{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "d841f273",
   "metadata": {},
   "source": [
    "# AutoML for Classification Model Screening\n",
    "\n",
    "The following are the steps for using AutoML for a classification task:\n",
    "\n",
    "\n",
    "1. Provide an input pandas dataframe consisting of two columns:<br>\n",
    "    * SMILES strings<br>\n",
    "    * target class values<br>\n",
    "\n",
    "\n",
    "2. If featurization = True, Molecules are represented as:<br>\n",
    "    * Coulomb matrix<br>\n",
    "    * RDKit Morgan (ECFP6 1024-bit) fingerprints<br>\n",
    "    * MACCs keys<br>\n",
    "    * RDKit hashed topological torsion<br>\n",
    "    * RDKit molecular descriptors (all)<br>\n",
    "    * Mordred molecular descriptors<br>\n",
    "    \n",
    "    If featurization=False, a feature set must be provided by the user.\n",
    "\n",
    "\n",
    "3. Screens through various classifier models:<br>\n",
    "    * Single-core (runs regardless of multi_core value):\n",
    "        * [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html)<br>\n",
    "        * [DecisionTreeClassifier](https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeClassifier.html)<br>\n",
    "        * [SVC](https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html)<br>\n",
    "        * [KNeighboursClassifier](https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsClassifier.html)<br>\n",
    "    * Multi-core(set multi_core=True):\n",
    "        * [RandomForestClassifier](https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestClassifier.html)<br>\n",
    "        * [ChemML_MLP](https://hachmannlab.github.io/chemml/ipython_notebooks/ml_model.html) (if n_datapoints>500)<br>\n",
    "        * (optional) [XGBClassifier](https://xgboost.readthedocs.io/en/latest/python/python_api.html)<br>\n",
    "        * (optional) [LightGBM](https://lightgbm.readthedocs.io/en/stable/)\n",
    "\n",
    "Yields 'n-best' models, with optimized hyperparamters.\n",
    "\n",
    "The output_dir argument specifies a folder that will be created wherever the code is run from, containing the following directory tree:\n",
    "\n",
    "<pre> &lt;output_dir&gt;/<br> |-- output.log<br> |-- scores.csv<br> |-- best_model/<br> |   |-- model.pkl # most non-MLP models<br> |   |-- model_chemml_model.json # MLP case (plus possible extra model files)<br> |   |-- scaler.pkl # present when scaler exists for chosen feature_key<br> |   |-- feature_order.json<br> |   |-- metadata.json<br> |-- .model_screener_artifacts/<br> |   |-- &lt;run_key_1&gt;/<br> |        |-- model.pkl # or MLP artifact files<br> |   |-- &lt;run_key_2&gt;/<br>... </pre>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a2ea142",
   "metadata": {},
   "source": [
    "## Load your data \n",
    "\n",
    "We are using ChemML's in-built dataset to demonstrate the minimum requirements to run AutoML."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3186feee",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from chemml.datasets import load_organic_density"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "56240d5a",
   "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>density_Kg/m3</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>361</th>\n",
       "      <td>c1scc(n1)c1ncc(s1)c1c(ccc2c1cccc2)c1cncs1</td>\n",
       "      <td>1328.35</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>73</th>\n",
       "      <td>S1CC(SC(C1)C1CCCC1)c1cocc1c1ccccc1</td>\n",
       "      <td>1143.80</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>374</th>\n",
       "      <td>N1CNC(NC1)c1sccc1C1(CSCCS1)c1cccs1</td>\n",
       "      <td>1351.33</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>c1nc(c(s1)c1nsnc1)c1csc(n1)c1cccs1</td>\n",
       "      <td>1466.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>104</th>\n",
       "      <td>Oc1ccc2c(c1c1cocc1)c(ccc2)c1ccccn1</td>\n",
       "      <td>1207.67</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>248</th>\n",
       "      <td>Oc1ncc(c(c1)C)c1cnccn1</td>\n",
       "      <td>1195.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>Sc1cc2ccccc2c(c1)c1cnccc1c1cnccn1</td>\n",
       "      <td>1213.41</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>92</th>\n",
       "      <td>c1sc(c(c1)c1ncccc1c1nsnc1)c1ccc2c(c1)cccc2</td>\n",
       "      <td>1264.16</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>152</th>\n",
       "      <td>N1CNC(NC1)(N1CNC(NC1)c1cncs1)c1cccc2c1cccc2</td>\n",
       "      <td>1270.40</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>367</th>\n",
       "      <td>C1CSC(CS1)C1(CSC(CS1)c1ccc2c(c1)cccc2)c1cnccn1</td>\n",
       "      <td>1268.28</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>200 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                             smiles  density_Kg/m3\n",
       "361       c1scc(n1)c1ncc(s1)c1c(ccc2c1cccc2)c1cncs1        1328.35\n",
       "73               S1CC(SC(C1)C1CCCC1)c1cocc1c1ccccc1        1143.80\n",
       "374              N1CNC(NC1)c1sccc1C1(CSCCS1)c1cccs1        1351.33\n",
       "155              c1nc(c(s1)c1nsnc1)c1csc(n1)c1cccs1        1466.57\n",
       "104              Oc1ccc2c(c1c1cocc1)c(ccc2)c1ccccn1        1207.67\n",
       "..                                              ...            ...\n",
       "248                          Oc1ncc(c(c1)C)c1cnccn1        1195.16\n",
       "145               Sc1cc2ccccc2c(c1)c1cnccc1c1cnccn1        1213.41\n",
       "92       c1sc(c(c1)c1ncccc1c1nsnc1)c1ccc2c(c1)cccc2        1264.16\n",
       "152     N1CNC(NC1)(N1CNC(NC1)c1cncs1)c1cccc2c1cccc2        1270.40\n",
       "367  C1CSC(CS1)C1(CSC(CS1)c1ccc2c(c1)cccc2)c1cnccn1        1268.28\n",
       "\n",
       "[200 rows x 2 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "molecules, target, dragon_subset = load_organic_density()\n",
    "df=pd.concat([molecules, target], axis=1)\n",
    "df = df.sample(200, random_state=42)\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e0fa0dbf",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Labeling data for classification instead of regression\n",
    "# Note: This is just for demonstration purposes. In practice, you would want to use a regression model for predicting density.\n",
    "df['density_class'] = pd.qcut(df['density_Kg/m3'], q=3, labels=range(3))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "61cdf76b",
   "metadata": {},
   "source": [
    "## Run autoML for a classification task"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "97133962",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "-------------------------ChemML AutoML Model Screening-------------------------\n",
      "\n",
      "-------------------------Model screening started at Mon Aug 31 01:28:19 2026-------------------------\n",
      "\n",
      "\n",
      "\n",
      "Converting SMILES to ChemML Molecule objects...\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Converting SMILES to ChemML Molecule objects: 100%|██████████| 200/200 [00:06<00:00, 28.92it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Generating Coulomb matrix representation...\n",
      "\n",
      "featurizing molecules in batches of 12 ...\n",
      "\u001b[1m200/200\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m14s\u001b[0m 69ms/step \n",
      "Merging batch features ...    [DONE]\n",
      "\n",
      "Generating RDKit fingerprint representations...\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Generating Morgan Fingerprints: 100%|██████████| 200/200 [00:00<00:00, 10268.08molecule/s]\n",
      "Generating MACCS Fingerprints: 100%|██████████| 200/200 [00:00<00:00, 998.62molecule/s] \n",
      "Generating Hashed Topological Torsion Fingerprints: 100%|██████████| 200/200 [00:00<00:00, 8634.43molecule/s]\n",
      "Generating Atom Pair Fingerprints: 100%|██████████| 200/200 [00:00<00:00, 9262.83molecule/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Generating RDKit descriptor representations...\n",
      "\n",
      "Step 1: Normalizing molecule input\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Step 2: Calculating RDKit descriptors: 100%|██████████| 200/200 [00:02<00:00, 95.34it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Generating Mordred descriptor representations...\n",
      "\n",
      "Step 1: Normalizing molecule input\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Normalizing Molecule input: 100%|██████████| 200/200 [00:00<?, ?it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Step 2/3: Optimizing geometry for 3D descriptor calculation\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "3D geometry already exists, loading geometry: 100%|██████████| 200/200 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Step 3/3: Calculating Mordred descriptors\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "100%|██████████| 200/200 [00:06<00:00, 31.55it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Cleaning feature sets to remove constant, highly correlated, low-variance, and complex features...\n",
      "\n",
      "Feature set 'CoulombMatrix' cleaned: 25 features retained.\n",
      "\n",
      "Feature set 'morganfingerprints_radius3' cleaned: 252 features retained.\n",
      "\n",
      "Feature set 'MACCS_radius3' cleaned: 48 features retained.\n",
      "\n",
      "Feature set 'hashedtopologicaltorsion_radius3' cleaned: 76 features retained.\n",
      "\n",
      "Feature set 'hashedatompair_radius3' cleaned: 421 features retained.\n",
      "\n",
      "Feature set 'rdkit_descriptors' cleaned: 90 features retained.\n",
      "\n",
      "Feature set 'mord_descriptors' cleaned: 530 features retained.\n",
      "\n",
      "\n",
      "-------------------------Run parameters-------------------------\n",
      "  Featurization: True\n",
      "  Multi_core: False\n",
      "  Screener_type: classifier\n",
      "  Number of datapoints: 200\n",
      "  Note: Dataset <= 500 samples; MLP is excluded from screening due to inefficiency.\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set CoulombMatrix, time taken: 16.359 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set morganfingerprints_radius3, time taken: 13.086 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set MACCS_radius3, time taken: 12.781 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set hashedtopologicaltorsion_radius3, time taken: 12.867 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set hashedatompair_radius3, time taken: 14.05 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set rdkit_descriptors, time taken: 12.805 seconds -------------------------\n",
      "\n",
      "split done!\n",
      "Single-core complete \n",
      "\n",
      "\n",
      "------------------------- Screening complete for feature set mord_descriptors, time taken: 16.855 seconds -------------------------\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from chemml.autoML import ModelScreener\n",
    "\n",
    "output_dir = \"automl_results_class\"\n",
    "\n",
    "MS = ModelScreener(df, target=\"density_class\", featurization=True, cache_features=False, smiles=\"smiles\", \n",
    "                   screener_type=\"classifier\", output_dir=output_dir)\n",
    "scores = MS.screen_models(n_best=10, multi_core=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "77ceb22b",
   "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>Model</th>\n",
       "      <th>Accuracy</th>\n",
       "      <th>Recall</th>\n",
       "      <th>Precision</th>\n",
       "      <th>F1-score</th>\n",
       "      <th>time(seconds)</th>\n",
       "      <th>parameters</th>\n",
       "      <th>Feature</th>\n",
       "      <th>run_key</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>LogisticRegression</td>\n",
       "      <td>0.8</td>\n",
       "      <td>0.793651</td>\n",
       "      <td>0.844444</td>\n",
       "      <td>0.797587</td>\n",
       "      <td>9.955029</td>\n",
       "      <td>[{'C': 0.1, 'class_weight': None, 'dual': Fals...</td>\n",
       "      <td>mord_descriptors</td>\n",
       "      <td>LogisticRegression_mord_descriptors_324dd7b551...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>KNeighborsClassifier</td>\n",
       "      <td>0.75</td>\n",
       "      <td>0.746032</td>\n",
       "      <td>0.811111</td>\n",
       "      <td>0.758371</td>\n",
       "      <td>6.259871</td>\n",
       "      <td>[{'algorithm': 'auto', 'leaf_size': 30, 'metri...</td>\n",
       "      <td>mord_descriptors</td>\n",
       "      <td>KNeighborsClassifier_mord_descriptors_1e7fa7c1...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>DecisionTreeClassifier</td>\n",
       "      <td>0.7</td>\n",
       "      <td>0.690476</td>\n",
       "      <td>0.763889</td>\n",
       "      <td>0.694444</td>\n",
       "      <td>3.405225</td>\n",
       "      <td>[{'ccp_alpha': 0.0, 'class_weight': None, 'cri...</td>\n",
       "      <td>mord_descriptors</td>\n",
       "      <td>DecisionTreeClassifier_mord_descriptors_6a4d98...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>LogisticRegression</td>\n",
       "      <td>0.65</td>\n",
       "      <td>0.642857</td>\n",
       "      <td>0.662963</td>\n",
       "      <td>0.646562</td>\n",
       "      <td>7.150034</td>\n",
       "      <td>[{'C': 42.16315789473685, 'class_weight': None...</td>\n",
