notebooks/2_eda_physprop.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# EDA of physprop.xlsx\n",
    "\n",
    "## Summary\n",
    "\n",
    "1. Experimental logP are 13553 out of total 41039 rows.\n",
    "2. There are 97% NA values for Temperature. (99% in experimental data)\n",
    "3. There is no pH column.\n",
    "4. Most of the molecules are unique. There is only 22 full duplicates in experimental data and 24 rows with equal molecules.\n",
    "5. There was 1 row with NaN SMILES info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "import sys\n",
    "#!conda install --yes --prefix {sys.prefix} xlrd\n",
    "\n",
    "PHYSPROP_DATA_FILE_PATH = \"../data/raw/physprop.xls\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "def check_na(df, column):\n",
    "    n = df.shape[0]\n",
    "    num_of_na = df[column].isna().sum()\n",
    "    frac_of_na = int(100.0*(num_of_na / n))\n",
    "    print(\"# of NA values \" + column + \": \" + str(num_of_na) + \", \" + str(frac_of_na) + \"%\")\n",
    "    print(df[df[column].isna()].head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>CAS #</th>\n",
       "      <th>Formula</th>\n",
       "      <th>Mol Weight</th>\n",
       "      <th>Chemical Name</th>\n",
       "      <th>WS (mg/L)</th>\n",
       "      <th>WS_temp</th>\n",
       "      <th>WS_type</th>\n",
       "      <th>WS_reference</th>\n",
       "      <th>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "      <th>...</th>\n",
       "      <th>OH (cm3/molecule-sec)</th>\n",
       "      <th>OH_temp</th>\n",
       "      <th>OH_type</th>\n",
       "      <th>OH_reference</th>\n",
       "      <th>BP_pressure (mm Hg)</th>\n",
       "      <th>MP (deg C)</th>\n",
       "      <th>BP (deg C)</th>\n",
       "      <th>FP (deg C)</th>\n",
       "      <th>SMILES</th>\n",
       "      <th>Unnamed: 33</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>000050-00-0</td>\n",
       "      <td>CH2O</td>\n",
       "      <td>30.026</td>\n",
       "      <td>FORMALDEHYDE</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>20.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>PICKRELL,JA ET AL. (1983)</td>\n",
       "      <td>0.35</td>\n",
       "      <td>25.0</td>\n",
       "      <td>...</td>\n",
       "      <td>9.370000e-12</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>KWOK,ESC &amp; ATKINSON,R (1994)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-92</td>\n",
       "      <td>-19.1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>O=C</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>000050-01-1</td>\n",
       "      <td>CH6ClN3</td>\n",
       "      <td>95.532</td>\n",
       "      <td>Guanidine hydrochloride</td>\n",
       "      <td>1000000.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EST</td>\n",
       "      <td>MEYLAN,WM ET AL. (1996)</td>\n",
       "      <td>-3.56</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>2.100000e-11</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EST</td>\n",
       "      <td>MEYLAN,WM &amp; HOWARD,PH (1993)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>182.3</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NC(N)=N(H)(H)Cl</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>000050-02-2</td>\n",
       "      <td>C22H29FO5</td>\n",
       "      <td>392.470</td>\n",
       "      <td>DEXAMETHASONE</td>\n",
       "      <td>89.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>YALKOWSKY,SH &amp; DANNENFELSER,RM (1992)</td>\n",
       "      <td>1.83</td>\n",
       "      <td>25.0</td>\n",
       "      <td>...</td>\n",
       "      <td>6.950100e-11</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EST</td>\n",
       "      <td>MEYLAN,WM &amp; HOWARD,PH (1993)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>262</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>000050-03-3</td>\n",
       "      <td>C23H32O6</td>\n",
       "      <td>404.510</td>\n",
       "      <td>HYDROCORTISONE ACETATE</td>\n",
       "      <td>14.1</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>YALKOWSKY,SH &amp; DANNENFELSER,RM (1992)</td>\n",
