example/ocr_label_propagation.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## `genalog.text` module: \n",
    "This module is responsible for:\n",
    "1. Text alignment\n",
    "1. NER label propagation using text alignment results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from genalog.text import ner_label\n",
    "from genalog.text import preprocess\n",
    "\n",
    "gt_txt = \"New York is big\"\n",
    "ocr_txt = \"New Yo rkis big\"\n",
    "\n",
    "# Input to the method\n",
    "gt_labels = [\"B-P\", \"I-P\", \"O\", \"O\"]\n",
    "gt_tokens = preprocess.tokenize(gt_txt) # tokenize into list of tokens\n",
    "ocr_tokens = preprocess.tokenize(ocr_txt)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['B-P', 'I-P', 'O', 'O']\n",
      "['New', 'York', 'is', 'big']\n",
      "['New', 'Yo', 'rkis', 'big']\n"
     ]
    }
   ],
   "source": [
    "# Inputs to the method\n",
    "print(gt_labels)\n",
    "print(gt_tokens)\n",
    "print(ocr_tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Method returns a tuple of 4 elements (gt_tokens, gt_labels, ocr_tokens, ocr_labels, gap_char)\n",
    "ocr_labels, aligned_gt, aligned_ocr, gap_char = ner_label.propagate_label_to_ocr(gt_labels, gt_tokens, ocr_tokens)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "OCR labels:           ['B-P', 'I-P', 'I-P', 'O']\n",
      "Aligned ground truth: New Yo@rk is big\n",
      "Alinged OCR text:     New Yo rk@is big\n"
     ]
    }
   ],
   "source": [
    "# Outputs\n",
    "print(f\"OCR labels:           {ocr_labels}\")\n",
    "print(f\"Aligned ground truth: {aligned_gt}\")\n",
    "print(f\"Alinged OCR text:     {aligned_ocr}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "B-P I-P  O  O   \n",
      "New York is big \n",
      "New Yo@rk is big\n",
      "||||||.||.||||||\n",
      "New Yo rk@is big\n",
      "New Yo  rkis big \n",
      "B-P I-P I-P  O   \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Format result for display\n",
    "print(ner_label.format_label_propagation(gt_tokens, gt_labels, ocr_tokens, ocr_labels, aligned_gt, aligned_ocr))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "B-P I-P  O  O   \n",
      "New York is big \n",
      "New Yo  rkis big \n",
      "B-P I-P I-P  O   \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# To turn off alignment information:\n",
    "print(ner_label.format_label_propagation(gt_tokens, gt_labels, ocr_tokens, ocr_labels, aligned_gt, aligned_ocr, show_alignment=False))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "B-P I-P I-P  O   \n",
      "New Yo  rkis big \n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Format tokens and labels\n",
    "print(ner_label.format_labels(ocr_tokens, ocr_labels))"
   ]
  },
  {
   "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}