       "      <td>hashedatompair_radius3</td>\n",
       "      <td>LogisticRegression_hashedatompair_radius3_c444...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>SVC</td>\n",
       "      <td>0.6</td>\n",
       "      <td>0.595238</td>\n",
       "      <td>0.604762</td>\n",
       "      <td>0.597691</td>\n",
       "      <td>2.851144</td>\n",
       "      <td>[{'C': 0.0037926901907322525, 'break_ties': Fa...</td>\n",
       "      <td>hashedatompair_radius3</td>\n",
       "      <td>SVC_hashedatompair_radius3_ef5a1fb731b9493682d...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>KNeighborsClassifier</td>\n",
       "      <td>0.55</td>\n",
       "      <td>0.563492</td>\n",
       "      <td>0.541667</td>\n",
       "      <td>0.545788</td>\n",
       "      <td>5.889152</td>\n",
       "      <td>[{'algorithm': 'auto', 'leaf_size': 30, 'metri...</td>\n",
       "      <td>hashedtopologicaltorsion_radius3</td>\n",
       "      <td>KNeighborsClassifier_hashedtopologicaltorsion_...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>DecisionTreeClassifier</td>\n",
       "      <td>0.5</td>\n",
       "      <td>0.507937</td>\n",
       "      <td>0.541667</td>\n",
       "      <td>0.505628</td>\n",
       "      <td>1.434301</td>\n",
       "      <td>[{'ccp_alpha': 0.0, 'class_weight': None, 'cri...</td>\n",
       "      <td>hashedatompair_radius3</td>\n",
       "      <td>DecisionTreeClassifier_hashedatompair_radius3_...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                     Model Accuracy    Recall Precision  F1-score  \\\n",
       "27      LogisticRegression      0.8  0.793651  0.844444  0.797587   \n",
       "26    KNeighborsClassifier     0.75  0.746032  0.811111  0.758371   \n",
       "24  DecisionTreeClassifier      0.7  0.690476  0.763889  0.694444   \n",
       "19      LogisticRegression     0.65  0.642857  0.662963  0.646562   \n",
       "17                     SVC      0.6  0.595238  0.604762  0.597691   \n",
       "15    KNeighborsClassifier     0.55  0.563492  0.541667  0.545788   \n",
       "16  DecisionTreeClassifier      0.5  0.507937  0.541667  0.505628   \n",
       "\n",
       "   time(seconds)                                         parameters  \\\n",
       "27      9.955029  [{'C': 0.1, 'class_weight': None, 'dual': Fals...   \n",
       "26      6.259871  [{'algorithm': 'auto', 'leaf_size': 30, 'metri...   \n",
       "24      3.405225  [{'ccp_alpha': 0.0, 'class_weight': None, 'cri...   \n",
       "19      7.150034  [{'C': 42.16315789473685, 'class_weight': None...   \n",
       "17      2.851144  [{'C': 0.0037926901907322525, 'break_ties': Fa...   \n",
       "15      5.889152  [{'algorithm': 'auto', 'leaf_size': 30, 'metri...   \n",
       "16      1.434301  [{'ccp_alpha': 0.0, 'class_weight': None, 'cri...   \n",
       "\n",
       "                             Feature  \\\n",
       "27                  mord_descriptors   \n",
       "26                  mord_descriptors   \n",
       "24                  mord_descriptors   \n",
       "19            hashedatompair_radius3   \n",
       "17            hashedatompair_radius3   \n",
       "15  hashedtopologicaltorsion_radius3   \n",
       "16            hashedatompair_radius3   \n",
       "\n",
       "                                              run_key  \n",
       "27  LogisticRegression_mord_descriptors_324dd7b551...  \n",
       "26  KNeighborsClassifier_mord_descriptors_1e7fa7c1...  \n",
       "24  DecisionTreeClassifier_mord_descriptors_6a4d98...  \n",
       "19  LogisticRegression_hashedatompair_radius3_c444...  \n",
       "17  SVC_hashedatompair_radius3_ef5a1fb731b9493682d...  \n",
       "15  KNeighborsClassifier_hashedtopologicaltorsion_...  \n",
       "16  DecisionTreeClassifier_hashedatompair_radius3_...  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "scores"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "35fd504e",
   "metadata": {},
   "source": [
    "## Validating AutoML-generated model\n",
    "\n",
    "Since ChemML v1.3.4, AutoML outputs the best model and required scaler and feature order as easy-to-import files. A quick demonstration of the model loading workflow is given below:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f527cd3a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "import json\n",
    "\n",
    "with open(f'{output_dir}/best_model/metadata.json', 'r') as f:\n",
    "    metadata = json.load(f)\n",
    "with open(f'{output_dir}/best_model/explanation.json', 'r') as f:\n",
    "    explanation = json.load(f)\n",
    "with open(f'{output_dir}/best_model/feature_order.json', 'r') as f:\n",
    "    feature_order = json.load(f)\n",
    "with open(f\"{output_dir}/best_model/model.pkl\", \"rb\") as f:\n",
    "    loaded_model = pickle.load(f)\n",
    "with open(f\"{output_dir}/best_model/scaler.pkl\", \"rb\") as f:\n",
    "    loaded_scaler = pickle.load(f)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c12e712d",
   "metadata": {},
   "source": [
    "Metadata isn't necessary for model validation, but gives us a lot of context from the AutoML screening workflow."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "b1127a85",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'artifact_schema_version': 1,\n",
       " 'model_name': 'LogisticRegression',\n",
       " 'feature_key': 'mord_descriptors',\n",
       " 'run_key': 'LogisticRegression_mord_descriptors_324dd7b551dd4d0e89563c3fa79868b8',\n",
       " 'screener_type': 'classifier',\n",
       " 'parameters': {'C': 0.1,\n",
       "  'class_weight': None,\n",
       "  'dual': False,\n",
       "  'fit_intercept': True,\n",
       "  'intercept_scaling': 1,\n",
       "  'l1_ratio': 0.0,\n",
       "  'max_iter': 100,\n",
       "  'n_jobs': None,\n",
       "  'penalty': 'deprecated',\n",
       "  'random_state': None,\n",
       "  'solver': 'sag',\n",
       "  'tol': 0.0001,\n",
       "  'verbose': 0,\n",
       "  'warm_start': False},\n",
       " 'n_folds': 5,\n",
       " 'n_datapoints': 200,\n",
       " 'metrics': {'Accuracy': 0.8,\n",
       "  'Recall': 0.7936507936507936,\n",
       "  'Precision': 0.8444444444444444,\n",
       "  'F1-score': 0.7975867269984916,\n",
       "  'time(seconds)': 9.955028772354126},\n",
       " 'model_serializer': 'pickle',\n",
       " 'model_artifact_dir': 'model_artifact',\n",
       " 'scaler_file': 'scaler.pkl',\n",
       " 'feature_order_file': 'feature_order.json',\n",
       " 'timestamp': 'Mon Aug 31 01:30:34 2026'}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "metadata"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c163ecf5",
   "metadata": {},
   "source": [
    "Explanation gives the user a list of feature importances alongside feature names; while not necessary for validation, this is useful to understand what features the model is actually using."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c0d50b6d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'model_type': 'LogisticRegression',\n",
       " 'explanation_type': 'linear.coef_',\n",
       " 'importance_values': {'BCUTs-1l': 0.12080837896578821,\n",
       "  'ATSC6s': 0.11705360020911237,\n",
       "  'BCUTdv-1l': 0.11643211939895474,\n",
       "  'MATS6s': 0.11176801885427924,\n",
       "  'MIC0': -0.10732155496149466,\n",
       "  'BCUTZ-1h': -0.10718923909200691,\n",
       "  'VSA_EState7': 0.10557335217812619,\n",
       "  'SM1_DzZ': -0.10481593783264181,\n",
       "  'MIC2': -0.10150151886248547,\n",
       "  'MDEC-22': 0.10067185163430138,\n",
       "  'PEOE_VSA4': -0.10042496013838315,\n",
       "  'Mor13': 0.09870373105961783,\n",
       "  'IC0': -0.09707281423378299,\n",
       "  'C2SP3': 0.09600380966243331,\n",
       "  'Mor19': 0.09434981175135433,\n",
       "  'IC2': -0.09216564338412887,\n",
       "  'Mor23v': -0.08944319176524317,\n",
       "  'WNSA4': 0.08883671204663847,\n",
       "  'Mor11m': 0.08859302230665116,\n",
       "  'nHetero': -0.08830107172063842,\n",
       "  'Mor21': -0.0877983270264638,\n",
       "  'nS': -0.0852109498551405,\n",
       "  'MATS1s': 0.0849868365554287,\n",
       "  'ATSC8i': -0.08486929913376605,\n",
       "  'Mor11v': 0.0843377479785362,\n",
       "  'PEOE_VSA6': 0.08371084437200652,\n",
       "  'GATS3Z': 0.08314941767103975,\n",
       "  'ZMIC4': -0.08291889991449908,\n",
       "  'SlogP_VSA11': -0.08264076194322785,\n",
       "  'Mor22': 0.0811945672039007,\n",
       "  'AATSC0Z': -0.08025587707186668,\n",
       "  'AATSC2Z': 0.07969179763267753,\n",
       "  'ATSC0Z': -0.07938387796472843,\n",
       "  'GATS1s': -0.0778363152307057,\n",
       "  'PNSA4': 0.07711466587068334,\n",
       "  'WNSA3': 0.07702985845556001,\n",
       "  'SMR_VSA5': 0.07635130453924953,\n",
       "  'ATS0Z': -0.07621573428909163,\n",
       "  'MIC1': -0.07537027853437128,\n",
       "  'Mor07v': 0.07493426507957587,\n",
       "  'ATSC2Z': 0.07423512895464822,\n",
       "  'Mor17': -0.07265706116251208,\n",
       "  'SM1_Dzse': -0.07258756393687768,\n",
       "  'Mor23m': -0.07243901248933617,\n",
       "  'AMID_h': -0.0715074895084047,\n",
       "  'Mor18': -0.07134081353269153,\n",
       "  'FNSA2': 0.07098238606356791,\n",
       "  'DPSA3': -0.07086776819047452,\n",
       "  'WNSA5': 0.07072208522949826,\n",
       "  'NaaS': -0.07011039127881565,\n",
       "  'Mor21m': -0.06984160210315588,\n",
       "  'Mor23': -0.06979633396704292,\n",
       "  'AATS5Z': -0.06776667525244524,\n",
       "  'DPSA4': -0.06743265563863299,\n",
       "  'AATS6Z': -0.0671288925307278,\n",
       "  'ATSC4c': -0.06709979041594832,\n",
       "  'Mor31': 0.06705804301418883,\n",
       "  'DPSA1': 0.06667074035047829,\n",
       "  'PNSA2': 0.06665612606226767,\n",
       "  'PNSA3': 0.06598975001498042,\n",
       "  'Mor07': 0.06558397866509244,\n",
       "  'ATSC6v': -0.06527858478714987,\n",
       "  'AATS0Z': -0.06513692171231619,\n",
       "  'RNCS': 0.06500833397631156,\n",
       "  'VSA_EState6': 0.06467998846396998,\n",
       "  'ATSC1s': 0.0639567175973236,\n",
       "  'SRW05': -0.06385335676797899,\n",
       "  'Mor03m': 0.0635536906752689,\n",
       "  'ZMIC2': 0.0633770766472029,\n",
       "  'ATSC1dv': 0.06315167855356948,\n",
       "  'Mor07m': 0.06299027299502238,\n",
       "  'PNSA1': -0.06284026238877223,\n",
       "  'MATS1c': 0.0627341979463412,\n",
       "  'SlogP_VSA5': 0.0625480201773812,\n",
       "  'GATS3p': 0.062294692738831585,\n",
       "  'Mor27': -0.06183006226945349,\n",
       "  'Mor06p': -0.061320930862255645,\n",
       "  'NsCH3': 0.061107468780475446,\n",
       "  'AATSC7i': 0.0609338990453993,\n",
       "  'Mor25': 0.06088850374545029,\n",
       "  'Mor16': 0.06065044433704577,\n",
       "  'n5HRing': -0.06056563915935044,\n",
       "  'ATSC6p': -0.060454239126411874,\n",
       "  'PEOE_VSA9': -0.0600792995531491,\n",
       "  'PNSA5': 0.05925226467000524,\n",
       "  'ATSC1c': 0.05879170065770135,\n",
       "  'EState_VSA4': -0.05878302306780468,\n",
       "  'Xch-7dv': -0.058671009652759135,\n",
       "  'Mor12': -0.05831698042454397,\n",
       "  'Mor27v': -0.05783720073530536,\n",
       "  'n6aRing': 0.05779768084307773,\n",
       "  'Mor05': -0.056562456827765124,\n",
       "  'AATS5p': -0.056103765160925564,\n",
       "  'AATS6p': -0.05584058998601546,\n",
       "  'nC': 0.055696487376654696,\n",
       "  'nHRing': -0.05569562438544719,\n",
       "  'NsSH': -0.05557082227059615,\n",
       "  'Mor22m': 0.05546542693895479,\n",
       "  'ATSC3c': 0.05545302844910022,\n",
       "  'Mor24m': -0.05518521095380485,\n",
       "  'GATS3s': 0.05507287368131927,\n",
       "  'ATSC3s': -0.054405275267100005,\n",
       "  'ATSC1pe': 0.053341518437240255,\n",
       "  'Mor20': 0.05289003546006708,\n",
       "  'AATS6se': -0.05263014767903107,\n",
       "  'ATSC6Z': -0.05225501029632406,\n",
       "  'Mor22v': 0.052208026618504474,\n",
       "  'AATS1se': -0.052016972573772045,\n",
       "  'WNSA1': -0.05171974088332188,\n",
       "  'Mor27m': -0.05160604383234613,\n",
       "  'Mor02m': -0.05150896285084032,\n",
       "  'ATSC8p': -0.05140676549186002,\n",
       "  'Mor08': 0.05065750034077404,\n",
       "  'ATSC1d': 0.05049038574033142,\n",
       "  'AATS7se': -0.050397534695051004,\n",
       "  'GATS7dv': 0.050337125780684985,\n",
       "  'AATS0p': -0.050133006029732294,\n",
       "  'nH': 0.04994985338326599,\n",
       "  'ATSC7pe': -0.0499325873419884,\n",
       "  'ATSC7i': 0.049757529903058186,\n",
       "  'Mor08m': -0.049655392893681344,\n",
       "  'n6aHRing': 0.049326708043321135,\n",
       "  'SMR_VSA6': -0.04875171896956202,\n",
       "  'ATSC0c': -0.04853618150329924,\n",
       "  'Mor06m': -0.04843296330364251,\n",
       "  'MATS7se': -0.04825440075448658,\n",
       "  'AATS0se': -0.04803193343483492,\n",
       "  'NaaCH': 0.047451231845715536,\n",
       "  'ATSC6d': -0.047438229513838054,\n",
       "  'Xch-7d': -0.04672316245021522,\n",
       "  'n5ARing': 0.04656107401997829,\n",
       "  'GATS8c': 0.046445633614312684,\n",
       "  'Mor03v': 0.04613276455370276,\n",
       "  'ATSC2s': -0.045158917984958566,\n",
       "  'AATSC6dv': 0.045088567124141644,\n",
       "  'GATS2i': 0.0449961983869565,\n",
       "  'SssssC': -0.04484900692779872,\n",
       "  'Xch-6dv': -0.044822868571114144,\n",
       "  'Mor19v': 0.044568215687565874,\n",
