Spaces:
Sleeping
Sleeping
File size: 1,481 Bytes
6183ded |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
{
"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
}
|