{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "import lzma\n",
    "import torch\n",
    "import numpy as np\n",
    "from gensim import downloader\n",
    "from gensim.models import Word2Vec\n",
    "import gensim.downloader\n",
    "import pandas as pd\n",
    "import csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "from sklearn.datasets import fetch_20newsgroups\n",
    "# https://scikit-learn.org/0.19/datasets/twenty_newsgroups.html\n",
    "\n",
    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\10118794\\AppData\\Local\\Temp\\ipykernel_32100\\3675615398.py:1: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.\n",
      "\n",
      "\n",
      "  train_x = pd.read_csv('train/in.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
      "C:\\Users\\10118794\\AppData\\Local\\Temp\\ipykernel_32100\\3675615398.py:2: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.\n",
      "\n",
      "\n",
      "  train_y = pd.read_csv('train/expected.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
      "C:\\Users\\10118794\\AppData\\Local\\Temp\\ipykernel_32100\\3675615398.py:3: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.\n",
      "\n",
      "\n",
      "  dev_x = pd.read_csv('dev-0/in.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
      "C:\\Users\\10118794\\AppData\\Local\\Temp\\ipykernel_32100\\3675615398.py:4: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.\n",
      "\n",
      "\n",
      "  dev_y = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
      "C:\\Users\\10118794\\AppData\\Local\\Temp\\ipykernel_32100\\3675615398.py:5: FutureWarning: The error_bad_lines argument has been deprecated and will be removed in a future version. Use on_bad_lines in the future.\n",
      "\n",
      "\n",
      "  test_x = pd.read_csv('test-A/in.tsv', header=None, sep='\\t',quoting=csv.QUOTE_NONE, error_bad_lines=False)\n"
     ]
    }
   ],
   "source": [
    "train_x = pd.read_csv('train/in.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
    "train_y = pd.read_csv('train/expected.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
    "dev_x = pd.read_csv('dev-0/in.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
    "dev_y = pd.read_csv('dev-0/expected.tsv', header=None, sep='\\t', quoting=csv.QUOTE_NONE, error_bad_lines=False)\n",
    "test_x = pd.read_csv('test-A/in.tsv', header=None, sep='\\t',quoting=csv.QUOTE_NONE, error_bad_lines=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_x = train_x[0]\n",
    "dev_x = dev_x[0]\n",
    "test_x = test_x[0]\n",
    "train_y = train_y[0]\n",
    "dev_y = dev_y[0]\n",
    "train_y = train_y.to_numpy()\n",
    "dev_y = dev_y.to_numpy()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[==================================================] 100.0% 387.1/387.1MB downloaded\n"
     ]
    }
   ],
   "source": [
    "word2vec_100 = downloader.load(\"glove-twitter-100\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_x_w2v = [np.mean([word2vec_100[word.lower()] for word in doc.split() if word.lower() in word2vec_100]\n",
    "                   or [np.zeros(100, dtype=float)], axis=0) for doc in train_x]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "dev_x_w2v2 = [np.mean([word2vec_100[word.lower()] for word in doc.split() if word.lower() in word2vec_100]\n",
    "                   or [np.zeros(100, dtype=float)], axis=0) for doc in dev_x]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_x_w2v = [np.mean([word2vec_100[word.lower()] for word in doc.split() if word.lower() in word2vec_100]\n",
    "                   or [np.zeros(100, dtype=float)], axis=0) for doc in test_x]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'list'>\n"
     ]
    }
   ],
   "source": [
    "print(type(x_train_w2v))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [],
   "source": [
    "class NeuralNetworkModelx(torch.nn.Module):\n",
    "\n",
    "    def __init__(self):\n",
    "        super(NeuralNetworkModelx, self).__init__()\n",
    "        self.fc1 = torch.nn.Linear(100,500)\n",
    "        self.fc2 = torch.nn.Linear(500,1)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.fc1(x)\n",
    "        x = torch.relu(x)\n",
    "        x = self.fc2(x)\n",
    "        x = torch.sigmoid(x)\n",
    "        return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict(model, data):\n",
    "    model.eval()\n",
    "    predictions = []\n",
    "    for x in data:\n",
    "        X = torch.tensor(np.array(x).astype(np.float32))\n",
    "        Y_predictions = model(X)\n",
    "        if Y_predictions[0] > 0.5:\n",
    "            predictions.append(\"1\")\n",
    "        else:\n",
    "            predictions.append(\"0\")\n",
    "    return predictions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [],