       "  'PPSA5': -0.044566700343472855,\n",
       "  'SlogP_VSA2': -0.04385382135295167,\n",
       "  'Mor13m': -0.043827443270466844,\n",
       "  'PPSA1': 0.04372327809832466,\n",
       "  'GATS5se': 0.04369325110545239,\n",
       "  'AATS6v': -0.04343297632486252,\n",
       "  'AATSC0i': -0.04341791286884424,\n",
       "  'GATS7i': -0.0434061357080254,\n",
       "  'EState_VSA5': 0.043374799734754096,\n",
       "  'AATS6d': -0.0433590548614338,\n",
       "  'VSA_EState4': -0.04324451352340742,\n",
       "  'GATS5s': 0.043077255568700526,\n",
       "  'IC3': -0.04304824612498354,\n",
       "  'GATS1c': -0.04268478018796047,\n",
       "  'BCUTi-1h': -0.042563074562621574,\n",
       "  'GATS8se': 0.04234499544350699,\n",
       "  'Mor04': 0.042174025066053104,\n",
       "  'ATSC1i': 0.042123078096283836,\n",
       "  'Mor11': 0.04183428134082267,\n",
       "  'Mor09v': -0.04139005913449453,\n",
       "  'PBF': -0.041357787060382276,\n",
       "  'ATS1s': 0.041118530026729085,\n",
       "  'WPSA4': -0.04103054559761104,\n",
       "  'ATSC1v': 0.04097175567563154,\n",
       "  'Mor06v': -0.04088194743414806,\n",
       "  'PPSA3': -0.040781104102206964,\n",
       "  'TSRW10': -0.04067851727584217,\n",
       "  'nAtom': 0.04061022541330121,\n",
       "  'ATSC5d': -0.04057738727442518,\n",
       "  'AATSC1dv': 0.040422250329272824,\n",
       "  'PPSA4': -0.040403788344096726,\n",
       "  'GATS8i': 0.04030302886012403,\n",
       "  'ATSC8v': -0.03998086414854392,\n",
       "  'FilterItLogS': -0.039921638053251565,\n",
       "  'ATS1Z': -0.03971944245657374,\n",
       "  'GATS8d': 0.039695789372516,\n",
       "  'Mor09m': -0.03913069799730909,\n",
       "  'EState_VSA7': -0.03912183849300865,\n",
       "  'BCUTdv-1h': 0.03900251000427328,\n",
       "  'MATS8se': -0.03868718084008164,\n",
       "  'PEOE_VSA3': -0.038544662912747045,\n",
       "  'EState_VSA8': 0.03832646356895805,\n",
       "  'GGI5': -0.03818453197788489,\n",
       "  'VSA_EState1': -0.03813749920248062,\n",
       "  'AATS4Z': -0.03793591279064621,\n",
       "  'C2SP2': 0.037918849523622865,\n",
       "  'Mor28v': 0.03791048872968623,\n",
       "  'ATSC2p': 0.0377302251776739,\n",
       "  'EState_VSA9': -0.03772536321427576,\n",
       "  'AATSC8i': -0.03756741721389703,\n",
       "  'ATSC7s': -0.03752247664142901,\n",
       "  'GATS3pe': 0.03748397243724362,\n",
       "  'MATS7pe': -0.037454316039981214,\n",
       "  'Mor03p': 0.03742225801021257,\n",
       "  'TIC0': -0.037091138743572956,\n",
       "  'MOMI-Z': -0.03673544730428269,\n",
       "  'ATSC2c': -0.03659842931031411,\n",
       "  'WPSA3': -0.03655098660898325,\n",
       "  'AATS8Z': -0.036426949000269715,\n",
       "  'GATS4c': 0.03640763506047627,\n",
       "  'C3SP2': 0.03622097013264929,\n",
       "  'n6Ring': 0.03600524256872238,\n",
       "  'VSA_EState3': -0.03598617330057456,\n",
       "  'AATS8se': -0.03598336238532537,\n",
       "  'AATS8v': -0.03588540437424892,\n",
       "  'Mor25v': 0.03575406686616382,\n",
       "  'GATS6c': -0.03571323705637587,\n",
       "  'AATS7dv': -0.035709233992754275,\n",
       "  'SlogP_VSA4': 0.035595726333001766,\n",
       "  'ATSC2i': -0.035533947698472214,\n",
       "  'GATS7pe': 0.03544377091744612,\n",
       "  'IC1': -0.035318856821838794,\n",
       "  'GATS2Z': -0.03523082334691317,\n",
       "  'AATSC5Z': -0.03518587363716325,\n",
       "  'GATS8v': 0.03515408663806315,\n",
       "  'GATS5c': 0.03499472480062851,\n",
       "  'nN': -0.034973671072659474,\n",
       "  'AATS3se': -0.03479487354198179,\n",
       "  'Mor28': 0.03465975459211602,\n",
       "  'ATSC1se': 0.03459650262766007,\n",
       "  'Mor20v': 0.03455455953869654,\n",
       "  'GATS3se': 0.03417833564230912,\n",
       "  'AATS7d': -0.03379234214974467,\n",
       "  'ATSC6se': 0.03368938958085084,\n",
       "  'ATSC4s': 0.03348157704550467,\n",
       "  'AETA_eta_F': 0.03344524366162438,\n",
       "  'GGI3': 0.03333809347740654,\n",
       "  'GATS7s': 0.03329907226614312,\n",
       "  'SLogP': 0.033296158740393066,\n",
       "  'ATSC5Z': -0.03291013612885785,\n",
       "  'Mor14': 0.032494717094798266,\n",
       "  'Mor02v': -0.03243454950353637,\n",
       "  'ATSC1p': 0.03235723703221591,\n",
       "  'GATS4d': 0.03213071756937961,\n",
       "  'WPSA1': 0.03204081935416987,\n",
       "  'ZMIC1': 0.03175504914419546,\n",
       "  'GATS6s': -0.03174403296326133,\n",
       "  'AATS7v': -0.03158880137632405,\n",
       "  'GATS8dv': 0.03149243806228315,\n",
       "  'BCUTv-1l': 0.03141600025632607,\n",
       "  'Mor02': -0.03141313893835163,\n",
       "  'Mor17m': -0.03108572632809317,\n",
       "  'Mor31v': 0.031030703631038617,\n",
       "  'AATS0v': -0.03094044861566445,\n",
       "  'AATS8dv': -0.03089234179186471,\n",
       "  'ATSC2d': 0.030859505152072943,\n",
       "  'ETA_beta_ns_d': -0.030760271583760854,\n",
       "  'AATS5se': -0.030673974188087906,\n",
       "  'AATSC7Z': 0.03062008976467808,\n",
       "  'GATS5dv': 0.030363024750366778,\n",
       "  'BCUTd-1l': 0.03034751402930108,\n",
       "  'AATS5v': -0.030054379260253988,\n",
       "  'Mor30': 0.030026921537975884,\n",
       "  'Mor12v': -0.02995494123464769,\n",
       "  'C1SP3': -0.029850079987276748,\n",
       "  'AATS0d': -0.029786400838106974,\n",
       "  'ATSC6c': 0.029634235738143305,\n",
       "  'AATS7p': -0.029579194629221896,\n",
       "  'ATSC8dv': 0.02956838830959986,\n",
       "  'GATS7se': 0.029560655514654085,\n",
       "  'AATS7Z': -0.02938696938277561,\n",
       "  'ATSC7p': 0.029294574241194842,\n",
       "  'ATSC7dv': -0.02927189635074724,\n",
       "  'Mor15m': 0.02924786240531492,\n",
       "  'Xch-5d': -0.0292284675316169,\n",
       "  'Mor26': 0.029227336506969362,\n",
       "  'ATSC3se': 0.029090242864351516,\n",
       "  'MATS8c': -0.028737757192897992,\n",
       "  'GATS7c': 0.02871728591065137,\n",
       "  'ATSC4Z': 0.02861463295868068,\n",
       "  'GATS4dv': -0.028602795346020473,\n",
       "  'SMR_VSA9': -0.028436211874360486,\n",
       "  'ATSC0pe': -0.028174027562501442,\n",
       "  'GATS8s': 0.028027497144830545,\n",
       "  'Mor32': -0.027993098403816467,\n",
       "  'ATSC5pe': -0.027865227096743512,\n",
       "  'EState_VSA10': -0.027765215131674813,\n",
       "  'Mor16m': -0.02747678915681787,\n",
       "  'SpDiam_A': 0.02707751469458059,\n",
       "  'GATS4Z': -0.027076555261340566,\n",
       "  'NaaaC': 0.027051961639268735,\n",
       "  'AETA_eta': -0.02635034188664906,\n",
       "  'SlogP_VSA3': 0.026101049264122173,\n",
       "  'GATS1v': 0.025984281294022943,\n",
       "  'PEOE_VSA1': -0.02595518355265528,\n",
       "  'GATS1i': -0.02579969730869756,\n",
       "  'ATSC7se': -0.025749022568350342,\n",
       "  'GATS6se': -0.024877375469614656,\n",
       "  'GATS1dv': -0.02487193856883485,\n",
       "  'ZMIC3': -0.02481406451167846,\n",
       "  'ATSC0s': -0.024664162611399188,\n",
       "  'Mor29m': 0.024635822452118733,\n",
       "  'naHRing': -0.0244160224209537,\n",
       "  'Mor26m': 0.024393142174503377,\n",
       "  'PEOE_VSA11': -0.024158926935076683,\n",
       "  'SsssCH': 0.024151614605519355,\n",
       "  'AATS5d': -0.0240537394560784,\n",
       "  'C3SP3': -0.023930094098212035,\n",
       "  'ATS8Z': -0.023845978695860522,\n",
       "  'Mor18m': 0.02372629202014074,\n",
       "  'Mor14m': 0.023681010725991394,\n",
       "  'ATSC4pe': 0.023497304830171806,\n",
       "  'PEOE_VSA7': 0.02335863107276624,\n",
       "  'ATSC3v': 0.023224391427887205,\n",
       "  'Mor14v': 0.022849585533492225,\n",
       "  'AATSC6i': 0.022733282370838992,\n",
       "  'Mor10m': 0.022693229431218653,\n",
       "  'PEOE_VSA10': 0.022612955260741616,\n",
       "  'Mor03': 0.022574412132690302,\n",
       "  'GATS7p': -0.022562967133813918,\n",
       "  'AATS8d': -0.022506183812222098,\n",
       "  'ATSC3d': 0.022434065641580275,\n",
       "  'MATS2c': -0.022235910306878787,\n",
       "  'Kier3': 0.02209691431108705,\n",
       "  'Mor18v': -0.022034478423942447,\n",
       "  'Mor20m': 0.022030408353566844,\n",
       "  'AATSC1Z': -0.021798724701541445,\n",
       "  'AATS6i': 0.021795803436324458,\n",
       "  'ATSC5s': 0.021724251870350087,\n",
       "  'GATS8p': 0.021561892868083674,\n",
       "  'AATSC3Z': -0.02138593757099824,\n",
       "  'AATS4v': -0.021380028623155453,\n",
       "  'Mor30v': 0.02128891759160878,\n",
       "  'nBondsS': 0.021245438965662014,\n",
       "  'ATSC5v': 0.021165322577128286,\n",
       "  'AATS6dv': -0.020618411361216192,\n",
       "  'ATSC3Z': 0.02055258260850909,\n",
       "  'GeomRadius': -0.020365194458673772,\n",
       "  'GGI6': 0.020245840183482973,\n",
       "  'GATS6i': -0.01996577030664135,\n",
       "  'GATS4s': -0.019901593682738417,\n",
       "  'Mor19m': 0.019894103328682643,\n",
       "  'ATSC8Z': -0.0197225636172513,\n",
       "  'nBase': -0.019564851553910717,\n",
       "  'AATSC4Z': 0.01954478320106971,\n",
       "  'Mor26v': 0.01944767438693513,\n",
       "  'ATS0s': 0.019420890511106893,\n",
       "  'Mor05m': 0.0191717524435837,\n",
       "  'nO': -0.019102406157183102,\n",
       "  'NssS': -0.019022275818320313,\n",
       "  'Mor24v': -0.01899422049238081,\n",
       "  'Mor15': -0.018963789164845295,\n",
       "  'PEOE_VSA2': -0.01888627921356993,\n",
       "  'AATS5i': 0.018883019070424507,\n",
       "  'NaasC': -0.018860335924556344,\n",
       "  'ATSC4se': -0.018718299423674763,\n",
       "  'MATS8pe': -0.018713655414184422,\n",
       "  'GATS2s': 0.01845801972633954,\n",
       "  'SlogP_VSA10': -0.018453408599639877,\n",
       "  'Mor15v': 0.018370474208481303,\n",
       "  'AATSC3dv': -0.01816487281000892,\n",
       "  'Mor16v': -0.018039991701816402,\n",
       "  'ATS8dv': -0.01803103830420602,\n",
       "  'bpol': -0.01790988535814143,\n",
       "  'SpMAD_Dzv': -0.017662584935053235,\n",
       "  'AATSC4dv': 0.017655581863441818,\n",
       "  'ATSC0dv': 0.01759992703689625,\n",
       "  'GeomDiameter': -0.017592270004226924,\n",
       "  'VSA_EState5': -0.017575783706958507,\n",
       "  'Mor24': -0.017247652356007122,\n",
       "  'AATSC0dv': -0.01679405907743964,\n",
       "  'GATS3i': 0.016729722877538884,\n",
       "  'GATS3d': 0.016716326167183247,\n",
       "  'nAromAtom': 0.01663544423871456,\n",
       "  'ATSC8pe': 0.0165489757976493,\n",
       "  'BCUTs-1h': -0.016375298303912638,\n",
       "  'EState_VSA3': -0.01637158872863449,\n",
       "  'Mor30m': 0.0162990875191024,\n",
       "  'ATSC4dv': 0.016052266391098753,\n",
       "  'AATS0dv': -0.01597193168906244,\n",
       "  'ATSC5i': 0.01595376511830446,\n",
       "  'Xc-5dv': -0.0159334533542992,\n",
       "  'BCUTse-1h': 0.01581502820625964,\n",
       "  'SM1_Dzv': 0.01567428400897486,\n",
       "  'ATSC4i': -0.01555376531026534,\n",
       "  'AATS8s': -0.015507668494879032,\n",
       "  'ATS5Z': -0.015505966323840633,\n",
       "  'AATS7i': 0.01529088377921347,\n",
       "  'AATSC5i': -0.015206230067802503,\n",
       "  'ABC': 0.01504900999678791,\n",
       "  'ATSC1Z': -0.01494853102953502,\n",
       "  'Mor17v': -0.014929294487106051,\n",
       "  'Mor09': -0.0148456512922033,\n",
       "  'Mor10': 0.014818335522133267,\n",
       "  'ATSC4d': -0.014671718922032085,\n",
       "  'EState_VSA6': -0.014620905427907517,\n",
       "  'NaaN': -0.01461249488018046,\n",
       "  'NssCH2': 0.014433326572594258,\n",
       "  'AATSC5dv': 0.014361123743243328,\n",
       "  'ATS4Z': -0.014295005564255907,\n",
       "  'Mor04v': -0.014274482358727676,\n",
       "  'Mor29v': 0.013942273803252875,\n",
       "  'AATSC7v': 0.013927729782467571,\n",
       "  'AATSC6v': -0.013845625977691081,\n",
       "  'IC4': 0.013841369031042643,\n",
       "  'ATSC6i': -0.013809963550853866,\n",
       "  'GATS6d': -0.013278827188968063,\n",
       "  'AATS5s': 0.01327335136899033,\n",
       "  'AATSC4v': -0.013265763055328393,\n",
       "  'AATSC4i': -0.013208798229842698,\n",
       "  'AATS6s': 0.013111145876303718,\n",
       "  'BCUTd-1h': 0.013039791446187431,\n",
       "  'AATS1s': 0.01297712631644322,\n",
       "  'MATS7s': -0.012819518397026159,\n",
       "  'ATSC6dv': -0.012695458971319025,\n",
       "  'ATSC2pe': 0.012627986175127386,\n",
       "  'MATS3c': 0.012532211191348218,\n",
       "  'GATS1se': -0.01226020248651081,\n",
       "  'GATS4se': 0.012044764182006677,\n",
       "  'ATS0p': -0.01202874740132981,\n",
       "  'MOMI-X': -0.01195705188224151,\n",
       "  'AATSC8dv': 0.011593901857097626,\n",
       "  'EState_VSA2': 0.011485509005819157,\n",
       "  'Mor29': 0.011442491495566209,\n",
       "  'ATSC3pe': 0.011252494641212038,\n",
       "  'GATS6Z': 0.011004069202544696,\n",
       "  'MATS6Z': -0.010922885759840106,\n",
       "  'SpMAD_Dzse': 0.01091386629500248,\n",
       "  'AATSC3i': -0.010792789862865448,\n",
       "  'VSA_EState2': -0.010669171906056407,\n",
       "  'PPSA2': -0.010552607701175708,\n",
       "  'NsssN': -0.01048360294504262,\n",
       "  'NsOH': -0.010399404378233161,\n",
       "  'GGI4': 0.010371577152687722,\n",
       "  'ATSC8s': -0.010289387062335077,\n",
       "  'HybRatio': -0.010203032282095544,\n",
       "  'VSA_EState8': -0.01012299968417748,\n",
       "  'Xc-3d': 0.01004582444826636,\n",
       "  'NsssCH': 0.00987138365890545,\n",
