notebooks/373_augment_triplets_for_cross_encoder.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "id": "139bee68",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:53:41.008868Z",
     "start_time": "2024-12-05T17:53:40.980480Z"
    }
   },
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ],
   "outputs": [],
   "execution_count": 1
  },
  {
   "cell_type": "markdown",
   "id": "028823c5",
   "metadata": {},
   "source": [
    "# Augment triplets\n",
    "\n",
    "Add easy-negatives and under-represented tokens"
   ]
  },
  {
   "cell_type": "code",
   "id": "e0364890",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:54:37.187130Z",
     "start_time": "2024-12-05T17:54:37.075831Z"
    }
   },
   "source": [
    "from collections import Counter\n",
    "import random\n",
    "import re\n",
    "\n",
    "import pandas as pd\n",
    "from tqdm.auto import tqdm\n",
    "\n",
    "from nama.data.filesystem import download_file_from_s3, save_file\n",
    "from nama.data.utils import read_csv\n",
    "from nama.models.tokenizer import get_tokenize_function_and_vocab"
   ],
   "outputs": [],
   "execution_count": 4
  },
  {
   "cell_type": "code",
   "id": "774de195",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:07:45.562848Z",
     "start_time": "2024-12-05T18:07:45.528329Z"
    }
   },
   "source": [
    "#config\n",
    "# TODO do for given and surname\n",
    "given_surname = \"given\"\n",
    "# given_surname = \"surname\"\n",
    "\n",
    "num_common_names = 10000 if given_surname == \"given\" else 25000\n",
    "\n",
    "num_easy_pos_negs = 100\n",
    "num_easy_neg_negs = 5\n",
    "num_common_negs = 1000\n",
    "num_common_neg_copies = 2\n",
    "num_anchor_pos_neg_copies = 1\n",
    "under_represented_threshold = 500\n",
    "\n",
    "max_tokens = 10\n",
    "vocab_size = 2048  # 256, 512, 1024, 1536, 2048\n",
    "tree_name_min_freq = 1000\n",
    "\n",
    "triplets_path=f\"s3://fs-nama-data/2024/familysearch-names/processed/tree-hr-{given_surname}-triplets-{tree_name_min_freq}.csv.gz\"\n",
    "pref_path = f\"s3://fs-nama-data/2024/familysearch-names/processed/tree-preferred-{given_surname}-aggr.csv.gz\"\n",
    "non_negatives_path = f\"s3://fs-nama-data/2024/familysearch-names/processed/common_{given_surname}_non_negatives.csv\"\n",
    "tokenizer_path=f\"s3://fs-nama-data/2024/nama-data/data/models/fs-{given_surname}-subword-tokenizer-{vocab_size}.json\"\n",
    "\n",
    "augmented_path=f\"s3://fs-nama-data/2024/familysearch-names/processed/tree-hr-{given_surname}-triplets-{tree_name_min_freq}-augmented.csv.gz\""
   ],
   "outputs": [],
   "execution_count": 32
  },
  {
   "cell_type": "markdown",
   "id": "e7c030b7",
   "metadata": {},
   "source": [
    "## Load data"
   ]
  },
  {
   "cell_type": "code",
   "id": "1a60fb5d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:55:06.995416Z",
     "start_time": "2024-12-05T17:54:57.622471Z"
    }
   },
   "source": [
    "# read triplets\n",
    "path = download_file_from_s3(triplets_path) if triplets_path.startswith(\"s3://\") else triplets_path\n",
    "triplets_df = read_csv(path)\n",
    "print(len(triplets_df))\n",
    "triplets_df.head(3)"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3289279\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "     anchor  positive  positive_score negative  negative_score\n",
       "0  aloysius  alaysius        0.961516  aloisia        0.403759\n",
       "1   rosanna  roseanna        0.792378  susanne        0.400109\n",
       "2   stephen    stehen        0.968966   stearn        0.501695"
      ],
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>anchor</th>\n",
       "      <th>positive</th>\n",
       "      <th>positive_score</th>\n",
       "      <th>negative</th>\n",
       "      <th>negative_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>aloysius</td>\n",
       "      <td>alaysius</td>\n",
       "      <td>0.961516</td>\n",
       "      <td>aloisia</td>\n",
       "      <td>0.403759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>rosanna</td>\n",
       "      <td>roseanna</td>\n",
       "      <td>0.792378</td>\n",
       "      <td>susanne</td>\n",
       "      <td>0.400109</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>stephen</td>\n",
       "      <td>stehen</td>\n",
       "      <td>0.968966</td>\n",
       "      <td>stearn</td>\n",
       "      <td>0.501695</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 5
  },
  {
   "cell_type": "code",
   "id": "c20e14fc",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:55:19.423160Z",
     "start_time": "2024-12-05T17:55:08.631465Z"
    }
   },
   "source": [
    "# count the number of unique anchor-pos pairs and anchor-neg pairs\n",
    "anchor_pos = set()\n",
    "anchor_neg = set()\n",
    "for tup in tqdm(triplets_df.itertuples()):\n",
    "    anchor = tup.anchor\n",
    "    pos = tup.positive\n",
    "    neg = tup.negative\n",
    "    anchor_pos.add(f\"{anchor}:{pos}\")\n",
    "    anchor_neg.add(f\"{anchor}:{neg}\")\n",
    "print(len(anchor_pos))\n",
    "print(len(anchor_neg))"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0it [00:00, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "b2718feca5de41c98663b2096171ff68"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "72350\n",
      "594206\n"
     ]
    }
   ],
   "execution_count": 6
  },
  {
   "cell_type": "markdown",
   "id": "4d0d0d78",
   "metadata": {},
   "source": [
    "### read common names"
   ]
  },
  {
   "cell_type": "code",
   "id": "6ee56867",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:56:51.160511Z",
     "start_time": "2024-12-05T17:56:46.937117Z"
    }
   },
   "source": [
    "path = download_file_from_s3(pref_path) if pref_path.startswith(\"s3://\") else pref_path\n",
    "pref_df = read_csv(path)\n",
    "common_names = [name for name in pref_df['name'][:num_common_names].tolist() \\\n",
    "                if len(name) > 1 and re.fullmatch(r'[a-z]+', name)]\n",
    "pref_df = None\n",
    "len(common_names)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "9977"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 8
  },
  {
   "cell_type": "markdown",
   "id": "401ad99c",
   "metadata": {},
   "source": [
    "### read common non-negatives"
   ]
  },
  {
   "cell_type": "code",
   "id": "3606383a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:56:57.668121Z",
     "start_time": "2024-12-05T17:56:52.606436Z"
    }
   },
   "source": [
    "common_non_negatives = set()\n",
    "path = download_file_from_s3(non_negatives_path) if non_negatives_path.startswith(\"s3://\") else non_negatives_path\n",
    "common_non_negatives_df = read_csv(path)\n",
    "for name1, name2 in common_non_negatives_df.values.tolist():\n",
    "    common_non_negatives.add((name1, name2))\n",
    "len(common_non_negatives)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1122584"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 9
  },
  {
   "cell_type": "markdown",
   "id": "8b6a6eec",
   "metadata": {},
   "source": [
    "## Create training data"
   ]
  },
  {
   "cell_type": "code",
   "id": "92da9a8e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:57:01.122216Z",
     "start_time": "2024-12-05T17:57:01.094390Z"
    }
   },
   "source": [
    "# don't add anchor-pos pairs that teach the model bad habits\n",
    "if given_surname == \"given\":\n",
    "    bad_anchor_pos_pairs = [('maria', 'annamaria'), \n",
    "                            ('marie', 'annamarie'),\n",
    "                           ]\n",
    "else:\n",
    "    bad_anchor_pos_pairs = []"
   ],
   "outputs": [],
   "execution_count": 10
  },
  {
   "cell_type": "code",
   "id": "9b51952a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T17:57:04.401313Z",
     "start_time": "2024-12-05T17:57:04.370913Z"
    }
   },
   "source": [
    "def is_bad_anchor_pos_pair(name1, name2):\n",
    "    for bad_name1, bad_name2 in bad_anchor_pos_pairs:\n",
    "        if (name1 == bad_name1 and name2 == bad_name2) or \\\n",
    "           (name2 == bad_name1 and name1 == bad_name2):\n",
    "            return True\n",
    "    return False"
   ],
   "outputs": [],
   "execution_count": 11
  },
  {
   "cell_type": "markdown",
   "id": "47871b51",
   "metadata": {},
   "source": [
    "### Get tokenizer"
   ]
  },
  {
   "cell_type": "code",
   "id": "0c28eaab",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:01:57.383669Z",
     "start_time": "2024-12-05T18:01:56.862057Z"
    }
   },
   "source": [
    "path = download_file_from_s3(tokenizer_path) if tokenizer_path.startswith(\"s3://\") else tokenizer_path\n",
    "tokenize, tokenizer_vocab = get_tokenize_function_and_vocab(tokenizer_path=path, max_tokens=max_tokens)\n",
    "len(tokenizer_vocab)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2048"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 12
  },
  {
   "cell_type": "code",
   "id": "9447cfa9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:02:00.847Z",
     "start_time": "2024-12-05T18:02:00.814615Z"
    }
   },
   "source": [
    "tokenize('dallan')"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1584, 489, 1, 1, 1, 1, 1, 1, 1, 1]"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 13
  },
  {
   "cell_type": "markdown",
   "id": "181fba23",
   "metadata": {},
   "source": [
    "### Add anchor-pos-neg triplets"
   ]
  },
  {
   "cell_type": "code",
   "id": "cdba9648",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:03:00.755397Z",
     "start_time": "2024-12-05T18:02:22.172879Z"
    }
   },
   "source": [
    "# augment data with easy negatives\n",
    "aug_data = []\n",
    "seen_anchor_pos = set()\n",
    "seen_anchor_neg = set()\n",
    "for tup in tqdm(triplets_df.itertuples()):\n",
    "    anchor = tup.anchor\n",
    "    pos = tup.positive\n",
    "    neg = tup.negative\n",
    "    if is_bad_anchor_pos_pair(anchor, pos):\n",
    "        continue\n",
    "    # anchor, positive, hard-negative\n",
    "    for _ in range(num_anchor_pos_neg_copies):\n",
    "        aug_data.append({\n",
    "            'anchor': anchor,\n",
    "            'positive': pos,\n",
    "            'negative': neg,\n",
    "            'positive_score': tup.positive_score,\n",
    "            'negative_score': tup.negative_score,\n",
    "        })\n",
    "\n",
    "    # add anchor-pos-easy-negatives\n",
    "    # only add easy negatives the first time we see this anchor,pos pair\n",
    "    anchor_pos = f\"{anchor},{pos}\"\n",
    "    if anchor_pos not in seen_anchor_pos:\n",
    "        seen_anchor_pos.add(anchor_pos)\n",
    "        ix = 0\n",
    "        while ix < num_easy_pos_negs:\n",
    "            # anchor, positive, easy-negative\n",
    "            easy_neg = random.choice(common_names)\n",
    "            # only add anchor-pos-easy-neg if easy-neg isn't really a non-negative\n",
    "            if anchor == easy_neg or pos == easy_neg or (anchor, easy_neg) in common_non_negatives:\n",
    "                continue\n",
    "            aug_data.append({\n",
    "                'anchor': anchor,\n",
    "                'positive': pos,\n",
    "                'negative': easy_neg,\n",
    "                'positive_score': tup.positive_score,\n",
    "                'negative_score': 0.0,\n",
    "            })\n",
    "            ix += 1\n",
    "\n",
    "    # add anchor-neg-easy-negatives\n",
    "    # only add easy negatives the first time we see this anchor,neg pair\n",
    "    neg_anchor = f\"{neg},{anchor}\"\n",
    "    if neg_anchor not in seen_anchor_neg:\n",
    "        seen_anchor_neg.add(neg_anchor)\n",
    "        ix = 0\n",
    "        while ix < num_easy_neg_negs:\n",
    "            easy_neg = random.choice(common_names)\n",
    "            # only add anchor-neg-easy-neg if easy-neg isn't really a non-negative\n",
    "            if anchor == easy_neg or neg == easy_neg or (anchor, easy_neg) in common_non_negatives:\n",
    "                continue\n",
    "            aug_data.append({\n",
    "                'anchor': anchor,\n",
    "                'positive': neg,\n",
    "                'negative': easy_neg,\n",
    "                'positive_score': tup.negative_score,\n",
    "                'negative_score': 0.0,\n",
    "            })\n",
    "            ix += 1\n",
    "            \n",
    "len(aug_data)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0it [00:00, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "e2de342969264f1683e8856d7ea1636a"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "13494823"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 14
  },
  {
   "cell_type": "markdown",
   "id": "a7e9f680",
   "metadata": {},
   "source": [
    "### Add pos-pos-easyneg triplets"
   ]
  },
  {
   "cell_type": "code",
   "id": "48a15d3d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:03:09.781638Z",
     "start_time": "2024-12-05T18:03:07.850030Z"
    }
   },
   "source": [
    "cnt = 0\n",
    "for pos in tqdm(common_names[:num_common_negs]):\n",
    "    for neg in common_names[:num_common_negs]:\n",
    "        if pos == neg or (pos, neg) in common_non_negatives:\n",
    "            continue\n",
    "        for _ in range(num_common_neg_copies):\n",
    "            aug_data.append({\n",
    "                'anchor': pos,\n",
    "                'positive': pos,\n",
    "                'negative': neg,\n",
    "                'positive_score': 1.0,\n",
    "                'negative_score': 0.0,\n",
    "            })\n",
    "            cnt += 1\n",
    "print(cnt)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "  0%|          | 0/1000 [00:00<?, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "3efa767d71f44e998a838574b31c9866"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1983724\n"
     ]
    }
   ],
   "execution_count": 15
  },
  {
   "cell_type": "markdown",
   "id": "706ca1ed",
   "metadata": {},
   "source": [
    "### Add triplets for names we want to push apart"
   ]
  },
  {
   "cell_type": "code",
   "id": "c32997ec",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:03:23.691946Z",
     "start_time": "2024-12-05T18:03:23.650597Z"
    }
   },
   "source": [
    "if given_surname == \"given\":\n",
    "    push_apart_pairs = [('charles', 'frances'),\n",
    "                        ('marie', 'annie'),\n",
    "                        ('james', 'jane'),\n",
    "                        ('jane', 'janos'),\n",
    "                        ('hannah', 'hans'),\n",
    "                        ('frank', 'frederick'),\n",
    "                        ('anne', 'anders'),\n",
    "                        ('maria', 'manuel'),\n",
    "                        ('maria', 'manuela'),\n",
    "                        ('juan','julia'),\n",
    "                        ('margaret','violet'),\n",
    "                        ('antonio','emilio'),\n",
    "                        ('edward','edwin'),\n",
    "                        ('samuel','smith'),\n",
    "                        ('martin','augustin'),\n",
    "                        ('eva','evan'),\n",
    "                        ('dejesus','de'),\n",
    "                        ('dejesus','dean'),\n",
    "                        ('eliza','luiza'),\n",
    "                        ('frank','mark'),\n",
    "                        ('benjamin','benita'),\n",
    "                        ('andrew','matthew'),\n",
    "                        ('andrew','mathew'),\n",
    "                        ('guadalupe','guy'),\n",
    "                        ('jeanne','susanne'),\n",
    "                        ('delacruz','delaconcepcion'),\n",
    "                        ('rebecca','veronica'),\n",
    "                        ('rebecca','francesca'),\n",
    "                        ('karl','karen'),\n",
    "                        ('karl','karin'),\n",
    "                        ('adam','ada'),\n",
    "                        ('adam','addie'),\n",
    "                        ('bertha','bruce'),\n",
    "                        ('edith','edmond'),\n",
    "                        ('mathias','elias'),\n",
    "                        ('anton','anta'),\n",
    "                        ('ethel','effie'),\n",
    "                        ('delcarmen','oscar'),\n",
    "                        ('santiago','santos'),\n",
    "                        ('vicente','clemente'),\n",
    "                        ('ysabel','ysidro'),\n",
    "                        ('karen','karolina'),\n",
    "                        ('ralph','christoph'),\n",
    "                        ('raymond','reyes'),\n",
    "                        ('maren','christen'),\n",
    "                        ('christoph','jph'),\n",
    "                        ('erzsebet','jozsef'),\n",
    "                        ('carlos','marcos'),\n",
    "                        ('ada','adamus'),\n",
    "                        ('delaluz','dela'),\n",
    "                        ('jennie','jemima'),\n",
    "                        ('lorenzo','vincenzo'),\n",
    "                        ('stina','stella'),\n",
    "                        ('pearl','per'),\n",
    "                        ('pearl','pehr'),\n",
    "                        ('oscar','encarnacion'),\n",
    "                        ('veronica','francesca'),\n",
    "                        ('sebastiana','victoriana'),\n",
    "                        ('elias','matias'),\n",
    "                        ('myrtle','estelle'),\n",
    "                        ('bernardo','leonardo'),\n",
    "                        ('amy','amos'),\n",
    "                        ('leslie','lester'),\n",
    "                        ('rosario','hilario'),\n",
    "                        ('karin','karolina'),\n",
    "                        ('nora','norma'),\n",
    "                        ('michaela','mc'),\n",
    "                        ('christiana','luciana'),\n",
    "                        ('chen','chester'),\n",
    "                        ('angelina','augustina'),\n",
    "                        ('sam','smith'),\n",
    "                        ('soledad','solomon'),\n",
    "                        ('mari','jacobi'),\n",
    "                        ('mari','eli'),\n",
    "                        ('mari','josephi'),\n",
    "                        ('mari','li'),\n",
    "                        ('delacrus','delaconcepcion'),\n",
    "                        ('etta','etienne'),\n",
    "                        ('imre','ines'),\n",
    "                        ('florentina','valentina'),\n",
    "                        ('jacobi','josephi'),\n",
    "                        ('joanne','susanne'),\n",
    "                        ('bernardino','florentino'),\n",
    "                        ('josefina','rufina'),\n",
    "                        ('eli','josephi'),\n",
    "                        ('dean','delia'),\n",
    "                        ('emilio','mario'),\n",
    "                        ('jenny','jemima'),\n",
    "                        ('paulino','antonino'),\n",
    "                        # 13 Oct 2023\n",
    "                        ('anne','anders'),\n",
    "                        ('ann','amy'),\n",
    "                        ('dejesus','de'),\n",
    "                        ('dejesus','dedios'),\n",
    "                        ('anders','an'),\n",
    "                        ('ana','anastacia'),\n",
    "                        ('de','dedios'),\n",
    "                        ('mae','mette'),\n",
    "                        ('betty','bell'),\n",
    "                        ('jesus','julius'),\n",
    "                        ('joao','joel'),\n",
    "                        ('clarence','claire'),\n",
    "                        ('martina','marta'),\n",
    "                        ('roy','ray'),\n",
    "                        ('pearl','per'),\n",
    "                        ('veronica','domenica'),\n",
    "                        ('elias','elisa'),\n",
    "                        ('lidia','li'),\n",
    "                        ('sven','sue'),\n",
    "                        ('bernardino','paulino'),\n",
    "                        ('bernardino','antonino'),\n",