       "      <td>2.19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>1.128800e-10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EST</td>\n",
       "      <td>MEYLAN,WM &amp; HOWARD,PH (1993)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>223 dec</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>000050-04-4</td>\n",
       "      <td>C23H30O6</td>\n",
       "      <td>402.490</td>\n",
       "      <td>CORTISONE ACETATE</td>\n",
       "      <td>20.0</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>YALKOWSKY,SH &amp; DANNENFELSER,RM (1992)</td>\n",
       "      <td>2.10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>...</td>\n",
       "      <td>1.083400e-10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EST</td>\n",
       "      <td>MEYLAN,WM &amp; HOWARD,PH (1993)</td>\n",
       "      <td>NaN</td>\n",
       "      <td>222</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 34 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         CAS #    Formula  Mol Weight            Chemical Name  WS (mg/L)  \\\n",
       "0  000050-00-0       CH2O      30.026             FORMALDEHYDE   400000.0   \n",
       "1  000050-01-1    CH6ClN3      95.532  Guanidine hydrochloride  1000000.0   \n",
       "2  000050-02-2  C22H29FO5     392.470            DEXAMETHASONE       89.0   \n",
       "3  000050-03-3   C23H32O6     404.510   HYDROCORTISONE ACETATE       14.1   \n",
       "4  000050-04-4   C23H30O6     402.490        CORTISONE ACETATE       20.0   \n",
       "\n",
       "   WS_temp WS_type                           WS_reference  LogP  LogP_temp  \\\n",
       "0     20.0     EXP              PICKRELL,JA ET AL. (1983)  0.35       25.0   \n",
       "1     25.0     EST                MEYLAN,WM ET AL. (1996) -3.56        NaN   \n",
       "2     25.0     EXP  YALKOWSKY,SH & DANNENFELSER,RM (1992)  1.83       25.0   \n",
       "3     25.0     EXP  YALKOWSKY,SH & DANNENFELSER,RM (1992)  2.19        NaN   \n",
       "4     25.0     EXP  YALKOWSKY,SH & DANNENFELSER,RM (1992)  2.10       25.0   \n",
       "\n",
       "   ... OH (cm3/molecule-sec) OH_temp  OH_type                  OH_reference  \\\n",
       "0  ...          9.370000e-12    25.0      EXP  KWOK,ESC & ATKINSON,R (1994)   \n",
       "1  ...          2.100000e-11    25.0      EST  MEYLAN,WM & HOWARD,PH (1993)   \n",
       "2  ...          6.950100e-11    25.0      EST  MEYLAN,WM & HOWARD,PH (1993)   \n",
       "3  ...          1.128800e-10    25.0      EST  MEYLAN,WM & HOWARD,PH (1993)   \n",
       "4  ...          1.083400e-10    25.0      EST  MEYLAN,WM & HOWARD,PH (1993)   \n",
       "\n",
       "  BP_pressure (mm Hg) MP (deg C)  BP (deg C)  FP (deg C)  \\\n",
       "0                 NaN        -92       -19.1         NaN   \n",
       "1                 NaN      182.3         NaN         NaN   \n",
       "2                 NaN        262         NaN         NaN   \n",
       "3                 NaN    223 dec         NaN         NaN   \n",
       "4                 NaN        222         NaN         NaN   \n",
       "\n",
       "                                              SMILES Unnamed: 33  \n",
       "0                                                O=C         NaN  \n",
       "1                                    NC(N)=N(H)(H)Cl         NaN  \n",
       "2  C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...         NaN  \n",
       "3  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...         NaN  \n",
       "4  CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...         NaN  \n",
       "\n",
       "[5 rows x 34 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "physprop_data = pd.read_excel(PHYSPROP_DATA_FILE_PATH)\n",
    "physprop_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['CAS #', 'Formula', 'Mol Weight', 'Chemical Name', 'WS (mg/L)',\n",
       "       'WS_temp', 'WS_type', 'WS_reference', 'LogP', 'LogP_temp', 'LogP_type',\n",
       "       'LogP_reference', 'VP (mm Hg)', 'VP_temp', 'VP_type', 'VP_reference',\n",
       "       'DC_pKa', 'DC_temp', 'DC_type', 'DC_reference', 'HL (atm-m3/mole)',\n",
       "       'HL_temp', 'HL_type', 'HL_reference', 'OH (cm3/molecule-sec)',\n",
       "       'OH_temp', 'OH_type', 'OH_reference', 'BP_pressure (mm Hg)',\n",
