kleister-nda/main.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import lzma\n",
    "\n",
    "# RTead file with lzma\n",
    "NDAs = []\n",
    "\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": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read expected information\n",
    "expected = []\n",
    "\n",
    "with open('train/expected.tsv') as f:\n",
    "    for line in f:\n",
    "        expected.append(line.replace('\\n', '').split(' '))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "\n",
    "months = {'01': 'January', '02': 'February', '03': 'March', \n",
    "    '04': 'April', '05': 'May', '06': 'June',\n",
    "    '07': 'July', '08': 'August', '09': 'September',\n",
    "    '10': 'October', '11': 'November', '12': 'December'}\n",
    "\n",
    "def dayToWord(day):\n",
    "    day = int(day)\n",
    "    if day > 3:\n",
    "        return str(day) + 'th'\n",
    "    elif day == 3:\n",
    "        return str(day) + 'rd'\n",
    "    elif day == 2 :\n",
    "        return str(day) + 'nd'\n",
    "    else: return str(day) + 'st'\n",
    "\n",
    "def numToWord(number):\n",
    "    try:\n",
    "        number = int(number)\n",
    "        d = {1 : 'one', 2 : 'two', 3 : 'three', 4 : 'four', 5 : 'five',\n",
    "            6 : 'six', 7 : 'seven', 8 : 'eight', 9 : 'nine', 10 : 'ten',\n",
    "            11 : 'eleven', 12 : 'twelve', 13 : 'thirteen', 14 : 'fourteen',\n",
    "            15 : 'fifteen', 16 : 'sixteen', 17 : 'seventeen', 18 : 'eighteen',\n",
    "            19 : 'nineteen', 20 : 'twenty',\n",
    "            30 : 'thirty', 40 : 'forty', 50 : 'fifty', 60 : 'sixty',\n",
    "            70 : 'seventy', 80 : 'eighty', 90 : 'ninety' }\n",
    "        if number < 20:\n",
    "            return d[number]\n",
    "        else:\n",
    "            if number % 10 == 0: return d[number]\n",
    "            else: return d[number // 10 * 10] + '-' + d[number % 10]\n",
    "    except:\n",
    "        return number\n",
    "\n",
    "def labelJurisdiction(text, jurisdiction):\n",
    "    jurisdictions = []\n",
    "    jurisdiction = jurisdiction.replace('_', ' ')\n",
    "    for match in re.finditer(jurisdiction, text):\n",
    "        tup = (match.start(), match.end(), 'jurisdiction')\n",
    "        jurisdictions.append(tup)\n",
    "    return jurisdictions\n",
    "\n",
    "def labelEffectiveDate(text, date):\n",
    "    dates = []\n",
    "    year, month, day = date.split('-')\n",
    "    \n",
    "    dateFormats = [month + '/' + day + '/' + year,\n",
    "        month + '/' + day + '/' + year[-2:], \n",
    "        month[1] + '/' + day + '/' + year, \n",
    "        month[1] + '/' + day[1] + '/' + year, \n",
    "        month[1] + '/' + day + '/' + year[-2:], \n",
    "        month[1] + '/' + day[1] + '/' + year[-2:],\n",
    "        dayToWord(day) + ' of ' + months[month] + ', ' + year,\n",
    "        dayToWord(day) + ' day of ' + months[month] + ', ' + year,\n",
    "        months[month] + ' ' + day + ', ' + year ]\n",
    "\n",
    "    for format in dateFormats:\n",
    "        for match in re.finditer(format, text, flags=re.IGNORECASE):\n",
    "            tup = (match.start(), match.end(), 'effective_date')\n",
    "            dates.append(tup)\n",
    "\n",
    "    return dates\n",
    "\n",
    "def labelParties(text, party):\n",
    "    parties = []\n",
    "    if 'Inc' in party:\n",
    "        regular = ''\n",
    "        for word in party.split('_'):\n",
    "            regular += word + '(.*)'\n",
    "        party = regular\n",
    "    party = party.replace('_', ' ')\n",
    "    for match in re.finditer(party, text, flags=re.IGNORECASE):\n",
    "        tup = (match.start(), match.end(), 'party')\n",
    "        parties.append(tup)\n",
    "    return parties\n",
    "\n",
    "def labelTerms(text, term):\n",
    "    terms = []\n",
    "    term = term.split('_')\n",
    "    number = numToWord(term[0])\n",
    "    units = term[1]\n",
    "    for match in re.finditer(number + ' ' + units, text, flags=re.IGNORECASE):\n",
    "        tup = (match.start(), match.end(), 'term')\n",
    "        terms.append(tup)\n",
    "    return terms"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "expectEntities = []\n",
    "\n",
    "for expect in expected:\n",
    "    # expect = expect.split()\n",
    "    entities = []\n",
    "    for e in expect:\n",
    "        label, entity = e.split('=')\n",
    "        entities.append((label, entity))\n",
    "    expectEntities.append(entities)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainData =[]\n",
    "\n",
    "for i in range(len(expectEntities)):\n",
    "    listOfEntities = []\n",
    "    for entity in expectEntities[i]:\n",
    "        if entity[0] == 'effective_date':\n",
