{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "e3b4fa50-eb34-4e53-b938-65cbd4c21f43",
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "from nltk.tokenize import word_tokenize\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import LabelEncoder\n",
    "import gensim\n",
    "from gensim.models import Word2Vec\n",
    "import numpy as np\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score, classification_report\n",
    "import pandas as pd\n",
    "from keras.src.utils import pad_sequences\n",
    "from keras.src.legacy.preprocessing.text import Tokenizer\n",
    "from keras.src.layers import Dropout, Dense, Activation, Embedding, MaxPooling1D, GlobalMaxPooling1D\n",
    "from keras.src.layers import Conv1D\n",
    "from keras import Sequential\n",
    "from keras.optimizers import Adam\n",
    "from sklearn.metrics import accuracy_score"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4363302f-a5e2-450b-bcee-5a0045101986",
   "metadata": {},
   "source": [
    "# Data preprocessing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40c5fe05-fe48-42ed-8d1a-9c128e8a7550",
   "metadata": {},
   "source": [
    "## Train data preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "80cdc748-8645-4724-afaf-f5af64be9052",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>sentence</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Mindaugas Budzinauskas wierzy w odbudowę formy...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>Przyjmujący reprezentacji Polski wrócił do PGE...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>FEN 9: Zapowiedź walki Róża Gumienna vs Katarz...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>Aleksander Filipiak: Czuję się dobrze w nowym ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>Victoria Carl i Aleksiej Czerwotkin mistrzami ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98127</th>\n",
       "      <td>1</td>\n",
       "      <td>Kamil Syprzak zaczyna kolekcjonować trofea. FC...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98128</th>\n",
       "      <td>1</td>\n",
       "      <td>Holandia: dwa gole Piotra Parzyszka Piotr Parz...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98129</th>\n",
       "      <td>1</td>\n",
       "      <td>Sparingowo: Korona gorsza od Stali. Lettieri s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98130</th>\n",
       "      <td>1</td>\n",
       "      <td>Vive - Wisła. Ośmiu debiutantów w tegorocznej ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98131</th>\n",
       "      <td>1</td>\n",
       "      <td>WTA Miami: Timea Bacsinszky pokonana, Swietłan...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>98132 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       label                                           sentence\n",
       "0          1  Mindaugas Budzinauskas wierzy w odbudowę formy...\n",
       "1          1  Przyjmujący reprezentacji Polski wrócił do PGE...\n",
       "2          0  FEN 9: Zapowiedź walki Róża Gumienna vs Katarz...\n",
       "3          1  Aleksander Filipiak: Czuję się dobrze w nowym ...\n",
       "4          0  Victoria Carl i Aleksiej Czerwotkin mistrzami ...\n",
       "...      ...                                                ...\n",
       "98127      1  Kamil Syprzak zaczyna kolekcjonować trofea. FC...\n",
       "98128      1  Holandia: dwa gole Piotra Parzyszka Piotr Parz...\n",
       "98129      1  Sparingowo: Korona gorsza od Stali. Lettieri s...\n",
       "98130      1  Vive - Wisła. Ośmiu debiutantów w tegorocznej ...\n",
       "98131      1  WTA Miami: Timea Bacsinszky pokonana, Swietłan...\n",
       "\n",
       "[98132 rows x 2 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Loading data\n",
    "train_data = pd.read_csv('./train/train.tsv/train.tsv', sep='\\t', header=None, on_bad_lines='skip')\n",
    "\n",
    "# Removing unnecessary column\n",
    "train_data = train_data.drop(train_data.columns[2], axis=1)\n",
    "\n",
    "# Renaming columns\n",
    "train_data.columns = [\"label\", \"sentence\"]\n",
    "\n",
    "display(train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "93ca5e9a-56f7-493f-b088-81d272cfe4aa",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>label</th>\n",
       "      <th>sentence</th>\n",
       "      <th>sentence_split</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>Mindaugas Budzinauskas wierzy w odbudowę formy...</td>\n",
       "      <td>[mindaugas, budzinauskas, wierzy, w, odbudowę,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>Przyjmujący reprezentacji Polski wrócił do PGE...</td>\n",
