Thesis/dataset/umls/get_neighbor.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "path1 = './entities.txt'\n",
    "path2 = './relations.txt'\n",
    "path3 = './train.tsv'\n",
    "path4 = './dev.tsv'\n",
    "path5 = './test.tsv'\n",
    "path6 = './get_neighbor/entity2id.txt'\n",
    "path7 = './get_neighbor/relation2id.txt'\n",
    "path8 = './get_neighbor/train2id.txt'\n",
    "path9 = './get_neighbor/valid2id.txt'\n",
    "path10 = './get_neighbor/test2id.txt'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path1, 'r') as f:\n",
    "    a = f.readlines()\n",
    "cnt = 0\n",
    "with open(path6, 'w') as f:\n",
    "    for line in a:\n",
    "        en = line.strip()\n",
    "        f.write(en + '\\t' + str(cnt) + '\\n')\n",
    "        cnt += 1\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path2, 'r') as f:\n",
    "    a = f.readlines()\n",
    "cnt = 0\n",
    "with open(path7, 'w') as f:\n",
    "    for line in a:\n",
    "        re = line.strip()\n",
    "        f.write(re + '\\t' + str(cnt) + '\\n')\n",
    "        cnt += 1\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path6, 'r') as f:\n",
    "    a = f.readlines()\n",
    "en2id = {}\n",
    "for line in a:\n",
    "    b = line.strip().split('\\t')\n",
    "    en, num = b[0], b[1]\n",
    "    en2id[en] = num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path7, 'r') as f:\n",
    "    a = f.readlines()\n",
    "re2id = {}\n",
    "for line in a:\n",
    "    b = line.strip().split('\\t')\n",
    "    re, num = b[0], b[1]\n",
    "    re2id[re] = num"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path3, 'r') as f:\n",
    "    a = f.readlines()\n",
    "with open(path8, 'w') as f:\n",
    "    for line in a:\n",
    "        b = line.strip().split('\\t')\n",
    "        h, r, t = b[0], b[1], b[2]\n",
    "        f.write(en2id[h] + ' ' + re2id[r] + ' ' + en2id[t] + '\\n')\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path4, 'r') as f:\n",
    "    a = f.readlines()\n",
    "with open(path9, 'w') as f:\n",
    "    for line in a:\n",
    "        b = line.strip().split('\\t')\n",
    "        h, r, t = b[0], b[1], b[2]\n",
    "        f.write(en2id[h] + ' ' + re2id[r] + ' ' + en2id[t] + '\\n')\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path5, 'r') as f:\n",
    "    a = f.readlines()\n",
    "with open(path10, 'w') as f:\n",
    "    for line in a:\n",
    "        b = line.strip().split('\\t')\n",
    "        h, r, t = b[0], b[1], b[2]\n",
    "        f.write(en2id[h] + ' ' + re2id[r] + ' ' + en2id[t] + '\\n')\n",
    "    "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [default]",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}