20240820_gplearn_adiabatic.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from gplearn.genetic import SymbolicRegressor\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "from sklearn.metrics import r2_score\n",
    "from sklearn.metrics import mean_absolute_error as MAE\n",
    "from sklearn.metrics import mean_squared_error as MSE\n",
    "import matplotlib.pyplot as plt\n",
    "import re\n",
    "\n",
    "# CSV 파일에서 데이터 로드\n",
    "file_path = '20240806_correlation_copy.csv'\n",
    "df = pd.read_csv(file_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "scaler = MinMaxScaler()\n",
    "normalized_data = scaler.fit_transform(df)\n",
    "\n",
    "normalized_df = pd.DataFrame(normalized_data, columns=df.columns)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    |   Population Average    |             Best Individual              |\n",
      "---- ------------------------- ------------------------------------------ ----------\n",
      " Gen   Length          Fitness   Length          Fitness      OOB Fitness  Time Left\n",
      "   0     9.62          6.17786        6        0.0975508              N/A      1.57m\n",
      "   1     4.63         0.446922        7        0.0593323              N/A      1.22m\n",
      "   2     4.33         0.442957        8        0.0496848              N/A      1.19m\n",
      "   3     9.18         0.372101       11        0.0458897              N/A      1.38m\n",
      "   4     8.29          0.24386       11        0.0458897              N/A      1.19m\n",
      "   5     8.17         0.127144       13        0.0444145              N/A      1.36m\n",
      "   6     9.23          0.14215       21        0.0442412              N/A      1.18m\n",
      "   7    10.32         0.160895       20        0.0440575              N/A      1.29m\n",
      "   8    12.26         0.154724       18        0.0440575              N/A      1.18m\n",
      "   9    11.84         0.158977       19        0.0442412              N/A      1.14m\n",
      "  10    11.13         0.158527       18        0.0442412              N/A      1.14m\n",
      "  11    10.78         0.177988       24        0.0442339              N/A      1.19m\n",
      "  12    10.13         0.174312       17        0.0442412              N/A      1.28m\n",
      "  13    10.20         0.162318       17        0.0442412              N/A      1.11m\n",
      "  14    10.00         0.171267       23        0.0441705              N/A      1.14m\n",
      "  15     9.99         0.179021       17        0.0442412              N/A      1.09m\n",
      "  16    10.21         0.160137       20        0.0442339              N/A      1.23m\n",
      "  17     9.89         0.174683       17        0.0442412              N/A      1.08m\n",
      "  18    10.07         0.158549       17        0.0442412              N/A      1.09m\n",
      "  19     9.82          0.21857       17        0.0442412              N/A      1.01m\n",
      "  20    10.11         0.157433       20        0.0442339              N/A      1.04m\n",
      "  21     9.88         0.179025       17        0.0442412              N/A      1.07m\n",
      "  22     9.99         0.277316       17        0.0442412              N/A      1.00m\n",
      "  23    10.08         0.165177       23        0.0441488              N/A      1.01m\n",
      "  24     9.79         0.181313       17        0.0442412              N/A     59.76s\n",
      "  25     9.86         0.176054       19        0.0441148              N/A      1.09m\n",
      "  26    10.10         0.166223       16        0.0440575              N/A     55.95s\n",
      "  27     9.83         0.187769       17        0.0442412              N/A     54.67s\n",
      "  28     9.79         0.179034       17        0.0442412              N/A     55.08s\n",
      "  29     9.99         0.177364       20        0.0442339              N/A     58.55s\n",
      "  30    10.09         0.167093       17        0.0442412              N/A      1.03m\n",
      "  31    10.03         0.172407       17        0.0442412              N/A     52.35s\n",
      "  32     9.99         0.166291       17        0.0442412              N/A     52.73s\n",