    "                        ('eli','elin'),\n",
    "                        ('emilio','mario'),\n",
    "                        ('antal','an'),\n",
    "                        ('anta','an'),\n",
    "                        ('paulino','antonino'),\n",
    "                       ]\n",
    "else:\n",
    "    push_apart_pairs = []\n",
    "push_apart_copies = 10"
   ],
   "outputs": [],
   "execution_count": 16
  },
  {
   "cell_type": "code",
   "id": "9eb430d5",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:03:29.026599Z",
     "start_time": "2024-12-05T18:03:28.979711Z"
    }
   },
   "source": [
    "for anchor, neg in push_apart_pairs:\n",
    "    for _ in range(push_apart_copies):\n",
    "        aug_data.append({\n",
    "            'anchor': anchor,\n",
    "            'positive': anchor,\n",
    "            'negative': neg,\n",
    "            'positive_score': 1.0,\n",
    "            'negative_score': 0.0,\n",
    "        })"
   ],
   "outputs": [],
   "execution_count": 17
  },
  {
   "cell_type": "markdown",
   "id": "99431d39",
   "metadata": {},
   "source": [
    "## Analyze training data"
   ]
  },
  {
   "cell_type": "code",
   "id": "de0f6b6e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:03:38.506909Z",
     "start_time": "2024-12-05T18:03:38.453956Z"
    }
   },
   "source": [
    "token_id2text = {}\n",
    "for text, id_ in tokenizer_vocab.items():\n",
    "    token_id2text[id_] = text"
   ],
   "outputs": [],
   "execution_count": 18
  },
  {
   "cell_type": "code",
   "id": "e5c83ad9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:28.652913Z",
     "start_time": "2024-12-05T18:03:59.897211Z"
    }
   },
   "source": [
    "counter = Counter()\n",
    "for row in tqdm(aug_data, mininterval=1.0):\n",
    "    for key in ['anchor', 'positive', 'negative']:\n",
    "        for token in tokenize(row[key]):\n",
    "            if token == 1:\n",
    "                break\n",
    "            counter[token] += 1\n",
    "for ix, (token, cnt) in enumerate(counter.most_common()):\n",
    "    print(ix, token, token_id2text[token], cnt)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "  0%|          | 0/15479697 [00:00<?, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "a3ea0f7b9faa408b846a08fd637bcb2f"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 34 ##a 2400867\n",
      "1 37 ##e 2189892\n",
      "2 35 ##n 1777948\n",
      "3 31 ##o 1551878\n",
      "4 45 ##s 1457386\n",
      "5 75 ##ia 1188281\n",
      "6 41 ##l 1183635\n",
      "7 42 ##t 1106371\n",
      "8 49 ##y 904235\n",
      "9 123 ##ina 851578\n",
      "10 38 ##i 771990\n",
      "11 39 ##r 768875\n",
      "12 71 ##ie 762546\n",
      "13 40 ##d 761814\n",
      "14 89 ##us 747787\n",
      "15 64 ##in 733467\n",
      "16 85 ##na 664897\n",
      "17 36 ##h 641336\n",
      "18 104 ##ine 633647\n",
      "19 94 ##la 594915\n",
      "20 171 ##io 562168\n",
      "21 59 ##er 561259\n",
      "22 72 ##on 545622\n",
      "23 135 ##ta 543891\n",
      "24 52 ##b 527673\n",
      "25 73 ##is 524536\n",
      "26 44 ##g 510915\n",
      "27 32 ##m 493290\n",
      "28 103 ##ne 478601\n",
      "29 62 ##en 466277\n",
      "30 56 ##z 415135\n",
      "31 119 ##da 409005\n",
      "32 65 ##el 375927\n",
      "33 51 ##f 371385\n",
      "34 705 ##ri 355007\n",
      "35 153 ##ra 339920\n",
      "36 61 mar 339460\n",
      "37 30 z 333899\n",
      "38 47 ##c 329101\n",
      "39 97 ##le 326423\n",
      "40 163 ar 326230\n",
      "41 46 ##k 323331\n",
      "42 58 ##an 319215\n",
      "43 108 al 306982\n",
      "44 33 ##p 300462\n",
      "45 1368 ##no 289938\n",
      "46 68 ##es 288016\n",
      "47 66 ##il 285533\n",
      "48 712 ##re 281678\n",
      "49 19 o 276387\n",
      "50 48 ##u 275225\n",
      "51 187 la 274943\n",
      "52 202 ##sa 273492\n",
      "53 251 re 271362\n",
      "54 134 el 265379\n",
      "55 159 ##de 253631\n",
      "56 142 ##te 244257\n",
      "57 5 a 243732\n",
      "58 95 ro 241746\n",
      "59 83 ##al 237759\n",
      "60 144 lu 237660\n",
      "61 358 ##va 237120\n",
      "62 50 ##w 236811\n",
      "63 128 ##ol 234549\n",
      "64 185 ##tt 230979\n",
      "65 249 ##ch 230409\n",
      "66 588 ##za 228199\n",
      "67 473 ##st 221548\n",
      "68 9 e 217610\n",
      "69 69 ##or 216417\n",
      "70 180 ##ir 214040\n",
      "71 907 se 213782\n",
      "72 92 ##ph 210550\n",
      "73 737 ##do 208971\n",
      "74 743 ##ino 207730\n",
      "75 8 d 205936\n",
      "76 595 ##je 203203\n",
      "77 611 ##cia 202453\n",
      "78 10 f 201386\n",
      "79 130 le 201272\n",
      "80 54 ##j 201244\n",
      "81 100 ##ce 199969\n",
      "82 671 ##vi 197073\n",
      "83 57 ##ar 195289\n",
      "84 15 k 194793\n",
      "85 368 de 193659\n",
      "86 7 c 192014\n",
      "87 973 eu 191677\n",
      "88 963 ##lo 190780\n",
      "89 194 ##as 190610\n",
      "90 24 t 188991\n",
      "91 98 ##ma 187370\n",
      "92 82 ##se 181665\n",
      "93 74 an 180536\n",
      "94 121 ##ur 179886\n",
      "95 200 ##man 178798\n",
      "96 79 ##ic 177954\n",
      "97 167 ##lia 176522\n",
      "98 1276 ##ha 175933\n",
      "99 133 lo 175865\n",
      "100 11 g 175164\n",
      "101 286 ##os 175065\n",
      "102 426 ger 173788\n",
      "103 512 or 173198\n",
      "104 326 del 172872\n",
      "105 90 ma 169039\n",
      "106 350 ##it 167019\n",
      "107 741 ##ke 166118\n",
      "108 183 ##id 165248\n",
      "109 449 ##ea 164566\n",
      "110 1332 ##me 164156\n",
      "111 140 ##ton 162837\n",
      "112 322 ##ro 162779\n",
      "113 310 ##im 162644\n",
      "114 497 gu 161285\n",
      "115 451 li 161178\n",
      "116 405 ##ita 160809\n",
      "117 219 ##son 159601\n",
      "118 43 ##v 158726\n",
      "119 147 ##lie 157436\n",
      "120 221 ##ena 156443\n",
      "121 235 er 155750\n",
      "122 337 ##un 155305\n",
      "123 241 ##ley 155107\n",
      "124 1334 me 154865\n",
      "125 29 y 154509\n",
      "126 667 ##ilia 154272\n",
      "127 101 ##bert 153636\n",
      "128 13 i 153313\n",
      "129 633 ##to 150677\n",
      "130 238 ben 150092\n",
      "131 647 ##illa 149184\n",
      "132 182 ##ora 148379\n",
      "133 529 mel 147417\n",
      "134 23 s 147245\n",
      "135 565 ##ida 147107\n",
      "136 374 mat 146629\n",
      "137 137 ##nie 145277\n",
      "138 231 ##ey 144931\n",
      "139 748 si 141709\n",
      "140 606 vi 140979\n",
      "141 308 laur 139582\n",
      "142 631 ra 138216\n",
      "143 323 ##ca 136418\n",
      "144 170 ##tha 134442\n",
      "145 275 flor 134190\n",
      "146 732 ne 132041\n",
      "147 291 ##ig 131937\n",
      "148 313 ag 130584\n",
      "149 145 ##ac 129946\n",
      "150 746 ##ge 129782\n",
      "151 27 w 129593\n",
      "152 63 ##th 129252\n",
      "153 1753 dela 129138\n",
      "154 1049 ##tje 129061\n",
      "155 345 ##ver 128065\n",
      "156 1075 ##ka 127326\n",
      "157 534 mer 127154\n",
      "158 160 em 126968\n",
      "159 338 ##tin 126447\n",
      "160 448 cor 126341\n",
      "161 120 th 124682\n",
      "162 1599 ##ss 124220\n",
      "163 744 na 123907\n",
      "164 360 ##co 123697\n",
      "165 81 ##et 123475\n",
      "166 783 ##em 123469\n",
      "167 67 jo 123411\n",
      "168 55 ##x 123410\n",
      "169 122 ed 122918\n",
      "170 602 ##ul 122694\n",
      "171 376 rosa 122412\n",
      "172 246 ##ru 122328\n",
      "173 132 marg 121876\n",
      "174 440 ##ve 121528\n",
      "175 434 ##qu 121387\n",
      "176 879 ##ila 121331\n",
      "177 1140 ce 120626\n",
      "178 301 ##ice 120598\n",
      "179 188 ##ene 120498\n",
      "180 228 luc 120271\n",
      "181 823 ##tta 119890\n",
      "182 1271 ##cen 119485\n",
      "183 294 leon 118903\n",
      "184 1012 hil 118791\n",
      "185 189 jan 118774\n",
      "186 370 ##ly 118124\n",
      "187 141 har 118017\n",
      "188 1161 ##ij 117927\n",
      "189 793 ##ica 117822\n",
      "190 22 r 117764\n",
      "191 1085 te 117562\n",
      "192 657 ##inda 117430\n",
      "193 110 ge 116597\n",
      "194 1035 mad 116334\n",
      "195 435 ##lina 116024\n",
      "196 765 ca 115576\n",
      "197 161 lou 114908\n",
      "198 484 ##etta 114819\n",
      "199 557 ##ius 114700\n",
      "200 1345 ##ad 114522\n",
      "201 984 ##ze 113899\n",
      "202 599 ##iana 113864\n",
      "203 695 ##cio 113797\n",
      "204 107 eli 113457\n",
      "205 88 ch 112977\n",
      "206 972 mal 111359\n",
      "207 768 ba 110845\n",
      "208 877 tr 110279\n",
      "209 152 ju 109977\n",
      "210 184 ##ian 108587\n",
      "211 524 he 108379\n",
      "212 1792 marce 108328\n",
      "213 205 dor 107929\n",
      "214 60 ##li 107913\n",
      "215 518 per 107758\n",
      "216 207 ber 107431\n",
      "217 146 ##dr 106500\n",
      "218 1839 bo 106209\n",
      "219 371 man 104030\n",
      "220 417 rose 103923\n",
      "221 459 sal 103865\n",
      "222 1329 bal 103712\n",
      "223 76 wil 103703\n",
      "224 423 ##ent 102190\n",
      "225 415 ab 102187\n",
      "226 1282 mart 101940\n",
      "227 844 ##ib 101386\n",
      "228 26 v 101192\n",
      "229 2037 ta 101144\n",
      "230 541 math 100925\n",
      "231 156 ##ter 100657\n",
      "232 663 bur 100420\n",
      "233 740 cas 99907\n",
      "234 1524 ##tie 99013\n",
      "235 752 val 98199\n",
      "236 193 ##line 97952\n",
      "237 344 am 97603\n",
      "238 1552 ##ba 97580\n",
      "239 77 fr 97189\n",
      "240 688 bert 97151\n",
      "241 1517 ##sia 97102\n",
      "242 722 ##um 96813\n",
      "243 233 her 96721\n",
      "244 738 sa 96021\n",
      "245 1595 ##ret 95846\n",
      "246 1001 lin 95570\n",
      "247 111 ##ry 95384\n",
      "248 1104 as 95020\n",
      "249 262 anton 94764\n",
      "250 190 car 94680\n",
      "251 1787 ga 94270\n",
      "252 421 ##mer 94014\n",
      "253 466 ##die 93851\n",
      "254 883 ##ven 93234\n",
      "255 1084 ap 92805\n",
      "256 535 ja 92689\n",
      "257 755 en 92524\n",
      "258 289 es 92173\n",
      "259 1264 gi 92097\n",
      "260 1204 ##ien 91703\n",
      "261 197 ##ick 91591\n",
      "262 661 phil 91184\n",
      "263 312 ##eli 90560\n",
      "264 1362 fa 90242\n",
      "265 247 ##vin 89779\n",
      "266 970 ##ana 89750\n",
      "267 298 ##od 89404\n",
      "268 1272 ##po 89106\n",
      "269 861 ##ee 89060\n",
      "270 203 ##ell 88782\n",
      "271 201 ##sie 88595\n",
      "272 181 pa 88175\n",
      "273 209 wal 88166\n",
      "274 105 ##ed 87888\n",
      "275 573 ##dia 87699\n",
      "276 406 ##ilda 87163\n",
      "277 900 sil 86316\n",
      "278 303 ##yn 86293\n",
      "279 1218 no 86265\n",
      "280 612 ##ant 85923\n",
      "281 198 christ 85600\n",
      "282 1370 ##go 85494\n",
      "283 253 ad 85362\n",
      "284 320 ha 85304\n",
      "285 1207 pas 85278\n",
      "286 407 ##der 85043\n",
      "287 551 ele 84814\n",
      "288 777 marc 84039\n",
      "289 968 ##den 84023\n",
      "290 217 ##lin 83764\n",
      "291 1898 ##dor 83621\n",
      "292 1680 mi 83554\n",
      "293 392 ale 83374\n",
      "294 268 ##fr 82290\n",
      "295 1117 ##enc 82153\n",
      "296 158 cath 82098\n",
      "297 296 ##at 82086\n",
      "298 564 bernard 82057\n",
      "299 926 herm 81307\n",
      "300 273 je 81269\n",
      "301 481 ##ela 80931\n",
      "302 931 hu 80817\n",
      "303 424 eva 80737\n",
      "304 432 ##ola 80627\n",
      "305 935 co 80316\n",
      "306 164 fred 80260\n",
      "307 918 ##don 80228\n",
      "308 802 ##of 80067\n",
      "309 373 ##ette 80065\n",
      "310 1108 ##via 79099\n",
      "311 1703 arm 78972\n",
      "312 20 p 78891\n",
      "313 1747 ##ild 78876\n",
      "314 70 ##am 78864\n",
      "315 1806 ##sen 78732\n",
      "316 6 b 78699\n",
      "317 1026 ##mo 78656\n",
      "318 336 ver 78427\n",
      "319 1520 ##vel 78206\n",
      "320 762 ##vina 78100\n",
      "321 1775 ##ut 78036\n",
      "322 318 is 78008\n",
      "323 867 ##ome 77826\n",
      "324 1437 dar 77459\n",
      "325 965 ##ele 77215\n",
      "326 632 cal 77086\n",
      "327 255 ##ella 77053\n",
      "328 1762 els 77000\n",
      "329 590 br 76547\n",
      "330 468 the 76530\n",
      "331 696 do 76321\n",
      "332 305 mag 76173\n",
      "333 263 carl 75946\n",
      "334 718 ##ile 75652\n",
      "335 436 martin 75607\n",
      "336 1555 il 75294\n",
      "337 881 ##ide 74904\n",
      "338 1230 ##que 74846\n",
      "339 195 ru 74685\n",
      "340 1444 ##the 74315\n",
      "341 403 pe 73951\n",
      "342 1507 ##zia 73508\n",
      "343 974 ##iano 73204\n",
      "344 658 ##ck 72998\n",
      "345 277 bar 72692\n",
      "346 932 ##ga 72516\n",
      "347 656 ##ona 72323\n",
      "348 1166 wa 72316\n",
      "349 640 will 72045\n",
      "350 288 clar 71836\n",
      "351 394 lor 71761\n",
      "352 578 win 71282\n",
      "353 619 ##ill 71272\n",
      "354 1201 ##itt 71236\n",
      "355 1576 cha 71171\n",
      "356 218 da 70938\n",
      "357 836 ##hard 70929\n",
      "358 1574 bart 70774\n",
      "359 428 ##ot 70716\n",
      "360 1890 ell 70637\n",
      "361 610 ##ford 70378\n",
      "362 760 ##eta 70130\n",
      "363 943 gar 70117\n",
      "364 1657 pr 69798\n",
      "365 585 ##pe 69687\n",
      "366 1467 ##gen 69575\n",
      "367 429 ste 69537\n",
      "368 401 ##dy 69468\n",
      "369 1206 alb 69105\n",
      "370 910 ##und 69074\n",
      "371 319 ##ion 68955\n",
      "372 363 st 68423\n",
      "373 1311 ##pa 68325\n",
      "374 894 ##van 68212\n",
      "375 413 august 68130\n",
      "376 102 ##ard 67764\n",
      "377 1546 cat 67719\n",
      "378 1357 gen 67607\n",
      "379 735 mor 67491\n",
      "380 348 paul 67455\n",
      "381 456 ##tor 67362\n",
      "382 476 ##ille 67327\n",
      "383 961 ##ira 67198\n",
      "384 617 ##ah 67110\n",
      "385 287 ##ec 66985\n",
      "386 1590 ##sel 66834\n",
      "387 1105 ##din 66707\n",
      "388 511 con 66381\n",
      "389 230 ##iel 66336\n",
      "390 1321 este 66227\n",
      "391 1829 barthol 66227\n",
      "392 1353 angel 66219\n",
      "393 212 ##len 66205\n",
      "394 1722 ##ise 66182\n",
      "395 1662 so 66180\n",
      "396 938 col 65823\n",
      "397 1328 ##ua 65810\n",
      "398 986 lud 65793\n",
      "399 1728 ##pha 65684\n",
      "400 259 ##mon 65632\n",
      "401 998 ##mar 65360\n",
      "402 589 leo 65309\n",
      "403 1498 carm 65286\n",
      "404 475 ##elia 65183\n",
      "405 649 nic 65163\n",
      "406 859 loren 64511\n",
      "407 531 ##zel 64508\n",
      "408 223 hel 63983\n",
      "409 227 kath 63964\n",
      "410 420 ##ore 63876\n",
      "411 1142 par 63811\n",
      "412 683 ##ias 63810\n",
      "413 131 hen 63553\n",
      "414 18 n 63470\n",
      "415 1466 ul 63377\n",
      "416 284 jacob 63250\n",
      "417 199 fl 63159\n",
      "418 498 ##yl 63097\n",
      "419 150 ##ris 62955\n",
      "420 539 ##lis 62911\n",
      "421 1236 ing 62776\n",
      "422 2043 let 62770\n",
      "423 375 ho 62691\n",
      "424 1291 aur 62418\n",
      "425 222 ##om 62411\n",
      "426 505 sh 62232\n",
      "427 1278 alm 62214\n",
      "428 1692 at 62072\n",
      "429 1675 ##if 61929\n",
      "430 627 ka 61664\n",
      "431 1011 ##onia 61491\n",
      "432 216 albert 61383\n",
      "433 234 ali 61370\n",
      "434 812 in 61294\n",
      "435 1323 just 61099\n",
      "436 530 os 61092\n",
      "437 2028 ##bell 60846\n",
      "438 724 ##dis 60828\n",
      "439 559 feli 60728\n",
      "440 1991 ##cu 60645\n",
      "441 1452 adel 60595\n",
      "442 317 min 60408\n",
      "443 258 mil 60257\n",
      "444 12 h 60195\n",
      "445 1384 mo 60073\n",
      "446 1469 du 59650\n",
      "447 799 dom 59456\n",
      "448 206 ##ob 59340\n",
      "449 220 ev 59338\n",
      "450 542 ##ney 59093\n",
      "451 215 ##anna 59006\n",
      "452 1018 ##ny 58604\n",
      "453 902 len 58558\n",
      "454 311 ##ith 58485\n",
      "455 1056 ##so 58252\n",
      "456 1397 felic 57956\n",
      "457 2001 ven 57732\n",
      "458 114 georg 57624\n",
      "459 315 ##ik 57610\n",
      "460 1866 ##rit 57607\n",
      "461 388 be 57358\n",
      "462 958 ##rine 57190\n",
      "463 1776 maxim 57143\n",
      "464 813 kat 57131\n",
      "465 570 jer 56722\n",
      "466 1450 ##val 56364\n",
      "467 465 emil 56197\n",
      "468 495 nor 56110\n",
      "469 2008 fil 56050\n",
      "470 543 fer 55943\n",
      "471 361 cla 55749\n",
      "472 196 ann 55730\n",
      "473 1366 ##ima 55695\n",
      "474 708 ol 55475\n",
      "475 1258 bu 55429\n",
      "476 2002 ##les 55427\n",
      "477 112 ##eth 55284\n",
      "478 136 franc 55045\n",
      "479 1836 va 55034\n",
      "480 893 ##cion 54912\n",
      "481 84 john 54878\n",
      "482 1516 ##nett 54748\n",
      "483 1249 jor 54364\n",
      "484 1365 anasta 54184\n",
      "485 533 ada 53957\n",
      "486 555 cle 53882\n",
      "487 1897 tor 53852\n",
      "488 1326 ##ito 53832\n",
      "489 148 margar 53760\n",
      "490 109 ##org 53731\n",
      "491 1033 ama 53728\n",
      "492 1286 sant 53698\n",
      "493 1810 gun 53586\n",
      "494 847 ##ner 53460\n",
      "495 1430 edu 53404\n",
      "496 91 ##ert 53242\n",
      "497 771 mon 53002\n",
      "498 1373 ##isa 52898\n",
      "499 1487 ##eus 52833\n",
      "500 1831 ##ip 52812\n",
      "501 651 ##iah 52811\n",
      "502 1479 petron 52791\n",
      "503 492 oli 52736\n",
      "504 962 ##ber 52623\n",
      "505 763 ##ale 52543\n",
      "506 1600 ##ten 52470\n",
      "507 229 ##ald 52351\n",
      "508 2006 ##let 52249\n",
      "509 1732 berna 52181\n",
      "510 342 gra 52139\n",
      "511 1538 sab 52135\n",
      "512 1619 alf 52085\n",
      "513 14 j 51971\n",
      "514 340 don 51801\n",
      "515 778 ##land 51783\n",
      "516 1580 han 51776\n",
      "517 1689 des 51537\n",
      "518 1871 dam 51489\n",
      "519 1627 crist 51481\n",
      "520 781 gil 51443\n",
      "521 213 ##rie 51365\n",
      "522 719 ##zo 51302\n",
      "523 831 den 51231\n",
      "524 1417 qu 51220\n",
      "525 983 ##vis 51170\n",
      "526 1372 bir 51094\n",
      "527 1605 ##oro 51042\n",
      "528 467 ##ing 50825\n",
      "529 1523 sig 50825\n",
      "530 391 ##ud 50789\n",
      "531 168 cl 50690\n",
      "532 138 ##ich 50656\n",
      "533 416 ##inia 50636\n",
      "534 1746 ##dell 50578\n",
      "535 1416 bas 50452\n",
      "536 414 susan 50165\n",
      "537 714 ##ite 50119\n",
      "538 450 ##win 50056\n",
      "539 214 ##nes 50051\n",
      "540 124 joseph 50039\n",
      "541 143 anna 49974\n",
      "542 1961 ##ves 49899\n",
      "543 716 ##bur 49692\n",
      "544 1604 ##mina 49681\n",
      "545 327 ##cy 49675\n",
      "546 354 anne 49665\n",
      "547 1308 delos 49515\n",
      "548 1640 cres 49467\n",
      "549 569 isa 49346\n",
      "550 1569 teod 49310\n",
      "551 1354 ##uz 49129\n",
      "552 1188 ##iz 49124\n",
      "553 875 ana 48918\n",
      "554 1303 ##lu 48688\n",
      "555 457 ##by 48683\n",
      "556 1145 ##ilde 48643\n",
      "557 995 philipp 48598\n",
      "558 1364 hal 48555\n",
      "559 860 lar 48399\n",
      "560 729 ##men 48316\n",
      "561 1952 lis 48238\n",
      "562 191 marie 48138\n",
      "563 281 may 48017\n",
      "564 733 est 47989\n",
      "565 874 ##vie 47896\n",
      "566 1857 henri 47544\n",
      "567 1000 ##des 47404\n",
      "568 463 pat 47050\n",
      "569 1042 ##ue 46945\n",
      "570 260 lil 46895\n",
      "571 2026 ##rina 46837\n",
      "572 1112 ##ire 46805\n",
      "573 1339 ser 46621\n",
      "574 1021 claud 46572\n",
      "575 1237 jos 46348\n",
      "576 1519 dion 46324\n",
      "577 1699 ##one 46263\n",
      "578 87 mary 46116\n",
      "579 151 ##oma 45972\n",
      "580 725 gene 45851\n",
      "581 1553 san 45846\n",
      "582 955 gott 45581\n",
      "583 837 ##per 45548\n",
      "584 257 ph 45542\n",
      "585 1214 ke 45517\n",
      "586 232 ##ett 45510\n",
      "587 330 ir 45486\n",
      "588 412 michael 45395\n",
      "589 1175 cam 45232\n",
      "590 1186 ##ery 45101\n",
      "591 178 margaret 45059\n",
      "592 25 u 45047\n",
      "593 1023 ##ach 45029\n",
      "594 1841 bel 44893\n",
      "595 643 ##ric 44828\n",