       "      <td>[przyjmujący, reprezentacji, polski, wrócił, d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>FEN 9: Zapowiedź walki Róża Gumienna vs Katarz...</td>\n",
       "      <td>[fen, 9, zapowiedź, walki, róża, gumienna, vs,...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "      <td>Aleksander Filipiak: Czuję się dobrze w nowym ...</td>\n",
       "      <td>[aleksander, filipiak, czuję, się, dobrze, w, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>Victoria Carl i Aleksiej Czerwotkin mistrzami ...</td>\n",
       "      <td>[victoria, carl, i, aleksiej, czerwotkin, mist...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98127</th>\n",
       "      <td>1</td>\n",
       "      <td>Kamil Syprzak zaczyna kolekcjonować trofea. FC...</td>\n",
       "      <td>[kamil, syprzak, zaczyna, kolekcjonować, trofe...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98128</th>\n",
       "      <td>1</td>\n",
       "      <td>Holandia: dwa gole Piotra Parzyszka Piotr Parz...</td>\n",
       "      <td>[holandia, dwa, gole, piotra, parzyszka, piotr...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98129</th>\n",
       "      <td>1</td>\n",
       "      <td>Sparingowo: Korona gorsza od Stali. Lettieri s...</td>\n",
       "      <td>[sparingowo, korona, gorsza, od, stali, lettie...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98130</th>\n",
       "      <td>1</td>\n",
       "      <td>Vive - Wisła. Ośmiu debiutantów w tegorocznej ...</td>\n",
       "      <td>[vive, wisła, ośmiu, debiutantów, w, tegoroczn...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98131</th>\n",
       "      <td>1</td>\n",
       "      <td>WTA Miami: Timea Bacsinszky pokonana, Swietłan...</td>\n",
       "      <td>[wta, miami, timea, bacsinszky, pokonana, swie...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>98132 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       label                                           sentence  \\\n",
       "0          1  Mindaugas Budzinauskas wierzy w odbudowę formy...   \n",
       "1          1  Przyjmujący reprezentacji Polski wrócił do PGE...   \n",
       "2          0  FEN 9: Zapowiedź walki Róża Gumienna vs Katarz...   \n",
       "3          1  Aleksander Filipiak: Czuję się dobrze w nowym ...   \n",
       "4          0  Victoria Carl i Aleksiej Czerwotkin mistrzami ...   \n",
       "...      ...                                                ...   \n",
       "98127      1  Kamil Syprzak zaczyna kolekcjonować trofea. FC...   \n",
       "98128      1  Holandia: dwa gole Piotra Parzyszka Piotr Parz...   \n",
       "98129      1  Sparingowo: Korona gorsza od Stali. Lettieri s...   \n",
       "98130      1  Vive - Wisła. Ośmiu debiutantów w tegorocznej ...   \n",
       "98131      1  WTA Miami: Timea Bacsinszky pokonana, Swietłan...   \n",
       "\n",
       "                                          sentence_split  \n",
       "0      [mindaugas, budzinauskas, wierzy, w, odbudowę,...  \n",
       "1      [przyjmujący, reprezentacji, polski, wrócił, d...  \n",
       "2      [fen, 9, zapowiedź, walki, róża, gumienna, vs,...  \n",
       "3      [aleksander, filipiak, czuję, się, dobrze, w, ...  \n",
       "4      [victoria, carl, i, aleksiej, czerwotkin, mist...  \n",
       "...                                                  ...  \n",
       "98127  [kamil, syprzak, zaczyna, kolekcjonować, trofe...  \n",
       "98128  [holandia, dwa, gole, piotra, parzyszka, piotr...  \n",
       "98129  [sparingowo, korona, gorsza, od, stali, lettie...  \n",
       "98130  [vive, wisła, ośmiu, debiutantów, w, tegoroczn...  \n",
       "98131  [wta, miami, timea, bacsinszky, pokonana, swie...  \n",
       "\n",
       "[98132 rows x 3 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def preprocess(sentence):\n",
    "    sentence = sentence.lower()\n",
    "    sentence = re.sub(r'\\W', ' ', sentence)\n",
    "    tokens = word_tokenize(sentence)\n",
    "    return tokens\n",
    "\n",
    "train_data[\"sentence_split\"] = train_data[\"sentence\"].apply(preprocess)\n",
    "display(train_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e6611779-e621-47f7-a908-1d8123d4426b",
   "metadata": {},
   "outputs": [],
   "source": [
    "w2v = gensim.models.Word2Vec(train_data[\"sentence_split\"], vector_size=500, window=5, min_count=2, workers=4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "85ffca71-529f-463f-a7da-25aa0aa9f8a1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "65861\n"
     ]
    }
   ],
   "source": [
    "# number of words in w2v\n",
    "print(len(w2v.wv))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c5366e81-5883-4fb7-a721-dd53b5016369",
