{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "e61a8ce1",
   "metadata": {},
   "source": [
    "## Generating and analyzing a dataset using RDKit\n",
    "\n",
    "This is an exploratory notebook using rdkit and other libraries to examine melting points of hydrocarbons."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "54cb0037",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from rdkit import Chem\n",
    "from rdkit.Chem import Descriptors, PandasTools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "3e334e5a",
   "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>Class of hydrocarbon</th>\n",
       "      <th>IUPAC name</th>\n",
       "      <th>Melting point</th>\n",
       "      <th>Boiling point</th>\n",
       "      <th>Density@20å¡C*</th>\n",
       "      <th>Flash point</th>\n",
       "      <th>Autoignition temp</th>\n",
       "      <th>pubchem_id</th>\n",
       "      <th>smiles</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Trimetylalkane</td>\n",
       "      <td>2,2,4-Trimethylpentane</td>\n",
       "      <td>-107.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.69</td>\n",
       "      <td>NaN</td>\n",
       "      <td>396</td>\n",
       "      <td>10907</td>\n",
       "      <td>CC(C)CC(C)(C)C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>Phenanthrene</td>\n",
       "      <td>99.0</td>\n",
       "      <td>338.0</td>\n",
       "      <td>1.18</td>\n",
       "      <td>171</td>\n",
       "      <td>&gt;450</td>\n",
       "      <td>995</td>\n",
       "      <td>C1=CC=C2C(=C1)C=CC3=CC=CC=C32</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>Anthracene</td>\n",
       "      <td>216.0</td>\n",
       "      <td>341.0</td>\n",
       "      <td>1.2825</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8418</td>\n",
       "      <td>C1=CC=C2C=C3C=CC=CC3=CC2=C1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>1-methylanthracene</td>\n",
       "      <td>86.0</td>\n",
       "      <td>342.0</td>\n",
       "      <td>1.04799</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11884</td>\n",
       "      <td>CC1=CC=CC2=CC3=CC=CC=C3C=C12</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>2-methylanthracene</td>\n",
       "      <td>209.0</td>\n",
       "      <td>340.0</td>\n",
       "      <td>1.8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11936</td>\n",
       "      <td>CC1=CC2=CC3=CC=CC=C3C=C2C=C1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Class of hydrocarbon              IUPAC name  Melting point  Boiling point  \\\n",
       "0       Trimetylalkane  2,2,4-Trimethylpentane         -107.0           99.0   \n",
       "1         Triaromatics            Phenanthrene           99.0          338.0   \n",
       "2         Triaromatics              Anthracene          216.0          341.0   \n",
       "3         Triaromatics      1-methylanthracene           86.0          342.0   \n",
       "4         Triaromatics      2-methylanthracene          209.0          340.0   \n",
       "\n",
       "  Density@20å¡C* Flash point Autoignition temp  pubchem_id  \\\n",
       "0           0.69         NaN               396       10907   \n",
       "1           1.18         171              >450         995   \n",
       "2         1.2825         NaN               NaN        8418   \n",
       "3        1.04799         NaN               NaN       11884   \n",
       "4            1.8         NaN               NaN       11936   \n",
       "\n",
       "                          smiles  \n",
       "0                 CC(C)CC(C)(C)C  \n",
       "1  C1=CC=C2C(=C1)C=CC3=CC=CC=C32  \n",
       "2    C1=CC=C2C=C3C=CC=CC3=CC2=C1  \n",
       "3   CC1=CC=CC2=CC3=CC=CC=C3C=C12  \n",
       "4   CC1=CC2=CC3=CC=CC=C3C=C2C=C1  "
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv(\"data/hydrocarbons.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "fea93cb9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use pandas tools to \n",
    "PandasTools.AddMoleculeColumnToFrame(df,'smiles', 'Molecule', includeFingerprints=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ae6424ff",
   "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>Class of hydrocarbon</th>\n",
       "      <th>IUPAC name</th>\n",
       "      <th>Melting point</th>\n",
       "      <th>Boiling point</th>\n",
       "      <th>Density@20å¡C*</th>\n",
       "      <th>Flash point</th>\n",
       "      <th>Autoignition temp</th>\n",