      "596 1275 ##ala 44817\n",
      "597 1578 ##est 44788\n",
      "598 835 ##ier 44735\n",
      "599 924 ##sey 44607\n",
      "600 367 barb 44556\n",
      "601 270 frances 44483\n",
      "602 809 joan 44322\n",
      "603 1089 au 44242\n",
      "604 1598 ther 44237\n",
      "605 366 bern 44186\n",
      "606 489 ##lan 44158\n",
      "607 1068 clem 43999\n",
      "608 1988 ##rell 43752\n",
      "609 1242 ola 43664\n",
      "610 162 thomas 43411\n",
      "611 454 gr 43405\n",
      "612 1233 ##oll 43177\n",
      "613 863 ##well 42915\n",
      "614 1867 jenn 42700\n",
      "615 1730 domin 42650\n",
      "616 1514 lucia 42588\n",
      "617 717 dol 42451\n",
      "618 1177 ##mie 42420\n",
      "619 1673 ##isla 42387\n",
      "620 1314 ole 42362\n",
      "621 552 leonard 42337\n",
      "622 857 carol 42160\n",
      "623 292 andr 42149\n",
      "624 779 ott 41968\n",
      "625 1474 theodor 41785\n",
      "626 547 ##ula 41747\n",
      "627 1679 tere 41719\n",
      "628 166 ##ann 41538\n",
      "629 490 ##rich 41519\n",
      "630 125 george 41457\n",
      "631 1313 clement 41244\n",
      "632 1220 ##ura 40989\n",
      "633 389 wilhelm 40881\n",
      "634 933 ##elina 40717\n",
      "635 359 jen 40687\n",
      "636 1494 ##ano 40594\n",
      "637 386 ros 40420\n",
      "638 1654 hin 40408\n",
      "639 1795 ##orn 40287\n",
      "640 1970 ##lyn 40268\n",
      "641 872 maur 40230\n",
      "642 653 ##res 40223\n",
      "643 339 gert 40158\n",
      "644 1434 die 40137\n",
      "645 1442 stephan 40041\n",
      "646 1398 ##ros 39975\n",
      "647 211 ##and 39945\n",
      "648 1656 po 39868\n",
      "649 1526 rob 39831\n",
      "650 396 ##dal 39787\n",
      "651 1893 bon 39774\n",
      "652 2036 ##imo 39667\n",
      "653 648 ##sh 39654\n",
      "654 1028 ##end 39597\n",
      "655 1065 ##ika 39500\n",
      "656 1203 const 39489\n",
      "657 2012 eng 39418\n",
      "658 808 gre 39417\n",
      "659 871 igna 39362\n",
      "660 814 cecil 39352\n",
      "661 1682 ##cie 39333\n",
      "662 1429 bla 39174\n",
      "663 776 ##ger 39148\n",
      "664 1557 ##onso 39096\n",
      "665 1798 ##mus 39021\n",
      "666 1305 ##aria 39018\n",
      "667 1183 levi 38951\n",
      "668 1094 emm 38847\n",
      "669 785 nicola 38818\n",
      "670 1587 til 38621\n",
      "671 515 ang 38598\n",
      "672 1918 geert 38576\n",
      "673 1832 deli 38555\n",
      "674 1663 michel 38524\n",
      "675 726 ##gar 38514\n",
      "676 745 vern 38492\n",
      "677 666 marian 38471\n",
      "678 650 stan 38460\n",
      "679 1818 hy 38347\n",
      "680 236 sam 38332\n",
      "681 1529 ##rik 38287\n",
      "682 1916 brig 38267\n",
      "683 1066 ##mund 38215\n",
      "684 848 ever 38110\n",
      "685 826 julian 37675\n",
      "686 1696 ##ilio 37632\n",
      "687 328 ##ff 37565\n",
      "688 1406 hendrik 37386\n",
      "689 797 ##las 37096\n",
      "690 971 tom 37074\n",
      "691 899 arn 36899\n",
      "692 1389 ##entin 36868\n",
      "693 1778 magd 36821\n",
      "694 430 ##eb 36740\n",
      "695 993 ##bie 36651\n",
      "696 99 jose 36649\n",
      "697 154 robert 36600\n",
      "698 1904 lon 36446\n",
      "699 1072 jud 36229\n",
      "700 2044 eb 36201\n",
      "701 192 ##uel 36186\n",
      "702 397 ernest 36072\n",
      "703 840 ##eline 36045\n",
      "704 711 kar 35962\n",
      "705 1250 ##ane 35943\n",
      "706 186 francis 35843\n",
      "707 597 ##tis 35826\n",
      "708 1584 dal 35794\n",
      "709 1541 henric 35791\n",
      "710 770 matth 35759\n",
      "711 1741 pal 35747\n",
      "712 1691 sebastian 35728\n",
      "713 324 ##ttie 35719\n",
      "714 1876 bra 35700\n",
      "715 948 mur 35696\n",
      "716 1027 ur 35603\n",
      "717 325 lee 35497\n",
      "718 1738 sever 35456\n",
      "719 1634 willem 35313\n",
      "720 700 dora 35285\n",
      "721 1333 hol 35282\n",
      "722 1299 ##eda 35237\n",
      "723 1724 cleo 35096\n",
      "724 1499 cand 35011\n",
      "725 851 alvin 34918\n",
      "726 849 phillip 34861\n",
      "727 994 ##nis 34800\n",
      "728 1642 elen 34790\n",
      "729 1817 ##ban 34751\n",
      "730 1485 wel 34674\n",
      "731 1265 sol 34646\n",
      "732 1385 lam 34627\n",
      "733 1880 adrian 34587\n",
      "734 283 ray 34488\n",
      "735 822 petr 34441\n",
      "736 1847 hon 34429\n",
      "737 1610 ##von 34316\n",
      "738 537 johan 34267\n",
      "739 791 sylv 34199\n",
      "740 1151 ##par 34187\n",
      "741 250 emma 34070\n",
      "742 975 victoria 33993\n",
      "743 964 simon 33991\n",
      "744 1734 ##ico 33977\n",
      "745 1641 celes 33938\n",
      "746 1034 ter 33879\n",
      "747 1095 bet 33833\n",
      "748 1875 hed 33716\n",
      "749 1855 narc 33715\n",
      "750 113 maria 33705\n",
      "751 271 ##old 33646\n",
      "752 758 ##rad 33645\n",
      "753 2027 bea 33605\n",
      "754 444 eliza 33417\n",
      "755 1942 ##itte 33404\n",
      "756 1827 nik 33387\n",
      "757 1288 ##wen 33371\n",
      "758 1294 eula 33312\n",
      "759 482 josef 33277\n",
      "760 1752 ##vig 33108\n",
      "761 621 ##zie 33100\n",
      "762 331 dan 33068\n",
      "763 306 ##oph 32974\n",
      "764 909 adolph 32877\n",
      "765 1460 ##ston 32712\n",
      "766 2015 ##jen 32652\n",
      "767 692 anth 32604\n",
      "768 885 krist 32422\n",
      "769 1192 ##lene 32417\n",
      "770 516 victor 32408\n",
      "771 409 ethel 32226\n",
      "772 1435 gabriel 32188\n",
      "773 494 pearl 32168\n",
      "774 1131 sy 32166\n",
      "775 1766 valentin 32120\n",
      "776 1489 lora 32087\n",
      "777 1030 georgia 32019\n",
      "778 1052 fern 32001\n",
      "779 930 vinc 31990\n",
      "780 2011 thom 31955\n",
      "781 280 ##hel 31792\n",
      "782 1136 pol 31734\n",
      "783 422 christian 31724\n",
      "784 1491 sim 31654\n",
      "785 1045 ##ario 31626\n",
      "786 1955 ces 31573\n",
      "787 687 joe 31559\n",
      "788 244 ##oy 31421\n",
      "789 1010 hendr 31376\n",
      "790 2014 mic 31357\n",
      "791 1234 margret 31353\n",
      "792 1130 eugen 31303\n",
      "793 1607 mill 31282\n",
      "794 155 elizabeth 31138\n",
      "795 1533 ##rey 31137\n",
      "796 282 ##ust 31043\n",
      "797 1761 ##dine 30980\n",
      "798 17 m 30937\n",
      "799 300 ##fred 30928\n",
      "800 356 jean 30752\n",
      "801 1742 ##issa 30710\n",
      "802 957 andre 30657\n",
      "803 1706 ##erina 30591\n",
      "804 175 ##ence 30472\n",
      "805 1690 ingeb 30444\n",
      "806 1783 julie 30435\n",
      "807 1907 ##sebet 30408\n",
      "808 2046 sera 30389\n",
      "809 1903 alej 30365\n",
      "810 626 hans 30321\n",
      "811 1169 tomas 30306\n",
      "812 514 philip 30295\n",
      "813 1227 ##seb 30094\n",
      "814 1528 iv 30010\n",
      "815 1122 ##ler 29971\n",
      "816 1571 xa 29879\n",
      "817 1873 ##fried 29864\n",
      "818 1685 ##rid 29523\n",
      "819 966 rud 29505\n",
      "820 464 alex 29496\n",
      "821 1812 ##itha 29462\n",
      "822 614 hein 29448\n",
      "823 1509 vil 29305\n",
      "824 750 ##ois 29271\n",
      "825 118 charl 29259\n",
      "826 402 soph 29225\n",
      "827 1884 ez 29201\n",
      "828 343 ##mond 29165\n",
      "829 369 ellen 29127\n",
      "830 1973 gerard 28983\n",
      "831 1004 ane 28972\n",
      "832 790 christoph 28920\n",
      "833 1925 jacin 28836\n",
      "834 1346 mir 28833\n",
      "835 1048 conrad 28706\n",
      "836 1504 jacqu 28660\n",
      "837 96 fran 28616\n",
      "838 1420 ##kin 28560\n",
      "839 544 herman 28493\n",
      "840 28 x 28460\n",
      "841 165 frank 28419\n",
      "842 382 alfred 28395\n",
      "843 1791 gus 28388\n",
      "844 527 theod 28378\n",
      "845 1625 hor 28341\n",
      "846 1110 mc 28179\n",
      "847 1558 ##idr 28154\n",
      "848 646 corne 28103\n",
      "849 1567 rol 28027\n",
      "850 1800 roza 27735\n",
      "851 1032 adela 27700\n",
      "852 1133 adr 27506\n",
      "853 1786 eric 27496\n",
      "854 355 peter 27367\n",
      "855 1908 ##ii 27352\n",
      "856 1029 ##wood 27256\n",
      "857 418 vic 27218\n",
      "858 691 margr 27186\n",
      "859 1586 frider 27155\n",
      "860 1927 wend 27150\n",
      "861 398 laura 27132\n",
      "862 1198 gustav 27122\n",
      "863 1943 wy 27110\n",
      "864 1745 mah 26953\n",
      "865 1144 ##sy 26951\n",
      "866 903 ##andr 26906\n",
      "867 1602 ela 26824\n",
      "868 1999 isid 26706\n",
      "869 980 ##linda 26679\n",
      "870 1165 ys 26655\n",
      "871 1723 ##vier 26622\n",
      "872 1835 gertrud 26620\n",
      "873 1500 frederic 26497\n",
      "874 759 adam 26474\n",
      "875 1100 vincent 26433\n",
      "876 1790 giov 26398\n",
      "877 1542 bernhard 26394\n",
      "878 1088 ##olf 26359\n",
      "879 1081 kirst 26270\n",
      "880 1628 frederik 26212\n",
      "881 1930 fre 26088\n",
      "882 352 nan 26063\n",
      "883 845 melvin 26056\n",
      "884 1646 ambro 25874\n",
      "885 1707 deb 25849\n",
      "886 664 max 25699\n",
      "887 346 clara 25646\n",
      "888 1921 alexandr 25609\n",
      "889 1889 ker 25607\n",
      "890 2007 octa 25556\n",
      "891 483 ly 25517\n",
      "892 919 ##lio 25510\n",
      "893 645 frieder 25483\n",
      "894 784 les 25477\n",
      "895 1949 kon 25473\n",
      "896 1674 elise 25456\n",
      "897 1713 van 25422\n",
      "898 566 cora 25375\n",
      "899 1103 ##lor 25329\n",
      "900 1292 rand 25304\n",
      "901 1295 bened 25232\n",
      "902 261 elis 25226\n",
      "903 1408 ##lino 25218\n",
      "904 1150 vicen 25183\n",
      "905 1111 rh 25153\n",
      "906 351 ida 25076\n",
      "907 1796 ##ok 25039\n",
      "908 1554 ##itz 25021\n",
      "909 1173 alph 25016\n",
      "910 446 ella 24965\n",
      "911 604 johanna 24954\n",
      "912 680 jakob 24872\n",
      "913 224 jane 24801\n",
      "914 1737 christen 24792\n",
      "915 299 frederick 24784\n",
      "916 1997 ##mira 24721\n",
      "917 1402 alva 24629\n",
      "918 642 lena 24610\n",
      "919 1335 juli 24570\n",
      "920 278 richard 24545\n",
      "921 1972 gerhard 24526\n",
      "922 86 william 24405\n",
      "923 1193 sebast 24333\n",
      "924 126 ##ara 24187\n",
      "925 1090 hubert 24150\n",
      "926 1182 janet 23991\n",
      "927 353 ##elle 23966\n",
      "928 1564 ##ang 23958\n",
      "929 581 margaretha 23923\n",
      "930 1989 ##omena 23910\n",
      "931 949 ##ustin 23869\n",
      "932 1180 ora 23863\n",
      "933 1781 joze 23848\n",
      "934 915 ##ville 23825\n",
      "935 380 daniel 23821\n",
      "936 117 ##ath 23743\n",
      "937 437 agnes 23671\n",
      "938 1123 harl 23654\n",
      "939 1457 nicolas 23610\n",
      "940 1990 syb 23562\n",
      "941 806 marguer 23551\n",
      "942 1024 francois 23545\n",
      "943 1063 raf 23518\n",
      "944 264 sus 23497\n",
      "945 868 ##wig 23474\n",
      "946 172 louis 23345\n",
      "947 1596 judith 23317\n",
      "948 736 char 23309\n",
      "949 1079 ##anda 23275\n",
      "950 1809 eph 23221\n",
      "951 487 ##etha 23161\n",
      "952 1512 barth 23160\n",
      "953 652 fan 23088\n",
      "954 1632 hay 23085\n",
      "955 210 edward 23053\n",
      "956 1132 gregor 23001\n",
      "957 1254 for 22958\n",
      "958 334 ##yr 22954\n",
      "959 365 nel 22947\n",
      "960 438 roy 22865\n",
      "961 204 jac 22814\n",
      "962 1002 earl 22776\n",
      "963 1506 ##my 22759\n",
      "964 1771 aloy 22739\n",
      "965 1683 grac 22731\n",
      "966 523 reb 22716\n",
      "967 728 eleanor 22714\n",
      "968 1813 benedic 22684\n",
      "969 461 gertrude 22678\n",
      "970 1585 nell 22636\n",
      "971 819 rachel 22618\n",
      "972 2041 alphon 22589\n",
      "973 297 ruth 22442\n",
      "974 805 susanna 22322\n",
      "975 1179 ferdinand 22282\n",
      "976 333 mich 22247\n",
      "977 723 gerald 22238\n",
      "978 169 sara 22198\n",
      "979 341 virg 22177\n",
      "980 1141 jens 22142\n",
      "981 390 benjamin 22119\n",
      "982 411 julia 22026\n",
      "983 2045 mattha 21965\n",
      "984 757 ##all 21961\n",
      "985 522 myrt 21961\n",
      "986 824 flora 21955\n",
      "987 697 alma 21926\n",
      "988 493 irene 21884\n",
      "989 1190 cyr 21876\n",
      "990 1070 seb 21860\n",
      "991 1698 emilia 21790\n",
      "992 1283 bro 21640\n",
      "993 1458 hermann 21632\n",
      "994 1025 arnold 21627\n",
      "995 225 ##ew 21567\n",
      "996 1181 mark 21565\n",
      "997 1223 ##abel 21531\n",
      "998 1802 pieter 21421\n",
      "999 1246 wh 21409\n",
      "1000 1006 nich 21390\n",
      "1001 1148 dean 21364\n",
      "1002 928 jona 21312\n",
      "1003 852 bell 21308\n",
      "1004 387 eth 21305\n",
      "1005 792 isabel 21296\n",
      "1006 644 magdalena 21235\n",
      "1007 226 johann 21197\n",
      "1008 892 leona 21156\n",
      "1009 625 ##gie 21129\n",
      "1010 1862 franzis 20976\n",
      "1011 293 elisabeth 20947\n",
      "1012 889 ##art 20916\n",
      "1013 2009 ##ustina 20914\n",
      "1014 2030 frans 20914\n",
      "1015 1910 ##sius 20905\n",
      "1016 1243 joanna 20790\n",
      "1017 891 glenn 20692\n",
      "1018 1854 shel 20647\n",
      "1019 1277 ##ider 20633\n",
      "1020 80 willi 20566\n",
      "1021 1684 lars 20542\n",
      "1022 1901 nick 20541\n",
      "1023 521 ken 20460\n",
      "1024 951 ##ebe 20419\n",
      "1025 1351 ##iam 20391\n",
      "1026 248 pet 20352\n",
      "1027 584 christina 20344\n",
      "1028 1981 salome 20311\n",
      "1029 789 nora 20301\n",
      "1030 314 juan 20295\n",
      "1031 1726 ##ruz 20245\n",
      "1032 536 magdal 20228\n",
      "1033 586 joann 20214\n",
      "1034 967 della 20155\n",
      "1035 2005 elisabet 20128\n",
      "1036 176 ##ay 20090\n",
      "1037 149 henry 20062\n",
      "1038 1992 leopold 20057\n",
      "1039 1127 sher 20036\n",
      "1040 499 mabel 20018\n",
      "1041 833 ##ow 20011\n",
      "1042 1289 ##ram 20010\n",
      "1043 603 evelyn 19999\n",
      "1044 1037 bru 19973\n",
      "1045 818 nathan 19970\n",
      "1046 1074 ruf 19966\n",
      "1047 747 ##ham 19921\n",
      "1048 1107 johanne 19881\n",
      "1049 276 jes 19845\n",
      "1050 798 claude 19813\n",
      "1051 408 barbara 19807\n",
      "1052 1284 angela 19791\n",
      "1053 239 martha 19767\n",
      "1054 866 sid 19764\n",
      "1055 795 ##jor 19760\n",
      "1056 715 stephen 19696\n",
      "1057 1711 ##ben 19695\n",
      "1058 1238 ham 19678\n",
      "1059 2034 pru 19676\n",
      "1060 506 law 19672\n",
      "1061 855 ram 19662\n",
      "1062 731 maud 19638\n",
      "1063 594 cli 19587\n",
      "1064 591 glen 19446\n",
      "1065 1302 carr 19435\n",
      "1066 285 samuel 19360\n",
      "1067 106 ##ab 19351\n",
      "1068 820 reg 19348\n",
      "1069 378 catharina 19275\n",
      "1070 1293 dorth 19271\n",
      "1071 517 gla 19238\n",
      "1072 1805 nil 19226\n",
      "1073 1395 anders 19193\n",
      "1074 1337 pie 19132\n",
      "1075 1453 ern 19128\n",
      "1076 332 mae 19107\n",
      "1077 508 friedr 19092\n",
      "1078 1361 delia 19092\n",
      "1079 1613 caspar 19045\n",
      "1080 636 elisabetha 19025\n",
      "1081 307 ##ael 18977\n",
      "1082 1881 emanuel 18881\n",
      "1083 629 francisca 18824\n",
      "1084 562 edwin 18782\n",
      "1085 1147 friederike 18750\n",
      "1086 804 dorothea 18620\n",
      "1087 1062 emi 18577\n",
      "1088 442 edith 18567\n",
      "1089 1872 luiz 18563\n",
      "1090 1262 theresia 18554\n",
      "1091 1194 ##idad 18504\n",
      "1092 1196 rudolph 18457\n",
      "1093 1655 adolf 18443\n",
      "1094 1965 ##ando 18441\n",
      "1095 256 dav 18407\n",
      "1096 500 ##rick 18393\n",
      "1097 279 david 18376\n",
      "1098 1751 antoin 18351\n",
      "1099 1454 gottlieb 18312\n",
      "1100 266 ##arina 18221\n",
      "1101 1609 andrea 18209\n",
      "1102 1425 urs 18201\n",
      "1103 1849 chris 18184\n",
      "1104 1176 edmund 18168\n",
      "1105 787 ##ike 18153\n",
      "1106 817 ##ott 18110\n",
      "1107 1263 cecilia 18108\n",
      "1108 1975 ##orah 18057\n",
      "1109 502 ##car 18042\n",
      "1110 1172 mathias 18040\n",
      "1111 997 helena 18026\n",
      "1112 425 bertha 18013\n",
      "1113 1974 ferenc 18003\n",
      "1114 404 ##ther 17996\n",
      "1115 609 sophia 17974\n",
      "1116 882 marguerite 17949\n",
      "1117 1848 adele 17944\n",
      "1118 939 ira 17900\n",
      "1119 689 isaac 17898\n",
      "1120 1834 domingo 17890\n",
      "1121 946 jim 17875\n",
      "1122 853 teres 17873\n",
      "1123 558 jesse 17868\n",
      "1124 455 myr 17862\n",
      "1125 1643 lem 17860\n",
      "1126 825 theresa 17851\n",
      "1127 952 ron 17832\n",
      "1128 2024 erz 17821\n",
      "1129 742 kate 17808\n",
      "1130 605 rebecca 17802\n",
      "1131 509 louisa 17799\n",
      "1132 843 olive 17794\n",
      "1133 269 helen 17784\n",
      "1134 309 ##ord 17774\n",
      "1135 693 beatr 17734\n",
      "1136 1510 marianna 17713\n",
      "1137 2013 cornelis 17706\n",
      "1138 1886 thur 17651\n",
      "1139 1462 ##ardo 17630\n",
      "1140 630 katharina 17619\n",
      "1141 267 catherine 17592\n",
      "1142 1124 christopher 17586\n",
      "1143 295 louise 17575\n",
      "1144 1909 alan 17556\n",
      "1145 1352 ygna 17526\n",
      "1146 620 allen 17490\n",
      "1147 1153 vivian 17489\n",
      "1148 563 friedrich 17487\n",
      "1149 953 gilbert 17486\n",
      "1150 1273 loretta 17414\n",
      "1151 1672 ivan 17410\n",
      "1152 385 minnie 17395\n",
      "1153 1146 rosina 17382\n",
      "1154 1376 emilie 17349\n",
      "1155 720 viola 17333\n",
      "1156 1977 ##anni 17327\n",
      "1157 1577 bridget 17311\n",
      "1158 618 joa 17304\n",
      "1159 520 jennie 17294\n",
      "1160 245 walter 17280\n",
      "1161 173 ##ward 17261\n",
      "1162 525 alexander 17245\n",
      "1163 865 fredrick 17240\n",
      "1164 1966 ##nard 17203\n",
      "1165 265 annie 17186\n",
      "1166 1483 rosalia 17104\n",
      "1167 252 arthur 17094\n",
      "1168 1336 ross 17072\n",
      "1169 1773 erik 17063\n",
      "1170 1629 ##ess 17062\n",
      "1171 988 harriett 17057\n",
      "1172 1216 lyn 17055\n",
      "1173 1036 ##ast 16991\n",
      "1174 1231 gab 16965\n",
      "1175 513 katherine 16961\n",
      "1176 713 amelia 16938\n",
      "1177 761 augusta 16936\n",
      "1178 981 violet 16934\n",
      "1179 1208 jeanne 16933\n",
      "1180 1057 anto 16923\n",
      "1181 1878 ##ior 16850\n",
      "1182 1477 margarita 16844\n",
      "1183 979 wilhelmina 16785\n",
      "1184 906 nettie 16767\n",
      "1185 772 lois 16765\n",
      "1186 1199 josepha 16756\n",
      "1187 577 betty 16744\n",
      "1188 177 sarah 16719\n",
      "1189 1823 ##more 16718\n",
      "1190 1149 roger 16710\n",
      "1191 678 maude 16695\n",
      "1192 1340 genevieve 16681\n",
      "1193 1660 ursula 16677\n",
      "1194 978 everett 16637\n",
      "1195 1822 elisa 16633\n",
      "1196 452 ##ude 16627\n",
      "1197 127 charles 16596\n",
      "1198 400 andrew 16587\n",
      "1199 1404 verna 16583\n",
      "1200 554 gladys 16543\n",
      "1201 1923 rena 16538\n",
      "1202 2031 pin 16538\n",
      "1203 1253 roland 16532\n",
      "1204 1422 ester 16517\n",
      "1205 488 harriet 16479\n",
      "1206 335 ##riet 16474\n",
      "1207 749 karl 16465\n",
      "1208 754 ll 16448\n",
      "1209 347 dorothy 16441\n",
      "1210 922 henrietta 16439\n",
      "1211 677 christine 16435\n",
      "1212 1322 nathaniel 16414\n",
      "1213 1020 matthew 16408\n",
      "1214 593 willie 16398\n",
      "1215 395 raymond 16395\n",
      "1216 1109 nicholas 16390\n",
      "1217 553 hazel 16369\n",
      "1218 839 lula 16323\n",
      "1219 1383 veron 16306\n",
      "1220 479 nellie 16296\n",
      "1221 528 manuel 16283\n",
      "1222 991 ##leen 16280\n",
      "1223 1164 ##delia 16264\n",
      "1224 1007 hilda 16238\n",
      "1225 1296 niels 16227\n",
      "1226 587 blan 16218\n",
      "1227 780 arch 16203\n",
      "1228 659 lillie 16198\n",
      "1229 654 lydia 16157\n",
      "1230 116 james 16156\n",