       "  'ATSC3i': 0.009860001349554158,\n",
       "  'AATSC8v': -0.009851679397161897,\n",
       "  'GATS5Z': 0.0098296033697443,\n",
       "  'Mor10v': 0.009524195326703427,\n",
       "  'RPCS': 0.009479618511522283,\n",
       "  'GATS4i': 0.009434124915095588,\n",
       "  'AATSC3v': -0.009250485551279448,\n",
       "  'ATSC2dv': -0.009248887894812406,\n",
       "  'n6HRing': 0.009220218970159056,\n",
       "  'GATS1p': 0.00913905968461284,\n",
       "  'ABCGG': 0.008846590790875604,\n",
       "  'ATSC7Z': 0.008836035647976647,\n",
       "  'ATSC5p': -0.008771074035330353,\n",
       "  'ATSC6pe': 0.008741724958691814,\n",
       "  'GATS7d': 0.008658437699936567,\n",
       "  'Mor31m': -0.008631865746234656,\n",
       "  'PEOE_VSA5': 0.008608479318108455,\n",
       "  'NaaO': 0.008470508231880062,\n",
       "  'Mor06': -0.008324047346850843,\n",
       "  'AATSC5v': 0.008244623690123996,\n",
       "  'Mor25m': 0.008210285307578077,\n",
       "  'Mor08v': -0.008176492232599985,\n",
       "  'TIC1': 0.008111812714411117,\n",
       "  'TASA': -0.008076971938866709,\n",
       "  'PEOE_VSA8': 0.007991740676410645,\n",
       "  'AATSC0s': -0.007880053497496244,\n",
       "  'AATS4d': -0.007847738060549957,\n",
       "  'ATS3Z': -0.007752947283317865,\n",
       "  'GATS5p': -0.007731696636388393,\n",
       "  'ATSC3dv': 0.007701331853378726,\n",
       "  'AATSC6Z': 0.007673583603162428,\n",
       "  'GATS7Z': -0.007672085357791472,\n",
       "  'GATS6dv': 0.007596712280292142,\n",
       "  'GATS4p': 0.007556136439638323,\n",
       "  'GeomShapeIndex': 0.007549975306883341,\n",
       "  'GATS2p': -0.007521998694664529,\n",
       "  'ATSC8d': 0.007378353981595479,\n",
       "  'MATS8s': -0.007371633631964059,\n",
       "  'GATS5d': 0.007259039134314974,\n",
       "  'GATS3c': 0.006907057823903871,\n",
       "  'AATS3i': 0.006784190636373167,\n",
       "  'ATSC7v': -0.006647635199080438,\n",
       "  'ATSC4v': -0.006415697640047022,\n",
       "  'GATS6p': 0.006413182801058924,\n",
       "  'TPSA': 0.006306411336226291,\n",
       "  'GATS2d': 0.006004335795723908,\n",
       "  'Diameter': 0.005906372134926628,\n",
       "  'GATS2dv': 0.005632581173283952,\n",
       "  'Mor13v': -0.005505364083768485,\n",
       "  'Mor32v': -0.005309891043961399,\n",
       "  'AATS4s': -0.004972038769412041,\n",
       "  'ATSC8se': 0.00496770140295598,\n",
       "  'SaasC': 0.0048910366323222255,\n",
       "  'GATS2se': 0.004797693231150838,\n",
       "  'GATS2c': -0.004746725781479923,\n",
       "  'nARing': -0.004642425776856336,\n",
       "  'SpAbs_Dzv': 0.00463528097789879,\n",
       "  'ATSC3p': 0.004558142291516235,\n",
       "  'ATSC2v': -0.004550088266698585,\n",
       "  'ATSC5se': -0.00442243501281143,\n",
       "  'ATSC0i': 0.004314492190282043,\n",
       "  'AATS0i': 0.004241714262895952,\n",
       "  'SMR_VSA4': 0.004214130514558937,\n",
       "  'Mor12m': 0.004123668433162665,\n",
       "  'GATS8Z': 0.003878508009245308,\n",
       "  'GATS2pe': 0.0038411985668661656,\n",
       "  'ATSC2se': -0.0036228142018597045,\n",
       "  'Mor05v': -0.0034515466442078917,\n",
       "  'BertzCT': 0.0033810458092780635,\n",
       "  'GATS1d': 0.0033145741419369507,\n",
       "  'AATSC7dv': 0.0032971353646910977,\n",
       "  'Mor32m': -0.0031899890121089096,\n",
       "  'GATS1pe': -0.0031599525391522725,\n",
       "  'Mor04m': -0.002994585785813329,\n",
       "  'Xpc-4d': 0.0029481044932680657,\n",
       "  'ATSC5c': -0.0027035010160079047,\n",
       "  'GATS7v': -0.0026707947283959163,\n",
       "  'C1SP2': 0.002609641521495827,\n",
       "  'BalabanJ': -0.0026005323726227417,\n",
       "  'Mor28m': -0.002558739893057113,\n",
       "  'Mor08p': 0.002402515626697463,\n",
       "  'ATS0dv': 0.002391766968703715,\n",
       "  'ATSC4p': 0.0023100954233423484,\n",
       "  'AATS0s': -0.002283643270338704,\n",
       "  'SlogP_VSA8': -0.0021781827981010656,\n",
       "  'ATSC7d': -0.002157439015782142,\n",
       "  'AATS7s': -0.0021031222183819803,\n",
       "  'AATS4i': 0.0018362999805065171,\n",
       "  'AATSC8Z': -0.0017249952237436636,\n",
       "  'AATSC8s': -0.0013104399048625135,\n",
       "  'ETA_eta': -0.0012892607379178737,\n",
       "  'AATSC0v': 0.0011370541916987963,\n",
       "  'ETA_beta_s': -0.0011002668124823179,\n",
       "  'GGI1': -0.00102978149010937,\n",
       "  'Xc-5d': 0.0009812545095996433,\n",
       "  'ATS6Z': -0.000951268458762142,\n",
       "  'AATS8i': -0.0006175520907965654,\n",
       "  'ATS7Z': 0.0006012797445065009,\n",
       "  'AATSC8d': 0.0005781758748009287,\n",
       "  'GATS5i': -0.0005646279557973399,\n",
       "  'Xc-3dv': 0.0005191797356694013,\n",
       "  'ATSC5dv': -0.0004020036125952537}}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "explanation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f49601b3",
   "metadata": {},
   "source": [
    "feature_order ensures that the trained model sees features in the exact same order as trained."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1333f74c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['ABC', 'ABCGG', 'nBase', 'SpDiam_A', 'nAromAtom']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_order[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "d14e97a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Converting SMILES to ChemML Molecule objects: 100%|██████████| 200/200 [00:06<00:00, 29.34it/s]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Step 1: Normalizing molecule input\n",
      "Step 2/3: Optimizing geometry for 3D descriptor calculation\n",
      "Step 3/3: Calculating Mordred descriptors\n"
     ]
    }
   ],
   "source": [
    "from chemml.chem import Molecule\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.model_selection import train_test_split\n",
    "import tqdm\n",
    "from chemml.chem import Mordred\n",
    "from sklearn.svm import SVR\n",
    "\n",
    "mol_objs_list = []\n",
    "for i, smi in enumerate(tqdm.tqdm(df[\"smiles\"], desc=\"Converting SMILES to ChemML Molecule objects\")):\n",
    "    mol = Molecule(smi, 'smiles')\n",
    "    mol.hydrogens('add')\n",
    "    try:\n",
    "        mol.to_xyz('MMFF', maxIters=10000, mmffVariant='MMFF94s')\n",
    "        mol_objs_list.append(mol)\n",
    "    except Exception as e:\n",
    "        print(f\"\\nUnable to process SMILES: {smi}; Error: {e}\")\n",
    "        # self.discarded_indices.append(i)\n",
    "loaded_mols = mol_objs_list\n",
    "features = Mordred(ignore_3D=False).represent(loaded_mols).drop(columns=['SMILES'])[feature_order].values\n",
    "targets = df[\"density_class\"].values\n",
    "\n",
    "\n",
    "X_test = loaded_scaler.transform(features)\n",
    "\n",
    "y_pred = loaded_model.predict(X_test)\n",
    "y_pred_proba = loaded_model.predict_proba(X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fb78402e",
   "metadata": {},
   "source": [
    "The loaded_model object can be treated just like any model object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "86a7dabc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>.sk-global {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: #000;\n",
       "  --sklearn-color-text-muted: #666;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "}\n",
       "\n",
       ".sk-global.light {\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: black;\n",
       "  --sklearn-color-background: white;\n",
       "  --sklearn-color-border-box: black;\n",
       "  --sklearn-color-icon: #696969;\n",
       "}\n",
       "\n",
       ".sk-global.dark {\n",
       "  --sklearn-color-text-on-default-background: white;\n",
       "  --sklearn-color-background: #111;\n",
       "  --sklearn-color-border-box: white;\n",
       "  --sklearn-color-icon: #878787;\n",
       "}\n",
       "\n",
       ".sk-global {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       ".sk-global pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       ".sk-global input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip-path: inset(100%);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       ".sk-global div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       ".sk-global div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       ".sk-global div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       ".sk-global label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "  align-items: center;\n",
       "  justify-content: center;\n",
       "  gap: 0.5em;\n",
       "}\n",
       "\n",
       ".sk-global label.sk-toggleable__label .caption {\n",
       "  font-size: 0.6rem;\n",
       "  font-weight: lighter;\n",
       "  color: var(--sklearn-color-text-muted);\n",
       "}\n",
       "\n",
       ".sk-global label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       ".sk-global label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       ".sk-global div.sk-toggleable__content {\n",
       "  display: none;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       ".sk-global input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  overflow: visible;\n",
       "}\n",
       "\n",
       ".sk-global input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       ".sk-global div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       ".sk-global div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-label label.sk-toggleable__label,\n",
       ".sk-global div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       ".sk-global div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       ".sk-global div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       ".sk-global div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       ".sk-global div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       ".sk-global div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       ".sk-global div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       ".sk-global div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 0.5em;\n",
       "  text-align: center;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-3) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-0);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  border: var(--sklearn-color-fitted-level-0) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-0);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       ".sk-global a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       ".sk-global a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       ".sk-global a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       ".sk-global a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-top-container.sk-global {\n",
       "  /* pydata-sphinx-theme hides overflow, so scrolling is disabled.\n",
       "   We need to set it to !important and add tabindex=\"0\" in the HTML\n",
       "   to allow keyboard-only users to navigate the display. */\n",
       "  overflow-x: scroll !important;\n",
       "  max-width: 100%;\n",
       "}\n",
       "\n",
       ".estimator-table {\n",
       "    font-family: monospace;\n",
       "}\n",
       "\n",
       ".estimator-table summary {\n",
       "    padding: .5rem;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".estimator-table summary::marker {\n",
       "    font-size: 0.7rem;\n",
       "}\n",
       "\n",
       ".estimator-table details[open] {\n",
       "    padding-left: 0.1rem;\n",
       "    padding-right: 0.1rem;\n",
       "    padding-bottom: 0.3rem;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table {\n",
       "    margin-left: auto !important;\n",
       "    margin-right: auto !important;\n",
       "    margin-top: 0;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(odd) {\n",
       "    background-color: #fff;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:nth-child(even) {\n",
       "    background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".estimator-table .parameters-table tr:hover td {\n",
       "    background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".estimator-table table :is(td, th) {\n",
       "    border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "}\n",
       "\n",
       "/*\n",
       "    `table td`is set in notebook with right text-align.\n",
       "    We need to overwrite it.\n",
       "*/\n",
       ".estimator-table table td.param {\n",
       "    text-align: left;\n",
       "    position: relative;\n",
       "    padding: 0;\n",
       "}\n",
       "\n",
       ".user-set td {\n",
       "    color:rgb(255, 94, 0);\n",
       "    text-align: left !important;\n",
       "}\n",
       "\n",
       ".user-set td.value {\n",
       "    color:rgb(255, 94, 0);\n",
       "    background-color: transparent;\n",
       "}\n",
       "\n",
       ".default td, .estimator-table th {\n",
       "    color: black;\n",
       "    text-align: left !important;\n",
       "}\n",
       "\n",
       ".user-set td i,\n",
       ".default td i {\n",
       "    color: black;\n",
       "}\n",
       "\n",
       "td.fitted-att-type {\n",
       "    white-space: preserve nowrap;\n",
       "}\n",
       "\n",
       "/*\n",
       "    Styles for parameter documentation links\n",
       "    We need styling for visited so jupyter doesn't overwrite it\n",
       "*/\n",
       "a.param-doc-link,\n",