       "      <th>pubchem_id</th>\n",
       "      <th>smiles</th>\n",
       "      <th>Molecule</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Trimetylalkane</td>\n",
       "      <td>2,2,4-Trimethylpentane</td>\n",
       "      <td>-107.0</td>\n",
       "      <td>99.0</td>\n",
       "      <td>0.69</td>\n",
       "      <td>NaN</td>\n",
       "      <td>396</td>\n",
       "      <td>10907</td>\n",
       "      <td>CC(C)CC(C)(C)C</td>\n",
       "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7fc5f994c970&gt;</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>Phenanthrene</td>\n",
       "      <td>99.0</td>\n",
       "      <td>338.0</td>\n",
       "      <td>1.18</td>\n",
       "      <td>171</td>\n",
       "      <td>&gt;450</td>\n",
       "      <td>995</td>\n",
       "      <td>C1=CC=C2C(=C1)C=CC3=CC=CC=C32</td>\n",
       "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7fc5f994ca50&gt;</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>Anthracene</td>\n",
       "      <td>216.0</td>\n",
       "      <td>341.0</td>\n",
       "      <td>1.2825</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8418</td>\n",
       "      <td>C1=CC=C2C=C3C=CC=CC3=CC2=C1</td>\n",
       "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7fc5f994cba0&gt;</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>1-methylanthracene</td>\n",
       "      <td>86.0</td>\n",
       "      <td>342.0</td>\n",
       "      <td>1.04799</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11884</td>\n",
       "      <td>CC1=CC=CC2=CC3=CC=CC=C3C=C12</td>\n",
       "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7fc5f994ccf0&gt;</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Triaromatics</td>\n",
       "      <td>2-methylanthracene</td>\n",
       "      <td>209.0</td>\n",
       "      <td>340.0</td>\n",
       "      <td>1.8</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>11936</td>\n",
       "      <td>CC1=CC2=CC3=CC=CC=C3C=C2C=C1</td>\n",
       "      <td>&lt;rdkit.Chem.rdchem.Mol object at 0x7fc5f994cc80&gt;</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Class of hydrocarbon              IUPAC name  Melting point  Boiling point  \\\n",
       "0       Trimetylalkane  2,2,4-Trimethylpentane         -107.0           99.0   \n",
       "1         Triaromatics            Phenanthrene           99.0          338.0   \n",
       "2         Triaromatics              Anthracene          216.0          341.0   \n",
       "3         Triaromatics      1-methylanthracene           86.0          342.0   \n",
       "4         Triaromatics      2-methylanthracene          209.0          340.0   \n",
       "\n",
       "  Density@20å¡C* Flash point Autoignition temp  pubchem_id  \\\n",
       "0           0.69         NaN               396       10907   \n",
       "1           1.18         171              >450         995   \n",
       "2         1.2825         NaN               NaN        8418   \n",
       "3        1.04799         NaN               NaN       11884   \n",
       "4            1.8         NaN               NaN       11936   \n",
       "\n",
       "                          smiles  \\\n",
       "0                 CC(C)CC(C)(C)C   \n",
       "1  C1=CC=C2C(=C1)C=CC3=CC=CC=C32   \n",
       "2    C1=CC=C2C=C3C=CC=CC3=CC2=C1   \n",
       "3   CC1=CC=CC2=CC3=CC=CC=C3C=C12   \n",
       "4   CC1=CC2=CC3=CC=CC=C3C=C2C=C1   \n",
       "\n",
       "                                           Molecule  \n",
       "0  <rdkit.Chem.rdchem.Mol object at 0x7fc5f994c970>  \n",
       "1  <rdkit.Chem.rdchem.Mol object at 0x7fc5f994ca50>  \n",
       "2  <rdkit.Chem.rdchem.Mol object at 0x7fc5f994cba0>  \n",
       "3  <rdkit.Chem.rdchem.Mol object at 0x7fc5f994ccf0>  \n",
       "4  <rdkit.Chem.rdchem.Mol object at 0x7fc5f994cc80>  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "18c4a53a",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Retrieve some descriptors\n",
    "\n",
    "descriptors_df = pd.DataFrame()\n",
    "descriptors_df[\"Melting point\"] = df[\"Melting point\"].copy()\n",
    "\n",
    "descriptors_df[\"molecular_weight\"] = df[\"Molecule\"].apply(Chem.Descriptors.MolWt)\n",
    "descriptors_df[\"num_aromatic_rings\"] = df[\"Molecule\"].apply(Chem.Descriptors.NumAromaticRings)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "1590653a",
   "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>Melting point</th>\n",