      "1231 445 lillian 16148\n",
      "1232 662 theodore 16108\n",
      "1233 1210 regina 16092\n",
      "1234 1686 ellis 16072\n",
      "1235 550 johannes 16052\n",
      "1236 1256 jeanette 16004\n",
      "1237 698 matilda 15997\n",
      "1238 676 aman 15975\n",
      "1239 976 mol 15972\n",
      "1240 1945 ##aela 15956\n",
      "1241 496 jack 15944\n",
      "1242 1310 adelaide 15933\n",
      "1243 1202 winifred 15924\n",
      "1244 1212 ##ht 15915\n",
      "1245 510 marion 15906\n",
      "1246 1481 bry 15881\n",
      "1247 1825 ##cey 15867\n",
      "1248 1125 adeline 15852\n",
      "1249 1099 andreas 15852\n",
      "1250 613 belle 15841\n",
      "1251 579 charlotte 15837\n",
      "1252 1232 ramon 15827\n",
      "1253 1391 baptis 15817\n",
      "1254 1316 juliana 15810\n",
      "1255 937 vera 15808\n",
      "1256 1821 jun 15807\n",
      "1257 1446 celia 15798\n",
      "1258 751 antonia 15782\n",
      "1259 2003 ##vinia 15782\n",
      "1260 908 patric 15756\n",
      "1261 78 joh 15739\n",
      "1262 486 edna 15717\n",
      "1263 1968 free 15700\n",
      "1264 764 edgar 15682\n",
      "1265 427 nancy 15667\n",
      "1266 1046 kathryn 15626\n",
      "1267 1712 veronica 15622\n",
      "1268 1720 matthias 15621\n",
      "1269 1120 morris 15620\n",
      "1270 431 caroline 15612\n",
      "1271 1851 maren 15611\n",
      "1272 1905 mathilde 15604\n",
      "1273 1850 mariana 15571\n",
      "1274 766 nath 15554\n",
      "1275 1015 carolina 15531\n",
      "1276 1260 doming 15516\n",
      "1277 491 lucy 15501\n",
      "1278 1163 felix 15491\n",
      "1279 504 antonio 15482\n",
      "1280 807 hugh 15478\n",
      "1281 668 ##ony 15478\n",
      "1282 447 virginia 15456\n",
      "1283 622 elsie 15442\n",
      "1284 655 pauline 15439\n",
      "1285 1205 carmen 15417\n",
      "1286 1772 tru 15380\n",
      "1287 1861 priscilla 15362\n",
      "1288 1644 phebe 15344\n",
      "1289 1167 lucinda 15333\n",
      "1290 1969 alli 15328\n",
      "1291 1488 ##atha 15319\n",
      "1292 115 jam 15317\n",
      "1293 567 carrie 15311\n",
      "1294 399 grace 15305\n",
      "1295 660 heinrich 15301\n",
      "1296 1358 gertrudis 15255\n",
      "1297 670 fannie 15254\n",
      "1298 888 dolores 15252\n",
      "1299 574 esther 15218\n",
      "1300 1545 mathew 15198\n",
      "1301 1530 linda 15169\n",
      "1302 954 wilhelmine 15166\n",
      "1303 830 ##ub 15157\n",
      "1304 982 abraham 15157\n",
      "1305 321 florence 15131\n",
      "1306 1563 elias 15074\n",
      "1307 549 lawrence 15064\n",
      "1308 2017 ax 15057\n",
      "1309 800 norman 15034\n",
      "1310 580 elmer 15031\n",
      "1311 240 alice 15009\n",
      "1312 471 herbert 15001\n",
      "1313 2040 nils 14990\n",
      "1314 1756 ##iza 14990\n",
      "1315 1630 nar 14953\n",
      "1316 901 teresa 14947\n",
      "1317 571 eugene 14915\n",
      "1318 947 isabella 14901\n",
      "1319 561 francisco 14900\n",
      "1320 302 aug 14879\n",
      "1321 1739 paulina 14833\n",
      "1322 1492 petra 14814\n",
      "1323 1143 cornelius 14807\n",
      "1324 560 cec 14804\n",
      "1325 734 beatrice 14782\n",
      "1326 1860 antoinette 14766\n",
      "1327 886 homer 14752\n",
      "1328 1612 ##andra 14749\n",
      "1329 379 harold 14731\n",
      "1330 1047 ##ker 14718\n",
      "1331 1621 elvira 14715\n",
      "1332 1565 gustaf 14713\n",
      "1333 914 marvin 14693\n",
      "1334 1155 cornelia 14684\n",
      "1335 1593 christiana 14682\n",
      "1336 1700 margareta 14657\n",
      "1337 1464 magdalene 14656\n",
      "1338 709 lucille 14654\n",
      "1339 1894 hard 14635\n",
      "1340 1374 lorraine 14601\n",
      "1341 501 josephine 14587\n",
      "1342 600 emily 14576\n",
      "1343 1080 miguel 14563\n",
      "1344 556 myrtle 14552\n",
      "1345 887 franz 14535\n",
      "1346 462 donald 14530\n",
      "1347 710 amanda 14523\n",
      "1348 854 bernice 14521\n",
      "1349 1651 edmond 14516\n",
      "1350 1274 sylvia 14508\n",
      "1351 458 lew 14503\n",
      "1352 1757 por 14502\n",
      "1353 1937 ##ster 14476\n",
      "1354 864 marjorie 14473\n",
      "1355 519 jessie 14472\n",
      "1356 702 doris 14462\n",
      "1357 685 josefa 14391\n",
      "1358 1290 kirstine 14378\n",
      "1359 1768 andres 14375\n",
      "1360 470 ##ander 14361\n",
      "1361 139 eliz 14358\n",
      "1362 453 mildred 14326\n",
      "1363 1933 angelina 14315\n",
      "1364 1497 ernst 14315\n",
      "1365 1803 hanna 14311\n",
      "1366 1040 addie 14280\n",
      "1367 1532 wilfred 14273\n",
      "1368 721 mattie 14273\n",
      "1369 616 wes 14270\n",
      "1370 1266 ##ling 14223\n",
      "1371 1432 lorenzo 14183\n",
      "1372 1922 nicolaus 14179\n",
      "1373 810 ##inc 14167\n",
      "1374 1156 kathleen 14123\n",
      "1375 1635 eugenia 14103\n",
      "1376 682 harvey 14070\n",
      "1377 1245 susannah 14067\n",
      "1378 989 mamie 14060\n",
      "1379 669 liz 14039\n",
      "1380 1484 rhoda 14007\n",
      "1381 598 hannah 13977\n",
      "1382 905 vernon 13940\n",
      "1383 873 otto 13938\n",
      "1384 987 etta 13919\n",
      "1385 1129 dennis 13916\n",
      "1386 1102 rafael 13914\n",
      "1387 1301 laver 13914\n",
      "1388 1014 willis 13907\n",
      "1389 1436 alberta 13880\n",
      "1390 665 ler 13876\n",
      "1391 1770 margrethe 13875\n",
      "1392 1591 rosalie 13861\n",
      "1393 1279 peder 13858\n",
      "1394 2033 ernestine 13858\n",
      "1395 384 clarence 13845\n",
      "1396 1092 pier 13824\n",
      "1397 681 wesley 13816\n",
      "1398 1174 isabelle 13812\n",
      "1399 2020 ##carna 13803\n",
      "1400 1158 jas 13795\n",
      "1401 794 joannes 13776\n",
      "1402 526 bessie 13755\n",
      "1403 1424 estelle 13749\n",
      "1404 1637 catalina 13727\n",
      "1405 1280 mos 13710\n",
      "1406 1189 norma 13673\n",
      "1407 1410 carolyn 13668\n",
      "1408 1297 carlos 13659\n",
      "1409 1669 marcus 13652\n",
      "1410 1281 pres 13650\n",
      "1411 474 lewis 13648\n",
      "1412 1403 karen 13633\n",
      "1413 1597 ysabel 13630\n",
      "1414 1601 franciscus 13623\n",
      "1415 1946 olivia 13572\n",
      "1416 1824 amalia 13571\n",
      "1417 992 jeff 13567\n",
      "1418 1219 luisa 13562\n",
      "1419 782 stanley 13529\n",
      "1420 850 stella 13507\n",
      "1421 1620 helene 13491\n",
      "1422 1128 lottie 13479\n",
      "1423 1984 joachim 13478\n",
      "1424 828 thelma 13451\n",
      "1425 821 sophie 13405\n",
      "1426 1041 fanny 13386\n",
      "1427 1727 muriel 13377\n",
      "1428 1285 juanita 13347\n",
      "1429 1478 christiane 13336\n",
      "1430 362 ##helm 13330\n",
      "1431 1963 kn 13326\n",
      "1432 634 ##vey 13325\n",
      "1433 1051 sadie 13309\n",
      "1434 1556 ##cilla 13288\n",
      "1435 1347 henriette 13285\n",
      "1436 1298 tim 13274\n",
      "1437 1093 sally 13268\n",
      "1438 1222 op 13261\n",
      "1439 1486 vicente 13246\n",
      "1440 898 oliver 13235\n",
      "1441 290 harry 13214\n",
      "1442 1401 mathilda 13210\n",
      "1443 637 hattie 13184\n",
      "1444 639 oscar 13177\n",
      "1445 582 catharine 13170\n",
      "1446 1579 gio 13164\n",
      "1447 756 anthony 13155\n",
      "1448 1407 cathrine 13107\n",
      "1449 1135 eunice 13101\n",
      "1450 1319 sylvester 13081\n",
      "1451 1616 pris 13060\n",
      "1452 93 ##arl 13056\n",
      "1453 1671 ##xie 13051\n",
      "1454 1349 ##thia 13040\n",
      "1455 1575 giusep 13022\n",
      "1456 2010 margretha 13013\n",
      "1457 834 charlie 12979\n",
      "1458 684 leroy 12974\n",
      "1459 1005 cur 12966\n",
      "1460 841 luther 12960\n",
      "1461 816 milton 12942\n",
      "1462 1649 solomon 12941\n",
      "1463 1225 clark 12938\n",
      "1464 1735 therese 12929\n",
      "1465 916 katie 12926\n",
      "1466 895 julius 12925\n",
      "1467 1859 eileen 12917\n",
      "1468 1050 rita 12890\n",
      "1469 1162 friederich 12862\n",
      "1470 1244 percy 12859\n",
      "1471 576 kenneth 12836\n",
      "1472 940 shirley 12828\n",
      "1473 1438 moses 12793\n",
      "1474 1367 phoebe 12790\n",
      "1475 815 chester 12774\n",
      "1476 846 leslie 12752\n",
      "1477 1126 curtis 12750\n",
      "1478 801 warren 12746\n",
      "1479 1971 mariano 12743\n",
      "1480 472 eug 12738\n",
      "1481 706 floyd 12723\n",
      "1482 1549 steven 12720\n",
      "1483 1939 agatha 12710\n",
      "1484 1531 paula 12693\n",
      "1485 775 patrick 12690\n",
      "1486 1229 ##eles 12685\n",
      "1487 1184 manoel 12668\n",
      "1488 703 clyde 12662\n",
      "1489 1247 jonathan 12652\n",
      "1490 1888 ##ory 12646\n",
      "1491 1121 maurice 12636\n",
      "1492 769 lester 12613\n",
      "1493 1355 ##lem 12608\n",
      "1494 1502 henrich 12604\n",
      "1495 1187 manuela 12603\n",
      "1496 1622 rosie 12597\n",
      "1497 1400 faye 12582\n",
      "1498 1073 greg 12563\n",
      "1499 1814 elaine 12545\n",
      "1500 1200 alonzo 12532\n",
      "1501 628 luis 12529\n",
      "1502 1957 anita 12514\n",
      "1503 1695 constance 12471\n",
      "1504 532 ##ans 12467\n",
      "1505 274 doroth 12462\n",
      "1506 1582 ignacio 12440\n",
      "1507 419 franklin 12420\n",
      "1508 694 blanche 12380\n",
      "1509 1543 jeremiah 12378\n",
      "1510 1833 gay 12371\n",
      "1511 1678 my 12357\n",
      "1512 1539 abigail 12300\n",
      "1513 674 maggie 12286\n",
      "1514 1375 polly 12285\n",
      "1515 1309 aaron 12274\n",
      "1516 1501 sp 12228\n",
      "1517 2042 charlotta 12228\n",
      "1518 890 calvin 12211\n",
      "1519 1562 lynn 12199\n",
      "1520 856 sallie 12136\n",
      "1521 1740 concepcion 12130\n",
      "1522 704 juana 12125\n",
      "1523 2021 elois 12102\n",
      "1524 941 gordon 12091\n",
      "1525 923 willard 12021\n",
      "1526 773 lloyd 12011\n",
      "1527 945 daisy 11970\n",
      "1528 1461 lilly 11958\n",
      "1529 1154 ##field 11949\n",
      "1530 1259 sof 11931\n",
      "1531 1097 dale 11922\n",
      "1532 969 augustus 11922\n",
      "1533 1178 mollie 11917\n",
      "1534 917 sidney 11884\n",
      "1535 1304 gold 11871\n",
      "1536 641 ruby 11851\n",
      "1537 1677 green 11805\n",
      "1538 1468 hester 11790\n",
      "1539 1934 dun 11784\n",
      "1540 1267 reuben 11768\n",
      "1541 1235 phyllis 11761\n",
      "1542 480 ralph 11757\n",
      "1543 1195 josephus 11755\n",
      "1544 1251 ludwig 11745\n",
      "1545 1071 jesus 11731\n",
      "1546 1496 margarethe 11696\n",
      "1547 1098 ear 11645\n",
      "1548 1749 wood 11619\n",
      "1549 1665 elijah 11614\n",
      "1550 1082 ronald 11557\n",
      "1551 1561 joshua 11508\n",
      "1552 1572 madeline 11501\n",
      "1553 1067 gua 11477\n",
      "1554 1994 isabell 11476\n",
      "1555 583 ##elyn 11471\n",
      "1556 1789 reginald 11437\n",
      "1557 242 arth 11428\n",
      "1558 1449 lela 11418\n",
      "1559 1733 lilian 11409\n",
      "1560 1915 joaquin 11400\n",
      "1561 1031 ##olas 11397\n",
      "1562 1931 frieda 11394\n",
      "1563 985 patricia 11389\n",
      "1564 1168 amy 11375\n",
      "1565 690 russell 11373\n",
      "1566 1896 cra 11371\n",
      "1567 460 ral 11370\n",
      "1568 1221 amos 11357\n",
      "1569 1016 dew 11347\n",
      "1570 950 new 11346\n",
      "1571 774 pedro 11322\n",
      "1572 2035 mck 11314\n",
      "1573 1116 susie 11309\n",
      "1574 477 howard 11258\n",
      "1575 1588 joaquim 11249\n",
      "1576 1475 sue 11234\n",
      "1577 944 ##ethe 11218\n",
      "1578 1993 ash 11208\n",
      "1579 1603 ramona 11182\n",
      "1580 1115 virgil 11177\n",
      "1581 1515 mercedes 11164\n",
      "1582 675 ##ugh 11132\n",
      "1583 1039 nelson 11124\n",
      "1584 912 mam 11110\n",
      "1585 507 phi 11107\n",
      "1586 364 gertru 11107\n",
      "1587 129 ##abeth 11095\n",
      "1588 996 wilbur 11082\n",
      "1589 1476 archibald 11080\n",
      "1590 913 clay 11055\n",
      "1591 1828 claire 11048\n",
      "1592 1777 felipe 11017\n",
      "1593 1059 katharine 10997\n",
      "1594 1241 jerry 10948\n",
      "1595 1617 owen 10945\n",
      "1596 1958 neil 10883\n",
      "1597 921 horace 10879\n",
      "1598 1455 ##rest 10869\n",
      "1599 1378 hul 10867\n",
      "1600 977 wilson 10836\n",
      "1601 1053 douglas 10819\n",
      "1602 1318 jacobus 10817\n",
      "1603 1386 pierre 10816\n",
      "1604 1721 joaquina 10807\n",
      "1605 1750 josiah 10801\n",
      "1606 701 lizzie 10796\n",
      "1607 897 effie 10791\n",
      "1608 2018 ignacia 10788\n",
      "1609 1797 karolina 10785\n",
      "1610 503 bett 10780\n",
      "1611 1936 ##aro 10778\n",
      "1612 739 gusta 10772\n",
      "1613 884 wayne 10769\n",
      "1614 1113 guadalupe 10722\n",
      "1615 243 ##oth 10722\n",
      "1616 1782 sofia 10710\n",
      "1617 1083 dejesus 10699\n",
      "1618 1159 inez 10682\n",
      "1619 1495 timothy 10669\n",
      "1620 1816 rosine 10614\n",
      "1621 990 ##erson 10598\n",
      "1622 1744 irma 10586\n",
      "1623 1631 melissa 10574\n",
      "1624 1505 auguste 10544\n",
      "1625 1725 antonius 10495\n",
      "1626 1892 georgius 10493\n",
      "1627 1731 allan 10477\n",
      "1628 2047 rafaela 10453\n",
      "1629 1096 june 10428\n",
      "1630 1807 gloria 10417\n",
      "1631 572 rebec 10390\n",
      "1632 1763 betsy 10385\n",
      "1633 1962 lavina 10374\n",
      "1634 254 freder 10355\n",
      "1635 1482 loy 10347\n",
      "1636 1594 olga 10321\n",
      "1637 2016 jess 10319\n",
      "1638 545 theres 10317\n",
      "1639 1924 aub 10310\n",
      "1640 1951 ygnacio 10293\n",
      "1641 1967 ##abe 10276\n",
      "1642 1647 trinidad 10260\n",
      "1643 1185 joyce 10225\n",
      "1644 1058 mable 10217\n",
      "1645 1845 vilhelm 10202\n",
      "1646 1412 jerome 10195\n",
      "1647 1983 gregorio 10194\n",
      "1648 1331 francisc 10176\n",
      "1649 956 wallace 10155\n",
      "1650 1431 alta 10138\n",
      "1651 1664 delcarmen 10131\n",
      "1652 1648 lily 10128\n",
      "1653 1396 ##fugio 10126\n",
      "1654 1540 karoline 10102\n",
      "1655 1382 petrus 10093\n",
      "1656 623 jak 10066\n",
      "1657 304 ##lian 10014\n",
      "1658 1887 dorothee 10006\n",
      "1659 2023 baptiste 9919\n",
      "1660 767 clifford 9884\n",
      "1661 1008 harrison 9849\n",
      "1662 1895 brad 9829\n",
      "1663 1891 hanss 9806\n",
      "1664 1559 joel 9760\n",
      "1665 1938 giuseppe 9736\n",
      "1666 876 ##ance 9694\n",
      "1667 1414 ##idg 9693\n",
      "1668 1852 refugio 9690\n",
      "1669 1522 smith 9612\n",
      "1670 1327 joannis 9584\n",
      "1671 1513 hulda 9546\n",
      "1672 53 ##q 9449\n",
      "1673 1636 catharinae 9429\n",
      "1674 1788 freda 9428\n",
      "1675 272 rich 9418\n",
      "1676 1879 kristian 9405\n",
      "1677 1759 lenora 9371\n",
      "1678 960 guy 9356\n",
      "1679 1087 karo 9345\n",
      "1680 1693 ##worth 9323\n",
      "1681 316 frie 9303\n",
      "1682 1009 mig 9299\n",
      "1683 1710 malinda 9295\n",
      "1684 1170 monroe 9267\n",
      "1685 1550 ina 9247\n",
      "1686 1443 naomi 9240\n",
      "1687 1439 jerem 9225\n",
      "1688 1270 bruce 9200\n",
      "1689 1729 ##cta 9179\n",
      "1690 1268 wilma 9167\n",
      "1691 1820 pablo 9137\n",
      "1692 1560 larry 9122\n",
      "1693 1447 scott 9059\n",
      "1694 1312 merce 9054\n",
      "1695 174 ##ug 9031\n",
      "1696 1518 cynthia 9027\n",
      "1697 1342 luise 9005\n",
      "1698 1624 eddie 8847\n",
      "1699 1618 ##gg 8846\n",
      "1700 1359 iva 8831\n",
      "1701 1360 audr 8828\n",
      "1702 1369 luella 8776\n",
      "1703 1101 viv 8760\n",
      "1704 1160 jefferson 8747\n",
      "1705 1815 ervin 8733\n",
      "1706 1956 lila 8712\n",
      "1707 1976 emeline 8671\n",
      "1708 1114 hir 8639\n",
      "1709 1490 cecelia 8628\n",
      "1710 1959 adelia 8597\n",
      "1711 1658 asa 8571\n",
      "1712 1614 elbert 8569\n",
      "1713 1508 geneva 8564\n",
      "1714 929 jackson 8552\n",
      "1715 372 benj 8541\n",
      "1716 1748 keith 8489\n",
      "1717 1418 ##oo 8482\n",
      "1718 1317 amb 8479\n",
      "1719 1566 donna 8464\n",
      "1720 1013 irvin 8456\n",
      "1721 1704 erma 8402\n",
      "1722 1448 ##vira 8341\n",
      "1723 1906 marilyn 8333\n",
      "1724 1608 rach 8297\n",
      "1725 934 kir 8269\n",
      "1726 1919 peggy 8266\n",
      "1727 540 ##rence 8234\n",
      "1728 1581 allie 8143\n",
      "1729 1325 annae 8122\n",
      "1730 1381 ##iley 8107\n",
      "1731 1228 earnest 8101\n",
      "1732 1257 lola 8071\n",
      "1733 1060 joao 8046\n",
      "1734 179 ##rist 8019\n",
      "1735 1224 mariae 8018\n",
      "1736 1548 minerva 8008\n",
      "1737 942 abra 7978\n",
      "1738 1846 bertie 7945\n",
      "1739 1511 merle 7915\n",
      "1740 441 ##usta 7907\n",
      "1741 1978 margie 7898\n",
      "1742 1606 angeline 7867\n",
      "1743 439 isab 7847\n",
      "1744 869 hora 7845\n",
      "1745 858 washington 7830\n",
      "1746 896 gord 7813\n",
      "1747 1874 ##igh 7790\n",
      "1748 1842 hellen 7781\n",
      "1749 1856 cordelia 7771\n",
      "1750 1986 annette 7765\n",
      "1751 1785 elva 7764\n",
      "1752 393 mab 7673\n",
      "1753 1544 ##talina 7642\n",
      "1754 1995 lorene 7636\n",
      "1755 1960 gustave 7592\n",
      "1756 1248 jay 7560\n",
      "1757 1830 miriam 7542\n",
      "1758 1287 byr 7518\n",
      "1759 2025 ##ray 7510\n",
      "1760 1139 nannie 7508\n",
      "1761 1320 velma 7485\n",
      "1762 1419 orville 7466\n",
      "1763 1837 adaline 7462\n",
      "1764 1405 geraldine 7459\n",
      "1765 1954 selma 7442\n",
      "1766 1217 phyl 7431\n",
      "1767 1714 ##cher 7421\n",
      "1768 1054 ##ield 7399\n",
      "1769 1755 ##pson 7396\n",
      "1770 1980 delores 7376\n",
      "1771 2022 elma 7343\n",
      "1772 607 ped 7321\n",
      "1773 1119 eun 7285\n",
      "1774 538 charlot 7216\n",
      "1775 1428 ##use 7199\n",
      "1776 1371 nina 7174\n",
      "1777 1086 marsh 7150\n",
      "1778 443 ##dred 7136\n",
      "1779 1300 estella 7107\n",
      "1780 1350 lucile 7100\n",
      "1781 1676 ##inald 7085\n",
      "1782 1765 laverne 7048\n",
      "1783 1044 beulah 7029\n",
      "1784 1076 ##onzo 6993\n",
      "1785 686 cly 6969\n",
      "1786 1157 hiram 6967\n",
      "1787 1701 lafayette 6953\n",
      "1788 1659 ##entine 6906\n",
      "1789 548 ##elma 6895\n",
      "1790 679 ##gna 6893\n",
      "1791 1392 ##celia 6852\n",
      "1792 2004 jeannette 6837\n",
      "1793 592 steph 6825\n",
      "1794 208 ##erine 6808\n",
      "1795 1940 winnie 6746\n",
      "1796 1611 wanda 6717\n",
      "1797 1838 jeann 6715\n",
      "1798 1911 mariah 6711\n",
      "1799 478 ##essie 6702\n",
      "1800 1743 josie 6676\n",
      "1801 699 ##ettie 6672\n",
      "1802 1780 ward 6667\n",
      "1803 1465 ##pcion 6651\n",
      "1804 2019 janie 6628\n",
      "1805 1736 mack 6600\n",
      "1806 2000 myra 6579\n",
      "1807 1670 malc 6533\n",
      "1808 1811 arlene 6533\n",
      "1809 1306 gro 6527\n",
      "1810 381 benjam 6515\n",
      "1811 1493 silas 6500\n",
      "1812 1639 elisab 6482\n",
      "1813 1650 carroll 6478\n",
      "1814 1521 burton 6463\n",
      "1815 596 ##olph 6458\n",
      "1816 1388 abig 6410\n",
      "1817 1900 lonnie 6385\n",
      "1818 1197 ##elis 6380\n",
      "1819 1239 ollie 6363\n",
      "1820 546 ##dys 6355\n",
      "1821 1069 clin 6313\n",
      "1822 1387 ##lieb 6306\n",
      "1823 1985 valentine 6280\n",
      "1824 1171 bob 6251\n",
      "1825 1767 roberta 6239\n",
      "1826 1379 ##riel 6221\n",
      "1827 1784 riley 6168\n",
      "1828 1950 ambrose 6127\n",
      "1829 1459 audrey 6124\n",
      "1830 1623 ##wn 6100\n",
      "1831 2032 callie 6085\n",
      "1832 1061 ##ifred 6074\n",
      "1833 1445 otis 6059\n",
      "1834 601 rus 6021\n",
      "1835 638 ##lius 6017\n",
      "1836 1017 doug 5974\n",
      "1837 237 pau 5931\n",
      "1838 1926 essie 5921\n",
      "1839 2038 ##ight 5896\n",
      "1840 1769 harley 5861\n",
      "1841 608 ##arr 5823\n",
      "1842 1717 leland 5784\n",