      "  33     9.86         0.171411       22        0.0440575              N/A     51.76s\n",
      "  34     9.87         0.201126       17        0.0442412              N/A     57.97s\n",
      "  35     9.89         0.169866       17        0.0442412              N/A     50.42s\n",
      "  36     9.73         0.171126       17        0.0442412              N/A     48.31s\n",
      "  37     9.90         0.177563       17        0.0442412              N/A     48.67s\n",
      "  38    10.27         0.164434       17        0.0442412              N/A     53.34s\n",
      "  39     9.85         0.157603       17        0.0442412              N/A     47.62s\n",
      "  40    10.07            0.176       17        0.0442412              N/A     47.45s\n",
      "  41     9.89          0.16949       17        0.0442412              N/A     44.67s\n",
      "  42     9.79         0.169669       20        0.0440061              N/A     46.44s\n",
      "  43    10.02          0.15862       17        0.0439996              N/A     45.67s\n",
      "  44     9.87         0.178577       17        0.0442412              N/A     49.36s\n",
      "  45    10.09          0.17229       20        0.0442339              N/A     58.06s\n",
      "  46     9.98         0.172199       17        0.0442412              N/A     47.54s\n",
      "  47     9.95         0.170802       17        0.0442412              N/A     41.88s\n",
      "  48     9.97         0.385702       17        0.0442412              N/A     41.82s\n",
      "  49    10.04         0.164454       17        0.0442412              N/A     40.15s\n",
      "  50     9.90         0.162077       22        0.0440575              N/A     40.87s\n",
      "  51    10.12          0.17295       17        0.0442412              N/A     41.03s\n",
      "  52    10.06          0.17209       17        0.0442412              N/A     37.54s\n",
      "  53    10.21         0.164792       20        0.0442339              N/A     37.10s\n",
      "  54     9.78         0.191205       17        0.0442412              N/A     40.74s\n",
      "  55     9.87          0.17886       17        0.0442412              N/A     39.10s\n",
      "  56    10.12         0.171718       22        0.0440575              N/A     34.29s\n",
      "  57    10.04          0.16997       17        0.0442412              N/A     34.93s\n",
      "  58     9.87         0.181186       17        0.0442412              N/A     33.82s\n",
      "  59     9.97         0.191786       20        0.0442339              N/A     35.79s\n",
      "  60    10.06         0.172743       20        0.0442339              N/A     32.01s\n",
      "  61    10.01         0.180355       17        0.0442412              N/A     30.73s\n",
      "  62    10.11         0.155093       16        0.0440575              N/A     31.16s\n",
      "  63    10.04         0.164711       17        0.0442412              N/A     31.60s\n",
      "  64     9.94         0.173285       17        0.0442412              N/A     29.34s\n",
      "  65     9.77         0.186518       17        0.0442412              N/A     27.12s\n",
      "  66    10.08         0.170082       19        0.0440457              N/A     26.77s\n",
      "  67     9.93         0.184679       17        0.0442412              N/A     26.17s\n",
      "  68     9.97         0.189916       16        0.0440575              N/A     27.55s\n",
      "  69     9.85         0.176512       17        0.0442412              N/A     23.23s\n",
      "  70     9.95         0.162279       17        0.0442412              N/A     25.06s\n",
      "  71    10.22         0.157698       17        0.0442412              N/A     23.14s\n",
      "  72    10.06         0.167249       23        0.0441488              N/A     23.51s\n",
      "  73    10.11         0.164318       20        0.0442339              N/A     20.71s\n",
      "  74    10.07         0.177146       17        0.0442412              N/A     21.04s\n",
      "  75    10.06         0.167105       23        0.0441488              N/A     19.17s\n",
      "  76    10.01         0.167574       17        0.0442412              N/A     20.29s\n",
      "  77     9.81         0.196863       17        0.0442412              N/A     20.47s\n",
