kleister-nda/heSaidEdgar.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "import lzma\n",
    "\n",
    "NDAs = []\n",
    "with lzma.open('train/in.tsv.xz') as f:\n",
    "    for line in f:\n",
    "        NDAs.append(line.decode('utf-8'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "import spacy\n",
    "from spacy import displacy\n",
    "\n",
    "nlp = spacy.load('NER')\n",
    "\n",
    "text = NDAs[9]\n",
    "doc = nlp(text)\n",
    "\n",
    "effective_date = []\n",
    "jurisdiction = []\n",
    "party = []\n",
    "term = []\n",
    "\n",
    "for word in doc.ents:\n",
    "    if word.label_ == 'effective_date':\n",
    "        effective_date.append(word.text)\n",
    "    elif word.label_ == 'jurisdiction':\n",
    "        jurisdiction.append(word.text)\n",
    "    elif word.label_ == 'party':\n",
    "        party.append(word.text)\n",
    "    else:\n",
    "        term.append(word.text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "12"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "jurisdiction.count('New York')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "juris = { j : jurisdiction.count(j) for j in jurisdiction}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'New York': 12}"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "juris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CompuDyne Corporation --> party\n",
      "two years --> term\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "CompuDyne Corporation --> party\n",
      "two years --> term\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "CompuDyne Corporation --> party\n",
      "two years --> term\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "CompuDyne Corporation --> party\n",
      "two years --> term\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n",
      "New York --> jurisdiction\n"
     ]
    }
   ],
   "source": [
    "text = NDAs[9]\n",
    "doc = nlp(text)\n",
    "for word in doc.ents:\n",
    "    print(word.text, '-->', word.label_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "3a5b3979b9a2fc2c8e649de363a592bbf5a2c9da164843b1adb5b45661722ad0"
  },
  "kernelspec": {
   "display_name": "Python 3.8.10 64-bit",
   "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": "3.8.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}