example_generation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from guacamol_baselines.smiles_lstm_hc.goal_directed_generation import  goal_directed_generation\n",
    "from pymongo import MongoClient\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import os\n",
    "\n",
    "db_storage = \"paperGenerationSynth\"\n",
    "os.environ[\"DB_STORAGE\"]= db_storage\n",
    "mongo_url = os.getenv(\"MONGO_URL\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "version name :  pi3kmtor\n",
      "selecting initial population...\n",
      "smiles loaded ... ,len. ? 463\n",
      "top k calculated\n",
      "database :  pi3kmtorRSPred_10\n",
      "going to score payload  177\n",
      "going to score payload  149\n",
      "going to score payload  127\n",
      "going to score payload  115\n",
      "going to score payload  92\n",
      "going to score payload  88\n",
      "going to score payload  87\n",
      "going to score payload  73\n",
      "going to score payload  49\n",
      "going to score payload  50\n",
      "going to score payload  59\n",
      "going to score payload  53\n",
      "going to score payload  62\n",
      "going to score payload  49\n"
     ]
    }
   ],
   "source": [
    "goal_directed_generation(\n",
    "        suite=\"pi3kmtor\",\n",
    "        synth_score=\"RSPred\",\n",
    "        n_epochs = 15,\n",
    "        mols_to_sample = 256,\n",
    "        keep_top = 64\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "name_database = \"pi3kmtorRSPred_10\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "db = MongoClient(mongo_url)[db_storage]\n",
    "results = pd.DataFrame(list(db[name_database].find({})))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7ff6805fbc10>]"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAD8CAYAAAB5Pm/hAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAplklEQVR4nO3deXyU5bn/8c9FQhK2ECBhT1gTEAWCRlzQilaUU1vpooDtaWsXPbbH83M/1bantfZ0c9eW0xZb7XY8gFptalWgiqK4ESRswUAISxKRsCTsS5br98eMOEYwg0x4Zibf9+uVl5nnuSe5bge+3HPP89y3uTsiIpK8OgRdgIiItC0FvYhIklPQi4gkOQW9iEiSU9CLiCQ5Bb2ISJKLKujNbLKZlZtZhZndepQ2U82szMxWmdmjEcd/YWYrw1/TYlW4iIhEJ7W1BmaWAswAJgHVwGIzK3b3sog2+cBtwAR3rzOz3uHjlwCnAoVAOvCimT3r7rti3hMRETmiaEb044EKd69090PALGBKizZXATPcvQ7A3WvDx0cBC9290d33AsuBybEpXUREotHqiB4YAFRFPK4GzmjRpgDAzBYBKcDt7v4csAz4oZndA3QGzgfK+AjZ2dk+ePDgqIoXEZGQJUuWbHP3nCOdiyboo5EK5AMTgYHAQjMb7e7zzOx04FVgK/Aa0NTyyWZ2NXA1QF5eHiUlJTEqS0SkfTCzjUc7F83UTQ2QG/F4YPhYpGqg2N0b3H09sIZQ8OPuP3H3QnefBFj43Ae4+0x3L3L3opycI/6DJCIiH1M0Qb8YyDezIWaWBkwHilu0eYrQaB4zyyY0lVNpZilm1it8fAwwBpgXm9JFRCQarU7duHujmV0LzCU0//6wu68yszuAEncvDp+7yMzKCE3N3OLu280sA3jZzAB2Af/q7o1t1RkREfkwi7dliouKilxz9CIix8bMlrh70ZHO6c5YEZEkp6AXEUlyCnoRkSSnoBcRCZi788yKzcx6c1Ob/PxY3TAlIiLHyN15ee027ppbzoqanYzLy2La6bmEr1SMGQW9iEgAlm6q487nynmtcjsDsjpx9+Vj+dy4ATEPeVDQi4icUGu27ObuueXMK9tCry5p3P6ZUVxxRh7pqSlt9jsV9CIiJ0DVjn3c9881PLm0hq5pqdw0qYCvnzOELultH8MKehGRNrR190FmLKjgf9/YSAczrjp3KN86bxg9uqSdsBoU9CIibWDXgQYeWljJ719Zz8HGZqYW5XLdJ/Pp2z3jhNeioBcRiaEDDU388dUN/PqlddTva+DTY/px46QChuZ0DawmBb2ISAw0NDXzWEk1Dzy/hi27DnJeQQ63XDyCUwZ0D7o0Bb2IyPFobnaeXrGZe+eVs2H7Pk4b1IMHp4/jjKG9gi7tMAW9iMjH4O68uGYrdz1XTtnmXYzs243ff7WIC0b2bpNr4Y+Hgl5E5BiVbNjBnc+V8+aGHeT17Mz90wr5zNj+pHSIr4B/j4JeRCRKqzfv4u655Tz/di053dL58ZSTmXZ6Hmmp8b1smIJeRKQVG7fv5d75ayhe9g7d0lP5z8kjuPLswXROS4wITYwqRUQCULvrAA++sJZZb1aRmmJcc94wrvnEMLp37hh0acckqqA3s8nAA4T2jP2du//8CG2mArcDDixz9y+Gj98JXEJoSeT5wHUeb/sXiohE2LmvgV+/tI4/vLqexibnivF5/McFw+mdeeJvdoqFVoPezFKAGcAkoBpYbGbF7l4W0SYfuA2Y4O51ZtY7fPxsYAIwJtz0FeA84MVYdkJEJBb2HWrkkUUb+O1L69h9sJEpY/tzw6QCBvXqEnRpxyWaEf14oMLdKwHMbBYwBSiLaHMVMMPd6wDcvTZ83IEMIA0woCOwJTali4jExqHGZmYv3sSDL1SwdfdBPjmyNzdfPIKT+mUGXVpMRBP0A4CqiMfVwBkt2hQAmNkiQtM7t7v7c+7+mpktADYTCvpfufvq4y9bROT4NTU7xctquG/+Wjbt2Mf4wT359ZdOpWhwz6BLi6lYfRibCuQDE4GBwEIzGw1kAyeFjwHMN7Nz3f3lyCeb2dXA1QB5eXkxKklE5MjcnedX13L3vHLefnc3o/pl8sjXTmdiQU7c3ewUC9EEfQ2QG/F4YPhYpGrgDXdvANab2RreD/7X3X0PgJk9C5wFfCDo3X0mMBOgqKhIH9SKSJt5o3I7d84tZ8nGOoZkd+GXV4zjktH96BCnNzvFQjRBvxjIN7MhhAJ+OvDFFm2eAq4AHjGzbEJTOZXAUOAqM/sZoamb84D7Y1K5iMgxWFmzk7vmlvPSmq30yUznp58bzeVFA+mYEt83O8VCq0Hv7o1mdi0wl9D8+8PuvsrM7gBK3L04fO4iMysDmoBb3H27mT0OXACsIPTB7HPu/ve26oyISEvrt+3lnnnlPL18