       "a.param-doc-link:link,\n",
       "a.param-doc-link:visited {\n",
       "    text-decoration: underline dashed;\n",
       "    text-underline-offset: .3em;\n",
       "    color: inherit;\n",
       "    display: block;\n",
       "    padding: .5em;\n",
       "}\n",
       "\n",
       "@supports(anchor-name: --doc-link) {\n",
       "    a.param-doc-link,\n",
       "    a.param-doc-link:link,\n",
       "    a.param-doc-link:visited {\n",
       "    anchor-name: --doc-link;\n",
       "    }\n",
       "}\n",
       "\n",
       "/* \"hack\" to make the entire area of the cell containing the link clickable */\n",
       "a.param-doc-link::before {\n",
       "    position: absolute;\n",
       "    content: \"\";\n",
       "    inset: 0;\n",
       "}\n",
       "\n",
       ".param-doc-description {\n",
       "    display: none;\n",
       "    position: absolute;\n",
       "    z-index: 9999;\n",
       "    left: 0;\n",
       "    padding: .5ex;\n",
       "    margin-left: 1.5em;\n",
       "    color: var(--sklearn-color-text);\n",
       "    box-shadow: .3em .3em .4em #999;\n",
       "    width: max-content;\n",
       "    text-align: left;\n",
       "    max-height: 10em;\n",
       "    overflow-y: auto;\n",
       "\n",
       "    /* unfitted */\n",
       "    background: var(--sklearn-color-unfitted-level-0);\n",
       "    border: thin solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       "@supports(position-area: center right) {\n",
       "    .param-doc-description {\n",
       "    position-area: center right;\n",
       "    position: fixed;\n",
       "    margin-left: 0;\n",
       "    }\n",
       "}\n",
       "\n",
       "/* Fitted state for parameter tooltips */\n",
       ".fitted .param-doc-description {\n",
       "    /* fitted */\n",
       "    background: var(--sklearn-color-fitted-level-0);\n",
       "    border: thin solid var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".param-doc-link:hover .param-doc-description {\n",
       "    display: block;\n",
       "}\n",
       "\n",
       ".copy-paste-icon {\n",
       "    background-image: url(data:image/svg+xml;base64,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);\n",
       "    background-repeat: no-repeat;\n",
       "    background-size: 14px 14px;\n",
       "    background-position: 0;\n",
       "    display: inline-block;\n",
       "    width: 14px;\n",
       "    height: 14px;\n",
       "    cursor: pointer;\n",
       "}\n",
       "\n",
       ".features {\n",
       "  font-family: monospace;\n",
       "  cursor: pointer;\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: .20em;\n",
       "  margin-bottom: 0.5em;\n",
       "  font-size: inherit; /* Needed for jupyter */\n",
       "}\n",
       "\n",
       ".features.fitted {\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       ".features summary {\n",
       "  cursor: pointer;\n",
       "  display: flex;\n",
       "  margin-bottom: 0;\n",
       "  text-align: center;\n",
       "  align-items: center;\n",
       "  justify-content: center;\n",
       "  gap: 0.5em;\n",
       "  padding: .25em;\n",
       "}\n",
       "\n",
       ".features details[open] > summary {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "  border-radius: .20em 0 0 0;\n",
       "}\n",
       "\n",
       ".features.fitted details[open] > summary {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "  border-radius: .20em 0 0 0;\n",
       "}\n",
       "\n",
       ".features details > summary .arrow::before {\n",
       "  content: \"▸\";\n",
       "  color: grey;\n",
       "}\n",
       "\n",
       ".features details[open] > summary .arrow::before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       ".features details:hover > summary {\n",
       "  margin: 0;\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       ".features.fitted details:hover > summary {\n",
       "  margin: 0;\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       ".features .features-container {\n",
       "  max-width: 15em;\n",
       "  max-height: 10em;\n",
       "  overflow: auto;\n",
       "  scrollbar-width: thin;\n",
       "  padding: .25em 0.1rem;\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "  border-radius: 0 0 .5em .5em;\n",
       "}\n",
       "\n",
       ".features.fitted .features-container {\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       ".features .image-container {\n",
       "  block-size: 1em;\n",
       "  inline-size: 1em;\n",
       "  padding: 0;\n",
       "  margin: 0%;\n",
       "  display: flex;\n",
       "  justify-content: center;\n",
       "  align-items: center;\n",
       "}\n",
       "\n",
       ".features .copy-paste-icon {\n",
       "  background-size: 1em 1em;\n",
       "  width: 1em;\n",
       "  height: 1em;\n",
       "  filter: grayscale(100%) opacity(60%);\n",
       "}\n",
       "\n",
       ".features .features-container table {\n",
       "  width: 100%;\n",
       "  margin: 0.01em;\n",
       "}\n",
       "\n",
       ".features .features-container table tr:nth-child(odd) {\n",
       "  background-color: #fff;\n",
       "}\n",
       "\n",
       ".features .features-container table tr:nth-child(even) {\n",
       "  background-color: #f6f6f6;\n",
       "}\n",
       "\n",
       ".features .features-container table tr:hover {\n",
       "  background-color: #e0e0e0;\n",
       "}\n",
       "\n",
       ".features .features-container table {\n",
       "  table-layout: inherit;\n",
       "}\n",
       "\n",
       ".features .features-container table td {\n",
       "  text-align: left;\n",
       "  padding: 0 0.5em;\n",
       "  border: 1px solid rgba(106, 105, 104, 0.232);\n",
       "  white-space: nowrap;\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       ".total_features {\n",
       "  display: flex;\n",
       "  justify-content: center;\n",
       "  margin-top: 0.5em;\n",
       "}\n",
       "</style><body><div id=\"sk-container-id-1\" tabindex=\"0\" class=\"sk-top-container sk-global\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(C=0.1, solver=&#x27;sag&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually sk-global\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow\"><div><div>LogisticRegression</div></div><div><a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></div></label><div class=\"sk-toggleable__content fitted\" data-param-prefix=\"\">\n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Parameters</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                  <tbody>\n",
       "                    \n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('C',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-C;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=C,-float%2C%20default%3D1.0\">\n",
       "            C\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-C;\">\n",
       "            C: float, default=1.0<br><br>Inverse of regularization strength; must be a positive float.<br>Like in support vector machines, smaller values specify stronger<br>regularization. `C=np.inf` results in unpenalized logistic regression.<br>For a visual example on the effect of tuning the `C` parameter<br>with an L1 penalty, see:<br>:ref:`sphx_glr_auto_examples_linear_model_plot_logistic_path.py`.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">0.1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"user-set\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('solver',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-solver;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=solver,-%7B%27lbfgs%27%2C%20%27liblinear%27%2C%20%27newton-cg%27%2C%20%27newton-cholesky%27%2C%20%27sag%27%2C%20%27saga%27%7D%2C%20%20%20%20%20%20%20%20%20%20%20%20%20default%3D%27lbfgs%27\">\n",
       "            solver\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-solver;\">\n",
       "            solver: {&#x27;lbfgs&#x27;, &#x27;liblinear&#x27;, &#x27;newton-cg&#x27;, &#x27;newton-cholesky&#x27;, &#x27;sag&#x27;, &#x27;saga&#x27;},             default=&#x27;lbfgs&#x27;<br><br>Algorithm to use in the optimization problem. Default is &#x27;lbfgs&#x27;.<br>To choose a solver, you might want to consider the following aspects:<br><br>- &#x27;lbfgs&#x27; is a good default solver because it works reasonably well for a wide<br>  class of problems.<br>- For :term:`multiclass` problems (`n_classes &gt;= 3`), all solvers except<br>  &#x27;liblinear&#x27; minimize the full multinomial loss, &#x27;liblinear&#x27; will raise an<br>  error.<br>- &#x27;newton-cholesky&#x27; is a good choice for<br>  `n_samples` &gt;&gt; `n_features * n_classes`, especially with one-hot encoded<br>  categorical features with rare categories. Be aware that the memory usage<br>  of this solver has a quadratic dependency on `n_features * n_classes`<br>  because it explicitly computes the full Hessian matrix.<br>- For small datasets, &#x27;liblinear&#x27; is a good choice, whereas &#x27;sag&#x27;<br>  and &#x27;saga&#x27; are faster for large ones;<br>- &#x27;liblinear&#x27; can only handle binary classification by default. To apply a<br>  one-versus-rest scheme for the multiclass setting one can wrap it with the<br>  :class:`~sklearn.multiclass.OneVsRestClassifier`.<br><br>.. warning::<br>   The choice of the algorithm depends on the penalty chosen (`l1_ratio=0`<br>   for L2-penalty, `l1_ratio=1` for L1-penalty and `0 &lt; l1_ratio &lt; 1` for<br>   Elastic-Net) and on (multinomial) multiclass support:<br><br>   ================= ======================== ======================<br>   solver            l1_ratio                 multinomial multiclass<br>   ================= ======================== ======================<br>   &#x27;lbfgs&#x27;           l1_ratio=0               yes<br>   &#x27;liblinear&#x27;       l1_ratio=1 or l1_ratio=0 no<br>   &#x27;newton-cg&#x27;       l1_ratio=0               yes<br>   &#x27;newton-cholesky&#x27; l1_ratio=0               yes<br>   &#x27;sag&#x27;             l1_ratio=0               yes<br>   &#x27;saga&#x27;            0&lt;=l1_ratio&lt;=1           yes<br>   ================= ======================== ======================<br><br>.. note::<br>   &#x27;sag&#x27; and &#x27;saga&#x27; fast convergence is only guaranteed on features<br>   with approximately the same scale. You can preprocess the data with<br>   a scaler from :mod:`sklearn.preprocessing`.<br><br>.. seealso::<br>   Refer to the :ref:`User Guide &lt;Logistic_regression&gt;` for more<br>   information regarding :class:`LogisticRegression` and more specifically the<br>   :ref:`Table &lt;logistic_regression_solvers&gt;`<br>   summarizing solver/penalty supports.<br><br>.. versionadded:: 0.17<br>   Stochastic Average Gradient (SAG) descent solver. Multinomial support in<br>   version 0.18.<br>.. versionadded:: 0.19<br>   SAGA solver.<br>.. versionchanged:: 0.22<br>   The default solver changed from &#x27;liblinear&#x27; to &#x27;lbfgs&#x27; in 0.22.<br>.. versionadded:: 1.2<br>   newton-cholesky solver. Multinomial support in version 1.6.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">&#x27;sag&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('penalty',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-penalty;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=penalty,-%7B%27l1%27%2C%20%27l2%27%2C%20%27elasticnet%27%2C%20None%7D%2C%20default%3D%27l2%27\">\n",
       "            penalty\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-penalty;\">\n",
       "            penalty: {&#x27;l1&#x27;, &#x27;l2&#x27;, &#x27;elasticnet&#x27;, None}, default=&#x27;l2&#x27;<br><br>Specify the norm of the penalty:<br><br>- `None`: no penalty is added;<br>- `&#x27;l2&#x27;`: add an L2 penalty term and it is the default choice;<br>- `&#x27;l1&#x27;`: add an L1 penalty term;<br>- `&#x27;elasticnet&#x27;`: both L1 and L2 penalty terms are added.<br><br>.. warning::<br>   Some penalties may not work with some solvers. See the parameter<br>   `solver` below, to know the compatibility between the penalty and<br>   solver.<br><br>.. versionadded:: 0.19<br>   l1 penalty with SAGA solver (allowing &#x27;multinomial&#x27; + L1)<br><br>.. deprecated:: 1.8<br>   `penalty` was deprecated in version 1.8 and will be removed in 1.10.<br>   Use `l1_ratio` and `C` instead. `l1_ratio=0` for `penalty=&#x27;l2&#x27;`,<br>   `l1_ratio=1` for `penalty=&#x27;l1&#x27;`, `l1_ratio` set to any float between 0 and 1<br>   for `penalty=&#x27;elasticnet&#x27;`, and `C=np.inf` for `penalty=None`.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">&#x27;deprecated&#x27;</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('l1_ratio',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-l1_ratio;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=l1_ratio,-float%2C%20default%3D0.0\">\n",
       "            l1_ratio\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-l1_ratio;\">\n",
