italian restaurant on Main Street.\"\n",
"\n",
"# Tokenize the text into words\n",
"tokens = word_tokenize(text)\n",
"\n",
"# Apply NER using NLTK's pre-trained models\n",
"ner_tags = ne_chunk(pos_tag(tokens))\n",
"\n",
"# Print the named entities\n",
"for chunk in ner_tags:\n",
" if hasattr(chunk, 'label'):\n",
" print(f\"Entity: {' '.join(c[0] for c in chunk)} | Type: {chunk}\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Entity: Lunch Tomorrow | Type: PERSON\n",
"Entity: Italian | Type: GPE\n",
"Entity: Main Street | Type: FACILITY\n"
]
}
],
"source": [
"# Apply NER using NLTK's pre-trained models\n",
"ner_tags = ne_chunk(pos_tag(tokens))\n",
"\n",
"# Print the named entities\n",
"for chunk in ner_tags:\n",
" if hasattr(chunk, 'label'):\n",
" print(f\"Entity: {' '.join(c[0] for c in chunk)} | Type: {chunk.label()}\")"
]
},
{
"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": "3.12.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|