      "  78     9.75         0.178427       17        0.0442412              N/A     17.16s\n",
      "  79     9.81          0.17411       17        0.0442412              N/A     15.92s\n",
      "  80     9.86         0.175135       19        0.0440457              N/A     16.56s\n",
      "  81    10.11         0.159445       16        0.0440575              N/A     14.23s\n",
      "  82     9.81         0.184387       20        0.0442339              N/A     13.75s\n",
      "  83     9.91         0.200045       19        0.0439996              N/A     13.28s\n",
      "  84     9.94         0.172481       17        0.0442412              N/A     13.19s\n",
      "  85    10.15         0.171083       17        0.0442412              N/A     12.07s\n",
      "  86    10.12         0.172288       17        0.0442412              N/A     10.24s\n",
      "  87    10.00         0.156995       19        0.0439996              N/A      9.97s\n",
      "  88     9.88         0.176257       17        0.0442412              N/A      9.79s\n",
      "  89    10.05         0.183726       17        0.0442412              N/A      8.87s\n",
      "  90     9.94         0.171712       17        0.0442412              N/A      7.17s\n",
      "  91    10.00         0.181971       17        0.0442412              N/A      6.62s\n",
      "  92     9.90         0.166849       26        0.0442159              N/A      5.64s\n",
      "  93    10.09         0.169198       20        0.0442339              N/A      5.26s\n",
      "  94    10.26         0.173554       17        0.0442412              N/A      3.97s\n",
      "  95     9.79         0.173039       17        0.0442412              N/A      3.17s\n",
      "  96     9.85         0.152077       17        0.0442412              N/A      2.44s\n",
      "  97    10.04         0.185217       17        0.0442412              N/A      1.83s\n",
      "  98    10.10         0.173132       17        0.0442412              N/A      0.80s\n",
      "  99     9.95         0.180545       17        0.0442412              N/A      0.00s\n",
      "mul(X2, sqrt(sqrt(mul(sqrt(mul(X2, sqrt(sqrt(mul(sqrt(mul(X2, -0.759)), -0.759))))), -0.759))))\n"
     ]
    }
   ],
   "source": [
    "y_min, y_max = df[\"adiabatic_S1-S0 (kcal/mol)\"].min(), df[\"adiabatic_S1-S0 (kcal/mol)\"].max()\n",
    "\n",
    "X = normalized_df[[\"homo (eV)\", \"lumo (eV)\", \"vertical_excitation_energy (eV)\", \"dipole_moment_norm_S0 (D)\",\n",
    "    \"dipole_moment_norm_S1 (D)\", \"dipole_moment_norm_T1 (D)\", \"0-0_T1 (eV)\",\n",
    "    \"reduction_S0 (kcal/mol)\", \"adiabatic_T1-S0 (kcal/mol)\", \"oxidation_S0 (kcal/mol)\",\n",
    "    \"lumo-homo (eV)\"]]\n",
    "y = normalized_df[\"adiabatic_S1-S0 (kcal/mol)\"]\n",
    "\n",
    "est = SymbolicRegressor(population_size=1000,\n",
    "                        generations=100,\n",
    "                        stopping_criteria=0.01,\n",
    "                        function_set=['add', 'sub', 'mul', 'div', 'sqrt', 'log', 'abs', 'neg', 'inv'],\n",
    "                        metric='mean absolute error',\n",
    "                        parsimony_coefficient=0.0001,\n",
    "                        verbose=1,\n",
    "                        random_state=0)\n",
    "\n",
    "est.fit(X, y)\n",
    "\n",
    "# 수식 출력\n",
    "if hasattr(est, '_program'):\n",
    "    print(est._program)\n",
    "else:\n",
    "    print(\"The model does not have a _program attribute.\")\n",
    "\n",
    "y_pred_normalized = est.predict(X)\n",
    "y_pred = y_pred_normalized * (y_max - y_min) + y_min\n",
    "y_actual = y * (y_max - y_min) + y_min\n",
    "\n",
    "r2 = r2_score(y_actual, y_pred)\n",
    "mae = MAE(y_actual, y_pred)\n",
    "rmse = np.sqrt(MSE(y_actual, y_pred))\n",
    "\n",
    "plt.figure()\n",
    "plt.plot([y_min, y_max], [y_min, y_max], 'k-', lw=2)\n",
    "plt.scatter(y_actual, y_pred, color = 'red', alpha=0.5)\n",
    "plt.xlabel(f'Actual values of adiabatic_S1-S0 (kcal/mol)')\n",
    "plt.ylabel(f'Predicted values of adiabatic_S1-S0 (kcal/mol)')\n",
    "plt.title('Parity Plot of adiabatic_S1-S0 (kcal/mol)')\n",
    "\n",
    "# R^2 값 그래프에 추가\n",