      "1843 730 ##fford 5781\n",
      "1844 1344 austin 5773\n",
      "1845 1118 ##nez 5760\n",
      "1846 1427 josh 5715\n",
      "1847 1472 ##omon 5698\n",
      "1848 1568 elij 5666\n",
      "1849 1525 goldie 5654\n",
      "1850 1702 laurence 5579\n",
      "1851 1252 clayton 5551\n",
      "1852 1463 timoth 5462\n",
      "1853 1315 pho 5459\n",
      "1854 1779 wiley 5457\n",
      "1855 1869 leah 5449\n",
      "1856 469 ##arine 5421\n",
      "1857 1774 millie 5411\n",
      "1858 1883 flossie 5369\n",
      "1859 786 ##ood 5346\n",
      "1860 1868 mitch 5277\n",
      "1861 1473 byron 5250\n",
      "1862 1137 perry 5183\n",
      "1863 21 q 5153\n",
      "1864 1877 miles 5123\n",
      "1865 1377 ##orth 5110\n",
      "1866 1003 ander 5070\n",
      "1867 1932 mike 5029\n",
      "1868 1536 bonnie 5020\n",
      "1869 1843 rachael 4987\n",
      "1870 1760 alton 4964\n",
      "1871 827 ##ayne 4949\n",
      "1872 707 ##iola 4904\n",
      "1873 1409 cyn 4895\n",
      "1874 1715 joach 4890\n",
      "1875 1393 dewey 4872\n",
      "1876 1191 ##than 4872\n",
      "1877 1534 ##ileen 4817\n",
      "1878 1719 johnnie 4814\n",
      "1879 1211 archie 4784\n",
      "1880 753 syl 4779\n",
      "1881 1929 kristine 4744\n",
      "1882 1215 ##ail 4741\n",
      "1883 1716 emmett 4736\n",
      "1884 1134 clinton 4732\n",
      "1885 1928 brown 4703\n",
      "1886 672 elean 4674\n",
      "1887 1996 carlton 4650\n",
      "1888 1947 abram 4635\n",
      "1889 1819 eman 4631\n",
      "1890 1551 ##cepcion 4621\n",
      "1891 1380 bettie 4608\n",
      "1892 1870 myron 4576\n",
      "1893 1964 malcolm 4532\n",
      "1894 1348 maxine 4458\n",
      "1895 1471 laf 4405\n",
      "1896 1363 ##dison 4395\n",
      "1897 788 ##uer 4379\n",
      "1898 1064 ##onnie 4379\n",
      "1899 377 ##ester 4353\n",
      "1900 1982 lemuel 4336\n",
      "1901 1537 bill 4264\n",
      "1902 1038 ##jes 4240\n",
      "1903 1638 delbert 4229\n",
      "1904 911 shir 4215\n",
      "1905 1592 melis 4210\n",
      "1906 1440 ##dney 4191\n",
      "1907 1652 forrest 4191\n",
      "1908 1573 columb 4157\n",
      "1909 568 kenne 4154\n",
      "1910 1694 lyle 4152\n",
      "1911 1503 sherman 4150\n",
      "1912 862 harris 4145\n",
      "1913 1913 web 4142\n",
      "1914 615 blanch 4129\n",
      "1915 878 fay 4123\n",
      "1916 1899 ##olm 4086\n",
      "1917 1668 abbie 4061\n",
      "1918 1019 joy 4030\n",
      "1919 1697 pab 3923\n",
      "1920 832 marjor 3922\n",
      "1921 1864 lyman 3919\n",
      "1922 803 ##ington 3895\n",
      "1923 1987 jewell 3852\n",
      "1924 1688 roscoe 3846\n",
      "1925 1935 jewel 3845\n",
      "1926 1645 beverly 3825\n",
      "1927 1213 rufus 3812\n",
      "1928 1885 madison 3810\n",
      "1929 1470 lulu 3809\n",
      "1930 1589 preston 3795\n",
      "1931 1106 ##aron 3768\n",
      "1932 1240 marshall 3758\n",
      "1933 1356 lorra 3620\n",
      "1934 433 ##oyd 3602\n",
      "1935 1764 betsey 3598\n",
      "1936 1209 newton 3596\n",
      "1937 1944 loyd 3533\n",
      "1938 1917 billie 3531\n",
      "1939 485 ##annah 3528\n",
      "1940 870 ##ffie 3523\n",
      "1941 1941 forest 3457\n",
      "1942 1441 clifton 3450\n",
      "1943 1844 millard 3413\n",
      "1944 1920 wade 3408\n",
      "1945 1399 naom 3391\n",
      "1946 1667 davis 3386\n",
      "1947 796 warr 3376\n",
      "1948 1793 cyrus 3352\n",
      "1949 727 henriet 3284\n",
      "1950 1433 billy 3281\n",
      "1951 920 viol 3272\n",
      "1952 1681 ##ellen 3267\n",
      "1953 1394 charley 3240\n",
      "1954 1338 ##fug 3230\n",
      "1955 1456 bridg 3211\n",
      "1956 1390 grover 3206\n",
      "1957 1914 sydney 3205\n",
      "1958 1426 ##erva 3155\n",
      "1959 999 ##ryn 3152\n",
      "1960 1226 reub 3107\n",
      "1961 1269 opal 3098\n",
      "1962 1413 grant 3013\n",
      "1963 1801 ##wart 3010\n",
      "1964 1307 ##vieve 2996\n",
      "1965 1138 ##roe 2944\n",
      "1966 904 dais 2931\n",
      "1967 1754 anderson 2919\n",
      "1968 1324 ##fton 2798\n",
      "1969 1858 stewart 2777\n",
      "1970 959 harrie 2772\n",
      "1971 383 ##lip 2766\n",
      "1972 1615 delcar 2730\n",
      "1973 1547 rosco 2729\n",
      "1974 1152 ferdin 2728\n",
      "1975 1527 bever 2719\n",
      "1976 936 ##ulah 2709\n",
      "1977 1411 sm 2705\n",
      "1978 1480 ##uste 2694\n",
      "1979 1840 gary 2679\n",
      "1980 1705 columbus 2676\n",
      "1981 1708 noah 2674\n",
      "1982 1953 bobby 2674\n",
      "1983 16 l 2673\n",
      "1984 1687 cleveland 2649\n",
      "1985 1022 ##oel 2641\n",
      "1986 1421 ##oda 2638\n",
      "1987 1626 ##itch 2638\n",
      "1988 1948 leop 2468\n",
      "1989 842 ##deline 2463\n",
      "1990 2029 morgan 2450\n",
      "1991 1255 niel 2442\n",
      "1992 1902 boyd 2435\n",
      "1993 1423 jasper 2413\n",
      "1994 1804 woodrow 2368\n",
      "1995 1758 glor 2352\n",
      "1996 1583 irving 2328\n",
      "1997 1261 jew 2288\n",
      "1998 624 russ 2139\n",
      "1999 1078 ##upe 2136\n",
      "2000 1979 russel 2043\n",
      "2001 1330 ##cott 2034\n",
      "2002 1633 lafay 2015\n",
      "2003 1882 hamilton 1994\n",
      "2004 1091 ##dalupe 1958\n",
      "2005 2039 walker 1932\n",
      "2006 1718 taylor 1906\n",
      "2007 1343 ##ptis 1899\n",
      "2008 1912 pegg 1896\n",
      "2009 927 ##lace 1890\n",
      "2010 838 wash 1858\n",
      "2011 1799 ##orest 1818\n",
      "2012 1998 morg 1761\n",
      "2013 349 caro 1725\n",
      "2014 1077 dejes 1679\n",
      "2015 575 ##atr 1678\n",
      "2016 157 ##omas 1637\n",
      "2017 880 joaqu 1516\n",
      "2018 673 rac 1505\n",
      "2019 1451 archib 1478\n",
      "2020 1826 ##ilton 1478\n",
      "2021 1043 ##eland 1462\n",
      "2022 1865 dwight 1420\n",
      "2023 1055 bil 1350\n",
      "2024 635 ##ores 1305\n",
      "2025 1808 ##ossie 1281\n",
      "2026 1341 ##asta 1213\n",
      "2027 357 ##nest 1177\n",
      "2028 329 ##irg 1119\n",
      "2029 1709 woodr 1028\n",
      "2030 1853 ##ilyn 954\n",
      "2031 829 ##omer 751\n",
      "2032 1535 ##umb 549\n",
      "2033 811 ##ash 527\n",
      "2034 925 ##anny 430\n",
      "2035 1415 ##inidad 319\n",
      "2036 1653 ##veland 315\n",
      "2037 410 ##eres 284\n",
      "2038 1666 ##oodr 225\n",
      "2039 1570 giuse 149\n",
      "2040 1661 ##aylor 126\n",
      "2041 1863 dwig 111\n"
     ]
    }
   ],
   "execution_count": 19
  },
  {
   "cell_type": "code",
   "id": "da51621c",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:33.056764Z",
     "start_time": "2024-12-05T18:05:33.011283Z"
    }
   },
   "source": [
    "tokenize('jewel')"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[1935, 1, 1, 1, 1, 1, 1, 1, 1, 1]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 20
  },
  {
   "cell_type": "markdown",
   "id": "0d3c6b49",
   "metadata": {},
   "source": [
    "### Find names that contain under-represented tokens"
   ]
  },
  {
   "cell_type": "code",
   "id": "1905c8ba",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:38.714911Z",
     "start_time": "2024-12-05T18:05:38.664777Z"
    }
   },
   "source": [
    "under_represented_token_ids = set([id_ for id_ in tokenizer_vocab.values() if counter[id_] < under_represented_threshold])\n",
    "print(len(under_represented_token_ids))"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "14\n"
     ]
    }
   ],
   "execution_count": 21
  },
  {
   "cell_type": "code",
   "id": "0a60b125",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:52.715583Z",
     "start_time": "2024-12-05T18:05:43.016900Z"
    }
   },
   "source": [
    "all_names = set()\n",
    "for tup in tqdm(triplets_df.itertuples()):\n",
    "    anchor = tup.anchor\n",
    "    pos = tup.positive\n",
    "    neg = tup.negative\n",
    "    all_names.add(anchor)\n",
    "    all_names.add(pos)\n",
    "    all_names.add(neg)\n",
    "all_names.update(common_names)\n",
    "len(all_names)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0it [00:00, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "ac05edcde1934cbc993837aadc3bc64f"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "66978"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 22
  },
  {
   "cell_type": "code",
   "id": "c4e66b77",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:52.840274Z",
     "start_time": "2024-12-05T18:05:52.717568Z"
    }
   },
   "source": [
    "under_represented_names = set()\n",
    "for name in all_names:\n",
    "    found_token = False\n",
    "    for token in tokenize(name):\n",
    "        if token == 1:\n",
    "            break\n",
    "        if token in under_represented_token_ids:\n",
    "            found_token = True\n",
    "            break\n",
    "    if found_token:\n",
    "        under_represented_names.add(name)\n",
    "print(len(under_represented_names))\n",
    "for name in under_represented_names:\n",
    "    token_counts = []\n",
    "    for token in tokenize(name):\n",
    "        if token == 1:\n",
    "            break\n",
    "        token_counts.append((token, token_id2text[token], counter[token]))\n",
    "    print(name, token_counts)"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12\n",
      "loveland [(133, 'lo', 175865), (1653, '##veland', 315)]\n",
      "doleres [(717, 'dol', 42451), (410, '##eres', 284)]\n",
      "goodridge [(11, 'g', 175164), (1666, '##oodr', 225), (1414, '##idg', 9693), (37, '##e', 2189892)]\n",
      "goodrich [(11, 'g', 175164), (1666, '##oodr', 225), (138, '##ich', 50656)]\n",
      "frinidad [(77, 'fr', 97189), (1415, '##inidad', 319)]\n",
      "giuse [(1570, 'giuse', 149)]\n",
      "zuzanny [(30, 'z', 333899), (1354, '##uz', 49129), (925, '##anny', 430)]\n",
      "cleaveland [(555, 'cle', 53882), (34, '##a', 2400867), (1653, '##veland', 315)]\n",
      "myfanny [(1678, 'my', 12357), (51, '##f', 371385), (925, '##anny', 430)]\n",
      "tinidad [(24, 't', 188991), (1415, '##inidad', 319)]\n",
      "traylor [(877, 'tr', 110279), (1661, '##aylor', 126)]\n",
      "dwigh [(1863, 'dwig', 111), (36, '##h', 641336)]\n"
     ]
    }
   ],
   "execution_count": 23
  },
  {
   "cell_type": "code",
   "id": "dfe8e3c9",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:52.874306Z",
     "start_time": "2024-12-05T18:05:52.842467Z"
    }
   },
   "source": [
    "# add any under-represented tokens that don't start with ## as under-represented names\n",
    "for token, id_ in tokenizer_vocab.items():\n",
    "    if counter[id_] >= under_represented_threshold:\n",
    "        continue\n",
    "    if '[' in token or '#' in token:\n",
    "        continue\n",
    "    print(token)\n",
    "    under_represented_names.add(token)"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "giuse\n",
      "dwig\n"
     ]
    }
   ],
   "execution_count": 24
  },
  {
   "cell_type": "code",
   "id": "c3ba9b03",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:52.908440Z",
     "start_time": "2024-12-05T18:05:52.875628Z"
    }
   },
   "source": [
    "len(under_represented_names)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "13"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 25
  },
  {
   "cell_type": "markdown",
   "id": "58f0b3de",
   "metadata": {},
   "source": [
    "### Add names that contain under-represented tokens to aug_data"
   ]
  },
  {
   "cell_type": "code",
   "id": "ce437155",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:05:52.974090Z",
     "start_time": "2024-12-05T18:05:52.909874Z"
    }
   },
   "source": [
    "cnt = 0\n",
    "for pos in tqdm(under_represented_names):\n",
    "    for neg in common_names[:under_represented_threshold]:\n",
    "        if pos == neg or (pos, neg) in common_non_negatives:\n",
    "            continue\n",
    "        pos_neg = f\"{pos},{neg}\"\n",
    "        if pos_neg in seen_anchor_pos:\n",
    "            continue\n",
    "        neg_pos = f\"{neg},{pos}\"\n",
    "        if neg_pos in seen_anchor_pos:\n",
    "            continue\n",
    "        aug_data.append({\n",
    "            'anchor': pos,\n",
    "            'positive': pos,\n",
    "            'negative': neg,\n",
    "            'positive_score': 1.0,\n",
    "            'negative_score': 0.0,\n",
    "        })\n",
    "        cnt += 1\n",
    "print(cnt)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "  0%|          | 0/13 [00:00<?, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "6de686225a5f4e4ea03962fbe67c0506"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "6493\n"
     ]
    }
   ],
   "execution_count": 26
  },
  {
   "cell_type": "markdown",
   "id": "5debcca1",
   "metadata": {},
   "source": [
    "## Re-Analyze training data"
   ]
  },
  {
   "cell_type": "code",
   "id": "ec2e9ae3",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:07:23.440505Z",
     "start_time": "2024-12-05T18:05:52.975593Z"
    }
   },
   "source": [
    "counter = Counter()\n",
    "for row in tqdm(aug_data):\n",
    "    for key in ['anchor', 'positive', 'negative']:\n",
    "        for token in tokenize(row[key]):\n",
    "            if token == 1:\n",
    "                break\n",
    "            counter[token] += 1\n",
    "for ix, (token, cnt) in enumerate(counter.most_common()):\n",
    "    print(ix, token, token_id2text[token], cnt)"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "  0%|          | 0/15486190 [00:00<?, ?it/s]"
      ],
      "application/vnd.jupyter.widget-view+json": {
       "version_major": 2,
       "version_minor": 0,
       "model_id": "f76e2215fb174bdfa6f1b0ba5d459dfb"
      }
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0 34 ##a 2402036\n",
      "1 37 ##e 2190918\n",
      "2 35 ##n 1777974\n",
      "3 31 ##o 1551943\n",
      "4 45 ##s 1457412\n",
      "5 75 ##ia 1188307\n",
      "6 41 ##l 1183635\n",
      "7 42 ##t 1106397\n",
      "8 49 ##y 904261\n",
      "9 123 ##ina 851591\n",
      "10 38 ##i 772003\n",
      "11 39 ##r 768888\n",
      "12 71 ##ie 762546\n",
      "13 40 ##d 761814\n",
      "14 89 ##us 747839\n",
      "15 64 ##in 733493\n",
      "16 85 ##na 664910\n",
      "17 36 ##h 642349\n",
      "18 104 ##ine 633647\n",
      "19 94 ##la 594928\n",
      "20 171 ##io 562168\n",
      "21 59 ##er 561259\n",
      "22 72 ##on 545622\n",
      "23 135 ##ta 543904\n",
      "24 52 ##b 527673\n",
      "25 73 ##is 524536\n",
      "26 44 ##g 510928\n",
      "27 32 ##m 493290\n",
      "28 103 ##ne 478601\n",
      "29 62 ##en 466303\n",
      "30 56 ##z 415161\n",
      "31 119 ##da 409005\n",
      "32 65 ##el 375927\n",
      "33 51 ##f 372396\n",
      "34 705 ##ri 355020\n",
      "35 153 ##ra 339920\n",
      "36 61 mar 339460\n",
      "37 30 z 334897\n",
      "38 47 ##c 329114\n",
      "39 97 ##le 326423\n",
      "40 163 ar 326230\n",
      "41 46 ##k 323331\n",
      "42 58 ##an 319215\n",
      "43 108 al 306982\n",
      "44 33 ##p 300462\n",
      "45 1368 ##no 289938\n",
      "46 68 ##es 288029\n",
      "47 66 ##il 285533\n",
      "48 712 ##re 281678\n",
      "49 19 o 276387\n",
      "50 48 ##u 275225\n",
      "51 187 la 274943\n",
      "52 202 ##sa 273505\n",
      "53 251 re 271362\n",
      "54 134 el 265379\n",
      "55 159 ##de 253631\n",
      "56 142 ##te 244257\n",
      "57 5 a 243732\n",
      "58 95 ro 241746\n",
      "59 83 ##al 237798\n",
      "60 144 lu 237673\n",
      "61 358 ##va 237133\n",
      "62 50 ##w 236811\n",
      "63 128 ##ol 234549\n",
      "64 185 ##tt 230979\n",
      "65 249 ##ch 230409\n",
      "66 588 ##za 228212\n",
      "67 473 ##st 221548\n",
      "68 9 e 217610\n",
      "69 69 ##or 216417\n",
      "70 180 ##ir 214040\n",
      "71 907 se 213782\n",
      "72 92 ##ph 210550\n",
      "73 737 ##do 208971\n",
      "74 743 ##ino 207730\n",
      "75 8 d 205936\n",
      "76 595 ##je 203203\n",
      "77 611 ##cia 202466\n",
      "78 10 f 201386\n",
      "79 130 le 201272\n",
      "80 54 ##j 201244\n",
      "81 100 ##ce 199969\n",
      "82 671 ##vi 197073\n",
      "83 57 ##ar 195289\n",
      "84 15 k 194793\n",
      "85 368 de 193672\n",
      "86 7 c 192027\n",
      "87 973 eu 191677\n",
      "88 963 ##lo 190780\n",
      "89 194 ##as 190636\n",
      "90 24 t 189989\n",
      "91 98 ##ma 187370\n",
      "92 82 ##se 181678\n",
      "93 74 an 180536\n",
      "94 121 ##ur 179886\n",
      "95 200 ##man 178798\n",
      "96 79 ##ic 177954\n",
      "97 11 g 177177\n",
      "98 133 lo 176865\n",
      "99 167 ##lia 176535\n",
      "100 1276 ##ha 175946\n",
      "101 286 ##os 175104\n",
      "102 426 ger 173788\n",
      "103 512 or 173198\n",
      "104 326 del 172872\n",
      "105 90 ma 169039\n",
      "106 350 ##it 167019\n",
      "107 741 ##ke 166118\n",
      "108 183 ##id 165248\n",
      "109 449 ##ea 164566\n",
      "110 1332 ##me 164156\n",
      "111 140 ##ton 162837\n",
      "112 322 ##ro 162792\n",
      "113 310 ##im 162644\n",
      "114 497 gu 161285\n",
      "115 451 li 161178\n",
      "116 405 ##ita 160822\n",
      "117 219 ##son 159601\n",
      "118 43 ##v 158726\n",
      "119 147 ##lie 157436\n",
      "120 221 ##ena 156443\n",
      "121 235 er 155763\n",
      "122 337 ##un 155305\n",
      "123 241 ##ley 155107\n",
      "124 1334 me 154865\n",
      "125 29 y 154509\n",
      "126 667 ##ilia 154272\n",
      "127 101 ##bert 153636\n",
      "128 13 i 153313\n",
      "129 633 ##to 150690\n",
      "130 238 ben 150092\n",
      "131 647 ##illa 149184\n",
      "132 182 ##ora 148379\n",
      "133 529 mel 147417\n",
      "134 23 s 147245\n",
      "135 565 ##ida 147107\n",
      "136 374 mat 146629\n",
      "137 137 ##nie 145277\n",
      "138 231 ##ey 144931\n",
      "139 748 si 141722\n",
      "140 606 vi 140979\n",
      "141 308 laur 139582\n",
      "142 631 ra 138216\n",
      "143 323 ##ca 136418\n",
      "144 170 ##tha 134442\n",
      "145 275 flor 134190\n",
      "146 732 ne 132041\n",
      "147 291 ##ig 131950\n",
      "148 313 ag 130610\n",
      "149 145 ##ac 129946\n",
      "150 746 ##ge 129782\n",
      "151 27 w 129593\n",
      "152 63 ##th 129252\n",
      "153 1753 dela 129164\n",
      "154 1049 ##tje 129061\n",
      "155 345 ##ver 128065\n",
      "156 1075 ##ka 127326\n",
      "157 534 mer 127154\n",
      "158 160 em 126968\n",
      "159 338 ##tin 126447\n",
      "160 448 cor 126341\n",
      "161 120 th 124682\n",
      "162 1599 ##ss 124220\n",
      "163 744 na 123907\n",
      "164 360 ##co 123710\n",
      "165 81 ##et 123475\n",
      "166 783 ##em 123469\n",
      "167 67 jo 123424\n",
      "168 55 ##x 123410\n",
      "169 122 ed 122918\n",
      "170 602 ##ul 122694\n",
      "171 376 rosa 122438\n",
      "172 246 ##ru 122328\n",
      "173 132 marg 121876\n",
      "174 440 ##ve 121528\n",
      "175 434 ##qu 121413\n",
      "176 879 ##ila 121331\n",
      "177 1140 ce 120626\n",
      "178 301 ##ice 120598\n",
      "179 188 ##ene 120498\n",
      "180 228 luc 120284\n",
      "181 823 ##tta 119890\n",
      "182 1271 ##cen 119485\n",
      "183 294 leon 118916\n",
      "184 189 jan 118800\n",
      "185 1012 hil 118791\n",
      "186 370 ##ly 118137\n",
      "187 141 har 118017\n",
      "188 1161 ##ij 117927\n",
      "189 793 ##ica 117822\n",
      "190 22 r 117764\n",
      "191 1085 te 117562\n",
      "192 657 ##inda 117430\n",
      "193 110 ge 116597\n",
      "194 1035 mad 116334\n",
      "195 435 ##lina 116037\n",
      "196 765 ca 115576\n",
      "197 161 lou 114908\n",
      "198 484 ##etta 114819\n",
      "199 557 ##ius 114700\n",
      "200 1345 ##ad 114522\n",
      "201 984 ##ze 113899\n",
      "202 599 ##iana 113877\n",
      "203 695 ##cio 113797\n",
      "204 107 eli 113457\n",
      "205 88 ch 112977\n",
      "206 972 mal 111359\n",
      "207 877 tr 111279\n",
      "208 768 ba 110845\n",
      "209 152 ju 109977\n",
      "210 184 ##ian 108587\n",
      "211 524 he 108379\n",
      "212 1792 marce 108341\n",
      "213 205 dor 107929\n",
      "214 60 ##li 107913\n",
      "215 518 per 107771\n",
      "216 207 ber 107431\n",
      "217 146 ##dr 106500\n",
      "218 1839 bo 106222\n",
      "219 371 man 104030\n",
      "220 417 rose 103936\n",
      "221 459 sal 103878\n",