M1mdO3Lbv4zkq2cPJqNj223dF28s3i5pLyoq8pKSkqDLEJEEt3nnfh58fi1zSqpJT+3AN84ZwlWfGEpmRmLd7BQtM1vi7kVHOqc7Y0UkqdTtPcSvX1rHH1/dQLM7Xz5zEP9+/nByuqUHXVpgFPQikhT2Hmzk96+s56GFlew51Mjnxw3k+gvzye3ZOejSAqegF5GEdrCxiUff2MSMBRVs23OIi0b14eaLR1DQp1vQpcUNBb2IJKSmZufJpTXcN38NNfX7OWtoL2Z+ZQSn5vUIurS4o6AXkYTi7sxdtYV75pWztnYPowd05+dfGM05w7OT8manWFDQi0jCeLViG7+YW86yqnqG5nTh1186lcmn9FXAt0JBLyJxb1lVPXfNLeeVim30657BnV8Yw+dPHUBqO7jZKRYU9CIStypq93DPvHKeXfkuPbuk8f1LTuJfzxzUrm52igUFvYjEnZr6/dw/fw1PvFVNp44pXH9hPt84ZwjdkvRmp7amoBeRuLF9z0FmLFjHX17fCMDXJgzh2xOH0atr+73ZKRYU9CISuN0HGvjdy+v53cuV7G9o4rLTBnLdhQUMyOoUdGlJQUEvIoE50NDEX17fyIwFFdTta+BTo/ty46QRDO/dNejSkoqCXkROuMamZp54q5r7/7mWzTsPcG5+NrdcPIIxA7OCLi0pKehF5IRxd55d+S53zyuncutexuZmcc/lYzl7eHbQpSU1Bb2ItDl35+W127hrbjkranaS37srv/3yaVw0qo9udjoBFPQi0qbe2lTHnc+9zeuVOxiQ1Yl7Lh/LZ8cNICWJt+6LNwp6EWkTa7bs5q655cwv20J21zRu/8worjgjj/RU3ex0oinoRSSmqnbs475/ruHJpTV0TUvlpkkFfP2cIXRJV9wEJar/82Y2GXiA0J6xv3P3nx+hzVTgdkJ7wy5z9y+a2fnAfRHNRgLT3f2p46xbROLM1t0H+dULa3n0zU10MOPqc4dyzXnD6NElLejS2r1Wg97MUoAZwCSgGlhsZsXuXhbRJh+4DZjg7nVm1hvA3RcAheE2PYEKYF6sOyEiwdm5v4GHFlby8KL1HGxsZmpRLtd9Mp++3TOCLk3CohnRjwcq3L0SwMxmAVOAsog2VwEz3L0OwN1rj/BzLgOedfd9x1eyiMSD/Yea+ONrG/j1i+vYub+Bz4ztz42TChiS3SXo0qSFaIJ+AFAV8bgaOKNFmwIAM1tEaHrndnd/rkWb6cC9R/oFZnY1cDVAXl5eFCWJSFAampqZU1LFg8+vZcuug0wckcPNF43glAHdgy5NjiJWn46kAvnARGAgsNDMRrt7PYCZ9QNGA3OP9GR3nwnMBCgqKvIY1SQiMdTc7Px9+TvcN38NG7bv47RBPXhw+jjOGNor6NKkFdEEfQ2QG/F4YPhYpGrgDXdvANab2RpCwb84fH4q8GT4vIgkEHfnxfKt3Dm3nNWbdzGybzd+/9UiLhjZWzc7JYhogn4xkG9mQwgF/HTgiy3aPAVcATxiZtmEpnIqI85fQejDWhFJICUbdnDnc+W8uWEHeT07c/+0Qi4d258OutkpobQa9O7eaGbXEpp2SQEedvdVZnYHUOLuxeFzF5lZGdAE3OLu2wHMbDChdwQvtVEfRCTGyt7Zxd3zynnh7VpyuqXz48+ewrSiXNJStXVfIjL3+JoSLyoq8pKSkqDLEGmXNm7fy73z11C87B26padyzcRhXHn2YDqn6WaneGdmS9y96Ejn9OqJCLW7DvDgC2uZ9WYVqSnGNecN45pPDKN7Z23dlwwU9CLt2M59Dfz6pXX84dX1NDY5V4zP4z8uGE7vTN3slEwU9CLt0L5DjTyyaAO/eWkdew42MmVsf26YVMCgXrrZKRkp6EXamY3b9zL1t6+xZddBLjypNzddNIKT+mUGXZa0IQW9SDvS2NTM9bNL2X+oicevOYuiwT2DLklOAAW9SDsyY8E6lm6q55dXjFPItyO6KFaknXhrUx0PvrCWz40bwGfG9g+6HDmBFPQi7cDeg43cMLuUvpkZ/GjKyUGXIyeYpm5E2oEfP13Gph37mHXVmWRm6