    "plt.text(x=0.05, y=0.95, s=f'$R^2 = {r2:.4f}$', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "plt.text(x=0.05, y=0.90, s=f'MAE = {mae:.4f} (kcal/mol)', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "plt.text(x=0.05, y=0.85, s=f'RMSE = {rmse:.4f} (kcal/mol)', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "\n",
    "# 그래프 이미지 파일로 저장\n",
    "plt.savefig('GPlearn Adiabatic1.png')\n",
    "plt.close()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "    |   Population Average    |             Best Individual              |\n",
      "---- ------------------------- ------------------------------------------ ----------\n",
      " Gen   Length          Fitness   Length          Fitness      OOB Fitness  Time Left\n",
      "   0     9.62          6.00665        3        0.0972795         0.110149      1.58m\n",
      "   1     4.73         0.494179        7        0.0585956        0.0659361      1.65m\n",
      "   2     4.56         0.572199        6         0.056741        0.0569442      1.44m\n",
      "   3     8.60         0.513912       10        0.0456634        0.0479178      1.57m\n",
      "   4     7.69         0.313713       17        0.0405968        0.0406937      1.40m\n",
      "   5     8.57         0.184794       17        0.0400368        0.0457127      1.49m\n",
      "   6    10.51         0.304793       25        0.0391324        0.0458407      1.46m\n",
      "   7    13.52         0.227028       17        0.0378206        0.0424851      1.56m\n",
      "   8    16.35         0.271018       17        0.0377292        0.0433048      1.79m\n",
      "   9    17.27         0.277413       25        0.0375033        0.0453299      1.61m\n",
      "  10    18.13         0.260814       32         0.036935        0.0373901      1.59m\n",
      "  11    17.86         0.206238       25        0.0368447        0.0451699      1.64m\n",
      "  12    17.49          0.21792       22        0.0370538        0.0432946      1.47m\n",
      "  13    16.92         0.213603       40        0.0366969        0.0390632      1.43m\n",
      "  14    16.76         0.207701       23        0.0371024        0.0428598      1.42m\n",
      "  15    16.60         0.230301       33        0.0368759        0.0370099      1.50m\n",
      "  16    16.46         0.367563       35        0.0368612        0.0375904      1.40m\n",
      "  17    16.77         0.692108       31        0.0366023         0.039463      1.35m\n",
      "  18    16.73          0.24006       31        0.0364547        0.0407855      1.48m\n",
      "  19    16.83         0.238871       32         0.036575        0.0400812      1.31m\n",
      "  20    17.00         0.241599       18        0.0364316        0.0488727      1.25m\n",
      "  21    16.92         0.230716       21         0.036836        0.0452474      1.27m\n",
      "  22    17.25          0.25971       37        0.0362815        0.0437795      1.37m\n",
      "  23    17.04         0.243674       18        0.0368924         0.044742      1.31m\n",
      "  24    16.97          0.24509       28        0.0367359        0.0382646      1.18m\n",
      "  25    17.32          0.24976       27        0.0363233        0.0419633      1.36m\n",
      "  26    17.95         0.245384       33        0.0366034        0.0399019      1.21m\n",
      "  27    17.50         0.258783       18        0.0363392        0.0497006      1.28m\n",
      "  28    17.50         0.253182       31        0.0360392        0.0449594      1.16m\n",
      "  29    17.77         0.258504       18        0.0365252        0.0480338      1.29m\n",
      "  30    17.87         0.716869       32        0.0364649        0.0411434      1.11m\n",
      "  31    17.68         0.238619       27        0.0363202         0.041991      1.16m\n",
      "  32    17.82         0.246557       19        0.0367385        0.0461216      1.20m\n",
      "  33    17.69           0.2772       35        0.0367299        0.0397601      1.14m\n",
      "  34    17.44         0.256547       21         0.036334         0.041856      1.06m\n",
      "  35    17.25          0.28004       23        0.0366083        0.0421126      1.10m\n",
      "  36    17.43         0.215969       21         0.036376        0.0414793      1.14m\n",