    "            listOfEntities.append(labelEffectiveDate(NDAs[i], entity[1]))\n",
    "        elif entity[0] == 'jurisdiction':\n",
    "            listOfEntities.append(labelJurisdiction(NDAs[i], entity[1]))\n",
    "        elif entity[0] == 'party':\n",
    "            listOfEntities.append(labelParties(NDAs[i], entity[1]))\n",
    "        else: listOfEntities.append(labelTerms(NDAs[i], entity[1]))\n",
    "    listOfEntities = [item for sublist in listOfEntities for item in sublist]\n",
    "    trainData.append((NDAs[i], {'entities': listOfEntities}))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Created blank \"en\" model\n"
     ]
    }
   ],
   "source": [
    "import spacy\n",
    "# from spacy.tokens import DocBin\n",
    "\n",
    "model = None\n",
    "nIter = 100\n",
    "\n",
    "if model is not None:\n",
    "    nlp = spacy.load(model)\n",
    "    print('Loaded model')\n",
    "else:\n",
    "    nlp = spacy.blank('en')\n",
    "    print('Created blank \"en\" model')\n",
    "\n",
    "if 'ner' not in nlp.pipe_names:\n",
    "    # ner = nlp.create_pipe('ner')\n",
    "    ner = nlp.add_pipe('ner', last=True)\n",
    "else:\n",
    "    ner = nlp.get_pipe('ner')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "for data in trainData:\n",
    "    for ent in data[1].get('entities'):\n",
    "        ner.add_label(ent[2])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "otherPipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  2%|▏         | 6/254 [00:04<03:23,  1.22it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"04bf0791804e8487c91ab84eaa47a335.pdf\teffective_dat...\" with entities \"[(198, 216, 'effective_date'), (22663, 22681, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  3%|▎         | 8/254 [00:07<04:12,  1.03s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"0587275477c6ad6d0d72419383e04b88.pdf\teffective_dat...\" with entities \"[(4528, 4536, 'jurisdiction'), (4604, 4612, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  4%|▎         | 9/254 [00:14<11:25,  2.80s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"05947711a24a5b7ce401911d31e19c91.pdf\teffective_dat...\" with entities \"[(18271, 18279, 'jurisdiction'), (18507, 18515, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  6%|▌         | 14/254 [00:19<04:40,  1.17s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"0859334b76224ff82c1312ae7b2b5da1.pdf\teffective_dat...\" with entities \"[(279, 296, 'effective_date'), (22981, 22998, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  7%|▋         | 17/254 [00:22<03:30,  1.13it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"0c3ab1d0c8bb3b1c2f7a64f3ab584368.pdf\teffective_dat...\" with entities \"[(243, 259, 'effective_date'), (35225, 35241, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  7%|▋         | 18/254 [00:24<04:43,  1.20s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"0c7b90701575b147c4ac245ca478ee7c.pdf\teffective_dat...\" with entities \"[(10058, 10065, 'jurisdiction'), (10252, 10259, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  8%|▊         | 20/254 [00:26<04:14,  1.09s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"0f446b4ed10d8d40824270d746511cca.pdf\tjurisdiction ...\" with entities \"[(261, 268, 'jurisdiction'), (901, 908, 'jurisdict...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  8%|▊         | 21/254 [00:28<04:43,  1.22s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"1058cd8d541c0622ad959facd34235ea.pdf\teffective_dat...\" with entities \"[(21973, 21981, 'jurisdiction'), (46056, 46064, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  9%|▉         | 23/254 [00:31<04:48,  1.25s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"15398fb3b5f357981a8be88dc4bb376e.pdf\teffective_dat...\" with entities \"[(579, 591, 'jurisdiction'), (17167, 17179, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "  9%|▉         | 24/254 [00:35<08:16,  2.16s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"154d30f607c74aa8a5f582bf84f7a5e2.pdf\teffective_dat...\" with entities \"[(379, 387, 'jurisdiction'), (22505, 22513, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 13%|█▎        | 32/254 [00:39<01:42,  2.17it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"1a5847e0b968e25ddcf41ac9c6fc63b4.pdf\teffective_dat...\" with entities \"[(210, 227, 'effective_date'), (708, 725, 'effecti...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 14%|█▍        | 36/254 [00:44<02:21,  1.54it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"1c1705ebb86fb8c9ddd2c765d1d59486.pdf\teffective_dat...\" with entities \"[(356, 373, 'effective_date'), (14632, 14649, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 15%|█▍        | 37/254 [00:45<03:24,  1.06it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"1c36bbc314ee3f0cbe059d15d4fdd36a.pdf\teffective_dat...