       "      <th>molecular_weight</th>\n",
       "      <th>num_aromatic_rings</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-107.0</td>\n",
       "      <td>114.232</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>99.0</td>\n",
       "      <td>178.234</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>216.0</td>\n",
       "      <td>178.234</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>86.0</td>\n",
       "      <td>192.261</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>209.0</td>\n",
       "      <td>192.261</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Melting point  molecular_weight  num_aromatic_rings\n",
       "0         -107.0           114.232                   0\n",
       "1           99.0           178.234                   3\n",
       "2          216.0           178.234                   3\n",
       "3           86.0           192.261                   3\n",
       "4          209.0           192.261                   3"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "descriptors_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c3dbb6b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "descriptors_melt = descriptors_df.melt(id_vars=\"Melting point\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "405b05a5",
   "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>Melting point</th>\n",
       "      <th>variable</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-107.0</td>\n",
       "      <td>molecular_weight</td>\n",
       "      <td>114.232</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>99.0</td>\n",
       "      <td>molecular_weight</td>\n",
       "      <td>178.234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>216.0</td>\n",
       "      <td>molecular_weight</td>\n",
       "      <td>178.234</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>86.0</td>\n",
       "      <td>molecular_weight</td>\n",
       "      <td>192.261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>209.0</td>\n",
       "      <td>molecular_weight</td>\n",
       "      <td>192.261</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Melting point          variable    value\n",
       "0         -107.0  molecular_weight  114.232\n",
       "1           99.0  molecular_weight  178.234\n",
       "2          216.0  molecular_weight  178.234\n",
       "3           86.0  molecular_weight  192.261\n",
       "4          209.0  molecular_weight  192.261"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "descriptors_melt.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "38873dc2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "g = sns.lmplot(data=descriptors_melt, y=\"Melting point\", x=\"value\", col=\"variable\", col_wrap=2, facet_kws={\"sharex\": False})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "64953c7d",
   "metadata": {},
   "source": [
    "## Linear and Multilinear Regression Using SciKitLearn\n",
    "\n",
    "Use this section to perform linear or multilinear regression using scikitlearn."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aa6f6bf7",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "eb9ff67c",
   "metadata": {},
   "source": [
    "## Fitting with Random Forest"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "322fe63f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a5a7045",
   "metadata": {},
   "outputs": [],
   "source": [
    "analyze = df.dropna(axis=0, subset=\"Melting point\")\n",
    "\n",
    "X = analyze[[\"molecular_weight\", \"num_aromatic_rings\"]].to_numpy()\n",
    "Y = analyze[\"Melting point\"].to_numpy()\n",
    "\n",
    "X_train, X_test, Y_train, Y_test = train_test_split(X, Y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1edd6288",
   "metadata": {},
   "outputs": [],
   "source": [
    "random_forest_model = RandomForestRegressor().fit(X_train, Y_train)\n",
    "yerr = random_forest_model.score(X_test, Y_test)\n",
    "print(yerr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "94feef15",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = random_forest_model.predict(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "4005b847",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure()\n",
    "plt.scatter(Y, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "32ff2375",
   "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": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}