   "metadata": {},
   "outputs": [],
   "source": [
    "token = Tokenizer(len(w2v.wv))\n",
    "token.fit_on_texts(train_data[\"sentence_split\"])\n",
    "text = token.texts_to_sequences(train_data[\"sentence_split\"])\n",
    "text = pad_sequences(text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "68346de7-774f-4b50-8256-1203be8dbec0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train:\n",
      "\t[[    0     0     0 ...  1630   724 11557]\n",
      " [    0     0     0 ...     3   129   594]\n",
      " [    0     0     0 ...     4   781 28351]\n",
      " ...\n",
      " [    0     0     0 ...   390    35    55]\n",
      " [    0     0     0 ... 44454 12175   329]\n",
      " [    0     0     0 ...   159   455  1172]]\n",
      "y_train:\n",
      "\t[1 1 0 ... 1 1 1]\n",
      "Vocabulary size:\n",
      "\t104277\n"
     ]
    }
   ],
   "source": [
    "X_train = np.array(text)\n",
    "y_train = train_data[\"label\"].to_numpy()\n",
    "vocabulary_size = len(token.word_index)\n",
    "print(f\"X_train:\\n\\t{X_train}\\ny_train:\\n\\t{y_train}\\nVocabulary size:\\n\\t{vocabulary_size}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "1c76644e-91a2-4189-84ca-5e4c5ee57e4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "embedding_matrix = np.zeros((vocabulary_size, 500))\n",
    "for word, i in token.word_index.items():\n",
    "    if word in w2v.wv:\n",
    "        embedding_matrix[i] = w2v.wv[word]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a24fd19f-6aa3-4b93-bf73-8b7c939f08bf",
   "metadata": {},
   "source": [
    "## Test data preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "908ab909-c05e-473b-82cf-9f7e044eb300",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ATP Sztokholm: Juergen Zopp wykorzystał szansę...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Krowicki z reprezentacją kobiet aż do igrzysk ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Wielki powrót Łukasza Kubota Odradza się zawsz...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marcel Hirscher wygrał ostatni slalom gigant m...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Polki do Czarnogóry z pełnią zaangażowania. Sy...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5443</th>\n",
       "      <td>Biało-czerwona siła w Falun. Oni będą reprezen...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5444</th>\n",
       "      <td>Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5445</th>\n",
       "      <td>Oni zapisali się w annałach. Hubert Hurkacz 15...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5446</th>\n",
       "      <td>Poprawia się stan Nikiego Laudy. Austriak może...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5447</th>\n",
       "      <td>Liga Mistrzów. Zabójcza końcówka Interu Mediol...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5448 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                      0\n",
       "0     ATP Sztokholm: Juergen Zopp wykorzystał szansę...\n",
       "1     Krowicki z reprezentacją kobiet aż do igrzysk ...\n",
       "2     Wielki powrót Łukasza Kubota Odradza się zawsz...\n",
       "3     Marcel Hirscher wygrał ostatni slalom gigant m...\n",
       "4     Polki do Czarnogóry z pełnią zaangażowania. Sy...\n",
       "...                                                 ...\n",
       "5443  Biało-czerwona siła w Falun. Oni będą reprezen...\n",
       "5444  Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...\n",
       "5445  Oni zapisali się w annałach. Hubert Hurkacz 15...\n",
       "5446  Poprawia się stan Nikiego Laudy. Austriak może...\n",
       "5447  Liga Mistrzów. Zabójcza końcówka Interu Mediol...\n",
       "\n",
       "[5448 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>sentence</th>\n",
       "      <th>sentence_split</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>ATP Sztokholm: Juergen Zopp wykorzystał szansę...</td>\n",
       "      <td>[atp, sztokholm, juergen, zopp, wykorzystał, s...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Krowicki z reprezentacją kobiet aż do igrzysk ...</td>\n",
       "      <td>[krowicki, z, reprezentacją, kobiet, aż, do, i...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Wielki powrót Łukasza Kubota Odradza się zawsz...</td>\n",
       "      <td>[wielki, powrót, łukasza, kubota, odradza, się...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Marcel Hirscher wygrał ostatni slalom gigant m...</td>\n",
       "      <td>[marcel, hirscher, wygrał, ostatni, slalom, gi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Polki do Czarnogóry z pełnią zaangażowania. Sy...</td>\n",
