{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[nltk_data] Downloading package stopwords to\n",
      "[nltk_data]     C:\\Users\\akida\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package stopwords is already up-to-date!\n",
      "[nltk_data] Downloading package wordnet to\n",
      "[nltk_data]     C:\\Users\\akida\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package wordnet is already up-to-date!\n",
      "[nltk_data] Downloading package punkt to\n",
      "[nltk_data]     C:\\Users\\akida\\AppData\\Roaming\\nltk_data...\n",
      "[nltk_data]   Package punkt is already up-to-date!\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import csv\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import re\n",
    "import string\n",
    "import torch\n",
    "\n",
    "import nltk\n",
    "from nltk.tokenize import word_tokenize\n",
    "from nltk.corpus import stopwords # used for preprocessing\n",
    "from nltk.stem import WordNetLemmatizer # used for preprocessing\n",
    "nltk.download('stopwords')\n",
    "nltk.download('wordnet')\n",
    "nltk.download('punkt')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_in = pd.read_csv(\"./train/in.tsv\", delimiter=\"\\t\", names=[\"text\", \"date\"], header=None)\n",
    "train_exp = pd.read_csv(\"./train/expected.tsv\", delimiter=\"\\t\", header=None)\n",
    "dev_in = pd.read_csv(\"./dev-0/in.tsv\", delimiter=\"\\t\", names=[\"text\", \"date\"],header=None)\n",
    "dev_exp = pd.read_csv(\"./dev-0/expected.tsv\", delimiter=\"\\t\", header=None)\n",
    "test_in = pd.read_csv(\"./test-A/in.tsv\", delimiter=\"\\t\", names=[\"text\", \"date\"], header=None)\n",
    "\n",
    "train_in.drop('date', axis=1, inplace=True)\n",
    "dev_in.drop('date', axis=1, inplace=True)\n",
    "test_in.drop('date', axis=1, inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_set = train_in\n",
    "train_set['result'] = train_exp\n",
    "# train_set = train_set[:1000]\n",
    "\n",
    "dev_set = dev_in\n",
    "dev_set['result'] = dev_exp\n",
    "\n",
    "test_set = test_in\n",
    "test_set['result'] = pd.DataFrame(np.zeros(len(test_in), dtype=int))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "289541"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def remove_urls(text):\n",
    "    return ' '.join(re.sub(\"(@[A-Za-z0-9]+)|([^0-9A-Za-z \\t])|(\\w+:\\/\\/\\S+)\",\" \",str(text)).split())\n",
    "\n",
    "def text_lowercase(text):   \n",
    "    return text.lower()\n",
    "\n",
    "def remove_numbers(text):\n",
    "    return re.sub(r'\\d+', '', text)\n",
    "\n",
    "def remove_punctuation(text):\n",
    "    return text.translate(str.maketrans('', '', string.punctuation))\n",
    "\n",
    "def remove_stopwords(text):\n",
    "    stop_words = set(stopwords.words('english'))\n",
    "    return [i for i in text if not i in stop_words]\n",
    "\n",
    "def tokenize(text):\n",
    "    return word_tokenize(text)\n",
    "\n",
    "def lemmatize(text):\n",
    "    lemmatizer = WordNetLemmatizer() \n",
    "    return [lemmatizer.lemmatize(token) for token in text]\n",
    "\n",
    "def preprocess(dataset):\n",
    "    texts_column = []\n",
    "    for num, text in enumerate(dataset['text']):\n",
    "        if num % 10000 == 0:\n",
    "            print(num)\n",
    "        prep_text = remove_urls(text)\n",
    "        prep_text = text_lowercase(prep_text)\n",
    "        prep_text = remove_numbers(prep_text)\n",
    "        prep_text = remove_punctuation(prep_text)\n",
    "        prep_text = tokenize(prep_text)\n",
    "        prep_text = remove_stopwords(prep_text)\n",
    "        prep_text = lemmatize(prep_text)\n",
    "        pre_text = ' '.join(prep_text)\n",
    "        texts_column.append(pre_text)\n",
    "    dataset['text'] = texts_column\n",
    "    return dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "0\n",
      "0\n"