      "222 1329 bal 103712\n",
      "223 76 wil 103703\n",
      "224 423 ##ent 102190\n",
      "225 415 ab 102187\n",
      "226 1282 mart 101953\n",
      "227 844 ##ib 101386\n",
      "228 26 v 101192\n",
      "229 2037 ta 101144\n",
      "230 541 math 100925\n",
      "231 156 ##ter 100657\n",
      "232 663 bur 100420\n",
      "233 740 cas 99907\n",
      "234 1524 ##tie 99013\n",
      "235 752 val 98199\n",
      "236 77 fr 98187\n",
      "237 193 ##line 97952\n",
      "238 344 am 97603\n",
      "239 1552 ##ba 97593\n",
      "240 688 bert 97151\n",
      "241 1517 ##sia 97102\n",
      "242 722 ##um 96813\n",
      "243 233 her 96721\n",
      "244 738 sa 96021\n",
      "245 1595 ##ret 95846\n",
      "246 1001 lin 95570\n",
      "247 111 ##ry 95384\n",
      "248 1104 as 95020\n",
      "249 262 anton 94777\n",
      "250 190 car 94680\n",
      "251 1787 ga 94270\n",
      "252 421 ##mer 94014\n",
      "253 466 ##die 93851\n",
      "254 883 ##ven 93234\n",
      "255 1084 ap 92805\n",
      "256 535 ja 92689\n",
      "257 755 en 92537\n",
      "258 289 es 92173\n",
      "259 1264 gi 92097\n",
      "260 1204 ##ien 91703\n",
      "261 197 ##ick 91591\n",
      "262 661 phil 91184\n",
      "263 312 ##eli 90560\n",
      "264 1362 fa 90242\n",
      "265 247 ##vin 89779\n",
      "266 970 ##ana 89750\n",
      "267 298 ##od 89404\n",
      "268 1272 ##po 89106\n",
      "269 861 ##ee 89060\n",
      "270 203 ##ell 88782\n",
      "271 201 ##sie 88595\n",
      "272 181 pa 88175\n",
      "273 209 wal 88166\n",
      "274 105 ##ed 87888\n",
      "275 573 ##dia 87699\n",
      "276 406 ##ilda 87163\n",
      "277 900 sil 86316\n",
      "278 303 ##yn 86293\n",
      "279 1218 no 86265\n",
      "280 612 ##ant 85923\n",
      "281 198 christ 85600\n",
      "282 1370 ##go 85520\n",
      "283 253 ad 85362\n",
      "284 1207 pas 85317\n",
      "285 320 ha 85304\n",
      "286 407 ##der 85043\n",
      "287 551 ele 84814\n",
      "288 777 marc 84052\n",
      "289 968 ##den 84023\n",
      "290 217 ##lin 83764\n",
      "291 1898 ##dor 83647\n",
      "292 1680 mi 83567\n",
      "293 392 ale 83374\n",
      "294 268 ##fr 82290\n",
      "295 1117 ##enc 82153\n",
      "296 158 cath 82098\n",
      "297 296 ##at 82086\n",
      "298 564 bernard 82083\n",
      "299 926 herm 81307\n",
      "300 273 je 81269\n",
      "301 481 ##ela 80931\n",
      "302 931 hu 80817\n",
      "303 424 eva 80750\n",
      "304 432 ##ola 80627\n",
      "305 935 co 80316\n",
      "306 164 fred 80273\n",
      "307 918 ##don 80228\n",
      "308 802 ##of 80080\n",
      "309 373 ##ette 80065\n",
      "310 1108 ##via 79099\n",
      "311 1703 arm 78972\n",
      "312 20 p 78891\n",
      "313 1747 ##ild 78876\n",
      "314 70 ##am 78864\n",
      "315 1806 ##sen 78732\n",
      "316 6 b 78699\n",
      "317 1026 ##mo 78656\n",
      "318 336 ver 78427\n",
      "319 1520 ##vel 78206\n",
      "320 762 ##vina 78100\n",
      "321 1775 ##ut 78036\n",
      "322 318 is 78021\n",
      "323 867 ##ome 77826\n",
      "324 1437 dar 77459\n",
      "325 965 ##ele 77215\n",
      "326 632 cal 77086\n",
      "327 255 ##ella 77053\n",
      "328 1762 els 77000\n",
      "329 590 br 76560\n",
      "330 468 the 76530\n",
      "331 696 do 76321\n",
      "332 305 mag 76173\n",
      "333 263 carl 75959\n",
      "334 718 ##ile 75652\n",
      "335 436 martin 75646\n",
      "336 1555 il 75294\n",
      "337 881 ##ide 74904\n",
      "338 1230 ##que 74846\n",
      "339 195 ru 74685\n",
      "340 1444 ##the 74315\n",
      "341 403 pe 73951\n",
      "342 1507 ##zia 73508\n",
      "343 974 ##iano 73204\n",
      "344 658 ##ck 72998\n",
      "345 277 bar 72692\n",
      "346 932 ##ga 72516\n",
      "347 656 ##ona 72323\n",
      "348 1166 wa 72316\n",
      "349 640 will 72045\n",
      "350 288 clar 71836\n",
      "351 394 lor 71761\n",
      "352 578 win 71282\n",
      "353 619 ##ill 71272\n",
      "354 1201 ##itt 71236\n",
      "355 1576 cha 71171\n",
      "356 218 da 70951\n",
      "357 836 ##hard 70929\n",
      "358 1574 bart 70774\n",
      "359 428 ##ot 70716\n",
      "360 1890 ell 70637\n",
      "361 610 ##ford 70378\n",
      "362 760 ##eta 70130\n",
      "363 943 gar 70117\n",
      "364 1657 pr 69798\n",
      "365 585 ##pe 69687\n",
      "366 1467 ##gen 69575\n",
      "367 429 ste 69537\n",
      "368 401 ##dy 69468\n",
      "369 1206 alb 69105\n",
      "370 910 ##und 69074\n",
      "371 319 ##ion 68955\n",
      "372 363 st 68436\n",
      "373 1311 ##pa 68338\n",
      "374 894 ##van 68225\n",
      "375 413 august 68156\n",
      "376 102 ##ard 67764\n",
      "377 1546 cat 67732\n",
      "378 1357 gen 67607\n",
      "379 735 mor 67491\n",
      "380 348 paul 67481\n",
      "381 456 ##tor 67362\n",
      "382 476 ##ille 67327\n",
      "383 961 ##ira 67198\n",
      "384 617 ##ah 67110\n",
      "385 287 ##ec 66985\n",
      "386 1590 ##sel 66834\n",
      "387 1105 ##din 66707\n",
      "388 511 con 66381\n",
      "389 230 ##iel 66336\n",
      "390 1353 angel 66245\n",
      "391 1321 este 66240\n",
      "392 1829 barthol 66227\n",
      "393 212 ##len 66205\n",
      "394 1722 ##ise 66182\n",
      "395 1662 so 66180\n",
      "396 938 col 65823\n",
      "397 1328 ##ua 65810\n",
      "398 986 lud 65793\n",
      "399 1728 ##pha 65684\n",
      "400 259 ##mon 65632\n",
      "401 998 ##mar 65360\n",
      "402 589 leo 65322\n",
      "403 1498 carm 65286\n",
      "404 475 ##elia 65183\n",
      "405 649 nic 65163\n",
      "406 859 loren 64524\n",
      "407 531 ##zel 64508\n",
      "408 223 hel 63983\n",
      "409 227 kath 63964\n",
      "410 420 ##ore 63876\n",
      "411 1142 par 63811\n",
      "412 683 ##ias 63810\n",
      "413 131 hen 63553\n",
      "414 18 n 63470\n",
      "415 1466 ul 63377\n",
      "416 284 jacob 63263\n",
      "417 199 fl 63159\n",
      "418 498 ##yl 63097\n",
      "419 150 ##ris 62955\n",
      "420 539 ##lis 62911\n",
      "421 1236 ing 62776\n",
      "422 2043 let 62770\n",
      "423 375 ho 62691\n",
      "424 1291 aur 62418\n",
      "425 222 ##om 62411\n",
      "426 505 sh 62232\n",
      "427 1278 alm 62214\n",
      "428 1692 at 62072\n",
      "429 1675 ##if 61929\n",
      "430 627 ka 61664\n",
      "431 1011 ##onia 61491\n",
      "432 216 albert 61409\n",
      "433 234 ali 61370\n",
      "434 812 in 61294\n",
      "435 1323 just 61099\n",
      "436 530 os 61092\n",
      "437 2028 ##bell 60846\n",
      "438 724 ##dis 60828\n",
      "439 559 feli 60741\n",
      "440 1991 ##cu 60658\n",
      "441 1452 adel 60595\n",
      "442 317 min 60408\n",
      "443 258 mil 60257\n",
      "444 12 h 60195\n",
      "445 1384 mo 60073\n",
      "446 1469 du 59650\n",
      "447 799 dom 59469\n",
      "448 206 ##ob 59340\n",
      "449 220 ev 59338\n",
      "450 542 ##ney 59093\n",
      "451 215 ##anna 59006\n",
      "452 1018 ##ny 58604\n",
      "453 902 len 58558\n",
      "454 311 ##ith 58485\n",
      "455 1056 ##so 58252\n",
      "456 1397 felic 57969\n",
      "457 2001 ven 57732\n",
      "458 114 georg 57637\n",
      "459 315 ##ik 57610\n",
      "460 1866 ##rit 57607\n",
      "461 388 be 57358\n",
      "462 958 ##rine 57190\n",
      "463 813 kat 57144\n",
      "464 1776 maxim 57143\n",
      "465 570 jer 56722\n",
      "466 1450 ##val 56364\n",
      "467 465 emil 56210\n",
      "468 495 nor 56110\n",
      "469 2008 fil 56063\n",
      "470 543 fer 55943\n",
      "471 361 cla 55749\n",
      "472 196 ann 55743\n",
      "473 1366 ##ima 55695\n",
      "474 708 ol 55488\n",
      "475 1258 bu 55429\n",
      "476 2002 ##les 55427\n",
      "477 112 ##eth 55284\n",
      "478 136 franc 55058\n",
      "479 1836 va 55034\n",
      "480 893 ##cion 54925\n",
      "481 84 john 54891\n",
      "482 555 cle 54882\n",
      "483 1516 ##nett 54748\n",
      "484 1249 jor 54364\n",
      "485 1365 anasta 54184\n",
      "486 533 ada 53970\n",
      "487 1897 tor 53852\n",
      "488 1326 ##ito 53832\n",
      "489 148 margar 53760\n",
      "490 109 ##org 53757\n",
      "491 1033 ama 53728\n",
      "492 1286 sant 53724\n",
      "493 1810 gun 53586\n",
      "494 847 ##ner 53460\n",
      "495 1430 edu 53417\n",
      "496 91 ##ert 53242\n",
      "497 771 mon 53002\n",
      "498 1373 ##isa 52898\n",
      "499 1487 ##eus 52833\n",
      "500 1831 ##ip 52812\n",
      "501 651 ##iah 52811\n",
      "502 1479 petron 52804\n",
      "503 492 oli 52736\n",
      "504 962 ##ber 52623\n",
      "505 763 ##ale 52543\n",
      "506 1600 ##ten 52470\n",
      "507 229 ##ald 52351\n",
      "508 2006 ##let 52249\n",
      "509 1732 berna 52181\n",
      "510 342 gra 52139\n",
      "511 1538 sab 52135\n",
      "512 1619 alf 52085\n",
      "513 14 j 51971\n",
      "514 340 don 51801\n",
      "515 778 ##land 51783\n",
      "516 1580 han 51776\n",
      "517 138 ##ich 51656\n",
      "518 1689 des 51537\n",
      "519 1871 dam 51489\n",
      "520 1627 crist 51481\n",
      "521 781 gil 51443\n",
      "522 213 ##rie 51365\n",
      "523 719 ##zo 51315\n",
      "524 831 den 51231\n",
      "525 1417 qu 51220\n",
      "526 983 ##vis 51170\n",
      "527 1372 bir 51094\n",
      "528 1605 ##oro 51042\n",
      "529 467 ##ing 50825\n",
      "530 1523 sig 50825\n",
      "531 391 ##ud 50789\n",
      "532 168 cl 50690\n",
      "533 416 ##inia 50636\n",
      "534 1746 ##dell 50578\n",
      "535 1416 bas 50452\n",
      "536 414 susan 50191\n",
      "537 1354 ##uz 50127\n",
      "538 714 ##ite 50119\n",
      "539 450 ##win 50056\n",
      "540 124 joseph 50052\n",
      "541 214 ##nes 50051\n",
      "542 143 anna 49987\n",
      "543 1961 ##ves 49899\n",
      "544 716 ##bur 49692\n",
      "545 1604 ##mina 49681\n",
      "546 354 anne 49678\n",
      "547 327 ##cy 49675\n",
      "548 1308 delos 49528\n",
      "549 1640 cres 49467\n",
      "550 569 isa 49346\n",
      "551 1569 teod 49310\n",
      "552 1188 ##iz 49124\n",
      "553 875 ana 48931\n",
      "554 1303 ##lu 48701\n",
      "555 457 ##by 48683\n",
      "556 1145 ##ilde 48643\n",
      "557 995 philipp 48611\n",
      "558 1364 hal 48555\n",
      "559 860 lar 48399\n",
      "560 729 ##men 48316\n",
      "561 1952 lis 48251\n",
      "562 191 marie 48151\n",
      "563 281 may 48030\n",
      "564 733 est 47989\n",
      "565 874 ##vie 47896\n",
      "566 1857 henri 47557\n",
      "567 1000 ##des 47404\n",
      "568 463 pat 47050\n",
      "569 1042 ##ue 46945\n",
      "570 260 lil 46895\n",
      "571 2026 ##rina 46837\n",
      "572 1112 ##ire 46805\n",
      "573 1339 ser 46621\n",
      "574 1021 claud 46572\n",
      "575 1237 jos 46348\n",
      "576 1519 dion 46324\n",
      "577 1699 ##one 46263\n",
      "578 87 mary 46129\n",
      "579 151 ##oma 45972\n",
      "580 1553 san 45859\n",
      "581 725 gene 45851\n",
      "582 955 gott 45594\n",
      "583 837 ##per 45548\n",
      "584 257 ph 45542\n",
      "585 1214 ke 45517\n",
      "586 232 ##ett 45510\n",
      "587 330 ir 45486\n",
      "588 412 michael 45408\n",
      "589 1175 cam 45232\n",
      "590 1186 ##ery 45101\n",
      "591 178 margaret 45072\n",
      "592 25 u 45047\n",
      "593 1023 ##ach 45029\n",
      "594 1841 bel 44893\n",
      "595 1275 ##ala 44830\n",
      "596 643 ##ric 44828\n",
      "597 1578 ##est 44788\n",
      "598 835 ##ier 44735\n",
      "599 924 ##sey 44607\n",
      "600 367 barb 44556\n",
      "601 270 frances 44509\n",
      "602 809 joan 44335\n",
      "603 1089 au 44242\n",
      "604 1598 ther 44237\n",
      "605 366 bern 44186\n",
      "606 489 ##lan 44158\n",
      "607 1068 clem 43999\n",
      "608 1988 ##rell 43752\n",
      "609 1242 ola 43664\n",
      "610 717 dol 43447\n",
      "611 162 thomas 43424\n",
      "612 454 gr 43405\n",
      "613 1233 ##oll 43177\n",
      "614 863 ##well 42915\n",
      "615 1867 jenn 42700\n",
      "616 1730 domin 42650\n",
      "617 1514 lucia 42601\n",
      "618 1177 ##mie 42420\n",
      "619 1673 ##isla 42387\n",
      "620 1314 ole 42375\n",
      "621 552 leonard 42350\n",
      "622 292 andr 42162\n",
      "623 857 carol 42160\n",
      "624 779 ott 41968\n",
      "625 1474 theodor 41798\n",
      "626 547 ##ula 41747\n",
      "627 1679 tere 41719\n",
      "628 166 ##ann 41538\n",
      "629 490 ##rich 41519\n",
      "630 125 george 41470\n",
      "631 1313 clement 41244\n",
      "632 1220 ##ura 40989\n",
      "633 389 wilhelm 40894\n",
      "634 933 ##elina 40717\n",
      "635 359 jen 40687\n",
      "636 1494 ##ano 40594\n",
      "637 386 ros 40420\n",
      "638 1654 hin 40408\n",
      "639 1795 ##orn 40287\n",
      "640 1970 ##lyn 40268\n",
      "641 872 maur 40230\n",
      "642 653 ##res 40223\n",
      "643 339 gert 40158\n",
      "644 1434 die 40150\n",
      "645 1442 stephan 40054\n",
      "646 1398 ##ros 39975\n",
      "647 211 ##and 39945\n",
      "648 1656 po 39868\n",
      "649 1526 rob 39831\n",
      "650 396 ##dal 39787\n",
      "651 1893 bon 39774\n",
      "652 2036 ##imo 39667\n",
      "653 648 ##sh 39654\n",
      "654 1028 ##end 39597\n",
      "655 1065 ##ika 39500\n",
      "656 1203 const 39489\n",
      "657 2012 eng 39418\n",
      "658 808 gre 39417\n",
      "659 871 igna 39362\n",
      "660 814 cecil 39352\n",
      "661 1682 ##cie 39333\n",
      "662 1429 bla 39174\n",
      "663 776 ##ger 39148\n",
      "664 1557 ##onso 39096\n",
      "665 1798 ##mus 39021\n",
      "666 1305 ##aria 39018\n",
      "667 1183 levi 38951\n",
      "668 1094 emm 38847\n",
      "669 785 nicola 38818\n",
      "670 1587 til 38621\n",
      "671 515 ang 38598\n",
      "672 1918 geert 38576\n",
      "673 1832 deli 38555\n",
      "674 1663 michel 38537\n",
      "675 726 ##gar 38514\n",
      "676 745 vern 38492\n",
      "677 666 marian 38471\n",
      "678 650 stan 38460\n",
      "679 1818 hy 38347\n",
      "680 236 sam 38345\n",
      "681 1529 ##rik 38287\n",
      "682 1916 brig 38267\n",
      "683 1066 ##mund 38215\n",
      "684 848 ever 38110\n",
      "685 826 julian 37701\n",
      "686 1696 ##ilio 37632\n",
      "687 328 ##ff 37565\n",
      "688 1406 hendrik 37399\n",
      "689 797 ##las 37096\n",
      "690 971 tom 37074\n",
      "691 899 arn 36899\n",
      "692 1389 ##entin 36868\n",
      "693 1778 magd 36821\n",
      "694 430 ##eb 36740\n",
      "695 99 jose 36662\n",
      "696 993 ##bie 36651\n",
      "697 154 robert 36613\n",
      "698 1904 lon 36446\n",
      "699 1072 jud 36229\n",
      "700 2044 eb 36201\n",
      "701 192 ##uel 36186\n",
      "702 397 ernest 36085\n",
      "703 840 ##eline 36045\n",
      "704 711 kar 35962\n",
      "705 1250 ##ane 35943\n",
      "706 186 francis 35856\n",
      "707 597 ##tis 35826\n",
      "708 1541 henric 35804\n",
      "709 1584 dal 35794\n",
      "710 1741 pal 35760\n",
      "711 770 matth 35759\n",
      "712 1691 sebastian 35754\n",
      "713 324 ##ttie 35719\n",
      "714 1876 bra 35700\n",
      "715 948 mur 35696\n",
      "716 1027 ur 35603\n",
      "717 325 lee 35510\n",
      "718 1738 sever 35456\n",
      "719 1634 willem 35326\n",
      "720 700 dora 35298\n",
      "721 1333 hol 35282\n",
      "722 1299 ##eda 35237\n",
      "723 1724 cleo 35096\n",
      "724 1499 cand 35011\n",
      "725 851 alvin 34918\n",
      "726 849 phillip 34874\n",
      "727 1642 elen 34803\n",
      "728 994 ##nis 34800\n",
      "729 1817 ##ban 34764\n",
      "730 1485 wel 34674\n",
      "731 1265 sol 34646\n",
      "732 1385 lam 34627\n",
      "733 1880 adrian 34587\n",
      "734 283 ray 34501\n",
      "735 822 petr 34441\n",
      "736 1847 hon 34429\n",
      "737 1610 ##von 34316\n",
      "738 537 johan 34280\n",
      "739 791 sylv 34199\n",
      "740 1151 ##par 34187\n",
      "741 250 emma 34083\n",
      "742 964 simon 34017\n",
      "743 975 victoria 34006\n",
      "744 1734 ##ico 33990\n",
      "745 1641 celes 33938\n",
      "746 1034 ter 33879\n",
      "747 1095 bet 33833\n",
      "748 113 maria 33718\n",
      "749 1875 hed 33716\n",
      "750 1855 narc 33715\n",
      "751 271 ##old 33646\n",
      "752 758 ##rad 33645\n",
      "753 2027 bea 33605\n",
      "754 444 eliza 33430\n",
      "755 1942 ##itte 33404\n",
      "756 1827 nik 33387\n",
      "757 1288 ##wen 33371\n",
      "758 1294 eula 33312\n",
      "759 482 josef 33290\n",
      "760 1752 ##vig 33108\n",
      "761 621 ##zie 33100\n",
      "762 331 dan 33068\n",
      "763 306 ##oph 32974\n",
      "764 909 adolph 32890\n",
      "765 1460 ##ston 32712\n",
      "766 2015 ##jen 32652\n",
      "767 692 anth 32604\n",
      "768 885 krist 32422\n",
      "769 516 victor 32421\n",
      "770 1192 ##lene 32417\n",
      "771 409 ethel 32239\n",
      "772 1435 gabriel 32201\n",
      "773 494 pearl 32181\n",
      "774 1131 sy 32166\n",
      "775 1766 valentin 32133\n",
      "776 1489 lora 32087\n",
      "777 1030 georgia 32019\n",
      "778 1052 fern 32014\n",
      "779 930 vinc 32003\n",
      "780 2011 thom 31955\n",
      "781 280 ##hel 31792\n",
      "782 422 christian 31737\n",
      "783 1136 pol 31734\n",
      "784 1491 sim 31654\n",
      "785 1045 ##ario 31626\n",
      "786 1955 ces 31573\n",
      "787 687 joe 31572\n",
      "788 244 ##oy 31421\n",
      "789 1010 hendr 31376\n",
      "790 2014 mic 31370\n",
      "791 1234 margret 31353\n",
      "792 1130 eugen 31303\n",
      "793 1607 mill 31282\n",
      "794 155 elizabeth 31151\n",
      "795 1533 ##rey 31137\n",
      "796 282 ##ust 31043\n",
      "797 1761 ##dine 30980\n",
      "798 17 m 30937\n",
      "799 300 ##fred 30928\n",
      "800 356 jean 30765\n",
      "801 1742 ##issa 30710\n",
      "802 957 andre 30670\n",
      "803 1706 ##erina 30591\n",
      "804 175 ##ence 30472\n",
      "805 1690 ingeb 30457\n",
      "806 1783 julie 30448\n",
      "807 1907 ##sebet 30434\n",
      "808 2046 sera 30389\n",
      "809 1903 alej 30365\n",
      "810 626 hans 30334\n",
      "811 1169 tomas 30332\n",
      "812 514 philip 30308\n",
      "813 1227 ##seb 30094\n",
      "814 1528 iv 30010\n",
      "815 1122 ##ler 29971\n",
      "816 1571 xa 29879\n",
      "817 1873 ##fried 29877\n",
      "818 1685 ##rid 29523\n",
      "819 966 rud 29505\n",
      "820 464 alex 29496\n",
      "821 1812 ##itha 29462\n",
      "822 614 hein 29448\n",
      "823 1509 vil 29305\n",
      "824 750 ##ois 29271\n",
      "825 118 charl 29259\n",
      "826 402 soph 29225\n",
      "827 1884 ez 29201\n",
      "828 343 ##mond 29165\n",
      "829 369 ellen 29140\n",
      "830 1004 ane 28985\n",
      "831 1973 gerard 28983\n",
      "832 790 christoph 28933\n",
      "833 1925 jacin 28836\n",
      "834 1346 mir 28833\n",
      "835 1048 conrad 28719\n",
      "836 1504 jacqu 28673\n",
      "837 96 fran 28616\n",
      "838 1420 ##kin 28560\n",
      "839 544 herman 28506\n",
      "840 28 x 28460\n",
      "841 165 frank 28432\n",
      "842 382 alfred 28408\n",
      "843 1791 gus 28388\n",
      "844 527 theod 28378\n",
      "845 1625 hor 28341\n",
      "846 1110 mc 28179\n",
      "847 1558 ##idr 28154\n",
      "848 646 corne 28103\n",
      "849 1567 rol 28027\n",
      "850 1800 roza 27748\n",
      "851 1032 adela 27700\n",
      "852 1786 eric 27509\n",
      "853 1133 adr 27506\n",
      "854 355 peter 27380\n",
      "855 1908 ##ii 27352\n",
      "856 1029 ##wood 27256\n",
      "857 418 vic 27218\n",
      "858 691 margr 27186\n",
      "859 1586 frider 27155\n",
      "860 1927 wend 27150\n",
      "861 398 laura 27145\n",
      "862 1198 gustav 27135\n",
      "863 1943 wy 27110\n",
      "864 1745 mah 26953\n",
      "865 1144 ##sy 26951\n",
      "866 903 ##andr 26906\n",
      "867 1602 ela 26824\n",
      "868 1999 isid 26706\n",
      "869 980 ##linda 26679\n",
      "870 1165 ys 26655\n",
      "871 1835 gertrud 26633\n",
      "872 1723 ##vier 26622\n",
      "873 1500 frederic 26497\n",
      "874 759 adam 26487\n",
      "875 1100 vincent 26446\n",
      "876 1790 giov 26411\n",
      "877 1542 bernhard 26394\n",
      "878 1088 ##olf 26359\n",
      "879 1081 kirst 26270\n",
      "880 1628 frederik 26212\n",
      "881 1930 fre 26088\n",
      "882 352 nan 26063\n",