\" with entities \"[(250, 267, 'effective_date'), (31244, 31261, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 17%|█▋        | 43/254 [00:52<02:10,  1.62it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"22526e24107177141dc9b66afed7106d.pdf\teffective_dat...\" with entities \"[(265, 273, 'jurisdiction'), (12609, 12617, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 18%|█▊        | 45/254 [00:53<02:12,  1.58it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"232b3bee703427df8e9893e4a52d5d60.pdf\teffective_dat...\" with entities \"[(16031, 16039, 'jurisdiction'), (16220, 16228, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 19%|█▉        | 48/254 [00:56<02:00,  1.71it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"247166e0245431dcf97ee884f1f07e35.pdf\teffective_dat...\" with entities \"[(156, 170, 'effective_date'), (508, 522, 'effecti...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 20%|█▉        | 50/254 [00:57<01:47,  1.90it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"2632c4c1238356489cab88d58e1a5fb0.pdf\teffective_dat...\" with entities \"[(15689, 15697, 'effective_date'), (15719, 15727, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 22%|██▏       | 56/254 [01:00<01:13,  2.69it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"2ab67f26bc51d57492e3f27b244fae3e.pdf\teffective_dat...\" with entities \"[(22097, 22111, 'effective_date'), (44207, 44221, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 24%|██▎       | 60/254 [01:06<02:59,  1.08it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"2ce3bbe2d6836d8b023c55883294fa63.pdf\teffective_dat...\" with entities \"[(9413, 9422, 'jurisdiction'), (9806, 9815, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 29%|██▊       | 73/254 [01:11<00:57,  3.13it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"376f9746de69416a9561e92517c356ee.pdf\teffective_dat...\" with entities \"[(306, 330, 'effective_date'), (9197, 9221, 'effec...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 30%|███       | 77/254 [01:13<00:49,  3.54it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"39610c6bf605fdd8d0d9bcb2aacb5e74.pdf\teffective_dat...\" with entities \"[(51002, 51012, 'jurisdiction'), (51132, 51142, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 31%|███       | 79/254 [01:22<05:44,  1.97s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"3acc6f6bdad6eaaf7ab21faea5ea95fa.pdf\teffective_dat...\" with entities \"[(251, 265, 'effective_date'), (23669, 23683, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 31%|███▏      | 80/254 [01:25<06:26,  2.22s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"3c19cab83f40f722fc8c1432299d7655.pdf\teffective_dat...\" with entities \"[(290, 312, 'effective_date'), (30391, 30413, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 37%|███▋      | 94/254 [01:32<00:47,  3.40it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"480fcdb1b3d02989c11ace2c69bc9ba6.pdf\teffective_dat...\" with entities \"[(22255, 22269, 'effective_date'), (44472, 44486, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 38%|███▊      | 96/254 [01:35<02:06,  1.25it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"495f7d16921a1c8531be0844db0828a4.pdf\teffective_dat...\" with entities \"[(130, 155, 'effective_date'), (19409, 19434, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 40%|███▉      | 101/254 [01:36<00:56,  2.73it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"4dc5c39e601cd476f4c2def0e6b96915.pdf\teffective_dat...\" with entities \"[(329, 343, 'jurisdiction'), (29204, 29218, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 41%|████      | 103/254 [01:40<02:33,  1.02s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"4dd5eca6802e0f03214db3dfd4881638.pdf\teffective_dat...\" with entities \"[(19819, 19832, 'effective_date'), (39990, 40003, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 41%|████▏     | 105/254 [01:43<02:36,  1.05s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"4f0e455a90c53f8e40e09d324aab4ea3.pdf\teffective_dat...\" with entities \"[(533, 550, 'effective_date'), (2868, 2885, 'effec...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 42%|████▏     | 106/254 [01:46<04:02,  1.64s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"4fd432d8ce6796dabc17d3838d8539a2.pdf\teffective_dat...\" with entities \"[(162, 176, 'effective_date'), (15065, 15079, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 44%|████▎     | 111/254 [01:49<01:21,  1.76it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"5b070e9583099dfdcddc9c9c811b7d44.pdf\teffective_dat...\" with entities \"[(10864, 10876, 'jurisdiction'), (23351, 23363, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 44%|████▍     | 112/254 [01:50<01:53,  1.25it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"5d18471dc0cb8c824fe86d5899aeb24b.pdf\teffective_dat...