       "      <td>[polki, do, czarnogóry, z, pełnią, zaangażowan...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5443</th>\n",
       "      <td>Biało-czerwona siła w Falun. Oni będą reprezen...</td>\n",
       "      <td>[biało, czerwona, siła, w, falun, oni, będą, r...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5444</th>\n",
       "      <td>Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...</td>\n",
       "      <td>[finał, wta, tokio, na, żywo, woźniacka, osaka...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5445</th>\n",
       "      <td>Oni zapisali się w annałach. Hubert Hurkacz 15...</td>\n",
       "      <td>[oni, zapisali, się, w, annałach, hubert, hurk...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5446</th>\n",
       "      <td>Poprawia się stan Nikiego Laudy. Austriak może...</td>\n",
       "      <td>[poprawia, się, stan, nikiego, laudy, austriak...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5447</th>\n",
       "      <td>Liga Mistrzów. Zabójcza końcówka Interu Mediol...</td>\n",
       "      <td>[liga, mistrzów, zabójcza, końcówka, interu, m...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5448 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                               sentence  \\\n",
       "0     ATP Sztokholm: Juergen Zopp wykorzystał szansę...   \n",
       "1     Krowicki z reprezentacją kobiet aż do igrzysk ...   \n",
       "2     Wielki powrót Łukasza Kubota Odradza się zawsz...   \n",
       "3     Marcel Hirscher wygrał ostatni slalom gigant m...   \n",
       "4     Polki do Czarnogóry z pełnią zaangażowania. Sy...   \n",
       "...                                                 ...   \n",
       "5443  Biało-czerwona siła w Falun. Oni będą reprezen...   \n",
       "5444  Finał WTA Tokio na żywo: Woźniacka - Osaka LIV...   \n",
       "5445  Oni zapisali się w annałach. Hubert Hurkacz 15...   \n",
       "5446  Poprawia się stan Nikiego Laudy. Austriak może...   \n",
       "5447  Liga Mistrzów. Zabójcza końcówka Interu Mediol...   \n",
       "\n",
       "                                         sentence_split  \n",
       "0     [atp, sztokholm, juergen, zopp, wykorzystał, s...  \n",
       "1     [krowicki, z, reprezentacją, kobiet, aż, do, i...  \n",
       "2     [wielki, powrót, łukasza, kubota, odradza, się...  \n",
       "3     [marcel, hirscher, wygrał, ostatni, slalom, gi...  \n",
       "4     [polki, do, czarnogóry, z, pełnią, zaangażowan...  \n",
       "...                                                 ...  \n",
       "5443  [biało, czerwona, siła, w, falun, oni, będą, r...  \n",
       "5444  [finał, wta, tokio, na, żywo, woźniacka, osaka...  \n",
       "5445  [oni, zapisali, się, w, annałach, hubert, hurk...  \n",
       "5446  [poprawia, się, stan, nikiego, laudy, austriak...  \n",
       "5447  [liga, mistrzów, zabójcza, końcówka, interu, m...  \n",
       "\n",
       "[5448 rows x 2 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "X_test_pd = pd.read_csv(\"test-A/in.tsv\", sep=\"\\t\", header=None)\n",
    "X_test_pd = X_test_pd.drop(X_test_pd.columns[1], axis=1)\n",
    "display(X_test_pd)\n",
    "X_test_pd.columns = [\"sentence\"]\n",
    "X_test_pd['sentence_split'] = X_test_pd['sentence'].apply(preprocess)\n",
    "X_test = token.texts_to_sequences(X_test_pd['sentence_split'])\n",
    "X_test = pad_sequences(X_test)\n",
    "display(X_test_pd)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "62b38223-cda6-443a-a05f-a1661233e94c",
   "metadata": {},
   "source": [
    "## Dev data preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "6a5fbb7d-2a8e-4633-8f4c-bec6acf624b2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Mundial 2018. Były reprezentant Anglii trenere...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Liga Mistrzyń: Podopieczne Kima Rasmussena bli...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Wyczerpujące treningi biegowe Justyny Kowalczy...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Mundial 2018. Zagraniczne media zareagowały na...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>BCL. Artur Gronek: Musimy grać twardziej. Pope...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5447</th>\n",
       "      <td>Michał Probierz szuka powodów do optymizmu. \"C...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5448</th>\n",
       "      <td>ME 2017 w siatkówce. Znakomita frekwencja. Kib...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5449</th>\n",
       "      <td>Zobacz oficjalny trailer KSW 42 (wideo) Organi...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5450</th>\n",
