{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "equal-singles",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import torch\n",
    "import csv\n",
    "import lzma\n",
    "import gensim.downloader\n",
    "from nltk import word_tokenize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "involved-understanding",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train = pd.read_table('in.tsv', sep='\\t', header=None, quoting=3)\n",
    "y_train = pd.read_table('expected.tsv', sep='\\t', header=None, quoting=3)\n",
    "#x_dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\\t', header=None, quoting=3)\n",
    "#x_test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\\t', header=None, quoting=3)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "collaborative-cincinnati",
   "metadata": {},
   "outputs": [
    {
     "ename": "AttributeError",
     "evalue": "module 'torch' has no attribute 'nn'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-5-11c9482004ae>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m#print('inicjalizacja modelu')\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mclass\u001b[0m \u001b[0mNeuralNetworkModel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mModule\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m         \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mNeuralNetworkModel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0ml01\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mLinear\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m300\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m300\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mAttributeError\u001b[0m: module 'torch' has no attribute 'nn'"
     ]
    }
   ],
   "source": [
    "#print('inicjalizacja modelu')\n",
    "class NeuralNetworkModel(torch.nn.Module):\n",
    "    def __init__(self):\n",
    "        super(NeuralNetworkModel, self).__init__()\n",
    "        self.l01 = torch.nn.Linear(300, 300)\n",
    "        self.l02 = torch.nn.Linear(300, 1)\n",
    "\n",
    "    def forward(self, x):\n",
    "        x = self.l01(x)\n",
    "        x = torch.relu(x)\n",
    "        x = self.l02(x)\n",
    "        x = torch.sigmoid(x)\n",
    "        return x"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "hydraulic-business",
   "metadata": {},
   "outputs": [],
   "source": [
    "#print('przygotowanie danych')\n",
    "\n",
    "x_train = x_train.str.lower()\n",
    "x_dev = x_dev[0].str.lower()\n",
    "x_test = x_test[0].str.lower()\n",
    "\n",
    "x_train = [word_tokenize(x) for x in x_train]\n",
    "x_dev = [word_tokenize(x) for x in x_dev]\n",
    "x_test = [word_tokenize(x) for x in x_test]\n",
    "\n",
    "word2vec = gensim.downloader.load('word2vec-google-news-300')\n",
    "x_train = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in x_train]\n",
    "x_dev = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in x_dev]\n",
    "x_test = [np.mean([word2vec[word] for word in content if word in word2vec] or [np.zeros(300)], axis=0) for content in x_test]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "heavy-sandwich",
   "metadata": {},
   "outputs": [],
   "source": [
    "#print('trenowanie modelu')\n",
    "model = NeuralNetworkModel()\n",
    "BATCH_SIZE = 5\n",
    "criterion = torch.nn.BCELoss()\n",
    "optimizer = torch.optim.SGD(model.parameters(), lr=0.01)\n",
    "\n",
    "for epoch in range(BATCH_SIZE):\n",
    "    model.train()\n",
    "    for i in range(0, y_train.shape[0], BATCH_SIZE):\n",
    "        X = x_train[i:i + BATCH_SIZE]\n",
    "        X = torch.tensor(X)\n",
    "        y = y_train[i:i + BATCH_SIZE]\n",
    "        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)\n",
    "        optimizer.zero_grad()\n",
    "        outputs = model(X.float())\n",
    "        loss = criterion(outputs, y)\n",
    "        loss.backward()\n",
    "        optimizer.step()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "small-pavilion",
   "metadata": {},
   "outputs": [],
   "source": [
    "#print('predykcja wynikow')\n",
    "y_dev = []\n",
    "y_test = []\n",
    "model.eval()\n",
    "\n",
    "with torch.no_grad():\n",
    "    for i in range(0, len(x_dev), BATCH_SIZE):\n",
    "        X = x_dev[i:i + BATCH_SIZE]\n",
    "        X = torch.tensor(X)\n",
    "        outputs = model(X.float())\n",
    "        prediction = (outputs > 0.5)\n",
    "        y_dev += prediction.tolist()\n",
    "\n",
    "    for i in range(0, len(x_test), BATCH_SIZE):\n",
    "        X = x_test[i:i + BATCH_SIZE]\n",
    "        X = torch.tensor(X)\n",
    "        outputs = model(X.float())\n",
    "        y = (outputs >= 0.5)\n",
    "        y_test += prediction.tolist()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "toxic-pendant",
   "metadata": {},
   "outputs": [],
   "source": [
    "# print('eksportowanie do plików')\n",
    "y_dev = np.asarray(y_dev, dtype=np.int32)\n",
    "y_test = np.asarray(y_test, dtype=np.int32)\n",
    "y_dev.tofile('./dev-0/out.tsv', sep='\\n')\n",
    "y_test.tofile('./test-A/out.tsv', sep='\\n')\n"
   ]
  }
 ],
 "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}