\" with entities \"[(25946, 25952, 'effective_date'), (52332, 52338, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 44%|████▍     | 113/254 [01:53<03:32,  1.51s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"5f542bf5a9d00298d7743fd2acbcbfd5.pdf\teffective_dat...\" with entities \"[(352, 360, 'jurisdiction'), (18053, 18061, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 48%|████▊     | 122/254 [01:57<00:36,  3.62it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"6c0e2103cb185f28b0c1e9109c674836.pdf\teffective_dat...\" with entities \"[(20591, 20598, 'effective_date'), (20707, 20714, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 50%|████▉     | 126/254 [02:00<00:51,  2.51it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"6ecf1846ef305f44deb8f5c64da3b999.pdf\teffective_dat...\" with entities \"[(1140, 1156, 'effective_date'), (23227, 23243, 'e...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 53%|█████▎    | 134/254 [02:04<00:32,  3.74it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"72f91408258be59298f412dad65e3baa.pdf\teffective_dat...\" with entities \"[(1190, 1199, 'jurisdiction'), (7274, 7283, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 53%|█████▎    | 135/254 [02:07<01:54,  1.04it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"73bfeebfeca04b3a804d844cbf16d7f3.pdf\teffective_dat...\" with entities \"[(3546, 3556, 'jurisdiction'), (9893, 9903, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 54%|█████▍    | 137/254 [02:08<01:22,  1.42it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"7496116e8680dac321f36147b6312411.pdf\teffective_dat...\" with entities \"[(13407, 13420, 'effective_date'), (26980, 26993, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 54%|█████▍    | 138/254 [02:09<01:52,  1.03it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"7684f321eb08514fa1794427e73479b9.pdf\teffective_dat...\" with entities \"[(16189, 16197, 'jurisdiction'), (16325, 16333, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 55%|█████▍    | 139/254 [02:12<02:59,  1.56s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"782c651fc7cf288ec2f8857de0d6bb58.pdf\teffective_dat...\" with entities \"[(5539, 5552, 'jurisdiction'), (11301, 11314, 'jur...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 59%|█████▊    | 149/254 [02:16<00:35,  3.00it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"7cf3dfaf7afd9989de90cb3cbd8d6a83.pdf\teffective_dat...\" with entities \"[(13571, 13578, 'effective_date'), (27080, 27087, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 59%|█████▉    | 151/254 [02:18<00:54,  1.88it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"7cfa17a4165369964337c2f46c40e3a2.pdf\teffective_dat...\" with entities \"[(13099, 13104, 'jurisdiction'), (13304, 13309, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 62%|██████▏   | 157/254 [02:20<00:32,  3.03it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"82b263d025fddef5a8048b34eed91942.pdf\teffective_dat...\" with entities \"[(15481, 15493, 'jurisdiction'), (15986, 15998, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 62%|██████▏   | 158/254 [02:22<01:04,  1.48it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"83a79ed689ef320a8f65e0268de91e10.pdf\teffective_dat...\" with entities \"[(57077, 57087, 'jurisdiction'), (57207, 57217, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 63%|██████▎   | 161/254 [02:34<02:56,  1.90s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"86e9c90fa3986691fcb140266f514c7d.pdf\teffective_dat...\" with entities \"[(14567, 14575, 'jurisdiction'), (30390, 30398, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 64%|██████▍   | 162/254 [02:36<02:54,  1.89s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"8a7fedc5ffa5c2ffa424753229b52943.pdf\teffective_dat...\" with entities \"[(10588, 10594, 'jurisdiction'), (11064, 11070, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 66%|██████▌   | 167/254 [02:38<00:50,  1.72it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"988f7c53c00bb333a4b7188738a25378.pdf\teffective_dat...\" with entities \"[(7568, 7576, 'jurisdiction'), (10008, 10016, 'jur...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 68%|██████▊   | 172/254 [02:43<00:46,  1.75it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"9d70181e77cf74279fb6712c569da104.pdf\teffective_dat...\" with entities \"[(226, 239, 'effective_date'), (26381, 26394, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 69%|██████▉   | 176/254 [02:47<00:45,  1.72it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"a373847e741d0b4db97466b8964a66ae.pdf\teffective_dat...