ireland-news-headlines/run.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import fasttext"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train = pd.read_csv('train/in.tsv', sep='\\t', header=None)\n",
    "X_train = X_train[2]\n",
    "y_train = pd.read_csv('train/expected.tsv', sep='\\t', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_dev = pd.read_csv('dev-0/in.tsv', sep='\\t', header=None)\n",
    "X_dev = X_dev[2]\n",
    "y_dev = pd.read_csv('dev-0/expected.tsv', sep='\\t', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test_A = pd.read_csv('test-A/in.tsv', sep='\\t', header=None)\n",
    "X_test_A = X_test_A[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_test_B = pd.read_csv('test-B/in.tsv', sep='\\t', header=None)\n",
    "X_test_B = X_test_B[2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('train.txt', 'w', encoding='utf-8') as f:\n",
    "    for i in range(len(X_train)):\n",
    "        f.write(f'__label__{y_train[0][i]} {X_train[i]}\\n')\n",
    "\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('dev.txt', 'w', encoding='utf-8') as f:\n",
    "    for i in range(len(X_dev)):\n",
    "        f.write(f'__label__{y_dev[0][i]} {X_dev[i]}\\n')\n",
    "\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = fasttext.train_supervised('train.txt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save_model(\"model_fasttext.bin\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "N\t149134\n",
      "P@1\t0.762\n",
      "R@1\t0.762\n"
     ]
    }
   ],
   "source": [
    "def print_results(N, p, r):\n",
    "    print(\"N\\t\" + str(N))\n",
    "    print(\"P@{}\\t{:.3f}\".format(1, p))\n",
    "    print(\"R@{}\\t{:.3f}\".format(1, r))\n",
    "\n",
    "print_results(*model.test('dev.txt'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('dev-0/out.tsv', 'w') as f:\n",
    "    for sentence in X_dev:\n",
    "        f.write(f'{model.predict(sentence)[0][0][9:]}\\n')\n",
    "\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('test-A/out.tsv', 'w') as f:\n",
    "    for sentence in X_test_A:\n",
    "        f.write(f'{model.predict(sentence)[0][0][9:]}\\n')\n",
    "\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('test-B/tsv.txt', 'w') as f:\n",
    "    for sentence in X_test_B:\n",
    "        f.write(f'{model.predict(sentence)[0][0][9:]}\\n')\n",
    "\n",
    "f.close()"
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "3ecbe772e0e869a386d256c10cc6d948e50cd4df13a3f02e58ab4f2a666d7bf0"
  },
  "kernelspec": {
   "display_name": "Python 3.8.13 ('eks')",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.13"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}