       "            l1_ratio: float, default=0.0<br><br>The Elastic-Net mixing parameter, with `0 &lt;= l1_ratio &lt;= 1`. Setting<br>`l1_ratio=1` gives a pure L1-penalty, setting `l1_ratio=0` a pure L2-penalty.<br>Any value between 0 and 1 gives an Elastic-Net penalty of the form<br>`l1_ratio * L1 + (1 - l1_ratio) * L2`.<br><br>.. warning::<br>   Certain values of `l1_ratio`, i.e. some penalties, may not work with some<br>   solvers. See the parameter `solver` below, to know the compatibility between<br>   the penalty and solver.<br><br>.. versionchanged:: 1.8<br>    Default value changed from None to 0.0.<br><br>.. deprecated:: 1.8<br>    `None` is deprecated and will be removed in version 1.10. Always use<br>    `l1_ratio` to specify the penalty type.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">0.0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('dual',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-dual;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=dual,-bool%2C%20default%3DFalse\">\n",
       "            dual\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-dual;\">\n",
       "            dual: bool, default=False<br><br>Dual (constrained) or primal (regularized, see also<br>:ref:`this equation &lt;regularized-logistic-loss&gt;`) formulation. Dual formulation<br>is only implemented for l2 penalty with liblinear solver. Prefer `dual=False`<br>when n_samples &gt; n_features.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('tol',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-tol;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=tol,-float%2C%20default%3D1e-4\">\n",
       "            tol\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-tol;\">\n",
       "            tol: float, default=1e-4<br><br>Tolerance for stopping criteria.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">0.0001</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('fit_intercept',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-fit_intercept;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=fit_intercept,-bool%2C%20default%3DTrue\">\n",
       "            fit_intercept\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-fit_intercept;\">\n",
       "            fit_intercept: bool, default=True<br><br>Specifies if a constant (a.k.a. bias or intercept) should be<br>added to the decision function.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">True</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('intercept_scaling',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-intercept_scaling;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=intercept_scaling,-float%2C%20default%3D1\">\n",
       "            intercept_scaling\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-intercept_scaling;\">\n",
       "            intercept_scaling: float, default=1<br><br>Useful only when the solver `liblinear` is used<br>and `self.fit_intercept` is set to `True`. In this case, `x` becomes<br>`[x, self.intercept_scaling]`,<br>i.e. a &quot;synthetic&quot; feature with constant value equal to<br>`intercept_scaling` is appended to the instance vector.<br>The intercept becomes<br>``intercept_scaling * synthetic_feature_weight``.<br><br>.. note::<br>    The synthetic feature weight is subject to L1 or L2<br>    regularization as all other features.<br>    To lessen the effect of regularization on synthetic feature weight<br>    (and therefore on the intercept) `intercept_scaling` has to be increased.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">1</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('class_weight',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-class_weight;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=class_weight,-dict%20or%20%27balanced%27%2C%20default%3DNone\">\n",
       "            class_weight\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-class_weight;\">\n",
       "            class_weight: dict or &#x27;balanced&#x27;, default=None<br><br>Weights associated with classes in the form ``{class_label: weight}``.<br>If not given, all classes are supposed to have weight one.<br><br>The &quot;balanced&quot; mode uses the values of y to automatically adjust<br>weights inversely proportional to class frequencies in the input data<br>as ``n_samples / (n_classes * np.bincount(y))``.<br><br>Note that these weights will be multiplied with sample_weight (passed<br>through the fit method) if sample_weight is specified.<br><br>.. versionadded:: 0.17<br>   *class_weight=&#x27;balanced&#x27;*</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('random_state',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-random_state;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=random_state,-int%2C%20RandomState%20instance%2C%20default%3DNone\">\n",
       "            random_state\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-random_state;\">\n",
       "            random_state: int, RandomState instance, default=None<br><br>Used when ``solver`` == &#x27;sag&#x27;, &#x27;saga&#x27; or &#x27;liblinear&#x27; to shuffle the<br>data. See :term:`Glossary &lt;random_state&gt;` for details.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('max_iter',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-max_iter;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=max_iter,-int%2C%20default%3D100\">\n",
       "            max_iter\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-max_iter;\">\n",
       "            max_iter: int, default=100<br><br>Maximum number of iterations taken for the solvers to converge.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">100</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('verbose',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-verbose;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=verbose,-int%2C%20default%3D0\">\n",
       "            verbose\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-verbose;\">\n",
       "            verbose: int, default=0<br><br>For the liblinear and lbfgs solvers set verbose to any positive<br>number for verbosity.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">0</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('warm_start',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-warm_start;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=warm_start,-bool%2C%20default%3DFalse\">\n",
       "            warm_start\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-warm_start;\">\n",
       "            warm_start: bool, default=False<br><br>When set to True, reuse the solution of the previous call to fit as<br>initialization, otherwise, just erase the previous solution.<br>Useless for liblinear solver. See :term:`the Glossary &lt;warm_start&gt;`.<br><br>.. versionadded:: 0.17<br>   *warm_start* to support *lbfgs*, *newton-cg*, *sag*, *saga* solvers.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">False</td>\n",
       "        </tr>\n",
       "    \n",
       "\n",
       "        <tr class=\"default\">\n",
       "            <td><i class=\"copy-paste-icon\"\n",
       "                 onclick=\"copyToClipboard('n_jobs',\n",
       "                          this.parentElement.nextElementSibling)\"\n",
       "            ></i></td>\n",
       "            <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-n_jobs;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=n_jobs,-int%2C%20default%3DNone\">\n",
       "            n_jobs\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-n_jobs;\">\n",
       "            n_jobs: int, default=None<br><br>Does not have any effect.<br><br>.. deprecated:: 1.8<br>   `n_jobs` is deprecated in version 1.8 and will be removed in 1.10.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "            <td class=\"value\">None</td>\n",
       "        </tr>\n",
       "    \n",
       "                  </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    \n",
       "        <div class=\"estimator-table\">\n",
       "            <details>\n",
       "                <summary>Fitted attributes</summary>\n",
       "                <table class=\"parameters-table\">\n",
       "                    <tbody>\n",
       "                        <tr>\n",
       "                        <th>Name</th>\n",
       "                        <th>Type</th>\n",
       "                        <th>Value</th>\n",
       "                        </tr>\n",
       "                        \n",
       "       <tr class=\"default\">\n",
       "           <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-classes_;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=classes_,-ndarray%20of%20shape%20%28n_classes%2C%20%29\">\n",
       "            classes_\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-classes_;\">\n",
       "            classes_: ndarray of shape (n_classes, )<br><br>A list of class labels known to the classifier.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "           <td class=\"fitted-att-type\">ndarray[int64](3,)</td>\n",
       "           <td>[0,1,2]</td>\n",
       "\n",
       "\n",
       "       </tr>\n",
       "    \n",
       "\n",
       "       <tr class=\"default\">\n",
       "           <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-coef_;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=coef_,-ndarray%20or%20CSR%20matrix%20of%20shape%20%281%2C%20n_features%29%20or%20%28n_classes%2C%20n_features%29\">\n",
       "            coef_\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-coef_;\">\n",
       "            coef_: ndarray or CSR matrix of shape (1, n_features) or (n_classes, n_features)<br><br>Coefficients of the features in the decision function.<br><br>`coef_` is of shape (1, n_features) when the given problem is binary.<br><br>By default, it will be created as a dense array, but can be turned to<br>sparse (CSR format) through :meth:`sparsify` (which can be beneficial<br>under L1 regularization when many coefficients are zero), and back to<br>dense through :meth:`densify`.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "           <td class=\"fitted-att-type\">ndarray[float64](3, 530)</td>\n",
       "           <td>[[ 0.02, 0.01,-0.02,..., 0.01,-0.06,-0.04],\n",
       " [-0.  ,-0.02, 0.  ,..., 0.03, 0.01, 0.01],\n",
       " [-0.01, 0.01, 0.02,...,-0.03, 0.05, 0.03]]</td>\n",
       "\n",
       "\n",
       "       </tr>\n",
       "    \n",
       "\n",
       "       <tr class=\"default\">\n",
       "           <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-intercept_;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=intercept_,-ndarray%20of%20shape%20%281%2C%29%20or%20%28n_classes%2C%29\">\n",
       "            intercept_\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-intercept_;\">\n",
       "            intercept_: ndarray of shape (1,) or (n_classes,)<br><br>Intercept (a.k.a. bias) added to the decision function.<br><br>If `fit_intercept` is set to False, the intercept is set to zero.<br>`intercept_` is of shape (1,) when the given problem is binary.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "           <td class=\"fitted-att-type\">ndarray[float64](3,)</td>\n",
       "           <td>[-0.49, 0.87,-0.38]</td>\n",
       "\n",
       "\n",
       "       </tr>\n",
       "    \n",
       "\n",
       "       <tr class=\"default\">\n",
       "           <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-n_features_in_;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=n_features_in_,-int\">\n",
       "            n_features_in_\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-n_features_in_;\">\n",
       "            n_features_in_: int<br><br>Number of features seen during :term:`fit`.<br><br>.. versionadded:: 0.24</span>\n",
       "        </a>\n",
       "    </td>\n",
       "           <td class=\"fitted-att-type\">int</td>\n",
       "           <td>530</td>\n",
       "\n",
       "\n",
       "       </tr>\n",
       "    \n",
       "\n",
       "       <tr class=\"default\">\n",
       "           <td class=\"param\">\n",
       "        <a class=\"param-doc-link\"\n",
       "            style=\"anchor-name: --doc-link-n_iter_;\"\n",
       "            rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.9/modules/generated/sklearn.linear_model.LogisticRegression.html#:~:text=n_iter_,-ndarray%20of%20shape%20%281%2C%20%29\">\n",
       "            n_iter_\n",
       "            <span class=\"param-doc-description\"\n",
       "            style=\"position-anchor: --doc-link-n_iter_;\">\n",
       "            n_iter_: ndarray of shape (1, )<br><br>Actual number of iterations for all classes.<br><br>.. versionchanged:: 0.20<br><br>    In SciPy &lt;= 1.0.0 the number of lbfgs iterations may exceed<br>    ``max_iter``. ``n_iter_`` will now report at most ``max_iter``.</span>\n",
       "        </a>\n",
       "    </td>\n",
       "           <td class=\"fitted-att-type\">ndarray[int32](1,)</td>\n",
       "           <td>[100]</td>\n",
       "\n",
       "\n",
       "       </tr>\n",
       "    \n",
       "                    </tbody>\n",
       "                </table>\n",
       "            </details>\n",
       "        </div>\n",
       "    </div></div></div></div></div><script>/*  Authors: The scikit-learn developers\n",
       " SPDX-License-Identifier: BSD-3-Clause\n",
       "*/\n",
       "\n",
       "function copyToClipboard(text, element) {\n",
       "    // Get the parameter prefix from the closest toggleable content\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${text}` : text;\n",
       "\n",
       "    const originalStyle = element.style;\n",
       "    const computedStyle = window.getComputedStyle(element);\n",
       "    const originalWidth = computedStyle.width;\n",