\" with entities \"[(18914, 18922, 'jurisdiction'), (19057, 19065, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 70%|██████▉   | 177/254 [02:51<01:53,  1.47s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"a3ba9b969b390ce8ec0f62dde48f5a1f.pdf\teffective_dat...\" with entities \"[(291, 303, 'effective_date'), (17055, 17067, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 70%|███████   | 178/254 [02:53<02:04,  1.64s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"a527509f8b744d57fc406679ab2287e0.pdf\teffective_dat...\" with entities \"[(315, 337, 'effective_date'), (11945, 11967, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 72%|███████▏  | 182/254 [02:54<00:45,  1.58it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"a87ebed40675b7ed9c2d4a0721abbefb.pdf\teffective_dat...\" with entities \"[(25895, 25903, 'jurisdiction'), (55588, 55596, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 74%|███████▍  | 188/254 [02:59<00:30,  2.19it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"b960e85adabccfba6d758948a1ecc804.pdf\teffective_dat...\" with entities \"[(12062, 12075, 'effective_date'), (24158, 24171, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 77%|███████▋  | 195/254 [03:03<00:37,  1.59it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"c2149cc784d2d783c2de0c7b2f02a12f.pdf\teffective_dat...\" with entities \"[(11364, 11371, 'effective_date'), (11398, 11405, ...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 78%|███████▊  | 197/254 [03:05<00:37,  1.54it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"c4ccca5a5502597fc4a75b4ca50337df.pdf\teffective_dat...\" with entities \"[(4849, 4859, 'jurisdiction'), (11069, 11079, 'jur...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 80%|████████  | 204/254 [03:07<00:14,  3.35it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"c94fdb196d2502f60e21793b387023de.pdf\teffective_dat...\" with entities \"[(240, 256, 'effective_date'), (23602, 23618, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 81%|████████▏ | 207/254 [03:10<00:28,  1.66it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"cbbcc01ea9cfa4ec8bfa27f0f9f71088.pdf\teffective_dat...\" with entities \"[(24491, 24504, 'jurisdiction'), (24775, 24788, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 83%|████████▎ | 210/254 [03:13<00:32,  1.35it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"cf34c9403e0092eca75ed9fc61284268.pdf\teffective_dat...\" with entities \"[(256, 272, 'effective_date'), (16765, 16781, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 85%|████████▍ | 215/254 [03:16<00:15,  2.48it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"d2cedafb5d6fc0a7a2f4693f652606ef.pdf\teffective_dat...\" with entities \"[(34099, 34104, 'jurisdiction'), (34219, 34224, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 85%|████████▌ | 216/254 [03:22<01:16,  2.01s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"d50b5f4cf1b059aed9adb4d3d8953d84.pdf\teffective_dat...\" with entities \"[(218, 223, 'jurisdiction'), (15327, 15332, 'juris...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 86%|████████▌ | 219/254 [03:24<00:38,  1.10s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"d789f0680308f0638a05078c5d896b7a.pdf\teffective_dat...\" with entities \"[(292, 310, 'effective_date'), (24569, 24587, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 90%|████████▉ | 228/254 [03:29<00:09,  2.78it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"e29c3877a103aaefcf77ebb110f981a5.pdf\teffective_dat...\" with entities \"[(24146, 24159, 'jurisdiction'), (24324, 24337, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 90%|█████████ | 229/254 [03:32<00:29,  1.19s/it]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"e33d3ca6885f31faa68b2ab766afc86b.pdf\teffective_dat...\" with entities \"[(360, 365, 'jurisdiction'), (551, 556, 'jurisdict...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 96%|█████████▌| 243/254 [03:40<00:10,  1.04it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"f4d4ef76c5ce9b0d5bca8c55369b753c.pdf\teffective_dat...\" with entities \"[(19234, 19242, 'jurisdiction'), (19468, 19476, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 97%|█████████▋| 246/254 [03:44<00:06,  1.16it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"f6cf95250272fd7f3fd767819ee11255.pdf\teffective_dat...\" with entities \"[(6008, 6016, 'jurisdiction'), (14222, 14230, 'jur...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 98%|█████████▊| 248/254 [03:45<00:04,  1.40it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"fbf608b62ef498171b70fb7b36be61a0.pdf\teffective_dat...\" with entities \"[(30197, 30220, 'effective_date'), (3688, 3695, 'j...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      " 99%|█████████▉| 252/254 [03:46<00:00,  2.19it/s]j:\\.AppData\\Python\\Python38\\site-packages\\spacy\\training\\iob_utils.py:141: UserWarning: [W030] Some entities could not be aligned in the text \"fdf657ad612664d6f363040992f9a93c.pdf\teffective_dat...\" with entities \"[(205, 221, 'effective_date'), (18571, 18587, 'eff...\". Use `spacy.training.offsets_to_biluo_tags(nlp.make_doc(text), entities)` to check the alignment. Misaligned entities ('-') will be ignored during training.\n",
