{
 "metadata": {
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.5-final"
  },
  "orig_nbformat": 2,
  "kernelspec": {
   "name": "python3",
   "display_name": "Python 3.9.5 64-bit",
   "metadata": {
    "interpreter": {
     "hash": "ac59ebe37160ed0dfa835113d9b8498d9f09ceb179beaac4002f036b9467c963"
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# https://gonito.net/challenge/paranormal-or-skeptic\n",
    "# dane + wyniki -> https://git.wmi.amu.edu.pl/s444380/paranormal-or-skeptic-ISI-public"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "import lzma\n",
    "from keras.models import Sequential\n",
    "from keras.layers import Dense\n",
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "from gensim import downloader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read train files\n",
    "with lzma.open(\"train/in.tsv.xz\", \"rt\", encoding=\"utf-8\") as train_file:\n",
    "    x_train = [x.strip().lower() for x in train_file.readlines()]\n",
    "\n",
    "with open(\"train/expected.tsv\", \"r\", encoding=\"utf-8\") as train_file:\n",
    "    y_train = np.array([int(x.strip()) for x in train_file.readlines()])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "word2vec = downloader.load(\"glove-twitter-200\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "x_train_w2v = [np.mean([word2vec[word.lower()] for word in doc.split() if word.lower() in word2vec]\n",
    "                   or [np.zeros(200)], axis=0) for doc in x_train]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Read dev files\n",
    "with lzma.open(\"dev-0/in.tsv.xz\", \"rt\", encoding=\"utf-8\") as dev_file:\n",
    "    x_dev = [x.strip().lower() for x in dev_file.readlines()]\n",
    "\n",
    "with open(\"dev-0/expected.tsv\", \"r\", encoding=\"utf-8\") as train_file:\n",
    "    y_dev = np.array([int(x.strip()) for x in train_file.readlines()])\n",
    "\n",
    "x_dev_w2v = [np.mean([word2vec[word.lower()] for word in doc.split() if word.lower() in word2vec]\n",
    "                   or [np.zeros(200)], axis=0) for doc in x_dev]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# y_train = y_train.reshape(-1, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Sequential()\n",
    "model.add(Dense(1000, activation='relu', input_dim=200))\n",
    "model.add(Dense(500, activation='relu'))\n",
    "model.add(Dense(1, activation='sigmoid'))\n",
    "model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "output_type": "stream",
     "name": "stdout",
     "text": [
      "Epoch 1/5\n",
      "9050/9050 [==============================] - 48s 5ms/step - loss: 0.5244 - accuracy: 0.7303 - val_loss: 0.5536 - val_accuracy: 0.6910\n",
      "Epoch 2/5\n",
      "9050/9050 [==============================] - 47s 5ms/step - loss: 0.5132 - accuracy: 0.7367 - val_loss: 0.5052 - val_accuracy: 0.7475\n",
      "Epoch 3/5\n",
      "9050/9050 [==============================] - 47s 5ms/step - loss: 0.5067 - accuracy: 0.7396 - val_loss: 0.5091 - val_accuracy: 0.7320\n",
      "Epoch 4/5\n",
      "9050/9050 [==============================] - 47s 5ms/step - loss: 0.5025 - accuracy: 0.7429 - val_loss: 0.5343 - val_accuracy: 0.7071\n",
      "Epoch 5/5\n",
      "9050/9050 [==============================] - 47s 5ms/step - loss: 0.4992 - accuracy: 0.7447 - val_loss: 0.5143 - val_accuracy: 0.7381\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(tf.stack(x_train_w2v), tf.stack(y_train), epochs=5, validation_data=(tf.stack(x_dev_w2v), tf.stack(y_dev)))"
   ]
  }
 ]
}