diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..fed376b
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+train/train.tsv
+.ipynb_checkpoints*
+word2vec.model
diff --git a/.ipynb_checkpoints/sport text classification-checkpoint.ipynb b/.ipynb_checkpoints/sport text classification-checkpoint.ipynb
new file mode 100644
index 0000000..ba71208
--- /dev/null
+++ b/.ipynb_checkpoints/sport text classification-checkpoint.ipynb
@@ -0,0 +1,204 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 19,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Requirement already satisfied: gensim in c:\\users\\annad\\anaconda3\\lib\\site-packages (3.8.3)\n",
+ "Requirement already satisfied: smart-open>=1.8.1 in c:\\users\\annad\\anaconda3\\lib\\site-packages (from gensim) (5.0.0)\n",
+ "Requirement already satisfied: six>=1.5.0 in c:\\users\\annad\\anaconda3\\lib\\site-packages (from gensim) (1.15.0)\n",
+ "Requirement already satisfied: numpy>=1.11.3 in c:\\users\\annad\\anaconda3\\lib\\site-packages (from gensim) (1.19.2)\n",
+ "Requirement already satisfied: scipy>=0.18.1 in c:\\users\\annad\\anaconda3\\lib\\site-packages (from gensim) (1.5.2)\n",
+ "Requirement already satisfied: Cython==0.29.14 in c:\\users\\annad\\anaconda3\\lib\\site-packages (from gensim) (0.29.14)\n"
+ ]
+ }
+ ],
+ "source": [
+ "!pip install gensim"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from gensim.test.utils import common_texts\n",
+ "from gensim.models import Word2Vec\n",
+ "import os.path"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import gzip\n",
+ "import shutil\n",
+ "with gzip.open('train/train.tsv.gz', 'rb') as f_in:\n",
+ " with open('train/train.tsv', 'wb') as f_out:\n",
+ " shutil.copyfileobj(f_in, f_out)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "
\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Ball | \n",
+ " Text | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Mindaugas Budzinauskas wierzy w odbudowę formy... | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 1 | \n",
+ " Przyjmujący reprezentacji Polski wrócił do PGE... | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 0 | \n",
+ " FEN 9: Zapowiedź walki Róża Gumienna vs Katarz... | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 1 | \n",
+ " Aleksander Filipiak: Czuję się dobrze w nowym ... | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 0 | \n",
+ " Victoria Carl i Aleksiej Czerwotkin mistrzami ... | \n",
+ "
\n",
+ " \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " 98127 | \n",
+ " 1 | \n",
+ " Kamil Syprzak zaczyna kolekcjonować trofea. FC... | \n",
+ "
\n",
+ " \n",
+ " 98128 | \n",
+ " 1 | \n",
+ " Holandia: dwa gole Piotra Parzyszka Piotr Parz... | \n",
+ "
\n",
+ " \n",
+ " 98129 | \n",
+ " 1 | \n",
+ " Sparingowo: Korona gorsza od Stali. Lettieri s... | \n",
+ "
\n",
+ " \n",
+ " 98130 | \n",
+ " 1 | \n",
+ " Vive - Wisła. Ośmiu debiutantów w tegorocznej ... | \n",
+ "
\n",
+ " \n",
+ " 98131 | \n",
+ " 1 | \n",
+ " WTA Miami: Timea Bacsinszky pokonana, Swietłan... | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
98132 rows × 2 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Ball Text\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]"
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = pd.read_csv('train/train.tsv', sep='\\t', names=[\"Ball\",\"Text\"])\n",
+ "data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = None\n",
+ "if not os.path.isfile('word2vec.model'): \n",
+ " model = Word2Vec(sentences=data[\"Text\"], window=5, min_count=1, workers=5)\n",
+ " model.save(\"word2vec.model\")\n",
+ "else:"
+ ]
+ }
+ ],
+ "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": "3.8.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/sport text classification.ipynb b/sport text classification.ipynb
new file mode 100644
index 0000000..618c670
--- /dev/null
+++ b/sport text classification.ipynb
@@ -0,0 +1,213 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from gensim.test.utils import common_texts\n",
+ "from gensim.models import Word2Vec\n",
+ "import os.path"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import gzip\n",
+ "import shutil\n",
+ "with gzip.open('train/train.tsv.gz', 'rb') as f_in:\n",
+ " with open('train/train.tsv', 'wb') as f_out:\n",
+ " shutil.copyfileobj(f_in, f_out)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "
\n",
+ " \n",
+ " \n",
+ " | \n",
+ " Ball | \n",
+ " Text | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " 0 | \n",
+ " 1 | \n",
+ " Mindaugas Budzinauskas wierzy w odbudowę formy... | \n",
+ "
\n",
+ " \n",
+ " 1 | \n",
+ " 1 | \n",
+ " Przyjmujący reprezentacji Polski wrócił do PGE... | \n",
+ "
\n",
+ " \n",
+ " 2 | \n",
+ " 0 | \n",
+ " FEN 9: Zapowiedź walki Róża Gumienna vs Katarz... | \n",
+ "
\n",
+ " \n",
+ " 3 | \n",
+ " 1 | \n",
+ " Aleksander Filipiak: Czuję się dobrze w nowym ... | \n",
+ "
\n",
+ " \n",
+ " 4 | \n",
+ " 0 | \n",
+ " Victoria Carl i Aleksiej Czerwotkin mistrzami ... | \n",
+ "
\n",
+ " \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " 98127 | \n",
+ " 1 | \n",
+ " Kamil Syprzak zaczyna kolekcjonować trofea. FC... | \n",
+ "
\n",
+ " \n",
+ " 98128 | \n",
+ " 1 | \n",
+ " Holandia: dwa gole Piotra Parzyszka Piotr Parz... | \n",
+ "
\n",
+ " \n",
+ " 98129 | \n",
+ " 1 | \n",
+ " Sparingowo: Korona gorsza od Stali. Lettieri s... | \n",
+ "
\n",
+ " \n",
+ " 98130 | \n",
+ " 1 | \n",
+ " Vive - Wisła. Ośmiu debiutantów w tegorocznej ... | \n",
+ "
\n",
+ " \n",
+ " 98131 | \n",
+ " 1 | \n",
+ " WTA Miami: Timea Bacsinszky pokonana, Swietłan... | \n",
+ "
\n",
+ " \n",
+ "
\n",
+ "
98132 rows × 2 columns
\n",
+ "
"
+ ],
+ "text/plain": [
+ " Ball Text\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]"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data = pd.read_csv('train/train.tsv', sep='\\t', names=[\"Ball\",\"Text\"])\n",