      "  warnings.warn(\n",
      "100%|██████████| 254/254 [03:49<00:00,  1.11it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 121367.40999465056}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 3064.6157787348466}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 2713.940178823442}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 2308.1697566876524}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 2081.409584430913}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 2703.6273422304675}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1873.849181939688}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 2970.6824737787374}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1536.9394466317704}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1567.1744353484294}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 12201.587548598394}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1475.4802474584865}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1637.554888988012}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 3338.4118373711162}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 3628.8529922539665}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1122.9326577445718}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:47<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1056.6042950392734}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:38<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1494.7422995005986}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1093.2139526897322}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1161.3516471813246}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 923.4026813110729}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 6822.4873693648}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 965.8564889386865}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1895.9738231120605}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 4759.545841583874}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 849.9946473153236}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 13133.735760338292}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1132.05477693737}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 727.2229101967696}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 712.5904286187064}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 709.1340100197092}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 677.6860686316803}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 467.8078318010227}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 577.8532304094363}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 593.7090201894682}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 545.9148195413269}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 5190.76835287416}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 10175.43726500724}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 525.8841523092841}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:47<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 652.4439105603246}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 12232.87218168916}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:47<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 584.2010901025561}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 11239.083920775602}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 479.70122952070625}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:48<00:00,  1.11it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 432.9402811895728}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 351.3015391408119}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 314.5821106558259}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:48<00:00,  1.11it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 674.1040463482614}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:51<00:00,  1.10it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 685.0549399011828}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:48<00:00,  1.11it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 346.72634777803324}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 282.34050623250107}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 528.4151804189036}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 207.02574239415026}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 