{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "a1e51cab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ea3ea81741954384b0b6ee0e2d5f8b43",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "README.md:   0%|          | 0.00/670 [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "16a23106959d4f4b870ac50ada254f73",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "data/train-00000-of-00004.parquet:   0%|          | 0.00/503M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a264fbf783704be8a18f62e7c352b1e7",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "data/train-00001-of-00004.parquet:   0%|          | 0.00/503M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ecdb1976f88f44c3aa5aef51508643e1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "data/train-00002-of-00004.parquet:   0%|          | 0.00/477M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "451d70b2799b4312b66d3d5a9d993726",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "data/train-00003-of-00004.parquet:   0%|          | 0.00/497M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "d93865e127a14f4a9179f3b86caa0cfe",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Generating train split:   0%|          | 0/1200 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "# Login using e.g. `huggingface-cli login` to access this dataset\n",
    "ds = load_dataset(\"weathon/nag_dataset\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ab34f490",
   "metadata": {},
   "outputs": [],
   "source": [
    "base = [{\n",
    "        \"prompt\": \"A cat with weird colors is sitting on the table, looking at the TV. The whole image has clashing colors.\",\n",
    "        \"missing_element\": \"nature colors\"\n",
    "    },]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "74c7ee35",
   "metadata": {},
   "outputs": [],
   "source": [
    "for sample in ds[\"train\"]:\n",
    "    prompt = sample[\"prompt\"]\n",
    "    missing_element = sample[\"negative_prompt\"]\n",
    "    base.append({\n",
    "        \"prompt\": prompt,\n",
    "        \"missing_element\": missing_element\n",
    "    })"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "c1aec56c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "with open(\"anti_aesthetics.json\", \"w\") as f:\n",
    "    json.dump(base, f, indent=4)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "neg",
   "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": "3.10.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}