+ "data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model = None\n",
+ "sentences = [x.split() for x in data[\"Text\"]]\n",
+ "if not os.path.isfile('word2vec.model'):\n",
+ " model = Word2Vec(sentences=data[\"Text\"])\n",
+ " model.save(\"word2vec.model\")\n",
+ " model.train(sentences, total_examples=len(sentences), epochs=10)\n",
+ "else:\n",
+ " model = Word2Vec.load(\"word2vec.model\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "KeyError",
+ "evalue": "\"word 'Mindaugas' not in vocabulary\"",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mprepared_training_data\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Text'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mprepared_training_data\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Text'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwv\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\pandas\\core\\series.py\u001b[0m in \u001b[0;36mapply\u001b[1;34m(self, func, convert_dtype, args, **kwds)\u001b[0m\n\u001b[0;32m 4198\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4199\u001b[0m \u001b[0mvalues\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobject\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4200\u001b[1;33m \u001b[0mmapped\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmap_infer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconvert\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mconvert_dtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4201\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4202\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmapped\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmapped\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mSeries\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mpandas\\_libs\\lib.pyx\u001b[0m in \u001b[0;36mpandas._libs.lib.map_infer\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m(x)\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mprepared_training_data\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Text'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mprepared_training_data\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'Text'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mlambda\u001b[0m \u001b[0mx\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mwv\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\gensim\\models\\keyedvectors.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, entities)\u001b[0m\n\u001b[0;32m 353\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentities\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 354\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 355\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mvstack\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentity\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mentity\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mentities\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 356\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 357\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__contains__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mentity\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\gensim\\models\\keyedvectors.py\u001b[0m in \u001b[0;36m\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 353\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentities\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 354\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 355\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mvstack\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mentity\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mentity\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mentities\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 356\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 357\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m__contains__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mentity\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\gensim\\models\\keyedvectors.py\u001b[0m in \u001b[0;36mget_vector\u001b[1;34m(self, word)\u001b[0m\n\u001b[0;32m 469\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 470\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mword\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 471\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mword_vec\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mword\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 472\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 473\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mwords_closer_than\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mw1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mw2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32m~\\anaconda3\\lib\\site-packages\\gensim\\models\\keyedvectors.py\u001b[0m in \u001b[0;36mword_vec\u001b[1;34m(self, word, use_norm)\u001b[0m\n\u001b[0;32m 466\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 467\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 468\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"word '%s' not in vocabulary\"\u001b[0m \u001b[1;33m%\u001b[0m \u001b[0mword\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 469\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 470\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mget_vector\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mword\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mKeyError\u001b[0m: \"word 'Mindaugas' not in vocabulary\""
+ ]
+ }
+ ],
+ "source": [
+ "prepared_training_data['Text'] = prepared_training_data['Text'].apply(lambda x: model.wv[x.split()])"
+ ]
+ }
+ ],
+ "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": "3.8.5"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}