{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8159f2eb-88ce-4c45-b1ae-584ce3a1976f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "179a6741-6649-4bea-be83-7fc9fd6c13c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "filename = \"gpt2_gene_multiv1_ft_en.jsonl\"\n",
    "data_list = []\n",
    "for line in open(filename):\n",
    "    data = json.loads(line)\n",
    "    data_list.append(data)\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "c8cc78e9-fbdf-4c95-847f-44ea953a38ec",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "en: 0.899\n",
      "fr: 0.8245\n",
      "de: 0.79\n",
      "zh: 0.7395\n",
      "dna_sim_pair_simple_150bp: 0.955\n",
      "dna_sim_pair_150bp: 0.86975\n",
      "dna_sim_pair_50bp: 0.8185\n",
      "protein_sim_pair_150bp: 0.9738888888888889\n",
      "protein_sim_pair_450bp: 0.975\n",
      "dna_protein_pair: 0.5575\n",
      "dna_protein_pair_100: 0.5725\n",
      "dna_protein_pair_full: 0.7324999999999999\n",
      "dna_protein_pair_rand: 0.6\n",
      "dna_protein_pair_rand_100: 0.60375\n",
      "dna_protein_pair_rand_full: 0.61125\n"
     ]
    }
   ],
   "source": [
    "# 假设您的数据存储在一个名为data_list的列表中\n",
    "# 初始化一个字典来保存每个键的最大accuracy值\n",
    "max_accuracies = {}\n",
    "\n",
    "dna_protein_pair_full_list = []\n",
    "\n",
    "\n",
    "# 遍历列表中的每个字典\n",
    "for data in data_list:\n",
    "    for key, metrics in data.items():\n",
    "        if key not in ['seed']:  # 忽略非目标键，例如'seed'\n",
    "            if isinstance(metrics, dict) and 'accuracy' in metrics:\n",
    "                accuracy = metrics['accuracy']\n",
    "                if accuracy<0.5:\n",
    "                    accuracy = 1-accuracy\n",
    "\n",
    "                if key==\"dna_protein_pair_full\":\n",
    "                    dna_protein_pair_full_list.append(accuracy)\n",
    "                    \n",
    "                if key not in max_accuracies or accuracy > max_accuracies[key]:\n",
    "                    max_accuracies[key] = accuracy\n",
    "\n",
    "# 打印每个键的最大accuracy值\n",
    "for key, max_accuracy in max_accuracies.items():\n",
    "    print(f\"{key}: {max_accuracy}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0d2f40f8-a817-4b6b-ae17-310478f6f8d8",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0.505,\n",
       " 0.4975,\n",
       " 0.575,\n",
       " 0.5025,\n",
       " 0.45,\n",
       " 0.4775,\n",
       " 0.515,\n",
       " 0.505,\n",
       " 0.475,\n",
       " 0.515,\n",
       " 0.5675,\n",
       " 0.4275,\n",
       " 0.4875,\n",
       " 0.5125,\n",
       " 0.505,\n",
       " 0.5025,\n",
       " 0.53,\n",
       " 0.5425,\n",
       " 0.51,\n",
       " 0.49,\n",
       " 0.3925,\n",
       " 0.4825,\n",
       " 0.5425,\n",
       " 0.385,\n",
       " 0.36,\n",
       " 0.5125,\n",
       " 0.535,\n",
       " 0.4825,\n",
       " 0.5025,\n",
       " 0.485,\n",
       " 0.5125,\n",
       " 0.3325,\n",
       " 0.6225,\n",
       " 0.4975,\n",
       " 0.5375,\n",
       " 0.4975,\n",
       " 0.5325,\n",
       " 0.2925,\n",
       " 0.4825,\n",
       " 0.4875,\n",
       " 0.4975,\n",
       " 0.53,\n",
       " 0.285,\n",
       " 0.4625,\n",
       " 0.4275,\n",
       " 0.48,\n",
       " 0.4225,\n",
       " 0.55,\n",
       " 0.385,\n",
       " 0.5175,\n",
       " 0.53,\n",
       " 0.4375,\n",
       " 0.495,\n",
       " 0.485,\n",
       " 0.3425,\n",
       " 0.4875,\n",
       " 0.5575,\n",
       " 0.4825,\n",
       " 0.2675,\n",
       " 0.4975,\n",
       " 0.5375,\n",
       " 0.5375,\n",
       " 0.475,\n",
       " 0.3525,\n",
       " 0.485,\n",
       " 0.34,\n",
       " 0.4625,\n",
       " 0.5,\n",
       " 0.505,\n",
       " 0.5075,\n",
       " 0.515,\n",
       " 0.4925,\n",
       " 0.445,\n",
       " 0.3675,\n",
       " 0.5125,\n",
       " 0.495,\n",
       " 0.4175,\n",
       " 0.4725,\n",
       " 0.5025,\n",
       " 0.4875,\n",
       " 0.53,\n",
       " 0.5425,\n",
       " 0.4175,\n",
       " 0.34,\n",
       " 0.5225,\n",
       " 0.49,\n",
       " 0.4125,\n",
       " 0.3575,\n",
       " 0.4925,\n",
       " 0.535,\n",
       " 0.51,\n",
       " 0.49,\n",
       " 0.535,\n",
       " 0.4975,\n",
       " 0.3825,\n",
       " 0.48,\n",
       " 0.485,\n",
       " 0.5]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dna_protein_pair_full_list"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "110b1efd-1ccb-43d1-9033-53cbf92146e2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}