   "source": [
    "BATCH_SIZE = 22"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [],
   "source": [
    "FEATURES = 100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = NeuralNetworkModelx()\n",
    "criterion = torch.nn.BCELoss()\n",
    "optimizer = torch.optim.ASGD(model.parameters(), lr=0.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 97,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_loss_acc(model, X_dataset, Y_dataset):\n",
    "    loss_score = 0\n",
    "    acc_score = 0\n",
    "    items_total = 0\n",
    "    model.eval()\n",
    "    for i in range(0, Y_dataset.shape[0], BATCH_SIZE):\n",
    "        X = np.array(X_dataset[i:i+BATCH_SIZE]).astype(np.float32)\n",
    "        X = torch.tensor(X)\n",
    "        Y = Y_dataset[i:i+BATCH_SIZE]\n",
    "        Y = torch.tensor(Y.astype(np.float32)).reshape(-1,1)\n",
    "        Y_predictions = model(X)\n",
    "        acc_score += torch.sum((Y_predictions > 0.5) == Y).item()\n",
    "        items_total += Y.shape[0]\n",
    "\n",
    "        loss = criterion(Y_predictions, Y)\n",
    "\n",
    "        loss_score += loss.item() * Y.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5251316127311283 0.7293691876828085\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "1"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5236849654193508 0.7303671882284282\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5224315920787511 0.7310509394672956\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "3"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5211956211888409 0.7323010301161341\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "4"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5201234243425219 0.7329606083314052\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "5"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5192769648569354 0.7337203319301469\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "6"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5182789765264713 0.7341761660893918\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "7"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5173362161154499 0.7348944502191112\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "8"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5163200458762819 0.7358717310302197\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "9"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.5155178654158614 0.7361583540242904\n"
     ]
    }
   ],
   "source": [
    "for epoch in range(10):\n",
    "    loss_score = 0\n",
    "    acc_score = 0\n",
    "    items_total = 0\n",
    "    for i in range(0, train_y.shape[0], BATCH_SIZE):\n",
    "        x = train_x_w2v[i:i+BATCH_SIZE]\n",
    "        x = torch.tensor(np.array(x).astype(np.float32))\n",
    "        y = train_y[i:i+BATCH_SIZE]\n",
    "        y = torch.tensor(y.astype(np.float32)).reshape(-1, 1)\n",
    "        y_pred = model(x)\n",
    "        acc_score += torch.sum((y_pred > 0.5) == y).item()\n",
    "        items_total += y.shape[0]\n",
    "\n",
    "        optimizer.zero_grad()\n",
    "        loss = criterion(y_pred, y)\n",
    "        loss.backward()\n",
    "        optimizer.step()\n",
    "\n",
    "        loss_score += loss.item() * y.shape[0]\n",
    "    display(epoch)\n",
    "    #display(get_loss_acc(model, train_x_w2v, train_y))\n",
    "    #display(get_loss_acc(model, dev_x_w2v2, dev_y))\n",
    "    print((loss_score / items_total), (acc_score / items_total))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 119,
   "metadata": {},
   "outputs": [],
   "source": [
    "pred_dev = predict(model, dev_x_w2v2)\n",
    "pred_test = predict(model, test_x_w2v)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 120,
   "metadata": {},
   "outputs": [],
   "source": [
    "dev_pred = [int(i) for i in pred_dev]\n",
    "test_pred = [int(i) for i in pred_test]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 121,
   "metadata": {},
   "outputs": [],
   "source": [
    "dev_pred = np.array(dev_pred)\n",
    "test_pred = np.array(test_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "numpy.ndarray"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "type(dev_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 123,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 1, 0, ..., 0, 1, 0])"
      ]
     },
     "execution_count": 123,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dev_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.savetxt(\"dev-0/out.tsv\",dev_pred, delimiter=\"\\t\", fmt='%d')\n",
    "np.savetxt(\"test-A/out.tsv\",test_pred, delimiter=\"\\t\", fmt='%d')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "py",
   "language": "python",
   "name": "py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}