       "       'MP (deg C)', 'BP (deg C)', 'FP (deg C)', 'SMILES', 'Unnamed: 33'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "physprop_data.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "      <th>LogP_type</th>\n",
       "      <th>SMILES</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.35</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>O=C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-3.56</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EST</td>\n",
       "      <td>NC(N)=N(H)(H)Cl</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.83</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>EXP</td>\n",
       "      <td>C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>EXP</td>\n",
       "      <td>CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   LogP  LogP_temp LogP_type  \\\n",
       "0  0.35       25.0       EXP   \n",
       "1 -3.56        NaN       EST   \n",
       "2  1.83       25.0       EXP   \n",
       "3  2.19        NaN       EXP   \n",
       "4  2.10       25.0       EXP   \n",
       "\n",
       "                                              SMILES  \n",
       "0                                                O=C  \n",
       "1                                    NC(N)=N(H)(H)Cl  \n",
       "2  C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...  \n",
       "3  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...  \n",
       "4  CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...  "
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "physprop_logp_data = physprop_data[['LogP', 'LogP_temp', 'LogP_type', 'SMILES']]\n",
    "physprop_logp_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(41039, 4)\n"
     ]
    }
   ],
   "source": [
    "print(physprop_logp_data.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of NA values LogP_temp: 40122, 97%\n",
      "   LogP  LogP_temp LogP_type  \\\n",
      "1 -3.56        NaN       EST   \n",
      "3  2.19        NaN       EXP   \n",
      "5  1.47        NaN       EXP   \n",
      "6 -0.40        NaN       EXP   \n",
      "7 -1.60        NaN       EST   \n",
      "\n",
      "                                              SMILES  \n",
      "1                                    NC(N)=N(H)(H)Cl  \n",
      "3  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...  \n",
      "5                     CCC1(C(=O)NC(=O)NC1=O)c2ccccc2  \n",
      "6  O=C1C(N)=C(C)C(=O)C2=C1C(COC(=O)N)C3(OC)C(N4)C...  \n",
      "7              O=C1N=C(O[Na])N(C)C(=O)C1(C)C2=CCCCC2  \n"
     ]
    }
   ],
   "source": [
    "check_na(physprop_logp_data, 'LogP_temp')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "      <th>SMILES</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.35</td>\n",
       "      <td>25.0</td>\n",
       "      <td>O=C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.83</td>\n",
       "      <td>25.0</td>\n",
       "      <td>C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.47</td>\n",
       "      <td>NaN</td>\n",
       "      <td>CCC1(C(=O)NC(=O)NC1=O)c2ccccc2</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   LogP  LogP_temp                                             SMILES\n",
       "0  0.35       25.0                                                O=C\n",
       "2  1.83       25.0  C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...\n",
       "3  2.19        NaN  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...\n",
       "4  2.10       25.0  CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...\n",
       "5  1.47        NaN                     CCC1(C(=O)NC(=O)NC1=O)c2ccccc2"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data = physprop_logp_data[physprop_logp_data['LogP_type'] == 'EXP']\n",
    "exp_physprop_logp_data = exp_physprop_logp_data.drop(['LogP_type'], axis=1)\n",
    "exp_physprop_logp_data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(13553, 3)\n"
     ]
    }
   ],
   "source": [
    "print(exp_physprop_logp_data.shape)\n",
    "LOGP_COLUMN = 'LogP'\n",
    "LOGP_TEMP_COLUMN = 'LogP_temp'\n",
    "SMILES_COLUMN = 'SMILES'\n",
    "n = exp_physprop_logp_data.shape[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of NA values SMILES: 1, 0%\n",
