{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Rewire Annotator\n",
"\n",
"The `RewireAnnotator` is an annotator that uses the [Rewire](https://rewire.online/rewire-api-access/) service to annotate documents. "
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from gatenlp import Document\n",
"from gatenlp.processing.client.rewire import RewireAnnotator\n",
"from gatenlp.lib_spacy import AnnSpacy"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"scrolled": false
},
"outputs": [],
"source": [
"apikey = os.environ[\"REWIRE_KEY\"] "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"docs = [\n",
" Document(\"Barack Obama visited Microsoft in New York last May.\"),\n",
" Document(\"\"\"This is just some example text. \n",
" Has a sentence that talks about shit in general. \n",
" And another talking about 💩💩💩💩 in general. This guy is a moron.\"\"\"),\n",
" Document(\"What a stupid bitch she is.\"),\n",
" Document(\"I am going to kill you, asshole!\"),\n",
"]\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/johann/software/anaconda/envs/gatenlp-37/lib/python3.7/site-packages/spacy/util.py:837: UserWarning: [W095] Model 'en_core_web_sm' (3.2.0) was trained with spaCy v3.2 and may not be 100% compatible with the current version (3.3.1). If you see errors or degraded performance, download a newer compatible model or retrain your custom model with the current spaCy version. For more details and available updates, run: python -m spacy validate\n",
" warnings.warn(warn_msg)\n"
]
}
],
"source": [
"# Just use the sentence annotations for annotating texts on a per-sentence level later\n",
"anntr = AnnSpacy(add_tokens=False, add_entities=False, add_sentences=True, add_nounchunks=False, add_deps=False)\n",
"for doc in docs:\n",
" doc = anntr(doc)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Document 0 : Features({'abuse': 0.007695647422224283, 'hate': 0.01182339433580637, 'profanity': 0.0, 'violent': 0.00013819332525599748, 'sexually_explicit': 0.0007839425234124064, 'positive': 0.03010033629834652})\n",
"Document 1 : Features({'abuse': 0.9521309733390808, 'hate': 0.07565305382013321, 'profanity': 1.0, 'violent': 0.00013135180051904172, 'sexually_explicit': 0.0008426422718912363, 'positive': 0.03213106095790863})\n",
"Document 2 : Features({'abuse': 0.9487276077270508, 'hate': 0.07640768587589264, 'profanity': 1.0, 'violent': 0.00017197855049744248, 'sexually_explicit': 0.0007524627144448459, 'positive': 0.051224932074546814})\n",
"Document 3 : Features({'abuse': 0.9973989725112915, 'hate': 0.03146960213780403, 'profanity': 1.0, 'violent': 0.9915707111358643, 'sexually_explicit': 0.003027835162356496, 'positive': 0.05033063143491745})\n"
]
}
],
"source": [
"# Annotator for annotating documents as a whole\n",
"rewire_doc = RewireAnnotator(auth_token=apikey)\n",
"# Annotator for annotating sentences\n",
"rewire_sent = RewireAnnotator(auth_token=apikey, ann_type=\"Sentence\")\n",
"\n",
"# run both annotators over all documents, show the document features assigned for each\n",
"for idx, doc in enumerate(docs):\n",
" doc.features.clear() \n",
" rewire_doc(doc)\n",
" print(\"Document\", idx, \":\", doc.features)\n",
" rewire_sent(doc)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"
\n",
"\n",
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"\n",
"
\n",
"
\n",
"\n",
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"\n",
"
\n",
"
\n",
"\n",
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"\n",
"
\n",
"
\n",
"\n",
"
\n",
"\n",
"
\n",
" \n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
"
\n",
" \n",
" \n",
"
\n",
"\n",
"