{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "text         1278\n",
      "n_tokens     1278\n",
      "embedding    1278\n",
      "dtype: int64\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df1=pd.read_csv('processed/embeddings-1.csv')\n",
    "df2=pd.read_csv('processed/embeddings-2.csv')\n",
    "df3=pd.read_csv('processed/embeddings-3.csv')\n",
    "df4=pd.read_csv('processed/embeddings-4.csv')\n",
    "df5=pd.read_csv('processed/embeddings-5.csv')\n",
    "df6=pd.read_csv('processed/embeddings-6.csv')\n",
    "df7=pd.read_csv('processed/embeddings-7.csv')\n",
    "\n",
    "df = pd.concat([df1, df2, df3, df4, df5, df6, df7], axis=0, ignore_index=True)\n",
    "df.columns = ['text', 'n_tokens', 'embedding']\n",
    "# df['embedding'] = df['embedding'].apply(literal_eval).apply(np.array)\n",
    "df.head()\n",
    "print(df.count())\n",
    "    "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "sample-projects",
   "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}