Nr49kYjepEkN3fVu8xaXMW3zhumlSbbKQW9SBKr3XWAW59YzikDMrn+woKgy5GAKOhFkpS7c/Pjy9nf0MT908ZpQbJ2TK+8SJL602sbWbhmK9+7ZBTDe3cNuhwJkIJeJAmt3bKbnz6zmvNH5PCvZ2h7zvZOQS+SZA42NnHdrFK6pqdy52VjtQuU6PJKkWRz7/w1lG3exe++UkROt/Sgy5E4oBG9SBJ5bd12Zi6s5Itn5HHhqD5BlyNxQkEvkiR27mvgxjmlDO7Vhe9fclLQ5UgciSrozWyymZWbWYWZ3XqUNlPNrMzMVpnZoxHH88xsnpmtDp8fHKPaRSTCf/1tJVt3H+T+aYXa+k8+oNU/DWaWAswAJgHVwGIzK3b3sog2+cBtwAR3rzOz3hE/4k/AT9x9vpl1BZpj2gMR4W+lNRQve4ebLypgbG5W0OVInIlmRD8eqHD3Snc/BMwCprRocxUww93rANy9FsDMRgGp7j4/fHyPu++LWfUiQnXdPr7/5EqKBvXgWxOHB12OxKFogn4AUBXxuDp8LFIBUGBmi8zsdTObHHG83sz+amZLzeyu8DuEDzCzq82sxMxKtm7d+nH6IdIuNTU7N85ZhgP3TSskpYMupZQPi9WHsalAPjARuAJ4yMyywsfPBW4GTgeGAle2fLK7z3T3IncvysnJiVFJIslv5sJK3ly/gx9dejK5PTsHXY7EqWiCvgbIjXg8MHwsUjVQ7O4N7r4eWEMo+KuB0vC0TyPwFHDqcVctIqys2cm988u5ZHQ/Pn9qyzfZIu+LJugXA/lmNsTM0oDpQHGLNk8RGs1jZtmEpmwqw8/NMrP3hukXAGWIyHHZf6iJ62YtpVeXdH7yuVN096t8pFaDPjwSvxaYC6wG5rj7KjO7w8wuDTebC2w3szJgAXCLu2939yZC0zbPm9kKwICH2qIjIu3Jz55dzbqte7ln6liyOqcFXY7EOXP3oGv4gKKiIi8pKQm6DJG4teDtWr72h8V885whfP/To4IuR+KEmS1x96IjndOdsSIJZNueg9zy+DJG9u3GzRePCLocSRC6fU4kQbg7tz6xgl0HGvnLN88go+OHrlQWOSKN6EUSxKzFVfxz9Ra+M3kkI/tmBl2OJBAFvUgCqNy6hzv+XsY5w7P52tmDgy5HEoyCXiTONTQ1c8PsUtI7duDuy8fSQXe/yjHSHL1InPvl82tZVr2T//nSqfTtnhF0OZKANKIXiWMlG3bwqwUVXHbaQD41ul/Q5UiCUtCLxKndBxq4YU4pA3p04oef0fXy8vFp6kYkTv3o72XU1O3nsWvOoltGx6DLkQSmEb1IHHpmxWYeX1LNtecP57RBPYMuRxKcgl4kzry78wC3/XUFY3Oz+I9P5gddjiQBBb1IHGludm5+bBmHGpu5f1ohHVP0V1SOn/4UicSRR17dwCsV2/jBZ0YxJLtL0OVIklDQi8SJt9/dxS+ee5sLT+rD9NNzW3+CSJQU9CJx4EBDE9fPKiUzoyO/+MJobSQiMaXLK0XiwN1zy3n73d088rXT6dU1PehyJMloRC8SsFfWbuN3r6znK2cN4vwRvYMuR5KQgl4kQPX7DnHTY6UMy+nCbf9yUtDlSJKKKujNbLKZlZtZhZndepQ2U82szMxWmdmjEcebzKw0/NVyU3GRdsvd+e6TK9ix9xAPTB9HpzRtJCJto9U5ejNLAWYAk4BqYLGZFbt7WUSbfOA2YIK715lZ5PvP/e5eGNuyRRLfX9+q4ZkV7/KdySM5ZUD3oMuRJBbNiH48UOHule5+CJgFTGnR5ipghrvXAbh7bWzLFEkuVTv28cPiVYwf0pOrPzE06HIkyUUT9AOAqojH1eFjkQqAAjNbZGavm9nkiHMZZlYSPv7ZI/0CM7s63KZk69atx1K/SMJpDG8kYgb3TSskRRuJSBuL1eWVqUA+MBEYCCw0s9HuXg8McvcaMxsKvGBmK9x9XeST3X0mMBOgqKjIY1STSFz6zUvrKNlYxwPTCxmQ1SnocqQdiGZEXwNE3qY3MHwsUjVQ7O4N7r4eWEMo+HH3mvB/K4EXgXHHWbNIwlpWVc/9/1zLpWP7M6Ww5RtjkbYRTdAvBvLNbIiZpQHTgZZXzzxFaDSPmWUTmsqpNLMeZpYecXwCUIZIO7TvUCPXzy6ld7d0fvzZU4IuR9qRVqdu3L3RzK4F5gIpwMPuvsrM7gBK3L04fO4iMysDmoBb3H27mZ0N/NbMmgn9o/LzyKt1RNqT//7HajZs38uj3zyT7p20kYicOFHN0bv7M8AzLY79IOJ7B24Mf0W2eRUYffxliiS2+WVbePSNTfzbeUM5a1ivoMuRdkZ3xoq0sdrdB/jOE8sZ1S+TGycVBF2OtEMKepE25O585/Hl7D3YyAPTC0lP1d2vcuIp6EXa0F/e2MSC8q1891Mnkd+nW9DlSDuloBdpIxW1e/jJP8o4ryCHr5w1KOhypB1T0Iu0gUONzVw/eymd01K56/Ix2khEAqWNR0TawP3/XMPKml389sun0btbRtDlSDunEb1IjL1RuZ1fv7SO6afncvHJfYMuR0RBLxJLuw40cOOcZQzq2Zn/+vSooMsRATR1IxJTP/zbKt7ddYDHrzmLLun66yXxQSN6kRgpXvYOTy6t4f9dkM+4vB5BlyNymIJeJAZq6vfzvSdXcGpeFv9+/rCgyxH5AAW9yHFqbnZumlNKc7Nz37RCUlP010rii/5Eihyn371SyeuVO/jhpSczqFeXoMsR+RAFvchxWPXOTu6aW87kk/ty+WkDgy5H5IgU9CIf04GGJq6fVUqPzmn87POjdferxC1d/yXyMf382bdZW7uHP319PD26pAVdjshRaUQv8jG8tGYrf3h1A1+bMJhPFOQEXY7IR1LQixyjHXsPcfNjyyjo05XvTB4ZdDkirYoq6M1sspmVm1mFmd16lDZTzazMzFaZ2aMtzmWaWbWZ/SoWRYsExd259Ynl7NzXwP3TxpHRURuJSPxrdY7ezFKAGcAkoBpYbGbFkZt8m1k+cBswwd3rzKx3ix/zY2Bh7MoWCcackirmlW3he586iVH9M4MuRyQq0YzoxwMV7l7p7oeAWcCUFm2uAma4ex2Au9e+d8LMTgP6APNiU7JIMDZs28uP/l7G2cN68Y1zhgRdjkjUogn6AUBVxOPq8LFIBUCBmS0ys9fNbDKAmXUA7gFu/qhfYGZXm1mJmZVs3bo1+upFTpDGpmaun11Kagfjnqlj6dBBl1JK4ojVh7GpQD4wEbgCeMjMsoBvA8+4e/VHPdndZ7p7kbsX5eToCgaJP79aUEFpVT0//fxo+nXvFHQ5Isckmuvoa4DciMcDw8ciVQNvuHsDsN7M1hAK/rOAc83s20BXIM3M9rj7ET/QFYlHb22q45cvVPD5cQP49Jj+QZcjcsyiGdEvBvLNbIiZpQHTgeIWbZ4iNJrHzLIJTeVUuvuX3D3P3QcTmr75k0JeEsmeg43cMLuUft0z+NGUk4MuR+RjaTXo3b0RuBaYC6wG5rj7KjO7w8wuDTebC2w3szJgAXCLu29vq6JFTpQf/72Mqh37uHdqId0yOgZdjsjHYu4edA0fUFRU5CUlJUGXIcJzK9/lmr8s4d/PH8YtF+vGKIlvZrbE3YuOdE53xoocwZZdB7j1r8sZM7A7119YEHQ5IsdFQS/SQnOzc/NjyzjQ0MR90wrpqI1EJMHpT7BIC398bQMvr93G9y8ZxbCcrkGXI3LcFPQiEdZs2c3Pnn2bT47szZfOyAu6HJGYUNCLhB1sbOK6WaVkZqTyi8vGaCMRSRraeEQk7N55a1i9eRe//2oR2V3Tgy5HJGY0ohcBXl23jZkvV/KlM/L45El9gi5HJKYU9NLu7dzXwE1zljEkuwvfv2RU0OWIxJymbqRdc3e+99QKtu4+yF+/fTad0rSRiCQfjeilXXuqtIanl2/mhkkFjBmYFXQ5Im1CQS/tVtWOffzgqVWcPrgH15w3LOhyRNqMgl7apaZm56Y5y3Dg3qmFpGgjEUlimqOXduk3L63jzQ07uHfqWHJ7dg66HJE2pRG9tDsrqndy3/w1XDKmH58b13JXTJHko6CXdmX/oSaum72UnG7p/PSzo3X3q7QLmrqRduWnz6ymcuteHv3mGXTvrI1EpH3QiF7ajRfe3sKfX9/IVecO4ezh2UGXI3LCRBX0ZjbZzMrNrMLMjrjnq5lNNbMyM1tlZo+Gjw0ys7fMrDR8/JpYFi8SrW17DvKfjy9nZN9u3HzxiKDLETmhWp26MbMUYAYwCagGFptZsbuXRbTJB24DJrh7nZn1Dp/aDJzl7gfNrCuwMvzcd2LeE5GjcHdufWI5uw408r/fPJP0VN39Ku1LNCP68UCFu1e6+yFgFjClRZurgBnuXgfg7rXh/x5y94PhNulR/j6RmHr0zU38c3Utt04eyYi+3YIuR+SEiyZ4BwBVEY+rw8ciFQAFZrbIzF43s8nvnTCzXDNbHv4Zv9BoXk6kdVv38OOnyzg3P5srzx4cdDkigYjVCDsVyAcmAlcAD5lZFoC7V7n7GGA48FUz+9AasGZ2tZmVmFnJ1q1bY1SStHcNTc3cMLuUjI4p3H35WDro7ldpp6IJ+hogN+LxwPCxSNVAsbs3uPt6YA2h4D8sPJJfCZzb8he4+0x3L3L3opycnGOpX+SoHvjnWpZX7+Tnnx9Nn8yMoMsRCUw0Qb8YyDezIWaWBkwHilu0eYrQaB4zyyY0lVNpZgPNrFP4eA/gHKA8NqWLHN3iDTv4nxcruPy0gUw+pV/Q5YgEqtWgd/dG4FpgLrAamOPuq8zsDjO7NNxsLrDdzMqABcAt7r4dOAl4w8yWAS8Bd7v7irboiMh7dh9o4IbZpQzs0ZkfXnpy0OWIBM7cPegaPqCoqMhLSkqCLkMS2E1zlvHk0moeu+ZsThvUI+hyRE4IM1vi7kVHOqfLHSWp/GP5Zp54q5prL8hXyIuEKeglaWzeuZ/vPrmCwtws/uOC4UGXIxI3FPSSFJqbnZsfW0ZDUzP3TSukY4r+aIu8R38bJCk8vGg9iyq284NPj2JIdpegyxGJKwp6SXirN+/izufKuWhUH6adntv6E0TaGQW9JLQDDU1cP6uU7p078vMvjNFGIiJHoI1HJKHd+Vw55Vt284evnU7PLmlBlyMSlzSil4T18tqtPLxoPVeePZiJI3q3/gSRdkpBLwmpbu8hbn5sGcN7d+XWfxkZdDkicU1BLwnH3fnukyvYsfcQ908rJKOjNhIR+SgKekk4jy+p5tmV73LTRSM4ZUD3oMsRiXsKekkom7bv4/biVZw5tCdXnTs06HJEEoKCXhJGY1MzN8wppUMH456phaRoIxGRqOjySkkY//PiOpZsrOOB6YUMyOoUdDkiCUMjekkIpVX1PPD8Wj5b2J8phS23LBaRj6Kgl7i392Aj189aSt/MDH405ZSgyxFJOJq6kbj33/8oY+OOffzfVWfSvVPHoMsRSTga0Utcm7fqXf7vzSquOW8YZw7tFXQ5IgkpqqA3s8lmVm5mFWZ261HaTDWzMjNbZWaPho8Vmtlr4WPLzWxaLIuPdKixmct/8yq3F6/ib6U1bNy+l3jbJlGOTe3uA9z61xWc3D+TGy4sCLockYTV6tSNmaUAM4BJQDWw2MyK3b0sok0+cBswwd3rzOy9hUf2AV9x97Vm1h9YYmZz3b0+1h2p23cIM2P24ir+8OoGAHp2SaMwN+vw19jcLL31TxDuzn8+vpy9Bxt5YHohaal68ynycUUzRz8eqHD3SgAzmwVMAcoi2lwFzHD3OgB3rw3/d817Ddz9HTOrBXKA+phUH6FPZgZz/u0sGpuaWbNlD0ur6ijdVE9pVT0Lymt5b3A/LKcLhbk9KMzLYlxuFiP7diNVuxHFnT+/vpEXy7dyx5STGd67W9DliCS0aIJ+AFAV8bgaOKNFmwIAM1sEpAC3u/tzkQ3MbDyQBqz72NVGITWlA6P6ZzKqfyZfOmMQALsONLC8aielVXWUVtXz0ppannirGoCMjh0YPaB7eNTfg3F5WfTrnqF1zQNUUbubn/xjNRNH5PDlMwcFXY5IwovVVTepQD4wERgILDSz0e9N0ZhZP+DPwFfdvbnlk83sauBqgLy8vBiV9L7MjI6ck5/NOfnZQGhaoLpuP0ur6sOj/jr++NpGHnp5PQC9u6WHgj8vi3G5PRgzsDtd0nWB0olwqLGZ62