      "       LogP  LogP_temp SMILES\n",
      "20325   5.5        NaN    NaN\n"
     ]
    }
   ],
   "source": [
    "check_na(exp_physprop_logp_data, SMILES_COLUMN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "exp_physprop_logp_data = exp_physprop_logp_data[exp_physprop_logp_data[SMILES_COLUMN].notna()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of NA values SMILES: 0, 0%\n",
      "Empty DataFrame\n",
      "Columns: [LogP, LogP_temp, SMILES]\n",
      "Index: []\n"
     ]
    }
   ],
   "source": [
    "check_na(exp_physprop_logp_data, SMILES_COLUMN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of NA values LogP: 0, 0%\n",
      "Empty DataFrame\n",
      "Columns: [LogP, LogP_temp, SMILES]\n",
      "Index: []\n"
     ]
    }
   ],
   "source": [
    "check_na(exp_physprop_logp_data, LOGP_COLUMN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "# of NA values LogP_temp: 13439, 99%\n",
      "    LogP  LogP_temp                                             SMILES\n",
      "3   2.19        NaN  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...\n",
      "5   1.47        NaN                     CCC1(C(=O)NC(=O)NC1=O)c2ccccc2\n",
      "6  -0.40        NaN  O=C1C(N)=C(C)C(=O)C2=C1C(COC(=O)N)C3(OC)C(N4)C...\n",
      "10  1.69        NaN                       CCC1(NC(=O)N(C)C1=O)c2ccccc2\n",
      "13  0.63        NaN                          C1CCNP(=O)(N(CCCl)CCCl)O1\n"
     ]
    }
   ],
   "source": [
    "check_na(exp_physprop_logp_data, LOGP_TEMP_COLUMN)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "22"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "exp_physprop_logp_data = exp_physprop_logp_data.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(13530, 3)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "13396"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data[SMILES_COLUMN].unique().size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>SMILES</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>C(=CC)C</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C(=CC=C)C</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C(=CCC(C(=C)C)C1)(C1)C</th>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C(=CCl)CCl</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C(=CCl)Cl</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c1ccccc1C(OC)C(C)NC</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c1ccccc1C2C(N)C2</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c1ccccc1C2OCC3C(c4ccccc4)=NOC3CO2</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c1ccccc1CCCC(C)Oc2cc(OC(=O)C)c3C4CC(O)CCC4C(C)Nc3c2</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c1ncccc1C2CC(O)C(=O)N2C</th>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>114 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                    LogP  LogP_temp\n",
       "SMILES                                                             \n",
       "C(=CC)C                                                2          1\n",
       "C(=CC=C)C                                              2          0\n",
       "C(=CCC(C(=C)C)C1)(C1)C                                 2          1\n",
       "C(=CCl)CCl                                             2          0\n",
       "C(=CCl)Cl                                              3          0\n",
       "...                                                  ...        ...\n",
       "c1ccccc1C(OC)C(C)NC                                    2          0\n",
       "c1ccccc1C2C(N)C2                                       2          0\n",
       "c1ccccc1C2OCC3C(c4ccccc4)=NOC3CO2                      2          0\n",
       "c1ccccc1CCCC(C)Oc2cc(OC(=O)C)c3C4CC(O)CCC4C(C)N...     2          0\n",
       "c1ncccc1C2CC(O)C(=O)N2C                                2          0\n",
       "\n",
       "[114 rows x 2 columns]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data[exp_physprop_logp_data[SMILES_COLUMN].duplicated(keep=False)].groupby(SMILES_COLUMN).count()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "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>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "      <th>SMILES</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1160</th>\n",