4602.387233055954}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1327.8107613080297}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 203.08545199977465}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 432.95780566657976}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 247.29635213365103}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 11141.300520583844}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 196.54009389246215}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 245.53696564695727}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 214.63265869778368}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 335.24755693518506}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1845.3869408136584}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 244.5266526305163}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 324.677549649568}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 193.7757545725294}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 214.0988065129845}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 211.30440763873858}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 311.3926866805724}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 152.8372567465775}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 167.19798372224142}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 269.8072879107703}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 172.78895767745234}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 152.2928964526185}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 241.40016408906854}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 174.4806328902659}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 430.183177284666}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 212.76146605464587}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 4264.537137806244}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:40<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 138.65115249654542}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 169.38315583287215}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 199.71923073314906}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 141.07872416249504}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 3239.6032942208617}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 125.13759326328476}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:39<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 166.43782435874667}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 193.75167109626358}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:37<00:00,  1.17it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 210.71080058930684}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:38<00:00,  1.16it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 94.89951866488516}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 135.40197065974007}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:41<00:00,  1.15it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 113.31096857552745}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:43<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 115.2365843483141}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:42<00:00,  1.14it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 1149.9128505764934}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:45<00:00,  1.13it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 110.24805298311857}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:47<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 122.23640644764889}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:50<00:00,  1.10it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 122.02146472314264}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 150.26241508963884}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:46<00:00,  1.12it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 135.2006315147592}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 254/254 [03:44<00:00,  1.13it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'ner': 160.26129673476012}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "# import random\n",
    "from tqdm import tqdm\n",
    "\n",
    "from spacy.training.example import Example\n",
    "\n",
    "with nlp.disable_pipes(*otherPipes):\n",
    "    optimizer = nlp.begin_training()\n",
    "    for itn in range(nIter):\n",
    "        # random.shuffle(trainData)\n",
    "        losses = {}\n",
    "        for text, annotations in tqdm(trainData):\n",
    "            try:\n",
    "                doc = nlp.make_doc(text)\n",
    "                example = Example.from_dict(doc, annotations)\n",
    "                nlp.update([example], drop=0.5, sgd=optimizer, losses=losses)\n",