     ]
    }
   ],
   "source": [
    "train_set = train_set[:12000]\n",
    "train_set = preprocess(train_set)\n",
    "dev_set = preprocess(dev_set)\n",
    "test_set = preprocess(dev_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_set_copy = train_set\n",
    "dev_set_copy = dev_set\n",
    "test_set_copy = test_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "5000\n"
     ]
    }
   ],
   "source": [
    "dictionary = set()\n",
    "\n",
    "for i, text_line in enumerate(train_set_copy['text']):\n",
    "    if i % 5000 == 0:\n",
    "        print(i)\n",
    "    for word in text_line.split():\n",
    "        dictionary.add(word)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "word_index_map = {}\n",
    "i = 0\n",
    "for w in dictionary:\n",
    "    word_index_map[w] = i\n",
    "    i += 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "21120"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(word_index_map)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n"
     ]
    }
   ],
   "source": [
    "prep_x = []\n",
    "for num, w in enumerate(train_set_copy['text']):\n",
    "    if num % 10000 == 0:\n",
    "        print(num)\n",
    "    a = np.zeros(len(word_index_map))\n",
    "    for word in w.split():\n",
    "        index = word_index_map[word]\n",
    "        a[index] = 1.\n",
    "    prep_x.append(a)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_y = train_set_copy['result'].astype(float).tolist()\n",
    "x = torch.tensor(prep_x, dtype=torch.float)\n",
    "y = torch.tensor(train_y, dtype=torch.float)\n",
    "k = torch.randn(len(dictionary), requires_grad=True)\n",
    "rate = torch.tensor(0.001)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "200\n",
      "400\n",
      "600\n",
      "800\n",
      "1000\n",
      "1200\n",
      "1400\n"
     ]
    }
   ],
   "source": [
    "for i in range(1500):\n",
    "    y_predicted = torch.sigmoid(x @ k)\n",
    "    price = (-1 / y.size()[0]) * torch.sum(y * torch.log(y_predicted + 1e-10) + (1 - y) * torch.log(1 - y_predicted + 1e-10))\n",
    "    price.backward()\n",
    "    with torch.no_grad():\n",
    "        k -= rate * k.grad\n",
    "    k.requires_grad = True\n",
    "    if i % 200 == 0:\n",
    "        print(i)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "def prepare_data(dataset):\n",
    "    prep_x = []\n",
    "    for num, w in enumerate(dataset['text']):\n",
    "        if num % 1000 == 0:\n",
    "            print(num)\n",
    "        a = np.zeros(len(word_index_map))\n",
    "        for word in w.split():\n",
    "            if word in word_index_map:\n",
    "                index = word_index_map[word]\n",
    "                a[index] = 1.\n",
    "        prep_x.append(a)\n",
    "    return torch.tensor(prep_x, dtype=torch.float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict(x, weights, save_path):\n",
    "    with open(save_path + '/out.tsv', 'wt', newline='') as f:\n",
    "        writer = csv.writer(f, delimiter='\\t')\n",
    "        y = torch.sigmoid(x @ weights)\n",
    "        for value in y:\n",
    "            if value > 0.90:\n",
    "                value = torch.tensor([0.90])\n",
    "            elif value < 0.10:\n",
    "                value = torch.tensor([0.10])\n",
    "            writer.writerow([str(value.item())])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0\n",
      "1000\n",
      "2000\n",
      "3000\n",
      "4000\n",
      "5000\n",
      "0\n",
      "1000\n",
      "2000\n",
      "3000\n",
      "4000\n",
      "5000\n"
     ]
    }
   ],
   "source": [
    "x_dev = prepare_data(dev_set_copy)\n",
    "x_test = prepare_data(test_set_copy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "predict(x_dev, k, './dev-0')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict(x_test, k, './test-A')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}