       "      <td>Rummenigge nie wyklucza, że ktoś odejdzie z Ba...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5451</th>\n",
       "      <td>Sympatyczny gest argentyńskich tenisistów. Obd...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5452 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                      0\n",
       "0     Mundial 2018. Były reprezentant Anglii trenere...\n",
       "1     Liga Mistrzyń: Podopieczne Kima Rasmussena bli...\n",
       "2     Wyczerpujące treningi biegowe Justyny Kowalczy...\n",
       "3     Mundial 2018. Zagraniczne media zareagowały na...\n",
       "4     BCL. Artur Gronek: Musimy grać twardziej. Pope...\n",
       "...                                                 ...\n",
       "5447  Michał Probierz szuka powodów do optymizmu. \"C...\n",
       "5448  ME 2017 w siatkówce. Znakomita frekwencja. Kib...\n",
       "5449  Zobacz oficjalny trailer KSW 42 (wideo) Organi...\n",
       "5450  Rummenigge nie wyklucza, że ktoś odejdzie z Ba...\n",
       "5451  Sympatyczny gest argentyńskich tenisistów. Obd...\n",
       "\n",
       "[5452 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "array([[    0,     0,     0, ...,   149,  3657, 28408],\n",
       "       [    0,     0,     0, ...,  2378, 59831, 31454],\n",
       "       [    0,     0,     0, ...,   311,   991, 15435],\n",
       "       ...,\n",
       "       [    0,     0,     0, ...,     2,  2999, 11543],\n",
       "       [    0,     0,     0, ...,     4,  1077, 38402],\n",
       "       [    0,     0,     0, ...,  1001,    39, 18089]])"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "array([[1],\n",
       "       [1],\n",
       "       [0],\n",
       "       ...,\n",
       "       [0],\n",
       "       [1],\n",
       "       [1]], dtype=int64)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dev_in = pd.read_csv(\"dev-0/in.tsv\", sep=\"\\t\", header=None, on_bad_lines='skip')\n",
    "display(dev_in)\n",
    "dev_in.columns = [\"sentence\"]\n",
    "dev_in['sentence_split'] = dev_in['sentence'].apply(preprocess)\n",
    "dev_text = token.texts_to_sequences(dev_in['sentence_split'])\n",
    "dev_text = pad_sequences(dev_text)\n",
    "\n",
    "dev_expected = pd.read_csv(\"dev-0/expected.tsv\", sep=\"\\t\", header=None, on_bad_lines='skip').to_numpy()\n",
    "display(dev_text)\n",
    "display(dev_expected)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d6dac3f7-d148-4629-bece-27d91fb7169b",
   "metadata": {},
   "source": [
    "# Training the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "11c1dc1d-18af-44e8-b026-7d5f637a2081",
   "metadata": {},
   "outputs": [],
   "source": [
    "opt = Adam(learning_rate=0.0001)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9bb42d4d-c33f-4f74-b111-c4366c3026d4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m31s\u001b[0m 18ms/step - acc: 0.8497 - loss: 0.2841\n",
      "Epoch 2/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 18ms/step - acc: 0.9729 - loss: 0.0774\n",
      "Epoch 3/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 18ms/step - acc: 0.9763 - loss: 0.0695\n",
      "Epoch 4/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 18ms/step - acc: 0.9790 - loss: 0.0608\n",
      "Epoch 5/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 20ms/step - acc: 0.9796 - loss: 0.0586\n",
      "Epoch 6/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9823 - loss: 0.0494\n",
      "Epoch 7/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9831 - loss: 0.0490\n",
      "Epoch 8/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9832 - loss: 0.0477\n",
      "Epoch 9/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9842 - loss: 0.0437\n",
      "Epoch 10/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9848 - loss: 0.0444\n",
      "Epoch 11/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9855 - loss: 0.0418\n",
      "Epoch 12/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 21ms/step - acc: 0.9862 - loss: 0.0420\n",
      "Epoch 13/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m36s\u001b[0m 24ms/step - acc: 0.9860 - loss: 0.0400\n",
      "Epoch 14/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m32s\u001b[0m 21ms/step - acc: 0.9864 - loss: 0.0392\n",
      "Epoch 15/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9865 - loss: 0.0387\n",
      "Epoch 16/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9871 - loss: 0.0369\n",
      "Epoch 17/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9875 - loss: 0.0349\n",
      "Epoch 18/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9877 - loss: 0.0357\n",
