spaCy/spacy/pipeline/textcat/pure_logistic_textcat.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'cells': [{'cell_type': 'markdown',\n",
       "   'metadata': {},\n",
       "   'source': ['# Pure Logistic Regression Text Categorizer\\n',\n",
       "    'This tutorial demonstrates how to use the custom logistic regression text categorizer.']},\n",
       "  {'cell_type': 'code',\n",
       "   'execution_count': None,\n",
       "   'metadata': {},\n",
       "   'source': ['import spacy\\n',\n",
       "    'from spacy.training import Example\\n',\n",
       "    '\\n',\n",
       "    '# Load spaCy model\\n',\n",
       "    'nlp = spacy.load(\"en_core_web_lg\")\\n',\n",
       "    'nlp.add_pipe(\"pure_logistic_textcat\")\\n',\n",
       "    '\\n',\n",
       "    '# Example training data\\n',\n",
       "    'TRAIN_DATA = [\\n',\n",
       "    '    (\"This is amazing!\", {\"cats\": {\"positive\": 1.0, \"negative\": 0.0}}),\\n',\n",
       "    '    (\"This is terrible!\", {\"cats\": {\"positive\": 0.0, \"negative\": 1.0}})\\n',\n",
       "    ']\\n',\n",
       "    '\\n',\n",
       "    '# Create training examples\\n',\n",
       "    'examples = []\\n',\n",
       "    'for text, annotations in TRAIN_DATA:\\n',\n",
       "    '    doc = nlp.make_doc(text)\\n',\n",
       "    '    example = Example.from_dict(doc, annotations)\\n',\n",
       "    '    examples.append(example)\\n',\n",
       "    '\\n',\n",
       "    '# Train the model\\n',\n",
       "    'textcat = nlp.get_pipe(\"pure_logistic_textcat\")\\n',\n",
       "    'losses = textcat.update(examples)\\n',\n",
       "    'print(f\"Losses: {losses}\")\\n',\n",
       "    '\\n',\n",
       "    '# Test the model\\n',\n",
       "    'test_text = \"This product is fantastic!\"\\n',\n",
       "    'doc = nlp(test_text)\\n',\n",
       "    'print(f\"\\\\nText: {test_text}\")\\n',\n",
       "    'print(f\"Predictions: {doc.cats}\")']}]}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "{\n",
    " \"cells\": [\n",
    "  {\n",
    "   \"cell_type\": \"markdown\",\n",
    "   \"metadata\": {},\n",
    "   \"source\": [\n",
    "    \"# Pure Logistic Regression Text Categorizer\\n\",\n",
    "    \"This tutorial demonstrates how to use the custom logistic regression text categorizer.\"\n",
    "   ]\n",
    "  },\n",
    "  {\n",
    "   \"cell_type\": \"code\",\n",
    "   \"execution_count\": None,\n",
    "   \"metadata\": {},\n",
    "   \"source\": [\n",
    "    \"import spacy\\n\",\n",
    "    \"from spacy.training import Example\\n\",\n",
    "    \"\\n\",\n",
    "    \"# Load spaCy model\\n\",\n",
    "    \"nlp = spacy.load(\\\"en_core_web_lg\\\")\\n\",\n",
    "    \"nlp.add_pipe(\\\"pure_logistic_textcat\\\")\\n\",\n",
    "    \"\\n\",\n",
    "    \"# Example training data\\n\",\n",
    "    \"TRAIN_DATA = [\\n\",\n",
    "    \"    (\\\"This is amazing!\\\", {\\\"cats\\\": {\\\"positive\\\": 1.0, \\\"negative\\\": 0.0}}),\\n\",\n",
    "    \"    (\\\"This is terrible!\\\", {\\\"cats\\\": {\\\"positive\\\": 0.0, \\\"negative\\\": 1.0}})\\n\",\n",
    "    \"]\\n\",\n",
    "    \"\\n\",\n",
    "    \"# Create training examples\\n\",\n",
    "    \"examples = []\\n\",\n",
    "    \"for text, annotations in TRAIN_DATA:\\n\",\n",
    "    \"    doc = nlp.make_doc(text)\\n\",\n",
    "    \"    example = Example.from_dict(doc, annotations)\\n\",\n",
    "    \"    examples.append(example)\\n\",\n",
    "    \"\\n\",\n",
    "    \"# Train the model\\n\",\n",
    "    \"textcat = nlp.get_pipe(\\\"pure_logistic_textcat\\\")\\n\",\n",
    "    \"losses = textcat.update(examples)\\n\",\n",
    "    \"print(f\\\"Losses: {losses}\\\")\\n\",\n",
    "    \"\\n\",\n",
    "    \"# Test the model\\n\",\n",
    "    \"test_text = \\\"This product is fantastic!\\\"\\n\",\n",
    "    \"doc = nlp(test_text)\\n\",\n",
    "    \"print(f\\\"\\\\nText: {test_text}\\\")\\n\",\n",
    "    \"print(f\\\"Predictions: {doc.cats}\\\")\"\n",
    "   ]\n",
    "  }\n",
    " ]\n",
    "}"
   ]
  }
 ],
 "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": "3.10.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}