      "  37    17.78         0.242745       18        0.0361507        0.0428702      1.07m\n",
      "  38    18.16         0.251204       18        0.0361082        0.0432506     59.82s\n",
      "  39    18.23         0.444068       18        0.0360985        0.0433384      1.07m\n",
      "  40    18.17         0.227396       18        0.0361152         0.043188     59.20s\n",
      "  41    17.82         0.238135       18        0.0357447        0.0465098     55.68s\n",
      "  42    17.72         0.254673       18        0.0358014        0.0460009     56.59s\n",
      "  43    17.79         0.395529       18        0.0358552        0.0455188      1.01m\n",
      "  44    17.56         0.225801       18        0.0359914        0.0442981     53.42s\n",
      "  45    17.75          0.23259       18        0.0358254        0.0457856     55.03s\n",
      "  46    17.74         0.306808       18        0.0359206         0.044933     57.87s\n",
      "  47    17.52         0.293523       18        0.0361082        0.0432506     52.94s\n",
      "  48    17.61         0.297213       18        0.0359325        0.0448263     50.07s\n",
      "  49    17.74         0.228422       18        0.0359738        0.0444559     51.59s\n",
      "  50    17.28         0.253407       18        0.0360946        0.0433729     53.13s\n",
      "  51    17.70         0.246895       18        0.0361036        0.0432921     46.59s\n",
      "  52    18.08         0.245258       18        0.0357584        0.0463867     50.62s\n",
      "  53    17.65         0.285308       18         0.035952         0.044651     51.90s\n",
      "  54    17.71         0.267584       18        0.0359259        0.0448852     43.25s\n",
      "  55    17.60         0.256833       18        0.0360251        0.0439959     41.55s\n",
      "  56    17.45         0.227112       18        0.0358493        0.0455721     45.87s\n",
      "  57    17.21         0.260626       18        0.0356778        0.0471095     42.73s\n",
      "  58    17.66         0.279839       18        0.0359123        0.0450067     39.99s\n",
      "  59    17.19         0.264761       18         0.036064        0.0436475     39.08s\n",
      "  60    17.58         0.608073       18        0.0357485        0.0464752     42.59s\n",
      "  61    17.34         0.287479       18        0.0360891         0.043422     39.11s\n",
      "  62    17.61         0.277654       18        0.0358764        0.0453288     37.55s\n",
      "  63    17.51         0.250624       18        0.0356949        0.0469558     38.76s\n",
      "  64    17.67          0.51317       18        0.0357343        0.0466029     36.05s\n",
      "  65    17.14         0.263118       18        0.0358328          0.04572     34.23s\n",
      "  66    17.60         0.234309       18        0.0359583        0.0445949     33.90s\n",
      "  67    17.15          0.58265       18        0.0360633        0.0436537     34.27s\n",
      "  68    17.50         0.250676       18        0.0358077        0.0459451     30.84s\n",
      "  69    17.44         0.298885       18        0.0360706         0.043588     28.80s\n",
      "  70    17.67         0.263216       18         0.036005        0.0441763     31.59s\n",
      "  71    17.40         0.319391       18        0.0357212        0.0467203     27.13s\n",
      "  72    17.21         0.240109       18        0.0359745        0.0444497     26.36s\n",
      "  73    17.38         0.269415       18        0.0360512        0.0437618     24.57s\n",
      "  74    17.74         0.250762       18        0.0358395        0.0456598     27.58s\n",
      "  75    17.42         0.248892       18        0.0359696        0.0444934     23.77s\n",
      "  76    17.79         0.265816       18        0.0360184        0.0440564     22.58s\n",
      "  77    17.55           0.2272       18        0.0358067        0.0459538     24.15s\n",
      "  78    17.39         0.264981       18        0.0360223        0.0440215     21.60s\n",
      "  79    17.58         0.261088       18        0.0359264        0.0448806     22.16s\n",
      "  80    17.78         0.268428       18         0.035897        0.0451441     18.86s\n",
      "  81    17.54         0.259296       18        0.0359435        0.0447271     19.06s\n",
