{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "fdbab969",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn import ensemble as sk_ensemble\n",
    "from sklearn import model_selection as sk_model_selection\n",
    "from sklearn import utils as sk_utils\n",
    "\n",
    "import model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "feccb798",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>smiles</th>\n",
       "      <th>binary_classification_preference_idx</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CN(C)C</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CCOC(=O)C(C)=O</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CCC/C=C\\CO</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NCCCCCN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CC/C=C\\CCO</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           smiles  binary_classification_preference_idx\n",
       "0          CN(C)C                                     1\n",
       "1  CCOC(=O)C(C)=O                                     0\n",
       "2      CCC/C=C\\CO                                     0\n",
       "3         NCCCCCN                                     1\n",
       "4      CC/C=C\\CCO                                     0"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_csv = './data/a_MacWilliam_et_al/data.csv'\n",
    "data_df = pd.read_csv(data_csv)\n",
    "data_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7f0eee41",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((58, 256), (58,))"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = model.get_embs(data_df['smiles'])\n",
    "y = data_df['binary_classification_preference_idx'].values\n",
    "x.shape, y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "28194e54",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9349999999999999"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x, y = sk_utils.shuffle(x, y)\n",
    "\n",
    "model = sk_ensemble.RandomForestClassifier()\n",
    "cv_auroc = sk_model_selection.cross_val_score(model, x, y, cv=10, scoring='roc_auc')\n",
    "np.average(cv_auroc)"
   ]
  }
 ],
 "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": "3.10.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}