       "      <td>4.83</td>\n",
       "      <td>25.0</td>\n",
       "      <td>C(C(CC1C2)C1(C)C)(=C2)C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20246</th>\n",
       "      <td>4.48</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C(C(CC1C2)C1(C)C)(=C2)C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20249</th>\n",
       "      <td>4.44</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C(C(CC1C2)C1(C)C)(=C2)C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       LogP  LogP_temp                   SMILES\n",
       "1160   4.83       25.0  C(C(CC1C2)C1(C)C)(=C2)C\n",
       "20246  4.48        NaN  C(C(CC1C2)C1(C)C)(=C2)C\n",
       "20249  4.44        NaN  C(C(CC1C2)C1(C)C)(=C2)C"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exp_physprop_logp_data[exp_physprop_logp_data[SMILES_COLUMN] == \"C(C(CC1C2)C1(C)C)(=C2)C\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x7f5a3cc4be50>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.distplot(exp_physprop_logp_data[LOGP_COLUMN])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "PROCESSED_PATH = \"../data/1_filtering/physprop.csv\"\n",
    "\n",
    "exp_physprop_logp_data.to_csv(PROCESSED_PATH)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "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>LogP</th>\n",
       "      <th>LogP_temp</th>\n",
       "      <th>SMILES</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.35</td>\n",
       "      <td>25.0</td>\n",
       "      <td>O=C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.83</td>\n",
       "      <td>25.0</td>\n",
       "      <td>C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2.19</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2.10</td>\n",
       "      <td>25.0</td>\n",
       "      <td>CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>1.47</td>\n",
       "      <td>NaN</td>\n",
       "      <td>CCC1(C(=O)NC(=O)NC1=O)c2ccccc2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40996</th>\n",
       "      <td>5.77</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ClC1(Cl)C2(C(Cl)Cl)C(Cl)C(Cl)C(C2(C(Cl)Cl)CCl)C1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40997</th>\n",
       "      <td>5.93</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ClC1C2(C(Cl)Cl)C(Cl)C(Cl)C(C2(C(Cl)Cl)CCl)C1Cl</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40998</th>\n",
       "      <td>6.64</td>\n",
       "      <td>NaN</td>\n",
       "      <td>ClC1(Cl)C2(C(Cl)Cl)C(Cl)C(Cl)(Cl)C(C2(C(Cl)Cl)...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40999</th>\n",
       "      <td>2.42</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1=C(C)C(=O)C2C(C)(C)C2C1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>41000</th>\n",
       "      <td>3.20</td>\n",
       "      <td>NaN</td>\n",
       "      <td>C1CC(C(C)=C)CC(O2)C12C</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>13530 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       LogP  LogP_temp                                             SMILES\n",
       "0      0.35       25.0                                                O=C\n",
       "2      1.83       25.0  C1(=O)C=C2CCC3C4CC(C)C(O)(C(=O)CO)C4(C)CC(O)C3...\n",
       "3      2.19        NaN  C1C(=O)C=C2CCC3C4CCC(O)(C(=O)COC(=O)C)C4(C)CC(...\n",
       "4      2.10       25.0  CC(=O)OCC(=O)C3(O)CCC4C2CCC1=CC(=O)CCC1(C)C2C(...\n",
       "5      1.47        NaN                     CCC1(C(=O)NC(=O)NC1=O)c2ccccc2\n",
       "...     ...        ...                                                ...\n",
       "40996  5.77        NaN   ClC1(Cl)C2(C(Cl)Cl)C(Cl)C(Cl)C(C2(C(Cl)Cl)CCl)C1\n",
       "40997  5.93        NaN     ClC1C2(C(Cl)Cl)C(Cl)C(Cl)C(C2(C(Cl)Cl)CCl)C1Cl\n",
       "40998  6.64        NaN  ClC1(Cl)C2(C(Cl)Cl)C(Cl)C(Cl)(Cl)C(C2(C(Cl)Cl)...\n",
       "40999  2.42        NaN                          C1=C(C)C(=O)C2C(C)(C)C2C1\n",
       "41000  3.20        NaN                             C1CC(C(C)=C)CC(O2)C12C\n",
       "\n",
       "[13530 rows x 3 columns]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.read_csv(PROCESSED_PATH, index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}