aV0iU9lTsv00YiIrEQTXrVAJH7sw0MH4tUDbzh7g3AejNbQyj4F5tZJvAP4Hvu/vqRfoG7zwRmAhQVFbX5J6hmRm7PzuT27MylY/sDoYBZvXkXpVWh6Z6lm+qYV7YFgA4GBX26UZibxbi80Mh/eO+uugW/Ddw7fw2r3tnFQ18pone3jKDLEUkK0QT9YiDfzIYQCvjpwBdbtHkKuAJ4xMyyCU3lVJpZGvAk8Cd3fzxmVbeBtNQOjA1/YPvV8LG6vYcora4/PNf/7Mp3mbU4NIvVNT2V0QO6h4M/NPpXMB2f1yu389uF67hifB6TRvUJuhyRpNFq0Lt7o5ldC8wlNP/+sLuvMrM7gBJ3Lw6fu8jMyoAm4BZ3325m/wp8AuhlZleGf+SV7l7aBn2JuR5d0jh/RG/OD+9e5O6s37Y3YtRfz8yFlTQ2h96EDMjqdPhD3sLcLE4Z0F1rpUdp5/4GbpqzjMG9uvBfnz4p6HJEkorF27XmRUVFXlJSEnQZUTvQ0MSqd3aydFP94Tn/mvr9AKR2ME7ql/n+JZ55WQzp1YUOmvL5kOtmLeXp5Zt54ltnU5ibFXQ5IgnHzJa4e9GRzukTxuOU0TGF0wb15LRBPQ8fq919gGVVO1m6KXSVz5NLa/jz6xsByMxIpTCvR2i+P/wPQI92vqn130pr+FvpO9w0qUAhL9IGFPRtoHe3DCaNyjg8z9zU7Kzbuudw8C/dVM+vXlhLeMaHwb06R4z6ezCqX2a7uUGopn4/339qJacN6sG3Jg4LuhyRpKSgPwFSOhgFfbpR0Kcb004PXT6692Ajy6t3huf763h13XaeKn0HCH0wfHL/96d8Ts3rwcAenZLuUsOmZufG2aU0Nzv3TS3UjWsibURBH5Au6amcNawXZw0LLdTl7mzeeeDwB72lm+r5vzc38ciiDQD0iljOYVxeD8bkdiczI7GXc3jo5UreWL+Duy4bQ16vzkGXI5K0FPRxwszon9WJ/lmd+NTofgA0NDVT/u7u98O/qp7n364Nt4dhOV0jwj+LEX0SZzmHlTU7uWdeOZ8a3ZfLThsYdDkiSU1X3SSYnfsbWB5xbf/Sqnp27D0EQKeOKaHlHN67xDMvi37d42/LvQMNTXz6l6+w+0ADz133iXb/YbRILOiqmyTSvVNHzs3P4dz8HCA05VO1Y39oEbfwB71/WLSBmU2hlSb6ZKYfnu4pzM1izMDudE4L9mX/2TOrqajdw5+/MV4hL3ICKOgTnJmR16szeb06H95L9WBjE6s376Z0U13o2v6qeuau+uByDuPyehwe9Q/P6XrCru1fUF7LH1/byDfOGXL4HysRaVuaumknduw9xLLwGj5Lq+pZVlXPrgONQGg5h7G576/gWZibRU639JjXsH3PQSY/8DI9O6fxt2sn6K5hkRjS1I3Qs0sa54/szfkjQ8s5NDc767fvZWl49c7Sqnp++9L7yzkM7NHpAx/0ntz/+JZzcHdu/esKdu5r4E9fH6+QFzmBFPTtVIcOxrCcrgzL6Xr4qpcDDU2srNkZDv/QfP/TyzcDoeUcRkVc21+Ym8WQ7C5RX9s/e3EV88u28P1LTuKkfplt1i8R+TAFvRyW0TGFosE9KRocsZzDrgOH5/lLN9XzxJJq/vRaaDmHrM4dGTswK2Lt/iyyOn/4w9X12/byo7+XMWF4L74+YcgJ64+IhCjo5SP1zszg4pP7cvHJfYHQ3axra3cfvryztKqeB19Ye3irxiHZXT4w5ZPfuxvXzy4lLbUDd18+Vgu6iQRAQS/HJKWDMbJvJiP7ZjJ9fGg5hz0HG0PX9odH/a9UbOPJpTWH2zc1O//zpVPj8pp+kfZAQS/HrWt6KmcPy+bsYe9v1fjOzgOHt2nM7pp++G5fETnxFPQSc2bGgKxODMjqxCVjFPAiQUuMhVFERORjU9CLiCS5qILezCabWbmZVZjZrUdpM9XMysxslZk9GnH8OTOrN7OnY1W0iIhEr9U5ejNLAWYAk4BqYLGZFbt7WUSbfOA2YIK715lZ74gfcRfQGfi3mFYuIiJRiWZEPx6ocPdKdz8EzAKmtGhzFTDD