    "            except:\n",
    "                pass\n",
    "        print(losses)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Test trained model\n",
    "# for text, _ in trainData[:1]:\n",
    "#     doc = nlp(text)\n",
    "    #print('Entities', [(ent.text, ent.label_) for ent in doc.ents])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the model to path\n",
    "nlp.to_disk('NER')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'00a1d238e37ac225b8045a97953e845d.pdf\\teffective_date jurisdiction party term\\tEX-10.23 5 dex1023.htm COVENANT NOT TO COMPETE AND NON-DISCLOSURE AGREEMENT\\\\nExhibit 10.23\\\\nCOVENANT NOT TO COMPETE\\\\nAND NON-DISCLOSURE AGREEMENT\\\\nPARTIES:\\\\nEric Dean Sprunk (“EMPLOYEE”)\\\\nand\\\\nNIKE, Inc., divisions, subsidiaries\\\\nand affiliates. (“NIKE”):\\\\nRECITALS:\\\\nA. This Covenant Not to Compete and Non-Disclosure Agreement is executed upon initial employment or upon the EMPLOYEE’s\\\\nadvancement with NIKE and is a condition of such employment or advancement.\\\\nB. Over the course of EMPLOYEE’s employment with NIKE, EMPLOYEE will be or has been exposed to and/or is in a position to\\\\ndevelop confidential information peculiar to NIKE’s business and not generally known to the public as defined below (“Protected Information”). It is\\\\nanticipated that EMPLOYEE will continue to be exposed to Protected Information of greater sensitivity as EMPLOYEE advances in the company.\\\\nC. The nature of NIKE’s business is highly competitive and disclosure of any Protected Information would result in severe damage to NIKE\\\\nand be difficult to measure.\\\\nD. NIKE makes use of its Protected Information throughout the world. Protected Information of NIKE can be used to NIKE’s detriment\\\\nanywhere in the world.\\\\nAGREEMENT:\\\\nIn consideration of the foregoing, and the terms and conditions set forth below, the parties agree as follows:\\\\n1. Covenant Not to Compete.\\\\n(a) Competition Restriction. During EMPLOYEE’s employment by NIKE, under the terms of any employment contract or\\\\notherwise, and for one year thereafter, (the “Restriction Period”), EMPLOYEE will not directly or indirectly, own, manage, control, or participate in\\\\nthe ownership,\\\\nmanagement or control of, or be employed by, consult for, or be connected in any manner with, any business engaged anywhere in the world in the\\\\nathletic footwear, athletic apparel or sports equipment and accessories business, or any other business which directly competes with NIKE or any of\\\\nits parent, subsidiaries or affiliated corporations ( “Competitor”). By way of illustration only, examples of NIKE competitors include, but are not\\\\nlimited to: Adidas, FILA, Reebok, Puma, Champion, Oakley, DKNY, Converse, Asics, Saucony, New Balance, Ralph Lauren/Polo Sport, B.U.M,\\\\nFUBU, The Gap, Tommy Hilfiger, Umbro, Northface, Venator (Foot lockers), Sports Authority, Columbia Sportswear, Wilson, Mizuno, Callaway\\\\nGolf and Titleist. This provision is subject to NIKE’s option to waive all or any portion of the Restriction Period as more specifically provided\\\\nbelow.\\\\n(b) Extension of Time. In the event EMPLOYEE breaches this covenant not to compete, the Restriction Period shall automatically\\\\ntoll from the date of the first breach, and all subsequent breaches, until the resolution of the breach through private settlement, judicial or other\\\\naction, including all appeals. The Restriction Period shall continue upon the effective date of any such settlement judicial or other resolution. NIKE\\\\nshall not be obligated to pay EMPLOYEE the additional compensation described in paragraph 1(d) below during any period of time in which this\\\\nAgreement is tolled due to EMPLOYEE’s breach. In the event EMPLOYEE receives such additional compensation after any such breach,\\\\nEMPLOYEE must immediately reimburse NIKE in the amount of all such compensation upon the receipt of a written request by NIKE.\\\\n(c) Waiver of Non-Compete. NIKE has the option, in its sole discretion, to elect to waive all or a portion of the Restriction Period or\\\\nto limit the definition of Competitor, by giving EMPLOYEE seven (7) days prior notice of such election. In the event all or a portion of the\\\\nRestriction Period is waived, NIKE shall not be obligated to pay EMPLOYEE for any period of time as to which the covenant not to compete has\\\\nbeen waived.\\\\n(d) Additional Consideration. As additional consideration for the cov
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "NDAs[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
  },
  "kernelspec": {
   "display_name": "Python 3.9.2 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": "3.9.2"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}