      "Epoch 19/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9888 - loss: 0.0312\n",
      "Epoch 20/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 19ms/step - acc: 0.9879 - loss: 0.0347\n",
      "Epoch 21/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 20ms/step - acc: 0.9879 - loss: 0.0326\n",
      "Epoch 22/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 20ms/step - acc: 0.9881 - loss: 0.0329\n",
      "Epoch 23/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 19ms/step - acc: 0.9874 - loss: 0.0337\n",
      "Epoch 24/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m29s\u001b[0m 19ms/step - acc: 0.9889 - loss: 0.0307\n",
      "Epoch 25/25\n",
      "\u001b[1m1534/1534\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m37s\u001b[0m 24ms/step - acc: 0.9893 - loss: 0.0290\n"
     ]
    }
   ],
   "source": [
    "keras_model = Sequential()\n",
    "keras_model.add(Embedding(vocabulary_size, 500, weights=[embedding_matrix], trainable=False))\n",
    "keras_model.add(Dropout(0.4))\n",
    "keras_model.add(Conv1D(50, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(Conv1D(50, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(MaxPooling1D())\n",
    "keras_model.add(Dropout(0.4))\n",
    "keras_model.add(Conv1D(100, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(Conv1D(100, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(MaxPooling1D())\n",
    "keras_model.add(Dropout(0.2))\n",
    "keras_model.add(Conv1D(200, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(Conv1D(200, 3, activation='relu', padding='same', strides=1))\n",
    "keras_model.add(GlobalMaxPooling1D())\n",
    "keras_model.add(Dropout(0.4))\n",
    "keras_model.add(Dense(200))\n",
    "keras_model.add(Activation('relu'))\n",
    "keras_model.add(Dropout(0.4))\n",
    "keras_model.add(Dense(1))\n",
    "keras_model.add(Activation('sigmoid'))\n",
    "keras_model.compile(loss='binary_crossentropy', metrics=['acc'], optimizer=opt)\n",
    "keras_model.fit(X_train, y_train, batch_size=64, epochs=25)\n",
    "\n",
    "model = keras_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "586e83f2-ff5a-498d-a06a-42476df2d972",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m171/171\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step\n"
     ]
    }
   ],
   "source": [
    "test_result = model.predict(X_test)\n",
    "test_predictions = np.where(test_result>=0.50, 1, 0)\n",
    "pd.DataFrame(test_predictions).to_csv('test-A/out.tsv', sep=\"\\t\", index=False, encoding='utf-8') "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f4727d5e-e15d-425d-abd3-7f01427e8385",
   "metadata": {},
   "source": [
    "# Evaluation\n",
    "I had problems installing GEval on Windows so I did the evaluation the old fashioned way "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "6c646808-088d-41f0-8f9c-1d143aec769f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m171/171\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 4ms/step\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5447</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5448</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5449</th>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5450</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5451</th>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5452 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      0\n",
       "0     1\n",
       "1     1\n",
       "2     0\n",
       "3     1\n",
       "4     1\n",
       "...  ..\n",
       "5447  1\n",
       "5448  1\n",
       "5449  0\n",
       "5450  1\n",
       "5451  1\n",
       "\n",
       "[5452 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dev_result = model.predict(dev_text)\n",
    "dev_predictions = np.where(dev_result>=0.50, 1, 0)\n",
    "predictions_df = pd.DataFrame(dev_predictions)\n",
    "display(predictions_df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "b5c1c0a1-8dae-4f6d-a0a6-badee37d32a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "dev_data = pd.read_csv(\"dev-0/in.tsv\", sep=\"\\t\", header=None, on_bad_lines='skip')\n",
    "predictions_df.to_csv('dev-0/out.tsv', sep=\"\\t\", index=False, header=None)\n",
    "dev_data.to_csv('in.tsv', sep=\"\\t\", index=False, header=None, encoding='utf-8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "ed802c5c-f63f-4618-b30d-5d8c0fe5e16d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.9888114453411592\n"
     ]
    }
   ],
   "source": [
    "score = accuracy_score(y_true=dev_expected, y_pred=dev_predictions)\n",
    "print(score)"
   ]
  }
 ],
 "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}