3esA3L32vRPu/jywO0b1iojIMYom6AcAVRGPq8PHIhUABWa2yMxeN7PJsSpQRESOT6wur0wF8oGJwEBgoZmNdvf6aJ5sZlcDVwPk5eXFqCQREYHoRvQ1QG7E44HhY5GqgWJ3b3D39cAaQsEfFXef6e5F7l6Uk6M1ykVEYimaEf1iIN/MhhAK+OnAF1u0eQq4AnjEzLIJTeVUfpyClixZss3MNn6c54ZlA9uO4/nxIln6AepLvEqWviRLP+D4+jLoaCdaDXp3bzSza4G5QArwsLuvMrM7gBJ3Lw6fu8jMyoAm4BZ33w5gZi8DI4GuZlYNfMPd537E7zuuIb2ZlRxt8f1Ekiz9APUlXiVLX5KlH9B2fYlqjt7dnwGeaXHsBxHfO3Bj+Kvlc889zhpFROQ46M5YEZEkl4xBPzPoAmIkWfoB6ku8Spa+JEs/oI36Enebg4uISGwl44heREQiJGTQt7bImpmlm9ns8Pk3zGxwAGVGJYq+XGlmW82sNPz1zSDqbI2ZPWxmtWa28ijnzcweDPdzuZmdeqJrjFYUfZloZjsjXpMfHKld0Mws18wWRCw2eN0R2iTE6xJlXxLldckwszfNbFm4Lz86QpvYZpi7J9QXoUs81wFDgTRgGTCqRZtvA78Jfz8dmB103cfRlyuBXwVdaxR9+QRwKrDyKOc/BTwLGHAm8EbQNR9HXyYCTwddZxT96AecGv6+G6EbGVv++UqI1yXKviTK62JA1/D3HYE3gDNbtIlphiXiiD6aRdamAH8Mf/848Ekzi8ddqaPpS0Jw94XAjo9oMgX4k4e8DmSZWVxuPxVFXxKCu29297fC3+8GVvPhdaoS4nWJsi8JIfz/ek/4YcfwV8sPS2OaYYkY9NEssna4jbs3AjuBXiekumMTTV8AvhB+W/24meUe4XwiiLavieKs8FvvZ83s5KCLaU34rf84QqPHSAn3unxEXyBBXhczSzGzUqAWmO/uR31dYpFhiRj07c3fgcHuPgaYz/v/yktw3gIGuftY4JeElgCJW2bWFXgCuN7ddwVdz/FopS8J87q4e5O7FxJaO2y8mZ3Slr8vEYM+mkXWDrcxs1SgO7D9hFR3bFrti7tvd/eD4Ye/A047QbXFWjSvW0Jw913vvfX20F3jHcNrPMUdM+tIKBj/193/eoQmCfO6tNaXRHpd3uOhFX4XAC2Xdo9phiVi0B9eZM3M0gh9UFHcok0x8NXw95cBL3j4U40402pfWsyXXkpobjIRFQNfCV/lcSaw0903B13Ux2Fmfd+bLzWz8YT+HsXdQCJc4++B1e5+71GaJcTrEk1fEuh1yTGzrPD3nQjt3vd2i2YxzbBYrUd/wnh0i6z9HvizmVUQ+lBtenAVH12Uffl/ZnYp0EioL1cGVvBHMLP/I3TVQ7aFFq/7IaEPmXD33xBaK+lTQAWwD/haMJW2Loq+XAZ8y8wagf3A9DgdSEwAvgysCM8HA3wXyIOEe12i6UuivC79gD9aaJvWDsAcd3+6LTNMd8aKiCS5RJy6ERGRY6CgFxFJcgp6EZEkp6AXEUlyCnoRkSSnoBcRSXIKehGRJKegFxFJcv8f9XVHkrXSs/kAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "evolution_reward = results[[\"reward\",\"epoch\"]].groupby(by=\"epoch\").mean()\n",
    "plt.plot(evolution_reward.reward.to_list())\n",
    "plt.title(\"Evolution of rewards\")\n",
    "plt.xlabel(\"Epochs\")\n",
    "plt.ylabel(\"Reward\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "guacamol_3.7",
   "language": "python",
   "name": "guacamol_project_3.7"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}