      "883 845 melvin 26056\n",
      "884 1646 ambro 25874\n",
      "885 1707 deb 25849\n",
      "886 664 max 25699\n",
      "887 346 clara 25659\n",
      "888 1921 alexandr 25609\n",
      "889 1889 ker 25607\n",
      "890 2007 octa 25556\n",
      "891 483 ly 25517\n",
      "892 919 ##lio 25510\n",
      "893 645 frieder 25483\n",
      "894 784 les 25477\n",
      "895 1949 kon 25473\n",
      "896 1674 elise 25469\n",
      "897 1713 van 25422\n",
      "898 566 cora 25388\n",
      "899 1103 ##lor 25329\n",
      "900 1292 rand 25304\n",
      "901 1295 bened 25232\n",
      "902 261 elis 25226\n",
      "903 1408 ##lino 25218\n",
      "904 1150 vicen 25196\n",
      "905 1111 rh 25153\n",
      "906 351 ida 25089\n",
      "907 1796 ##ok 25039\n",
      "908 1554 ##itz 25021\n",
      "909 1173 alph 25016\n",
      "910 446 ella 24978\n",
      "911 604 johanna 24967\n",
      "912 680 jakob 24885\n",
      "913 224 jane 24814\n",
      "914 1737 christen 24805\n",
      "915 299 frederick 24797\n",
      "916 1997 ##mira 24721\n",
      "917 1402 alva 24629\n",
      "918 642 lena 24623\n",
      "919 1335 juli 24583\n",
      "920 278 richard 24558\n",
      "921 1972 gerhard 24526\n",
      "922 86 william 24418\n",
      "923 1193 sebast 24333\n",
      "924 126 ##ara 24187\n",
      "925 1090 hubert 24163\n",
      "926 1182 janet 24004\n",
      "927 353 ##elle 23966\n",
      "928 1564 ##ang 23958\n",
      "929 581 margaretha 23936\n",
      "930 1989 ##omena 23923\n",
      "931 949 ##ustin 23882\n",
      "932 1180 ora 23863\n",
      "933 1781 joze 23848\n",
      "934 380 daniel 23834\n",
      "935 915 ##ville 23825\n",
      "936 117 ##ath 23743\n",
      "937 437 agnes 23684\n",
      "938 1123 harl 23654\n",
      "939 1457 nicolas 23636\n",
      "940 1024 francois 23571\n",
      "941 1990 syb 23562\n",
      "942 806 marguer 23551\n",
      "943 1063 raf 23518\n",
      "944 264 sus 23497\n",
      "945 868 ##wig 23474\n",
      "946 172 louis 23358\n",
      "947 1596 judith 23330\n",
      "948 736 char 23309\n",
      "949 1079 ##anda 23275\n",
      "950 1809 eph 23221\n",
      "951 487 ##etha 23161\n",
      "952 1512 barth 23160\n",
      "953 652 fan 23088\n",
      "954 1632 hay 23085\n",
      "955 210 edward 23066\n",
      "956 1132 gregor 23014\n",
      "957 1254 for 22958\n",
      "958 334 ##yr 22954\n",
      "959 365 nel 22947\n",
      "960 438 roy 22878\n",
      "961 204 jac 22814\n",
      "962 1002 earl 22776\n",
      "963 1506 ##my 22759\n",
      "964 1771 aloy 22739\n",
      "965 1683 grac 22731\n",
      "966 728 eleanor 22727\n",
      "967 523 reb 22716\n",
      "968 461 gertrude 22691\n",
      "969 1813 benedic 22684\n",
      "970 1585 nell 22636\n",
      "971 819 rachel 22631\n",
      "972 2041 alphon 22589\n",
      "973 297 ruth 22455\n",
      "974 805 susanna 22334\n",
      "975 1179 ferdinand 22295\n",
      "976 333 mich 22247\n",
      "977 723 gerald 22238\n",
      "978 169 sara 22211\n",
      "979 341 virg 22177\n",
      "980 1141 jens 22155\n",
      "981 390 benjamin 22132\n",
      "982 411 julia 22039\n",
      "983 824 flora 21968\n",
      "984 2045 mattha 21965\n",
      "985 757 ##all 21961\n",
      "986 522 myrt 21961\n",
      "987 697 alma 21939\n",
      "988 493 irene 21897\n",
      "989 1190 cyr 21876\n",
      "990 1070 seb 21860\n",
      "991 1698 emilia 21803\n",
      "992 1458 hermann 21645\n",
      "993 1283 bro 21640\n",
      "994 1025 arnold 21627\n",
      "995 225 ##ew 21567\n",
      "996 1181 mark 21565\n",
      "997 1223 ##abel 21531\n",
      "998 1802 pieter 21434\n",
      "999 1246 wh 21409\n",
      "1000 1006 nich 21390\n",
      "1001 1148 dean 21364\n",
      "1002 928 jona 21325\n",
      "1003 792 isabel 21309\n",
      "1004 852 bell 21308\n",
      "1005 387 eth 21305\n",
      "1006 644 magdalena 21248\n",
      "1007 226 johann 21210\n",
      "1008 892 leona 21156\n",
      "1009 625 ##gie 21129\n",
      "1010 1862 franzis 20976\n",
      "1011 293 elisabeth 20960\n",
      "1012 2009 ##ustina 20927\n",
      "1013 889 ##art 20916\n",
      "1014 2030 frans 20914\n",
      "1015 1910 ##sius 20905\n",
      "1016 1243 joanna 20803\n",
      "1017 891 glenn 20692\n",
      "1018 1854 shel 20647\n",
      "1019 1277 ##ider 20633\n",
      "1020 80 willi 20566\n",
      "1021 1684 lars 20555\n",
      "1022 1901 nick 20541\n",
      "1023 521 ken 20460\n",
      "1024 951 ##ebe 20419\n",
      "1025 1351 ##iam 20391\n",
      "1026 584 christina 20357\n",
      "1027 248 pet 20352\n",
      "1028 789 nora 20314\n",
      "1029 1981 salome 20311\n",
      "1030 314 juan 20308\n",
      "1031 1726 ##ruz 20271\n",
      "1032 536 magdal 20228\n",
      "1033 586 joann 20214\n",
      "1034 967 della 20155\n",
      "1035 2005 elisabet 20128\n",
      "1036 176 ##ay 20090\n",
      "1037 149 henry 20075\n",
      "1038 1992 leopold 20057\n",
      "1039 1127 sher 20036\n",
      "1040 499 mabel 20031\n",
      "1041 603 evelyn 20012\n",
      "1042 833 ##ow 20011\n",
      "1043 1289 ##ram 20010\n",
      "1044 1037 bru 19973\n",
      "1045 818 nathan 19970\n",
      "1046 1074 ruf 19966\n",
      "1047 747 ##ham 19921\n",
      "1048 1107 johanne 19894\n",
      "1049 276 jes 19845\n",
      "1050 798 claude 19826\n",
      "1051 408 barbara 19820\n",
      "1052 1284 angela 19804\n",
      "1053 239 martha 19780\n",
      "1054 866 sid 19764\n",
      "1055 795 ##jor 19760\n",
      "1056 715 stephen 19709\n",
      "1057 1711 ##ben 19695\n",
      "1058 1238 ham 19678\n",
      "1059 2034 pru 19676\n",
      "1060 506 law 19672\n",
      "1061 855 ram 19662\n",
      "1062 731 maud 19651\n",
      "1063 594 cli 19587\n",
      "1064 591 glen 19446\n",
      "1065 1302 carr 19435\n",
      "1066 285 samuel 19373\n",
      "1067 106 ##ab 19351\n",
      "1068 820 reg 19348\n",
      "1069 378 catharina 19288\n",
      "1070 1293 dorth 19271\n",
      "1071 517 gla 19238\n",
      "1072 1805 nil 19226\n",
      "1073 1395 anders 19206\n",
      "1074 1337 pie 19145\n",
      "1075 1453 ern 19128\n",
      "1076 332 mae 19120\n",
      "1077 508 friedr 19092\n",
      "1078 1361 delia 19092\n",
      "1079 1613 caspar 19058\n",
      "1080 636 elisabetha 19038\n",
      "1081 307 ##ael 18977\n",
      "1082 1881 emanuel 18881\n",
      "1083 629 francisca 18837\n",
      "1084 562 edwin 18795\n",
      "1085 1147 friederike 18763\n",
      "1086 804 dorothea 18633\n",
      "1087 1872 luiz 18589\n",
      "1088 442 edith 18580\n",
      "1089 1062 emi 18577\n",
      "1090 1262 theresia 18567\n",
      "1091 1194 ##idad 18504\n",
      "1092 1196 rudolph 18457\n",
      "1093 1965 ##ando 18454\n",
      "1094 1655 adolf 18443\n",
      "1095 256 dav 18407\n",
      "1096 500 ##rick 18393\n",
      "1097 279 david 18389\n",
      "1098 1751 antoin 18364\n",
      "1099 1454 gottlieb 18325\n",
      "1100 266 ##arina 18234\n",
      "1101 1609 andrea 18222\n",
      "1102 1425 urs 18201\n",
      "1103 1849 chris 18184\n",
      "1104 1176 edmund 18181\n",
      "1105 787 ##ike 18153\n",
      "1106 1263 cecilia 18121\n",
      "1107 817 ##ott 18110\n",
      "1108 1975 ##orah 18057\n",
      "1109 1172 mathias 18053\n",
      "1110 502 ##car 18042\n",
      "1111 997 helena 18039\n",
      "1112 425 bertha 18026\n",
      "1113 1974 ferenc 18003\n",
      "1114 404 ##ther 17996\n",
      "1115 609 sophia 17987\n",
      "1116 882 marguerite 17962\n",
      "1117 1848 adele 17944\n",
      "1118 689 isaac 17911\n",
      "1119 1834 domingo 17903\n",
      "1120 939 ira 17900\n",
      "1121 558 jesse 17881\n",
      "1122 946 jim 17875\n",
      "1123 853 teres 17873\n",
      "1124 825 theresa 17864\n",
      "1125 455 myr 17862\n",
      "1126 1643 lem 17860\n",
      "1127 2024 erz 17834\n",
      "1128 952 ron 17832\n",
      "1129 742 kate 17821\n",
      "1130 605 rebecca 17815\n",
      "1131 509 louisa 17812\n",
      "1132 843 olive 17807\n",
      "1133 269 helen 17797\n",
      "1134 309 ##ord 17774\n",
      "1135 693 beatr 17734\n",
      "1136 1510 marianna 17726\n",
      "1137 2013 cornelis 17719\n",
      "1138 1886 thur 17651\n",
      "1139 1462 ##ardo 17643\n",
      "1140 630 katharina 17632\n",
      "1141 267 catherine 17605\n",
      "1142 1124 christopher 17599\n",
      "1143 295 louise 17588\n",
      "1144 1909 alan 17556\n",
      "1145 1352 ygna 17539\n",
      "1146 620 allen 17503\n",
      "1147 563 friedrich 17500\n",
      "1148 1153 vivian 17489\n",
      "1149 953 gilbert 17486\n",
      "1150 1273 loretta 17414\n",
      "1151 1672 ivan 17410\n",
      "1152 385 minnie 17408\n",
      "1153 1146 rosina 17395\n",
      "1154 1376 emilie 17362\n",
      "1155 720 viola 17346\n",
      "1156 1977 ##anni 17340\n",
      "1157 1577 bridget 17324\n",
      "1158 520 jennie 17307\n",
      "1159 618 joa 17304\n",
      "1160 245 walter 17293\n",
      "1161 173 ##ward 17261\n",
      "1162 525 alexander 17258\n",
      "1163 865 fredrick 17240\n",
      "1164 1966 ##nard 17203\n",
      "1165 265 annie 17199\n",
      "1166 1483 rosalia 17117\n",
      "1167 252 arthur 17107\n",
      "1168 1773 erik 17076\n",
      "1169 1336 ross 17072\n",
      "1170 1629 ##ess 17062\n",
      "1171 988 harriett 17057\n",
      "1172 1216 lyn 17055\n",
      "1173 1036 ##ast 16991\n",
      "1174 513 katherine 16974\n",
      "1175 1231 gab 16965\n",
      "1176 713 amelia 16951\n",
      "1177 761 augusta 16949\n",
      "1178 981 violet 16947\n",
      "1179 1208 jeanne 16946\n",
      "1180 1057 anto 16923\n",
      "1181 1477 margarita 16857\n",
      "1182 1878 ##ior 16850\n",
      "1183 979 wilhelmina 16798\n",
      "1184 772 lois 16778\n",
      "1185 1199 josepha 16769\n",
      "1186 906 nettie 16767\n",
      "1187 577 betty 16757\n",
      "1188 177 sarah 16732\n",
      "1189 1149 roger 16723\n",
      "1190 1823 ##more 16718\n",
      "1191 678 maude 16708\n",
      "1192 1660 ursula 16690\n",
      "1193 1340 genevieve 16681\n",
      "1194 978 everett 16637\n",
      "1195 1822 elisa 16633\n",
      "1196 452 ##ude 16627\n",
      "1197 127 charles 16609\n",
      "1198 400 andrew 16600\n",
      "1199 1404 verna 16583\n",
      "1200 554 gladys 16556\n",
      "1201 1923 rena 16538\n",
      "1202 2031 pin 16538\n",
      "1203 1253 roland 16532\n",
      "1204 1422 ester 16517\n",
      "1205 488 harriet 16492\n",
      "1206 749 karl 16478\n",
      "1207 335 ##riet 16474\n",
      "1208 347 dorothy 16454\n",
      "1209 922 henrietta 16452\n",
      "1210 754 ll 16448\n",
      "1211 677 christine 16448\n",
      "1212 1020 matthew 16421\n",
      "1213 1322 nathaniel 16414\n",
      "1214 593 willie 16411\n",
      "1215 395 raymond 16408\n",
      "1216 1109 nicholas 16403\n",
      "1217 553 hazel 16382\n",
      "1218 839 lula 16323\n",
      "1219 479 nellie 16309\n",
      "1220 1383 veron 16306\n",
      "1221 528 manuel 16296\n",
      "1222 991 ##leen 16280\n",
      "1223 1164 ##delia 16264\n",
      "1224 1007 hilda 16251\n",
      "1225 1296 niels 16240\n",
      "1226 587 blan 16218\n",
      "1227 659 lillie 16211\n",
      "1228 780 arch 16203\n",
      "1229 654 lydia 16170\n",
      "1230 116 james 16169\n",
      "1231 445 lillian 16161\n",
      "1232 662 theodore 16121\n",
      "1233 1210 regina 16105\n",
      "1234 1686 ellis 16072\n",
      "1235 550 johannes 16065\n",
      "1236 698 matilda 16010\n",
      "1237 1256 jeanette 16004\n",
      "1238 676 aman 15975\n",
      "1239 976 mol 15972\n",
      "1240 1945 ##aela 15969\n",
      "1241 496 jack 15957\n",
      "1242 1310 adelaide 15946\n",
      "1243 1202 winifred 15924\n",
      "1244 510 marion 15919\n",
      "1245 1212 ##ht 15915\n",
      "1246 1481 bry 15881\n",
      "1247 1825 ##cey 15867\n",
      "1248 1099 andreas 15865\n",
      "1249 613 belle 15854\n",
      "1250 1125 adeline 15852\n",
      "1251 579 charlotte 15850\n",
      "1252 1232 ramon 15840\n",
      "1253 1316 juliana 15823\n",
      "1254 1391 baptis 15817\n",
      "1255 937 vera 15808\n",
      "1256 1821 jun 15807\n",
      "1257 1446 celia 15798\n",
      "1258 751 antonia 15795\n",
      "1259 2003 ##vinia 15782\n",
      "1260 908 patric 15756\n",
      "1261 78 joh 15739\n",
      "1262 486 edna 15730\n",
      "1263 1968 free 15700\n",
      "1264 764 edgar 15695\n",
      "1265 427 nancy 15680\n",
      "1266 1712 veronica 15635\n",
      "1267 1720 matthias 15634\n",
      "1268 1046 kathryn 15626\n",
      "1269 431 caroline 15625\n",
      "1270 1851 maren 15624\n",
      "1271 1120 morris 15620\n",
      "1272 1905 mathilde 15617\n",
      "1273 1850 mariana 15584\n",
      "1274 766 nath 15554\n",
      "1275 1015 carolina 15544\n",
      "1276 1260 doming 15529\n",
      "1277 491 lucy 15514\n",
      "1278 1163 felix 15504\n",
      "1279 504 antonio 15495\n",
      "1280 807 hugh 15491\n",
      "1281 668 ##ony 15478\n",
      "1282 447 virginia 15469\n",
      "1283 622 elsie 15455\n",
      "1284 655 pauline 15452\n",
      "1285 1205 carmen 15430\n",
      "1286 1772 tru 15380\n",
      "1287 1861 priscilla 15362\n",
      "1288 1644 phebe 15344\n",
      "1289 1167 lucinda 15333\n",
      "1290 1969 alli 15328\n",
      "1291 567 carrie 15324\n",
      "1292 1488 ##atha 15319\n",
      "1293 399 grace 15318\n",
      "1294 115 jam 15317\n",
      "1295 660 heinrich 15314\n",
      "1296 1358 gertrudis 15268\n",
      "1297 670 fannie 15267\n",
      "1298 888 dolores 15264\n",
      "1299 574 esther 15231\n",
      "1300 1545 mathew 15198\n",
      "1301 954 wilhelmine 15179\n",
      "1302 982 abraham 15170\n",
      "1303 1530 linda 15169\n",
      "1304 830 ##ub 15157\n",
      "1305 321 florence 15144\n",
      "1306 1563 elias 15087\n",
      "1307 549 lawrence 15077\n",
      "1308 2017 ax 15057\n",
      "1309 800 norman 15047\n",
      "1310 580 elmer 15044\n",
      "1311 240 alice 15022\n",
      "1312 471 herbert 15014\n",
      "1313 2040 nils 15003\n",
      "1314 1756 ##iza 14990\n",
      "1315 901 teresa 14960\n",
      "1316 1630 nar 14953\n",
      "1317 571 eugene 14928\n",
      "1318 947 isabella 14914\n",
      "1319 561 francisco 14913\n",
      "1320 302 aug 14879\n",
      "1321 1739 paulina 14846\n",
      "1322 1492 petra 14827\n",
      "1323 1143 cornelius 14820\n",
      "1324 560 cec 14804\n",
      "1325 734 beatrice 14795\n",
      "1326 1860 antoinette 14766\n",
      "1327 886 homer 14752\n",
      "1328 1612 ##andra 14749\n",
      "1329 379 harold 14744\n",
      "1330 1621 elvira 14728\n",
      "1331 1565 gustaf 14726\n",
      "1332 1047 ##ker 14718\n",
      "1333 1155 cornelia 14697\n",
      "1334 914 marvin 14693\n",
      "1335 1593 christiana 14682\n",
      "1336 1700 margareta 14670\n",
      "1337 709 lucille 14667\n",
      "1338 1464 magdalene 14656\n",
      "1339 1894 hard 14635\n",
      "1340 1374 lorraine 14601\n",
      "1341 501 josephine 14600\n",
      "1342 600 emily 14589\n",
      "1343 1080 miguel 14576\n",
      "1344 556 myrtle 14565\n",
      "1345 887 franz 14548\n",
      "1346 462 donald 14543\n",
      "1347 710 amanda 14536\n",
      "1348 854 bernice 14521\n",
      "1349 1651 edmond 14516\n",
      "1350 1274 sylvia 14508\n",
      "1351 458 lew 14503\n",
      "1352 1757 por 14502\n",
      "1353 519 jessie 14485\n",
      "1354 1937 ##ster 14476\n",
      "1355 702 doris 14474\n",
      "1356 864 marjorie 14473\n",
      "1357 685 josefa 14404\n",
      "1358 1290 kirstine 14391\n",
      "1359 1768 andres 14388\n",
      "1360 470 ##ander 14361\n",
      "1361 139 eliz 14358\n",
      "1362 453 mildred 14339\n",
      "1363 1933 angelina 14328\n",
      "1364 1497 ernst 14328\n",
      "1365 1803 hanna 14311\n",
      "1366 721 mattie 14286\n",
      "1367 1040 addie 14280\n",
      "1368 1532 wilfred 14273\n",
      "1369 616 wes 14270\n",
      "1370 1266 ##ling 14223\n",
      "1371 1432 lorenzo 14196\n",
      "1372 1922 nicolaus 14192\n",
      "1373 810 ##inc 14167\n",
      "1374 1156 kathleen 14136\n",
      "1375 1635 eugenia 14116\n",
      "1376 682 harvey 14083\n",
      "1377 1245 susannah 14080\n",
      "1378 989 mamie 14060\n",
      "1379 669 liz 14039\n",
      "1380 1484 rhoda 14007\n",
      "1381 598 hannah 13990\n",
      "1382 873 otto 13951\n",
      "1383 905 vernon 13940\n",
      "1384 1102 rafael 13927\n",
      "1385 987 etta 13919\n",
      "1386 1129 dennis 13916\n",
      "1387 1301 laver 13914\n",
      "1388 1014 willis 13907\n",
      "1389 1436 alberta 13880\n",
      "1390 665 ler 13876\n",
      "1391 1770 margrethe 13875\n",
      "1392 1591 rosalie 13874\n",
      "1393 1279 peder 13871\n",
      "1394 384 clarence 13858\n",
      "1395 2033 ernestine 13858\n",
      "1396 681 wesley 13829\n",
      "1397 1092 pier 13824\n",
      "1398 2020 ##carna 13816\n",
      "1399 1174 isabelle 13812\n",
      "1400 1158 jas 13795\n",
      "1401 794 joannes 13789\n",
      "1402 526 bessie 13768\n",
      "1403 1424 estelle 13749\n",
      "1404 1637 catalina 13740\n",
      "1405 1280 mos 13710\n",
      "1406 1189 norma 13673\n",
      "1407 1297 carlos 13672\n",
      "1408 1410 carolyn 13668\n",
      "1409 474 lewis 13661\n",
      "1410 1669 marcus 13652\n",
      "1411 1281 pres 13650\n",
      "1412 1403 karen 13646\n",
      "1413 1597 ysabel 13643\n",
      "1414 1601 franciscus 13636\n",
      "1415 1824 amalia 13584\n",
      "1416 1219 luisa 13575\n",
      "1417 1946 olivia 13572\n",
      "1418 992 jeff 13567\n",
      "1419 782 stanley 13542\n",
      "1420 850 stella 13507\n",
      "1421 1620 helene 13504\n",
      "1422 1128 lottie 13479\n",
      "1423 1984 joachim 13478\n",
      "1424 828 thelma 13451\n",
      "1425 821 sophie 13418\n",
      "1426 1041 fanny 13398\n",
      "1427 1727 muriel 13377\n",
      "1428 1678 my 13355\n",
      "1429 1478 christiane 13349\n",
      "1430 1285 juanita 13347\n",
      "1431 362 ##helm 13330\n",
      "1432 1963 kn 13326\n",
      "1433 634 ##vey 13325\n",
      "1434 1051 sadie 13309\n",
      "1435 1347 henriette 13298\n",
      "1436 1556 ##cilla 13288\n",
      "1437 1298 tim 13274\n",
      "1438 1093 sally 13268\n",
      "1439 1222 op 13261\n",
      "1440 1486 vicente 13259\n",
      "1441 898 oliver 13248\n",
      "1442 290 harry 13227\n",
      "1443 1401 mathilda 13210\n",
      "1444 637 hattie 13197\n",
      "1445 639 oscar 13190\n",
      "1446 582 catharine 13183\n",
      "1447 756 anthony 13168\n",
      "1448 1579 gio 13164\n",
      "1449 1407 cathrine 13107\n",
      "1450 1135 eunice 13101\n",
      "1451 1319 sylvester 13081\n",
      "1452 1616 pris 13060\n",
      "1453 93 ##arl 13056\n",
      "1454 1671 ##xie 13051\n",
      "1455 1349 ##thia 13040\n",
      "1456 1575 giusep 13022\n",
      "1457 2010 margretha 13013\n",
      "1458 684 leroy 12987\n",
      "1459 834 charlie 12979\n",
      "1460 1005 cur 12966\n",
      "1461 841 luther 12960\n",
      "1462 816 milton 12942\n",
      "1463 1735 therese 12942\n",
      "1464 1649 solomon 12941\n",
      "1465 895 julius 12938\n",
      "1466 1225 clark 12938\n",
      "1467 916 katie 12926\n",
      "1468 1859 eileen 12917\n",
      "1469 1050 rita 12903\n",
      "1470 1162 friederich 12862\n",
      "1471 1244 percy 12859\n",
      "1472 576 kenneth 12849\n",
      "1473 940 shirley 12828\n",
      "1474 1438 moses 12793\n",
      "1475 1367 phoebe 12790\n",
      "1476 815 chester 12774\n",
      "1477 846 leslie 12765\n",
      "1478 1971 mariano 12756\n",
      "1479 1126 curtis 12750\n",
      "1480 801 warren 12746\n",
      "1481 472 eug 12738\n",
      "1482 706 floyd 12723\n",
      "1483 1549 steven 12720\n",
      "1484 1939 agatha 12710\n",
      "1485 1531 paula 12706\n",
      "1486 775 patrick 12703\n",
      "1487 1229 ##eles 12685\n",
      "1488 1184 manoel 12681\n",
      "1489 1247 jonathan 12665\n",
      "1490 703 clyde 12662\n",
      "1491 1888 ##ory 12646\n",
      "1492 1121 maurice 12636\n",
      "1493 1502 henrich 12617\n",
      "1494 1187 manuela 12616\n",
      "1495 769 lester 12613\n",
      "1496 1355 ##lem 12608\n",
      "1497 1622 rosie 12597\n",
      "1498 1400 faye 12582\n",