      "  82    17.47          0.24902       18        0.0356491        0.0473664     17.26s\n",
      "  83    17.48         0.252712       18        0.0358637        0.0454429     17.10s\n",
      "  84    17.49         0.270505       18        0.0359081        0.0450444     16.59s\n",
      "  85    17.52         0.228984       18        0.0358751        0.0453403     14.24s\n",
      "  86    17.11         0.280295       18        0.0359886        0.0443228     13.46s\n",
      "  87    17.84         0.276062       18        0.0361563        0.0428203     12.71s\n",
      "  88    17.36         0.346191       18        0.0358001        0.0460125     11.35s\n",
      "  89    17.71          0.23467       18        0.0360529         0.043747      9.85s\n",
      "  90    17.48         0.250013       18        0.0359155        0.0449782      8.64s\n",
      "  91    17.68         0.327358       18        0.0360664        0.0436262      8.95s\n",
      "  92    17.47          0.28513       18        0.0361557         0.042825      6.92s\n",
      "  93    17.93         0.300628       18        0.0360129        0.0441056      6.39s\n",
      "  94    18.15         0.249863       18        0.0356651        0.0472226      5.51s\n",
      "  95    17.38          0.29196       18        0.0359035        0.0450863      3.94s\n",
      "  96    17.41         0.241191       18        0.0360011        0.0442115      2.97s\n",
      "  97    17.87         0.249052       18        0.0359625        0.0445567      2.02s\n",
      "  98    17.78         0.251259       18        0.0360618        0.0436668      1.09s\n",
      "  99    17.58         0.238528       18        0.0360601        0.0436825      0.00s\n",
      "mul(add(X9, X0), mul(add(X9, X0), mul(X2, sqrt(sqrt(mul(sqrt(mul(X2, -0.675)), -0.759))))))\n"
     ]
    }
   ],
   "source": [
    "y_min, y_max = df[\"adiabatic_S1-S0 (kcal/mol)\"].min(), df[\"adiabatic_S1-S0 (kcal/mol)\"].max()\n",
    "\n",
    "X = normalized_df[[\"homo (eV)\", \"lumo (eV)\", \"vertical_excitation_energy (eV)\", \"dipole_moment_norm_S0 (D)\",\n",
    "    \"dipole_moment_norm_S1 (D)\", \"dipole_moment_norm_T1 (D)\", \"0-0_T1 (eV)\",\n",
    "    \"reduction_S0 (kcal/mol)\", \"adiabatic_T1-S0 (kcal/mol)\", \"oxidation_S0 (kcal/mol)\",\n",
    "    \"lumo-homo (eV)\"]]\n",
    "y = normalized_df[\"adiabatic_S1-S0 (kcal/mol)\"]\n",
    "\n",
    "est = SymbolicRegressor(population_size=1000,\n",
    "                           generations=100, stopping_criteria=0.01,\n",
    "                           function_set=['add', 'sub', 'mul', 'div', 'sqrt', 'log', 'abs', 'neg', 'inv'],\n",
    "                           p_crossover=0.7, p_subtree_mutation=0.1,\n",
    "                           p_hoist_mutation=0.05, p_point_mutation=0.1,\n",
    "                           max_samples=0.9, verbose=1,\n",
    "                           parsimony_coefficient=0.0001, random_state=0)\n",
    "\n",
    "est.fit(X, y)\n",
    "\n",
    "# 수식 출력\n",
    "print(est._program)\n",
    "\n",
    "y_pred_normalized = est.predict(X)\n",
    "y_pred = y_pred_normalized * (y_max - y_min) + y_min\n",
    "y_actual = y * (y_max - y_min) + y_min\n",
    "\n",
    "r2 = r2_score(y_actual, y_pred)\n",
    "mae = MAE(y_actual, y_pred)\n",
    "rmse = np.sqrt(MSE(y_actual, y_pred))\n",
    "\n",
    "plt.figure()\n",
    "plt.plot([y_min, y_max], [y_min, y_max], 'k-', lw=2)\n",
    "plt.scatter(y_actual, y_pred, color = 'red', alpha=0.5)\n",
    "plt.xlabel(f'Actual values of adiabatic_S1-S0 (kcal/mol)')\n",
    "plt.ylabel(f'Predicted values of adiabatic_S1-S0 (kcal/mol)')\n",
    "plt.title('Parity Plot of adiabatic_S1-S0 (kcal/mol)')\n",
    "\n",
    "# R^2 값 그래프에 추가\n",
    "plt.text(x=0.05, y=0.95, s=f'$R^2 = {r2:.4f}$', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "plt.text(x=0.05, y=0.90, s=f'MAE = {mae:.4f} (kcal/mol)', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "plt.text(x=0.05, y=0.85, s=f'RMSE = {rmse:.4f} (kcal/mol)', fontsize=12, ha='left', va='top', transform=plt.gca().transAxes)\n",
    "\n",
    "# 그래프 이미지 파일로 저장\n",
    "plt.savefig('GPlearn Adiabatic2.png')\n",
    "plt.close()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}