      "1499 1073 greg 12563\n",
      "1500 1814 elaine 12545\n",
      "1501 628 luis 12542\n",
      "1502 1200 alonzo 12532\n",
      "1503 1957 anita 12514\n",
      "1504 1695 constance 12471\n",
      "1505 532 ##ans 12467\n",
      "1506 274 doroth 12462\n",
      "1507 1582 ignacio 12453\n",
      "1508 419 franklin 12433\n",
      "1509 694 blanche 12393\n",
      "1510 1543 jeremiah 12378\n",
      "1511 1833 gay 12371\n",
      "1512 1539 abigail 12300\n",
      "1513 674 maggie 12299\n",
      "1514 1375 polly 12285\n",
      "1515 1309 aaron 12274\n",
      "1516 1501 sp 12228\n",
      "1517 2042 charlotta 12228\n",
      "1518 890 calvin 12211\n",
      "1519 1562 lynn 12199\n",
      "1520 1740 concepcion 12143\n",
      "1521 704 juana 12138\n",
      "1522 856 sallie 12136\n",
      "1523 2021 elois 12102\n",
      "1524 941 gordon 12091\n",
      "1525 923 willard 12021\n",
      "1526 773 lloyd 12011\n",
      "1527 945 daisy 11970\n",
      "1528 1461 lilly 11958\n",
      "1529 1154 ##field 11949\n",
      "1530 1259 sof 11931\n",
      "1531 1097 dale 11922\n",
      "1532 969 augustus 11922\n",
      "1533 1178 mollie 11917\n",
      "1534 917 sidney 11884\n",
      "1535 1304 gold 11871\n",
      "1536 641 ruby 11864\n",
      "1537 1677 green 11805\n",
      "1538 1468 hester 11790\n",
      "1539 1934 dun 11784\n",
      "1540 480 ralph 11770\n",
      "1541 1267 reuben 11768\n",
      "1542 1195 josephus 11768\n",
      "1543 1235 phyllis 11761\n",
      "1544 1251 ludwig 11758\n",
      "1545 1071 jesus 11744\n",
      "1546 1496 margarethe 11709\n",
      "1547 1098 ear 11645\n",
      "1548 1749 wood 11619\n",
      "1549 1665 elijah 11614\n",
      "1550 1082 ronald 11570\n",
      "1551 1561 joshua 11508\n",
      "1552 1572 madeline 11501\n",
      "1553 1067 gua 11477\n",
      "1554 1994 isabell 11476\n",
      "1555 583 ##elyn 11471\n",
      "1556 1789 reginald 11437\n",
      "1557 242 arth 11428\n",
      "1558 1449 lela 11418\n",
      "1559 1915 joaquin 11413\n",
      "1560 1733 lilian 11409\n",
      "1561 985 patricia 11402\n",
      "1562 1031 ##olas 11397\n",
      "1563 1931 frieda 11394\n",
      "1564 1168 amy 11388\n",
      "1565 690 russell 11386\n",
      "1566 1896 cra 11371\n",
      "1567 460 ral 11370\n",
      "1568 1221 amos 11357\n",
      "1569 1016 dew 11347\n",
      "1570 950 new 11346\n",
      "1571 774 pedro 11335\n",
      "1572 2035 mck 11314\n",
      "1573 1116 susie 11309\n",
      "1574 477 howard 11271\n",
      "1575 1588 joaquim 11262\n",
      "1576 1475 sue 11234\n",
      "1577 944 ##ethe 11218\n",
      "1578 1993 ash 11208\n",
      "1579 1603 ramona 11195\n",
      "1580 1115 virgil 11177\n",
      "1581 1515 mercedes 11177\n",
      "1582 675 ##ugh 11132\n",
      "1583 1039 nelson 11124\n",
      "1584 912 mam 11110\n",
      "1585 507 phi 11107\n",
      "1586 364 gertru 11107\n",
      "1587 129 ##abeth 11095\n",
      "1588 996 wilbur 11082\n",
      "1589 1476 archibald 11080\n",
      "1590 913 clay 11055\n",
      "1591 1828 claire 11048\n",
      "1592 1777 felipe 11030\n",
      "1593 1059 katharine 10997\n",
      "1594 1241 jerry 10948\n",
      "1595 1617 owen 10945\n",
      "1596 1958 neil 10883\n",
      "1597 921 horace 10879\n",
      "1598 1455 ##rest 10869\n",
      "1599 1378 hul 10867\n",
      "1600 977 wilson 10836\n",
      "1601 1318 jacobus 10830\n",
      "1602 1386 pierre 10829\n",
      "1603 1721 joaquina 10820\n",
      "1604 1053 douglas 10819\n",
      "1605 701 lizzie 10809\n",
      "1606 1750 josiah 10801\n",
      "1607 897 effie 10791\n",
      "1608 2018 ignacia 10788\n",
      "1609 1797 karolina 10785\n",
      "1610 884 wayne 10782\n",
      "1611 503 bett 10780\n",
      "1612 1936 ##aro 10778\n",
      "1613 739 gusta 10772\n",
      "1614 1113 guadalupe 10735\n",
      "1615 1782 sofia 10723\n",
      "1616 243 ##oth 10722\n",
      "1617 1083 dejesus 10712\n",
      "1618 1414 ##idg 10693\n",
      "1619 1159 inez 10682\n",
      "1620 1495 timothy 10669\n",
      "1621 1816 rosine 10614\n",
      "1622 990 ##erson 10598\n",
      "1623 1744 irma 10586\n",
      "1624 1631 melissa 10574\n",
      "1625 1505 auguste 10557\n",
      "1626 1725 antonius 10508\n",
      "1627 1892 georgius 10506\n",
      "1628 1731 allan 10477\n",
      "1629 2047 rafaela 10466\n",
      "1630 1096 june 10428\n",
      "1631 1807 gloria 10417\n",
      "1632 572 rebec 10390\n",
      "1633 1763 betsy 10385\n",
      "1634 1962 lavina 10374\n",
      "1635 254 freder 10355\n",
      "1636 1482 loy 10347\n",
      "1637 1594 olga 10321\n",
      "1638 2016 jess 10319\n",
      "1639 545 theres 10317\n",
      "1640 1924 aub 10310\n",
      "1641 1951 ygnacio 10306\n",
      "1642 1967 ##abe 10276\n",
      "1643 1647 trinidad 10271\n",
      "1644 1185 joyce 10238\n",
      "1645 1058 mable 10217\n",
      "1646 1983 gregorio 10207\n",
      "1647 1845 vilhelm 10202\n",
      "1648 1412 jerome 10195\n",
      "1649 1331 francisc 10176\n",
      "1650 956 wallace 10155\n",
      "1651 1664 delcarmen 10144\n",
      "1652 1431 alta 10138\n",
      "1653 1648 lily 10128\n",
      "1654 1396 ##fugio 10126\n",
      "1655 1382 petrus 10106\n",
      "1656 1540 karoline 10102\n",
      "1657 623 jak 10066\n",
      "1658 304 ##lian 10014\n",
      "1659 1887 dorothee 10006\n",
      "1660 2023 baptiste 9932\n",
      "1661 767 clifford 9884\n",
      "1662 1008 harrison 9849\n",
      "1663 1895 brad 9829\n",
      "1664 1891 hanss 9806\n",
      "1665 1559 joel 9760\n",
      "1666 1938 giuseppe 9748\n",
      "1667 876 ##ance 9694\n",
      "1668 1852 refugio 9690\n",
      "1669 1522 smith 9612\n",
      "1670 1327 joannis 9597\n",
      "1671 1513 hulda 9546\n",
      "1672 53 ##q 9449\n",
      "1673 1636 catharinae 9429\n",
      "1674 1788 freda 9428\n",
      "1675 272 rich 9418\n",
      "1676 1879 kristian 9405\n",
      "1677 1759 lenora 9371\n",
      "1678 960 guy 9356\n",
      "1679 1087 karo 9345\n",
      "1680 1693 ##worth 9323\n",
      "1681 316 frie 9303\n",
      "1682 1009 mig 9299\n",
      "1683 1710 malinda 9295\n",
      "1684 1170 monroe 9267\n",
      "1685 1550 ina 9247\n",
      "1686 1443 naomi 9240\n",
      "1687 1439 jerem 9225\n",
      "1688 1270 bruce 9200\n",
      "1689 1729 ##cta 9179\n",
      "1690 1268 wilma 9167\n",
      "1691 1820 pablo 9150\n",
      "1692 1560 larry 9122\n",
      "1693 1447 scott 9059\n",
      "1694 1312 merce 9054\n",
      "1695 174 ##ug 9031\n",
      "1696 1518 cynthia 9027\n",
      "1697 1342 luise 9018\n",
      "1698 1624 eddie 8847\n",
      "1699 1618 ##gg 8846\n",
      "1700 1359 iva 8831\n",
      "1701 1360 audr 8828\n",
      "1702 1369 luella 8776\n",
      "1703 1101 viv 8760\n",
      "1704 1160 jefferson 8747\n",
      "1705 1815 ervin 8733\n",
      "1706 1956 lila 8712\n",
      "1707 1976 emeline 8671\n",
      "1708 1114 hir 8639\n",
      "1709 1490 cecelia 8628\n",
      "1710 1959 adelia 8597\n",
      "1711 1658 asa 8571\n",
      "1712 1614 elbert 8569\n",
      "1713 1508 geneva 8564\n",
      "1714 929 jackson 8552\n",
      "1715 372 benj 8541\n",
      "1716 1748 keith 8489\n",
      "1717 1418 ##oo 8482\n",
      "1718 1317 amb 8479\n",
      "1719 1566 donna 8464\n",
      "1720 1013 irvin 8456\n",
      "1721 1704 erma 8402\n",
      "1722 1448 ##vira 8341\n",
      "1723 1906 marilyn 8333\n",
      "1724 1608 rach 8297\n",
      "1725 934 kir 8269\n",
      "1726 1919 peggy 8266\n",
      "1727 540 ##rence 8234\n",
      "1728 1581 allie 8143\n",
      "1729 1325 annae 8135\n",
      "1730 1381 ##iley 8107\n",
      "1731 1228 earnest 8101\n",
      "1732 1257 lola 8071\n",
      "1733 1060 joao 8059\n",
      "1734 1224 mariae 8031\n",
      "1735 179 ##rist 8019\n",
      "1736 1548 minerva 8008\n",
      "1737 942 abra 7978\n",
      "1738 1846 bertie 7945\n",
      "1739 1511 merle 7915\n",
      "1740 441 ##usta 7907\n",
      "1741 1978 margie 7898\n",
      "1742 1606 angeline 7867\n",
      "1743 439 isab 7847\n",
      "1744 869 hora 7845\n",
      "1745 858 washington 7830\n",
      "1746 896 gord 7813\n",
      "1747 1874 ##igh 7790\n",
      "1748 1842 hellen 7781\n",
      "1749 1856 cordelia 7771\n",
      "1750 1986 annette 7765\n",
      "1751 1785 elva 7764\n",
      "1752 393 mab 7673\n",
      "1753 1544 ##talina 7642\n",
      "1754 1995 lorene 7636\n",
      "1755 1960 gustave 7592\n",
      "1756 1248 jay 7560\n",
      "1757 1830 miriam 7542\n",
      "1758 1287 byr 7518\n",
      "1759 2025 ##ray 7510\n",
      "1760 1139 nannie 7508\n",
      "1761 1320 velma 7485\n",
      "1762 1419 orville 7466\n",
      "1763 1837 adaline 7462\n",
      "1764 1405 geraldine 7459\n",
      "1765 1954 selma 7442\n",
      "1766 1217 phyl 7431\n",
      "1767 1714 ##cher 7421\n",
      "1768 1054 ##ield 7399\n",
      "1769 1755 ##pson 7396\n",
      "1770 1980 delores 7376\n",
      "1771 2022 elma 7343\n",
      "1772 607 ped 7321\n",
      "1773 1119 eun 7285\n",
      "1774 538 charlot 7216\n",
      "1775 1428 ##use 7199\n",
      "1776 1371 nina 7174\n",
      "1777 1086 marsh 7150\n",
      "1778 443 ##dred 7136\n",
      "1779 1300 estella 7107\n",
      "1780 1350 lucile 7100\n",
      "1781 1676 ##inald 7085\n",
      "1782 1765 laverne 7048\n",
      "1783 1044 beulah 7029\n",
      "1784 1076 ##onzo 6993\n",
      "1785 686 cly 6969\n",
      "1786 1157 hiram 6967\n",
      "1787 1701 lafayette 6953\n",
      "1788 1659 ##entine 6906\n",
      "1789 548 ##elma 6895\n",
      "1790 679 ##gna 6893\n",
      "1791 1392 ##celia 6852\n",
      "1792 2004 jeannette 6837\n",
      "1793 592 steph 6825\n",
      "1794 208 ##erine 6808\n",
      "1795 1940 winnie 6746\n",
      "1796 1611 wanda 6717\n",
      "1797 1838 jeann 6715\n",
      "1798 1911 mariah 6711\n",
      "1799 478 ##essie 6702\n",
      "1800 1743 josie 6676\n",
      "1801 699 ##ettie 6672\n",
      "1802 1780 ward 6667\n",
      "1803 1465 ##pcion 6651\n",
      "1804 2019 janie 6628\n",
      "1805 1736 mack 6600\n",
      "1806 2000 myra 6579\n",
      "1807 1670 malc 6533\n",
      "1808 1811 arlene 6533\n",
      "1809 1306 gro 6527\n",
      "1810 381 benjam 6515\n",
      "1811 1493 silas 6500\n",
      "1812 1639 elisab 6482\n",
      "1813 1650 carroll 6478\n",
      "1814 1521 burton 6463\n",
      "1815 596 ##olph 6458\n",
      "1816 1388 abig 6410\n",
      "1817 1900 lonnie 6385\n",
      "1818 1197 ##elis 6380\n",
      "1819 1239 ollie 6363\n",
      "1820 546 ##dys 6355\n",
      "1821 1069 clin 6313\n",
      "1822 1387 ##lieb 6306\n",
      "1823 1985 valentine 6280\n",
      "1824 1171 bob 6251\n",
      "1825 1767 roberta 6239\n",
      "1826 1379 ##riel 6221\n",
      "1827 1784 riley 6168\n",
      "1828 1950 ambrose 6127\n",
      "1829 1459 audrey 6124\n",
      "1830 1623 ##wn 6100\n",
      "1831 2032 callie 6085\n",
      "1832 1061 ##ifred 6074\n",
      "1833 1445 otis 6059\n",
      "1834 601 rus 6021\n",
      "1835 638 ##lius 6017\n",
      "1836 1017 doug 5974\n",
      "1837 237 pau 5931\n",
      "1838 1926 essie 5921\n",
      "1839 2038 ##ight 5896\n",
      "1840 1769 harley 5861\n",
      "1841 608 ##arr 5823\n",
      "1842 1717 leland 5784\n",
      "1843 730 ##fford 5781\n",
      "1844 1344 austin 5773\n",
      "1845 1118 ##nez 5760\n",
      "1846 1427 josh 5715\n",
      "1847 1472 ##omon 5698\n",
      "1848 1568 elij 5666\n",
      "1849 1525 goldie 5654\n",
      "1850 1702 laurence 5579\n",
      "1851 1252 clayton 5551\n",
      "1852 1463 timoth 5462\n",
      "1853 1315 pho 5459\n",
      "1854 1779 wiley 5457\n",
      "1855 1869 leah 5449\n",
      "1856 469 ##arine 5421\n",
      "1857 1774 millie 5411\n",
      "1858 1883 flossie 5369\n",
      "1859 786 ##ood 5346\n",
      "1860 1868 mitch 5277\n",
      "1861 1473 byron 5250\n",
      "1862 1137 perry 5183\n",
      "1863 21 q 5153\n",
      "1864 1877 miles 5123\n",
      "1865 1377 ##orth 5110\n",
      "1866 1003 ander 5070\n",
      "1867 1932 mike 5029\n",
      "1868 1536 bonnie 5020\n",
      "1869 1843 rachael 4987\n",
      "1870 1760 alton 4964\n",
      "1871 827 ##ayne 4949\n",
      "1872 707 ##iola 4904\n",
      "1873 1409 cyn 4895\n",
      "1874 1715 joach 4890\n",
      "1875 1393 dewey 4872\n",
      "1876 1191 ##than 4872\n",
      "1877 1534 ##ileen 4817\n",
      "1878 1719 johnnie 4814\n",
      "1879 1211 archie 4784\n",
      "1880 753 syl 4779\n",
      "1881 1929 kristine 4744\n",
      "1882 1215 ##ail 4741\n",
      "1883 1716 emmett 4736\n",
      "1884 1134 clinton 4732\n",
      "1885 1928 brown 4703\n",
      "1886 672 elean 4674\n",
      "1887 1996 carlton 4650\n",
      "1888 1947 abram 4635\n",
      "1889 1819 eman 4631\n",
      "1890 1551 ##cepcion 4621\n",
      "1891 1380 bettie 4608\n",
      "1892 1870 myron 4576\n",
      "1893 1964 malcolm 4532\n",
      "1894 1348 maxine 4458\n",
      "1895 1471 laf 4405\n",
      "1896 1363 ##dison 4395\n",
      "1897 788 ##uer 4379\n",
      "1898 1064 ##onnie 4379\n",
      "1899 377 ##ester 4353\n",
      "1900 1982 lemuel 4336\n",
      "1901 1537 bill 4264\n",
      "1902 1038 ##jes 4240\n",
      "1903 1638 delbert 4229\n",
      "1904 911 shir 4215\n",
      "1905 1592 melis 4210\n",
      "1906 1440 ##dney 4191\n",
      "1907 1652 forrest 4191\n",
      "1908 1573 columb 4157\n",
      "1909 568 kenne 4154\n",
      "1910 1694 lyle 4152\n",
      "1911 1503 sherman 4150\n",
      "1912 862 harris 4145\n",
      "1913 1913 web 4142\n",
      "1914 615 blanch 4129\n",
      "1915 878 fay 4123\n",
      "1916 1899 ##olm 4086\n",
      "1917 1668 abbie 4061\n",
      "1918 1019 joy 4030\n",
      "1919 1697 pab 3923\n",
      "1920 832 marjor 3922\n",
      "1921 1864 lyman 3919\n",
      "1922 803 ##ington 3895\n",
      "1923 1987 jewell 3852\n",
      "1924 1688 roscoe 3846\n",
      "1925 1935 jewel 3845\n",
      "1926 1645 beverly 3825\n",
      "1927 1213 rufus 3812\n",
      "1928 1885 madison 3810\n",
      "1929 1470 lulu 3809\n",
      "1930 1589 preston 3795\n",
      "1931 1106 ##aron 3768\n",
      "1932 1240 marshall 3758\n",
      "1933 1356 lorra 3620\n",
      "1934 433 ##oyd 3602\n",
      "1935 1764 betsey 3598\n",
      "1936 1209 newton 3596\n",
      "1937 1944 loyd 3533\n",
      "1938 1917 billie 3531\n",
      "1939 485 ##annah 3528\n",
      "1940 870 ##ffie 3523\n",
      "1941 1941 forest 3457\n",
      "1942 1441 clifton 3450\n",
      "1943 1844 millard 3413\n",
      "1944 1920 wade 3408\n",
      "1945 1399 naom 3391\n",
      "1946 1667 davis 3386\n",
      "1947 796 warr 3376\n",
      "1948 1793 cyrus 3352\n",
      "1949 727 henriet 3284\n",
      "1950 1433 billy 3281\n",
      "1951 920 viol 3272\n",
      "1952 1681 ##ellen 3267\n",
      "1953 1394 charley 3240\n",
      "1954 1338 ##fug 3230\n",
      "1955 1456 bridg 3211\n",
      "1956 1390 grover 3206\n",
      "1957 1914 sydney 3205\n",
      "1958 1426 ##erva 3155\n",
      "1959 999 ##ryn 3152\n",
      "1960 1226 reub 3107\n",
      "1961 1269 opal 3098\n",
      "1962 1413 grant 3013\n",
      "1963 1801 ##wart 3010\n",
      "1964 1307 ##vieve 2996\n",
      "1965 1138 ##roe 2944\n",
      "1966 904 dais 2931\n",
      "1967 1754 anderson 2919\n",
      "1968 1324 ##fton 2798\n",
      "1969 1858 stewart 2777\n",
      "1970 959 harrie 2772\n",
      "1971 383 ##lip 2766\n",
      "1972 1615 delcar 2730\n",
      "1973 1547 rosco 2729\n",
      "1974 1152 ferdin 2728\n",
      "1975 1527 bever 2719\n",
      "1976 936 ##ulah 2709\n",
      "1977 1411 sm 2705\n",
      "1978 1480 ##uste 2694\n",
      "1979 1840 gary 2679\n",
      "1980 1705 columbus 2676\n",
      "1981 1708 noah 2674\n",
      "1982 1953 bobby 2674\n",
      "1983 16 l 2673\n",
      "1984 1687 cleveland 2649\n",
      "1985 1022 ##oel 2641\n",
      "1986 1421 ##oda 2638\n",
      "1987 1626 ##itch 2638\n",
      "1988 1948 leop 2468\n",
      "1989 842 ##deline 2463\n",
      "1990 2029 morgan 2450\n",
      "1991 1255 niel 2442\n",
      "1992 1902 boyd 2435\n",
      "1993 925 ##anny 2426\n",
      "1994 1423 jasper 2413\n",
      "1995 1804 woodrow 2368\n",
      "1996 1758 glor 2352\n",
      "1997 1583 irving 2328\n",
      "1998 1653 ##veland 2315\n",
      "1999 1415 ##inidad 2315\n",
      "2000 1261 jew 2288\n",
      "2001 1666 ##oodr 2225\n",
      "2002 624 russ 2139\n",
      "2003 1078 ##upe 2136\n",
      "2004 1863 dwig 2111\n",
      "2005 1979 russel 2043\n",
      "2006 1330 ##cott 2034\n",
      "2007 1633 lafay 2015\n",
      "2008 1882 hamilton 1994\n",
      "2009 1091 ##dalupe 1958\n",
      "2010 2039 walker 1932\n",
      "2011 1718 taylor 1906\n",
      "2012 1343 ##ptis 1899\n",
      "2013 1912 pegg 1896\n",
      "2014 927 ##lace 1890\n",
      "2015 838 wash 1858\n",
      "2016 1799 ##orest 1818\n",
      "2017 1998 morg 1761\n",
      "2018 349 caro 1725\n",
      "2019 1077 dejes 1679\n",
      "2020 575 ##atr 1678\n",
      "2021 157 ##omas 1637\n",
      "2022 880 joaqu 1516\n",
      "2023 673 rac 1505\n",
      "2024 1451 archib 1478\n",
      "2025 1826 ##ilton 1478\n",
      "2026 1043 ##eland 1462\n",
      "2027 1865 dwight 1420\n",
      "2028 1055 bil 1350\n",
      "2029 635 ##ores 1305\n",
      "2030 1808 ##ossie 1281\n",
      "2031 410 ##eres 1280\n",
      "2032 1341 ##asta 1213\n",
      "2033 357 ##nest 1177\n",
      "2034 1570 giuse 1147\n",
      "2035 1661 ##aylor 1126\n",
      "2036 329 ##irg 1119\n",
      "2037 1709 woodr 1028\n",
      "2038 1853 ##ilyn 954\n",
      "2039 829 ##omer 751\n",
      "2040 1535 ##umb 549\n",
      "2041 811 ##ash 527\n"
     ]
    }
   ],
   "execution_count": 27
  },
  {
   "cell_type": "code",
   "id": "205c4769",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:07:23.475216Z",
     "start_time": "2024-12-05T18:07:23.444112Z"
    }
   },
   "source": [
    "for token, id_ in tokenizer_vocab.items():\n",
    "    if counter[id_] == 0:\n",
    "        print(id_, token, counter[id_])"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 [CLS] 0\n",
      "0 [UNK] 0\n",
      "3 [SEP] 0\n",
      "1 [PAD] 0\n",
      "1794 ##frie 0\n",
      "4 [MASK] 0\n"
     ]
    }
   ],
   "execution_count": 28
  },
  {
   "cell_type": "code",
   "id": "a766a635",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:07:23.508043Z",
     "start_time": "2024-12-05T18:07:23.476884Z"
    }
   },
   "source": [
    "tokenize('zetty')"
   ],
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[30, 232, 49, 1, 1, 1, 1, 1, 1, 1]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 29
  },
  {
   "cell_type": "markdown",
   "id": "e0df5a95",
   "metadata": {},
   "source": [
    "## Save augmented triplets"
   ]
  },
  {
   "cell_type": "code",
   "id": "523f3464",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:09:55.869704Z",
     "start_time": "2024-12-05T18:09:55.840543Z"
    }
   },
   "source": [
    "print(type(aug_data))\n",
    "print(len(aug_data))"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'list'>\n",
      "15486190\n"
     ]
    }
   ],
   "execution_count": 35
  },
  {
   "cell_type": "code",
   "id": "efe649b2",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:13:17.816889Z",
     "start_time": "2024-12-05T18:10:02.066162Z"
    }
   },
   "source": [
    "random.shuffle(aug_data)\n",
    "df = pd.DataFrame(aug_data)\n",
    "save_file(augmented_path,\n",
    "          lambda local_out_path : df.to_csv(local_out_path, index=False))"
   ],
   "outputs": [],
   "execution_count": 36
  },
  {
   "cell_type": "code",
   "id": "dd31da69",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-05T18:09:55.839238Z",
     "start_time": "2024-12-05T18:09:55.783629Z"
    }
   },
   "source": "augmented_path",
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'s3://fs-nama-data/2024/familysearch-names/processed/tree-hr-given-triplets-1000-augmented.csv.gz'"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "execution_count": 34
  },
  {
   "metadata": {},
   "cell_type": "code",
   "outputs": [],
   "execution_count": null,
   "source": "",
   "id": "6650b0a7a7582309"
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}