       "    const originalHTML = element.innerHTML.replace('Copied!', '');\n",
       "\n",
       "    navigator.clipboard.writeText(fullParamName)\n",
       "        .then(() => {\n",
       "            element.style.width = originalWidth;\n",
       "            element.style.color = 'green';\n",
       "            element.innerHTML = \"Copied!\";\n",
       "\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'red';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 2000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "\n",
       "document.querySelectorAll('.copy-paste-icon').forEach(function(element) {\n",
       "    const toggleableContent = element.closest('.sk-toggleable__content');\n",
       "    const paramPrefix = toggleableContent ? toggleableContent.dataset.paramPrefix : '';\n",
       "\n",
       "    const parent = element.parentElement;\n",
       "    if (!parent || !parent.nextElementSibling) {\n",
       "        console.warn('Expected copy-paste icon is missing from the DOM structure');\n",
       "        return;\n",
       "    }\n",
       "\n",
       "    const paramName = element.parentElement.nextElementSibling\n",
       "        .textContent.trim().split(' ')[0];\n",
       "    const fullParamName = paramPrefix ? `${paramPrefix}${paramName}` : paramName;\n",
       "\n",
       "    element.setAttribute('title', fullParamName);\n",
       "});\n",
       "\n",
       "/**\n",
       " * Copy the list of feature names formatted as a Python list.\n",
       " *\n",
       " * @param {HTMLElement} element - The copy button inside a `.features` block; its siblings\n",
       " *   contain a `details` element and a table containing feature named.\n",
       " * @returns {boolean} Always returns `false` so callers can prevent the default click behavior.\n",
       " */\n",
       "function copyFeatureNamesToClipboard(element) {\n",
       "    var detailsElem = element.closest('.features').querySelector('details');\n",
       "    var wasOpen = detailsElem.open;\n",
       "    detailsElem.open = true;\n",
       "    var content = element.closest('.features').querySelector('tbody')\n",
       "                  .innerText.trim();\n",
       "    if (!wasOpen) detailsElem.open = false;\n",
       "    const rows = content.split('\\n').map(row => `    \"${row}\"`);\n",
       "    const formattedText = `[\\n${rows.join(',\\n')},\\n]`;\n",
       "    const originalHTML = element.innerHTML.replace('✔', '');\n",
       "    const originalStyle = element.style;\n",
       "    const copyMark = document.createElement('span');\n",
       "    copyMark.innerHTML = '✔';\n",
       "    copyMark.style.color = 'blue';\n",
       "    copyMark.style.fontSize = '1em';\n",
       "\n",
       "    navigator.clipboard.writeText(formattedText)\n",
       "        .then(() => {\n",
       "            element.style.display = 'none';\n",
       "            element.parentElement.appendChild(copyMark);\n",
       "\n",
       "            setTimeout(() => {\n",
       "                copyMark.remove();\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 1000);\n",
       "        })\n",
       "        .catch(err => {\n",
       "            console.error('Failed to copy:', err);\n",
       "            element.style.color = 'orange';\n",
       "            element.innerHTML = \"Failed!\";\n",
       "            setTimeout(() => {\n",
       "                element.innerHTML = originalHTML;\n",
       "                element.style = originalStyle;\n",
       "            }, 1000);\n",
       "        });\n",
       "    return false;\n",
       "}\n",
       "/**\n",
       " * Adapted from Skrub\n",
       " * https://github.com/skrub-data/skrub/blob/403466d1d5d4dc76a7ef569b3f8228db59a31dc3/skrub/_reporting/_data/templates/report.js#L789\n",
       " * @returns \"light\" or \"dark\"\n",
       " */\n",
       "function detectTheme(element) {\n",
       "    const body = document.querySelector('body');\n",
       "\n",
       "    // Check VSCode theme\n",
       "    const themeKindAttr = body.getAttribute('data-vscode-theme-kind');\n",
       "    const themeNameAttr = body.getAttribute('data-vscode-theme-name');\n",
       "\n",
       "    if (themeKindAttr && themeNameAttr) {\n",
       "        const themeKind = themeKindAttr.toLowerCase();\n",
       "        const themeName = themeNameAttr.toLowerCase();\n",
       "\n",
       "        if (themeKind.includes(\"dark\") || themeName.includes(\"dark\")) {\n",
       "            return \"dark\";\n",
       "        }\n",
       "        if (themeKind.includes(\"light\") || themeName.includes(\"light\")) {\n",
       "            return \"light\";\n",
       "        }\n",
       "    }\n",
       "\n",
       "    // Check Jupyter theme\n",
       "    if (body.getAttribute('data-jp-theme-light') === 'false') {\n",
       "        return 'dark';\n",
       "    } else if (body.getAttribute('data-jp-theme-light') === 'true') {\n",
       "        return 'light';\n",
       "    }\n",
       "\n",
       "    // Guess based on a parent element's color\n",
       "    const color = window.getComputedStyle(element.parentNode, null).getPropertyValue('color');\n",
       "    const match = color.match(/^rgb\\s*\\(\\s*(\\d+)\\s*,\\s*(\\d+)\\s*,\\s*(\\d+)\\s*\\)\\s*$/i);\n",
       "    if (match) {\n",
       "        const [r, g, b] = [\n",
       "            parseFloat(match[1]),\n",
       "            parseFloat(match[2]),\n",
       "            parseFloat(match[3])\n",
       "        ];\n",
       "\n",
       "        // https://en.wikipedia.org/wiki/HSL_and_HSV#Lightness\n",
       "        const luma = 0.299 * r + 0.587 * g + 0.114 * b;\n",
       "\n",
       "        if (luma > 180) {\n",
       "            // If the text is very bright we have a dark theme\n",
       "            return 'dark';\n",
       "        }\n",
       "        if (luma < 75) {\n",
       "            // If the text is very dark we have a light theme\n",
       "            return 'light';\n",
       "        }\n",
       "        // Otherwise fall back to the next heuristic.\n",
       "    }\n",
       "\n",
       "    // Fallback to system preference\n",
       "    return window.matchMedia('(prefers-color-scheme: dark)').matches ? 'dark' : 'light';\n",
       "}\n",
       "\n",
       "\n",
       "function forceTheme(elementId) {\n",
       "    const estimatorElement = document.querySelector(`#${elementId}`);\n",
       "    if (estimatorElement === null) {\n",
       "        console.error(`Element with id ${elementId} not found.`);\n",
       "    } else {\n",
       "        const theme = detectTheme(estimatorElement);\n",
       "        estimatorElement.classList.add(theme);\n",
       "    }\n",
       "}\n",
       "\n",
       "forceTheme('sk-container-id-1');</script></body>"
      ],
      "text/plain": [
       "LogisticRegression(C=0.1, solver='sag')"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loaded_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "b74d7ee7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "([2, 0, 2, 2, 0]\n",
       " Categories (3, int64): [0 < 1 < 2],\n",
       " array([2, 0, 2, 2, 0]))"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "targets[:5], y_pred[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "397854f9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "TP:  [65 66 65]\n",
      "FP:  [0 3 1]\n",
      "TN:  [131 130 131]\n",
      "FN : [2 4 2]\n",
      "Accuracy:  0.98\n",
      "Precision:  [1.         0.95652174 0.98484848]\n",
      "Recall:  [0.97014925 1.         0.97014925]\n",
      "f1_score:  [0.98484848 0.97777778 0.97744361]\n",
      "FPR:  [0.         0.02255639 0.00757576]\n",
      "TPR:  [0.97014925 0.94285714 0.97014925]\n",
      "                    0           1           2\n",
      "TP          65.000000   66.000000   65.000000\n",
      "TN         131.000000  130.000000  131.000000\n",
      "FP           0.000000    3.000000    1.000000\n",
      "FN           2.000000    4.000000    2.000000\n",
      "precision    1.000000    0.956522    0.984848\n",
      "recall       0.970149    1.000000    0.970149\n",
      "f1_score     0.984848    0.977778    0.977444\n",
      "TPR          0.970149    0.942857    0.970149\n",
      "FPR          0.000000    0.022556    0.007576\n",
      "TNR          1.000000    0.977444    0.992424\n",
      "PPV          1.000000    0.956522    0.984848\n",
      "NPV          0.984962    0.970149    0.984962\n",
      "FNR          0.029851    0.057143    0.029851\n",
      "FDR          0.000000    0.043478    0.015152\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(np.float64(0.98),\n",
       "       0     1     2\n",
       " 0  65.0   1.0   1.0\n",
       " 1   0.0  66.0   0.0\n",
       " 2   0.0   2.0  65.0,\n",
       "                     0           1           2\n",
       " TP          65.000000   66.000000   65.000000\n",
       " TN         131.000000  130.000000  131.000000\n",
       " FP           0.000000    3.000000    1.000000\n",
       " FN           2.000000    4.000000    2.000000\n",
       " precision    1.000000    0.956522    0.984848\n",
       " recall       0.970149    1.000000    0.970149\n",
       " f1_score     0.984848    0.977778    0.977444\n",
       " TPR          0.970149    0.942857    0.970149\n",
       " FPR          0.000000    0.022556    0.007576\n",
       " TNR          1.000000    0.977444    0.992424\n",
       " PPV          1.000000    0.956522    0.984848\n",
       " NPV          0.984962    0.970149    0.984962\n",
       " FNR          0.029851    0.057143    0.029851\n",
       " FDR          0.000000    0.043478    0.015152)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from chemml.utils import classification_metrics\n",
    "classification_metrics(targets, y_pred)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "592b1e91",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA60AAAGICAYAAACqWwZzAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjExLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvctoD+AAAAAlwSFlzAAAPYQAAD2EBqD+naQAAj5lJREFUeJzt3QV4U2cXB/BDKe7uMlyG+4Bhw2FjY8hw2JABGzbcfTgMh8EYso0xHIa7u7u7DC9QCpR8z//su1kS0pKWtEma/+958rS5kd7cNLn33HPe80YymUwmISIiIiIiInJDPq5eASIiIiIiIqKgMGglIiIiIiIit8WglYiIiIiIiNwWg1YiIiIiIiJyWwxaiYiIiIiIyG0xaCUiIiIiIiK3xaCViIiIiIiI3BaDViIiIiIiInJbDFrJ7Tx79kx69eolJUqUkOzZs8uUKVOc/jeOHDki2bJlk82bNzv9uT0ZtwsRERERuRtfV68AuZ/AwED5888/Zfny5XL+/Hm9njZtWsmXL580a9ZMUqdOHaZ/v0uXLrJw4UKZN2+epEqVSpIkSeL0v+Hv7y9nzpyRp0+fSni7dOmSVK5cWX9v27atXmxNmzZNRo8erb/jfcicOXOI/sbevXulUaNG8vPPP2vw7wnbhYiIPNdff/2lJ5wNvr6+kjhxYilZsqS0b99eEiVKZPdx9+/f15PTOIl8584diRs3rhQsWFBatGghOXLksPuYJ0+eyMyZM2XDhg1y48YNiR49uh6nlC5dWurXry9x4sR55/o64zmIKPxEMplMpnD8e+Tmrl+/Lp999plcvXpVOnbsKKVKlZKYMWPK8ePHZfz48XLgwAG5cuWKBpNhBTuNTz75RHcmYeXFixdy+fJlSZMmjcSKFUvC0+nTpzWDHCVKFMmYMaOcOnXqrfvkzp1b7/fq1Ss5duyYfPjhhyH6G9j5lylTRlatWiWVKlXyiO1CRESeCydJmzdvLtOnT9eTpQEBAbJ//37p2rWrBoCHDx+WePHivbWv+uKLL3Rf2LlzZ8maNavcvXtXfvnlFz15Pnz4cD0WsbR9+3apWbOmBsQdOnTQE+o4ub5z50492Rs1alQ94R4cZzwHEYUvZlrJDAFStWrV9EwnglMEj4a8efNKvXr1pFu3bnq/sHT79m090xqWcEYV5cGuhGzrsmXLZPfu3VK0aFHzcmx7BKo1atSQJUuWhOs6ucN2ISIiz4VqLGM/kidPHkFuBMHsrFmzpF27dub7Xbx4UU+SI2Bcs2aNRIsWzXxb+fLlJV26dNKpUyf9iQDTqFTCcQqed/Xq1RIjRgzzYwoXLqzVYJZ/wx5nPAcRhT+OaSWzuXPn6pjGQYMGWQWs5n8WHx8964ksnOX406FDh2pGFtlB7Ah+++23t85oYgeGktW1a9dq5g9BMHYMKMkxzJ49W++HoNj4HZdHjx5p2RF+RwbYEh6P5fPnz7dajtLi6tWrS/78+aVixYoyZMgQq5LXoMZuOvP1vEuxYsX0rDJ25JZwhhnlwMWLF3/rMcbrNS7Y6X7++eeyePFi833wO0qDAQcKxn2xTW3X/++//9bgOWfOnLojt7ddWrZsqdsRWXhLPXr00AywvUwxERERYP8BZ8+etdoggwcP1hLdSZMmWQWshgEDBkjKlCn1ZLkBxyePHz+WqVOnWgWbBpzwRsY3OCF9ju7du2uJsy0M3cH+8ty5c+Zl48aNMx/H/PTTT/Lxxx/LRx99pFljLEe22dbWrVv1tnXr1pmXYf2wfVCqbByLYNiU7fEKjskQ4CPwx7EA9vNv3rwJ9vUTeSpmWsls6dKl+hNffMGJHDmy/nz+/Ll+IV+7dk1GjhypX7o4W4qAadeuXVpODAgWMU4SX9oPHz6Unj176o4KYzmrVKmiX+KRIkXSIBNnOREI4XfsKABlRQhc8RwvX760WhfsGLAcz2vAuvTu3Vt/IjDEYxGEtWnTRn799dcgx246+/U4okmTJjJs2DAZO3asZjlRTvX777/r2WV7kiZNapV9xd9H4Pnll1/qTrZp06ZStmxZ3Sk3btxY+vbtax7TmixZMqv1nzNnju4YsZ2xzti29rZL//79dYdYu3Zt2bJli5Y1L1iwQIP7H3/8UUudiYiI7Ll586b+tO1PgaAP+4+gxq1iX/Ppp5/qeNcTJ07oyVVUJ+ExwVUEGccoQQnpc9y6dcsqMDVg/4n9Jfbbhn/++UeXoSQapdDYv+PvYciT0WdiwoQJVs+D4Bkl0UZgjGo37LeRKEDgjtJpBLYNGjTQYUM45gCMu8WJ5hEjRuiJbhy7LFq0SI8LmCmmCAljWokgZ86cpgQJEji8MQYPHozx0KYtW7ZYLe/bt68u37Vrl15ftWqVXq9UqZLV/RYvXqzL161bZ7U8cuTIpnbt2lktmz59ut733LlzVssvXbqkyydPnmxeVqRIEVP16tXfWt+XL1+af8e64XHLly8P89dj69SpU3q/oUOHmq5fv27y8fEx/f7773rb/Pnz9fq1a9dMI0aM0PsdO3bM9C7ffPONKVOmTObrmzZt0sdiXW0Z61+6dGmr5W/evLG7XWDz5s36vnz33Xem06dPm+LEiWP69NNP9TFERETGftpyv3Pr1i1TwYIFTTFixDCdOXPGvPzRo0d6X3v7aksjR47U+y1dutT08OFDhx4TnNA8R+PGjU3JkiV7a/mcOXPe2kf37NlTl/Xq1cu8zNhP1q1bV4+x/P39rdYH26Zt27bmZfXq1TPFjRvXdOPGDau/N2rUKJOvr6/p6tWrphcvXug+ediwYcEe6xBFJCwPJqusJc5sOmrlypXywQcfaHbSErJ9sGLFCqvlderUsbqOrCrgrKSzx9Ns27ZNs4HIHBre9dpc8XrQ0AqlPUaJMEqDcUY2uA7NKOv95ptvpEiRIuazxci+YnyQbSY6OF999ZXV9eCywyiXRvYW2WY0eELzCmStHc0oExGRdzCGpWB/in3ZvXv3tNopS5Ys5vsY+6p37ZeN23F/o59GSI5TbDnjOUK6fzX2k9hvIwtqOZwHw49wnPL111+b1w+3Y9gOSqMtoQru9evXsn79ei2nRuYaw7ow5MeyJDisXxuRqzBoJbMUKVLIgwcPHA58UPJjb+wrxryirMUoCbJcbilhwoT6Ezs0ZxozZowGkHXr1pUECRJoEIoSHT8/P7d8PSgRxliWffv26U8jSLYHTSMwPgY7OZQNoUQZAStKd7HTCknQau+1BgclyygxRqkUxtHEjx8/RI8nIqKID8NSsF9CL4o+ffpoLwrb8ZjYXyLwst2v2jJux/GJ8Rjsg0LLGc8R2v0rhu4gkLecGQG/Y8wv+mIY5cXYv2MaHgyVQkk0LiihNmYCQLNKwIl5NLlCWTGmE0IpNce0UkTGMa1khgwaxiwiS1muXLl3bhmMNbUcS2rAMgRQtnOcBTXOxJFZl4zpVywzp4BxILYQTGIsKoJHnIFEIIhxmTijic68mDvO1a/HEroEo/EDAk/8DVwPCho7oJMizq5aZjkxVU1IYQxtSGAcDXaoOHjAQQnOBHNaHCIiCqp7cIECBTQ7OHDgQB2niX4Vxv4T17GPRt+JoE6Cbty4UWLHjq3ztuIxCNDwGIwntZ0+xxGheQ7s52yPPYI6/ghu/4p9Nho2IpDH1HL4+zgmQSMqA14rVK1a1aoBlSVjbDC2H2YaQJUVXg/GzqKXBX7HXO9EEQ0zrWTWqlUrDZqwcwmq+xx2IMZZPmT80BTAtmMuSlfAXvfb0EKgBrbzptl2/7WEElYEgBMnTtSdxNGjR+XChQtB3j88X4/tzg2lxtiJITscXDCJbHHy5MmtAlY0gcB8rLbPCThYcFaTLjSnwnZEGTV2kugqTEREFBw0+0Op6w8//GC1T0L1DvZfaOpnD5oMogIJTQ6N7sKYyxUnadEEMCiYPSA4IX0OHH+g2aJtkBrc8UdQUEmFyi0MBZoxY4Z2L7YsJcYJbATohw4d0uZKlrMFGBdkVS1lyJBBmzwhs41g17L8mCgiYdBKZij9ROdajJlEmQkCOAPOhKL9OrrjGlk97HAwdgJnDnE7HD9+XLp06aIt2t/VhTgkUO6LL2Z0yTPKfNFND119bX333XeyZ88ec+CNM6S4jjOqtmNELIXn67GF8mVMHYOfwcHYUuzE8dqNjscYJ4NtYwklSNgx2muvH1IIUFHCXKFCBe3KjE7CyPhip46uh0REREFBYNarVy+d8sZyijdU6yCgxXATVO8YXesDAwN16AuCOUz50q9fP/NjsB9C5RT2lQg+Uf1jwLRt2FcFlaEM7XOgOz8qtPAYVFLhgo7GCGRDCn0sMA0fglZUf2H+Wdss86hRo/R4oEWLFjpky3LdEPijSzAuOGbB/tmAkmf01AiqGzORp2PQSlZwlg5BUcyYMaVQoUIayKZPn15LQtFKHeNF8aULOAuILCS+VFGugoAQYzPwOJTkOrMZAHYYaPyDLCimfUG2EW3j0RzIXplzx44dNWuM4A1nJbFTwllb2xJfS+H5emwhoMYZVJxlfVeJLnZyeI0owcLrw7Q+xlgXA943zKOKca84S2w5T2tI4AQFdthYLwSpCISNRhs4s4u2+gcPHgzx8xIRkffAyVXsrxD4WU4RgznUMTYTjQ6x38UJWIw7RTCJaWMw1Md2Dlej4gfHKtgPYvwojksw9hPTxUyePPmd6xOS58A6oWIL08Rh3XD8gQARryk00HQJQef9+/fNDZgsoQ8Hhmphmh3syzHkCccICHaxjlhmLMe+H0EvjtOwnjip/K5MM5GnioQWwq5eCXJPKOPBlzcylgjggpv7DIEespP4MkfAazsBNr6gsVOwvA3/ejgriDJeXAxYhgZKCE5t4TFo6oDgEzsPdNpDyS/+ru3ZSgRcKGXGl7vtBOK4DeW4+NK3Ny7Tma/HFpol4ewoXp/RvMkerAPKkbAjiho1qtVtyLAiEMf7gmAaOz9cz5o1q1XpMLLMaGSB7YTtgO0a1Prb2y7Gfe29Jhx44Mwvtju2ExEReS+M0UQwF9R+FccT6BGBAMveMBhUUWE/hv277ZyuQcE+DvtJPB/2qaHpaO/oc2DfjRPn2Jdi34lMK/avlvto9NLAJbg5YJFJNuZ9td1n20L2GeuGvxlUDwmsB7Y99sPsHEwRGYNWIiIiIiIiclssDyYiIiIiIiK3xaCViIiIiIiI3BaDViIiIiIiInJbDFqJiIiIiIjIbTFoJSIiIiIiIrflKx4MU7Gg3Tjao4emzTkRkbvAlEmY8gHTGBnz4RK9C/eDRETkDcc0Hh20ImDFfGBERBEF5sXFZPdEjuB+kIiIvOGYxqODVmRYIWquZhIp8r8TO5P7uLTuR1evApHH8PN7IlkzpDV/rxE5wvh/wYFB3LhxudGIiMjlnjx5oolFZx7TeHTQapQEI2CNFDmaq1eHbPAAiijkONSBQvP/gu9bfucSEVFEPabhwCkiIiIiIiJyWwxaiYiIiIiIyG0xaCUiIiIiIiK3xaCViIiIiIiI3BaDViIiIiIiInJbDFqJiIiIiIjIbTFoJSIiIiIiIrfl0fO0EhERuZPdu3fLokWLJGPGjNKyZUuHHrNy5UrZsWOHTsJeq1YtyZQpU5ivJxERkSdhppWIiOg9PXr0SPLlyyft2rWTVatWyeLFix16XKtWraRp06ZiMpnk2LFjkitXLtm8eTPfDyIiIgvMtBIREb2nKFGiyC+//CJ58+aVBg0ayL179975mL1798rUqVNl27ZtUqJECV3WpEkTadu2rRw/fpzvCRER0f8x00pERPSeYsWKpQFrSCxdulTSpUtnDlihUaNGcuLECTl37hzfEyIiov9jppWIiMgFzp49q2NfLRnXEbRmzpz5rccEBAToxfDkyROH/taBv3+RxPtHSow3z997vendtsSMLLMSRJPnTA0QkRd67R/o9Odk0EpEROQCz58/1+ZLluLGjWu+zZ6hQ4dK//79Q/y3ELCme3M9lGtKITUnQQq5GpURKxF5p0Bfk9Ofk0ErERGRCyBgvX37ttWyhw8fmm+zp3v37tKxY0erTGuaNGne+beMDGugKZLcj5TgPdec3sXPJ7L+9DGZJGGg8w/eiIjcReCrN3Jp8V1JnDeOxM8SS5e9fv3G6X+HQSsREZEL5MiRQ7Zu3aqdgyNFiqTLTp8+rT+zZ89u9zHRokXTS2ghYE3a71KoH0+O8VlQTuT5XUkcK5lsqLWBm42IIqTDhw9Lw4YN5frxB+J7Nq5sObJLK4ZwQjXed/Gc+rdYu0JERBQO0FG4ffv2cvLkSb3+5Zdfyp07d7QhEyB4nTJlihQtWlTSpk3L94SIiNxSYGCgDBs2TAoXLmzudn/z5k3ZtWtXmP1NZlqJiIicoE+fPnp2+cCBA+Lv768BKqbCGTFihHku13Hjxsknn3yiWVZcBgwYoFPkVK9eXa5evarNmTZsCHlmruzIzeIbPdZ/19/slBavf5eY4q/XE5keivybzKX3sObyGpl4eKI8e/Us2Pvd83/3lEdERJ7o4sWL0rhxY9m+fbt5We7cuWXu3Lk613hYYdBKRETkBBhb+uzZM2nZsuV/O1nf/3azSZIkkTFjxkjOnDnNy3r27Cmffvqp7Ny5U8exVq5cWRIkCPmY07t+AeLz8t9xlNAs6m+S3ufmf3f4f8Dq7xMzFK+MDAhYLz12vLw6VpT/TiQQEXkyk8kkM2fO1BOyT58+1WUY2tKlSxdtEPg+Q1ccwaCViIjICZo3bx7s7fHixdOdvS2cmX7fs9M+kUSSx41uvh735Qv9GSg+cl/imwPW+4V+kHTv9Ze8m5Fh9YnkI4ljJH5nwNo2b9twWjMiorBz9+5d3cctW7bMvCx9+vQye/ZsKVmypIQHBq1EREQeLnHsaLK7R7n/FoyKLuInEjlOckna6ZR5MQNWJ23vGInZYImIvMaDBw9k7dq15uvNmjXTyiFjmrbwwKCViIjIw/knGyLlFoz7b0GCyCLxU4pEiiyCTrbkFByrSkTeKFu2bDJ8+HAZOHCgTJ8+XT777LNwXwcGrURERB7OFPmJ3H1u0RwocqT/dvHP77psvSIqjlUloohs79692lwpevT/hp20adNGvvrqK0mcOPihEWGFQSsREZGnM0WSpDGT/nfd746IKfDfTGucZK5cswiHY1WJKKJ6+fKl9OvXT6ezadeunYwePdp8m4+Pj8sCVmDQSkRE5OEivYljPcZyVHYRv5sicVKKNAv5FDpERORdTpw4oVOwHT58WK9jzGrt2rV17nB34OPqFSAiIiIiIqLw9+bNGw1QCxQoYA5YMcf40KFDpVChQm7zljDTSkRERERE5GWuXr0qTZo0kU2bNpmXYS7xuXPnSt68ecWdMNNKRERERETkJUwmkwammCPcCFgjRYokHTt2lP3797tdwArMtBIREREREXmJv/76Sxo2bGi+niZNGvn111+lTJky4q6YaSUiIiIiIvISn3/+uRQpUkR/R/B69OhRtw5YgZlWIiIiIiKiCNxsycfnv1ylr6+vzJkzR44cOSJffvmleAJmWomIiIiIiCKgPXv26NjVffv2WS3PnDmzxwSswKCViIiIiIgoAnn16pX07dtXihcvLidPntQy4OfPn4unYnkwERERERFRBHHmzBlp0KCBdgI2xIsXTx48eCAxY8YUT8RMKxERERERUQSYymbChAmSL18+c8AaOXJk6d+/v+zYsUNSp04tnoqZViIiIiIiIg9248YNadasmaxdu9a8LGvWrNpwqVChQuLpmGklIiIiIiLyUKtWrdJmS5YBa9u2beXgwYMRImAFZlqJiIiIiIg8VIoUKeTp06f6e8qUKeWXX36RChUqSETCoJWIiIiIiMhD5c2bVwYMGCCHDx+WSZMmScKECSWiYdBKRERERETkAfz9/WX8+PHSvn17iRo1qnl5165dJVKkSBJRMWglIiIiIiJycwcOHNCpbE6fPi1+fn4ycOBA820ROWAFNmIiIiIiIiJyU69fv5ZBgwZJ0aJFNWCFMWPGyL1798RbMNNKRERERETkhs6dOyeNGjWS3bt3m5flz59fp7JJnDixeAsGrS4QK0ZU+eKTvJI5bVI5eeGW/Ln2oLx5YzLf/mP7zySyj3USfOnmo7L94AUXrK13u3njhsyb+6v8c/euDBk2Unx9+ZFxF7t27pAVy5ZIlqzZpHHTr129OkREREROYzKZZNq0adKxY0d5/vy5LvPx8ZHu3btLnz59rMazegOWB4ezLOmSyqEF3aXJZ0XlybMXUjx/Rpk/0vqAu03djyVaNF+5cuuB+eL37EV4r6rX69T+OylXurjs2rFDJk34SUszyPX++ecfKVIgj/Tq3kVWr/pbVq1c4epVIiIiInKaW7duSbVq1aRVq1bmgDVjxoyyfft2LRP2toAVXJo2evjwofTs2VM2bNgg0aNHlzp16mjnq8iRI0tENWdoYzly9obU6vizedkHqRK9db/lm4/Jul3/1qyTa9T5qr4MGzlGli9bImvXrOLb4CaiRYsmM36dKx9+mEvq160lgTyZQERERBHI1KlT5e+//zZfb9mypYwcOVJix44t3srXlSnvTz/9VF6+fCm//vqrBrCNGzeWBw8e6JsSERXPm0FyZ0klrQf9YbX80o37b90X5cMfF8gkl28+kOWbj8rdB/9OGEzhp3CRotzcbihu3LgasBIRERFFRCgBXrx4sdy5c0dmzJghVatWFW/nsqB106ZNmuI+efKkZM+eXZcNGTJE2rRpI7169ZL48eNLRJM/Rxp5/uKlXLv9UNo3KCNxY0eX4+duypJNR63GtPo9D9Drz/xfSu2K+WVg22pS+4cZHNNKRERERBQBy4FTpEhhVVW2cOFCiRcvniRJksSl6ybePqZ1y5Ytkjp1anPACpUqVdLMq2V3rIgkbuwY8up1oKya3EZSJo0ngW9MMvj7T2Xt1LbiG/m/t6JovRHSZvB8+XHGWqnYcoKs3n5Spvet59J1JyIiIiIi53nx4oV07txZx6seP37c6rZMmTIxYHWHoPX69euSPHlyq2XJkiXTnzdu3LD7mICAAHny5InVxZM8ffZC4sWOIcNmrpMuo5fI4GmrpXyL8VIkV3otBzZcvf3Q6nHzVu6T9KkSSaqk8Vyw1kRERERE5ExHjhyRQoUK6bBIf39/qV+/vsY65GZB65s3b96aPgQNmNDKOTAw0O5jhg4dqmly45ImTRrxJCcv3tafB09dMy+7fueR/PPwqQalQYka5d/GVL6+EbdBFRERERFRRIc4Z/jw4RqwGtlVdANu2LAhp1Z0x6AV9dn37t2zWoYmTAhmg6rdxqDkx48fmy/Xrv0X/HmCLfvPya17j6Vs4SzmZTkyJpdkieLIsbP/ZpdzZU4pieLFMt+OsuFWtUvKuSt35crNBy5ZbyIiIiIiej+XLl2SMmXK6Gwpr1690mW5c+eW/fv3yw8//BChZ1Dx2EZMhQsXllGjRsnt27fNZcLbtm2TSJEiScGCBe0+BoOScfFUL18FSot+v8vcHxtr4PrkWYBUK/Wh/Lpsj6zaflLvEztmNFk3/Ts5f+0fuffwqZTIl1F8fCJJox6zXb36XmfRwgWye+cOuXjhgl7v2a2zfpl83byVZM2WzdWr59X69uqupTTHjx7RE11dOrWXGDFiSP9BQ129akRERERvzZoya9Ys+f777+Xp039nBEHM06VLF+nfv79HxzcRPmjFhLko78WbNX36dPHz85MBAwboNDieVvYbEut3n5Y8NYdIuaLZJLJPJJnw+xY5+v8sK+w6ckmKNxwlpQpmluSJ48qfaw7KjkMXtYETha+ECRNJunTp9VKmbDnzcgRH5Fqp06SVlwEB0qJVa/OyqPzCJyIiIjfUsWNHGTt2rPl6+vTpZfbs2VKyZEmXrpcncVnQGj16dFm+fLk0atRIp7dBfXfFihVl5syZEtHdue8nv63cF+Tt/gGvZPWOfzOv5Dqly5TVC7mf5i2/dfUqEBERETmkTp068tNPP2l1WLNmzWTMmDE67zx5QNAKuXLlkkOHDsnDhw8lSpQoEjt2bFeuDhERERERkVMVLVpUhg0bptPY1KhRg1vXkxoxWUqQIAEDViIiIiIi8mg7d+7UTsC2s6Gg0RIDVg8PWomIiIiIiDzVy5cvpWfPnjpOde7cuTJixAhXr1KEwqCViIiIiIgolE6cOKElwEOGDNFxq7B27Vrz7/T+GLQSERERERGFEIJSdAUuUKCA9ukBX19fDV7XrVsnPj4MtSJEIyYiIiIiIiJPc/XqVWnatKls3LjRvCxHjhxaGpwvXz6XrltExPCfiIiIiIjIQfPmzZPcuXNbBawdOnSQAwcOMGANI8y0EhEREREROWj37t3y+PFj/T1NmjQya9YsKVu2LLdfGGKmlYiIiIiIyEGYczVr1qzSoEEDOXr0KAPWcMBMKxERERERkR3Pnj3Tst+PP/7YvCxmzJiabY0fPz63WThhppWIiIiIiMjGnj17dIxq5cqV5dy5c1a3MWANXwxaiYiIiIiI/u/Vq1fSt29fKV68uAarz58/l5YtW3L7uBCDViIiIie4ffu2Tn+QJUsWnbNv3Lhx73zMli1b5NNPP9WxUTib//3338vdu3f5fhARucjp06flo48+kgEDBkhgYKAuK1SokEyePJnviQsxaCUiInLCWfny5cvLtWvX5Pfff5eePXtK79695ccffwzyMcePH5cKFSrovH7Lli2TiRMnys6dO6VGjRp8P4iIwpnJZJIJEyboCcT9+/frssiRI0u/fv1kx44denKRXIeNmIiIiN7T4sWL5eTJk7J+/XpJliyZZlrPnj2rHSY7duwoUaNGfesxOAjy8fGRoUOHSqRIkXRZp06dpF69evLixQuJHj063xcionBw48YNadasmaxdu9a8DEHqnDlzNMtKrsdMKxER0XtCmS8mmkfAaqhUqZI8evRIp0Owp2TJknpmf/ny5XodgerSpUulVKlSDFiJiMIJvoerVatmFbC2bdtWDh48yIDVjTBoJSIiek/Xr1+X5MmTWy0zAlicwbcHZcErVqyQJk2aSMKECbUT5c2bNzVwDUpAQIA8efLE6kJERKGHSpfRo0fr7ylTppQ1a9bI+PHjdVobch8MWomIiN7TmzdvxNfXesRNlChR9KfRyMPWqVOnpE6dOtKiRQstFUZpMbKtDRs2DPLvoJQ4Xrx45kuaNGn43hERhdDr16+trpcpU0bmzp0rx44d014D5H4YtBIREb2nJEmSyL1796yWGddxmz04k58qVSpt1pQ9e3YpUaKEdqdEufC+ffvsPqZ79+7y+PFj8wWNn4iIyDH+/v7Svn17qVq1qp5stFS/fn2teiH3xKCViIjoPRUuXFiOHDkiz549My/btm2bNmDKkydPkKW+ceLEsVoWN25c/YmMqz3RokXT+1heiIjo3Q4cOGCejgzjV9GxnTwHg1YiIqL3hDJfjH/CVDeY/gZjXNE5GKW+RmB5+fJlSZ06tWzYsEGvV6xYUXbv3i1LliwxZwD69+8vSZMm1SkXiIjIOaXAgwcPlqJFi+qwDEB3dtshHeTeGLQSERG9pwQJEmhTJTTwwFjTDBkySMGCBfWMvuWBE5oyITiF2rVra2kwxrTiMXgOTJODOVtjx47N94SI6D2dP39eO7X36tXLPI41f/782hn422+/5fb1IDzFQERE5ATGWfz79+9LjBgx3uo8+cEHH+gY1MSJE5uXde7cWS+YGgePQfkvERG9/zQ206ZN03mynz9/rsswL3aPHj2kd+/edufOJvfGoJWIiMiJEiVKZHd55MiRtTzYHkx3Q0RE7+/ly5fyxRdfyMqVK83LMmbMKHPmzJFixYpxE3solgcTEREREVGEgCwqegMYWrZsKYcPH2bA6uGYaSUiIiIioghj7NixOlwDY1kxvQ15PgatRERERETkkbZu3arzYqMk2ICu7Tt37pRIkSK5dN3IeVgeTEREREREHgVzXXfp0kVKly4tTZs2latXr1rdzoA1YmHQSkREREREHuPo0aNSqFAhGTFihHYKfvLkifz000+uXi0KQwxaiYiIiIjI7QUGBmqgioD12LFj5sZLWDZs2DBXrx6FIY5pJSIiIiIit3b58mVp1KiRbNu2zbwsd+7cOpUNflLExkwrERERERG5JZT/zpo1SwNTI2DFeFWMZ927dy8DVi/BTCsREREREbkljFft1q2b+Pn56fX06dPLr7/+Kh9//LGrV43CETOtRERERETkluLFiyczZszQ39El+MiRIwxYvRAzrURERERE5BaePn2q09kkSpTIvKxq1apy6NAhyZs3r0vXjVyHmVYiIiIiInK5HTt2SJ48eaRZs2Y6ltUSA1bvxqCViIi82pkzZ6RGjRqSKlUqGT16tPnAaeLEia5eNSIir/Dy5Uvp0aOHlv1evHhRli1bJjNnznT1apEbYdBKRERe6+HDh1K6dGlJnjy5FChQQA+cAHMAYqL6mzdvunoViYgitBMnTkiRIkVk6NCh8ubNG1320Ucf6XczkYFBKxERea3FixdLsWLFZMqUKZIzZ07zckxWj8B19erVLl0/IqKICgHqmDFj9ITh4cOHdZmvr68MGTJEtm7dKhkzZnT1KpIbYSMmIiLyWleuXJFcuXKZ5/2zFDNmTJ1qgYiInOvq1avSpEkT2bRpk3lZjhw5ZO7cuZIvXz5ubnoLM61EROS1MN/fgQMH3gpa0b1y7dq1ki1bNheuHRFRxD1ZaBmwdujQQb+LGbBSUBi0EhGR16pVq5YcPXpUD5guX74sN27ckN9++01KliwpcePGlfLly7t6FYmIIpS0adNK5cqV9fc0adLIhg0btAle9OjRXb1q5MZYHkxERF4rduzYsnHjRvn222/1J8ZYTZo0SSpWrCjTp0+XyJEju3oViYgiFFS14Hs2adKkMmDAAIkfP76rV4k8ADOtRETk1WVqOLu/bt067SR8/vx5/fn333/L69ev5fr1665eRSIij/X8+XNp27atLFy40Gp5woQJtUM7A1ZyFINWIiLyWpMnT9bGH4ByYHSrxE/b24iIKGT27t2rY1Qx53XLli3l1q1b3IQUagxaiYiI7Hj06JE5gCUiIse8evVK+vXrp3Otnj171pxxPXjwIDchefeY1qsbhvHAwg0lKNTW1atAQXi4bwK3jZuJ7GM93QqFrfnz58vy5ct1bsAoUaLI8ePHrW7HVDcoGd6+fTvfCiIiB505c0YaNmwo+/btMy8rXLiwzJkzR7JkycLtSKHGTCsREXkdHx8fncQeDUGM340LgliUCS9atEgnvSciouCZTCYtA0Y5sBGwopFd//79ZceOHQxY6b1FiEwrERFRSKe6wQUNl2LEiCFlypThBiQiCgWMVW3atKmsWbPGvCxr1qyaXS1UqBC3KTkFg1YiIvJaVapUcfUqEBF5fJYVTZcM6BY8bNgwiRkzpkvXiyIWBq1EROT1Tp06JSdOnNDmS5YwFit37txev32IiIKSMmVKmTJlinTo0EF++eUXqVChAjcWOR2DViIi8motWrTQAy2UCWMMlr+/vwQEBEi8ePFk6NChDFqJiCxs3LhRx64mSJDAvKx27dpauRI7dmxuKwoTbMREREReCx2CV69eLZcuXZLWrVtL165d5dmzZzJp0iSJFSuW1K9f39WrSETkFnBCr3379lKuXDlp06bNW7czYKWwxKCViIi81oEDB6Ru3bqSOnVq7SL88uVLzbZ+++23UqRIEVmxYoWrV5GIyC2+K9FNfdy4cXr9999/15N+ROGFQSsREXktjGFNmDCh/p4kSRK5ceOG+bYUKVLI3bt3Xbh2RESu9fr1axk8eLAULVpUx/5DtGjRZOzYsZpxJQovHNNKREQkIiVKlJBBgwZJtWrVdP7W+fPnazaBiMgbnT9/Xho1aiS7du0yL8NY1rlz50qOHDlcum7kfRi0EhGR1ypbtqw2YALMJ4iyYJQLv3r1Spo3by7ly5d39SoSEYX7FDbTp0+Xjh076hh/wPCJ7t27S58+fSRq1Kh8RyjcMWglIiKvZTs1AzKtAwYMkMDAQIkSJYrL1ouIyFVWrVolLVu2NF/PmDGjzJ49Wz766CO+KeQyHNNKRERkuWP08dGA9eDBg7J27VpuGyLyKpUrV9ZhEsaUYIcPH2bASi7HoJWIiLwWDsYWLVokx48fNy+7cuWK1KtXTwoWLKhjuoiIIjLMS20JY/p//vln7Z4+depUTmVDboFBKxEReSUEpmgqUrNmTcmVK5f07t1blixZog1GEMQuX75c524lIoqotmzZItmyZdOSYEvJkiWTqlWrumy9iGxxTCsREXmdDRs2yMqVK2XhwoUauKI7JsZwoSx4yJAh8t1332mZMBFRRM2u9urVS0aNGqWNl5o1a6Yn6xIlSuTqVSOyi0ErERF5HYxXbdKkiXzxxRd6/YMPPtBMA4LWdu3auXr1iIjCzNGjR6VBgwZy7Ngx87IsWbLIixcvuNXJbfE0MhEReZ0HDx5IihQprJalSpVKMmfO7LJ1IiIKS+iKPnz4cB2vbwSsmL5mxIgRsnHjRv0OJHJXzLQSEZHXQTnc/fv3rRotPXr0SA/qLJclTpxY4seP76K1JCJyjkuXLknjxo1l27Zt5mW5c+eWuXPn6ph+InfHoJWIiLzSyJEj9WJvuWHo0KHSrVu3cF4zIiLnwdCHOnXqiJ+fn7k7cOfOnXVO6mjRonFTk0dg0EpERF7n22+/Nc9DGJz06dOHy/oQEYWV7NmzW32n/frrr/Lxxx9zg5NHYdBKREReJ126dHohIoroEKiOHz9ep7cZO3asxI0b19WrRBRibMRERERERBQBPH36VHr06GEuBTZgPOvMmTMZsJLHYqaViIiIiMjD7dy5Uxo2bCgXL16Ue/fuybRp01y9SkROw0wrERGRk2CeQ8wBe+7cuRA97s6dO/o4zpNIRCH18uVL6dmzp5QsWVIDVvjtt9/k+vXr3JgUYTBoJSIicoJly5ZJypQptUtn4cKFpVixYnL37t1gH/Pw4UP57LPPJFOmTNKyZUvJmjWrzJ8/n+8HETnk5MmTUrRoURkyZIi8efNGl+G758iRI5I6dWpuRYowGLQSEZHXwziwffv2yZUrV0K1LW7duiVfffWVdO/eXbOsN27c0OxHq1atgp0rtkaNGhrY4u/i7584cUICAgK8/v0gouAhQEVTpfz588uhQ4d0ma+vrwwePFi2bt0qGTNm5CakCIVBKxERebUZM2ZIihQpNDv6+++/67JNmzZJ9erVHX6OP/74Qw8Y27Vrp9djxowpHTt21Ozr/fv37T5m3bp1enA5adIkSZgwoS6LHTu2NGrUyCmvi4gipmvXrkn58uWlQ4cO5pNcOXLkkD179mgTJnwXEUU0DFqJiMhrHT9+XH744QdZsGCBBpmGMmXK6DjTAwcOOPQ8yHTkypVLokaNal6GIDgwMFCOHj1q9zEbNmyQVKlSSb58+eT06dMOZVlx+5MnT6wuRORdlixZIhs3bjRfb9++vezfv1+zrkQRFYNWIiLyWuvXr5cGDRpIpUqVrAJOKFCggOzYscOh53nw4IEkSpTIaplxHbfZc/PmTb0PMiYY14pSYYyJRdY2KEOHDpV48eKZL2nSpHFo/Ygo4mjTpo2ULVtWx6ziO2zMmDESI0YMV68WUZhi0EpERF4Lmco4ceLo75EiRbK67dGjRxIlShSHngf3s+386+/vrz9tg2HLxyAL++mnn8qZM2d0LGy3bt2kSZMmcvXqVbuPwZjZx48fmy8oEySiiM22G7mPj4/MnTtXjh07JuXKlXPZehGFJwatRETktYoUKSJLly7VgNMyaEW5L0rwihcv7tDzpEuXTpsvWTKup02b1u5j0qdPr38TXYMNaNyEEuC9e/fafUy0aNEkbty4VhciipiePXumWdVs2bLJli1brG7DOPz48eO7bN2IwhuDViIi8loVKlSQDBky6LjStWvX6qV27doazNavX19y587t0POgxBdjUi9cuGBehmA4efLkOtYVEBhv375dp7mBihUragdhlAkbjHkVkyRJ4uRXSkSeBE2V8L2ERm3oFNy4cWPx8/Nz9WoRuQyDViIi8lrIdC5evFjatm2rY0T/+ecfHYM6YcIEmT59usPPU6VKFSlVqpTUrFlTFi5cKKNHj5YRI0bo9BMo5TMC0pIlS5rHySIwrlWrll6wDosWLZJ69eppdrdEiRJh9pqJyH29evVK+vXrp98DRlkwxqt26dJFu4sTeSv2xCYiIq+FDsFJkybVEjxc3if4XblypQaqU6ZM0XGyf/75pzZXMuDAEweixvQ2MG/ePA2Qp02bpmNfMdfrd999J5EjR37v10ZEngVj29EYDp2ADYUKFZI5c+ZI1qxZXbpuRK7GoJWIiLwWum4icESGs2HDhvLhhx+G+rlixYqlGZKgYHoblAfbNmPCXIu4EJF3wjCBiRMnajbVaOCGE1e9e/fWeVcdbQhHFJGxPJiIiLyWETBi2giMPc2TJ49mS22bKhERhZXOnTtrhYURsGbJkkV27twpffv2ZcBK9D5BK8b7YCJjTJz+448/6jI0oPj5559D83REREQukSxZMunYsaMcOHBATp06pdPPoLwXHX8xlcTu3bv5zhBRmGrevLl5nlUMU0D3chxjE9F7BK0YIF6mTBk5efKkjgO6d++eLketPcqsLl++HNKnJCIicjlMKzFw4EAdV9azZ0+dYmLz5s2uXi0iiuBwDI2TZatWrdIx7jFjxnT1KhF5ftC6bt06bRaxZs0aDV4Nvr6+eh3dD4mIiDxxionvv/9ex54OHz5cPvvsM52WhojIWTZu3KjfK0YpsKFRo0ZSqVIlbmgiZwWtFy9e1JIFdEq0nIgdEiRIIPfv3w/pUxIREbnElStXdNxYpkyZ5KOPPpJjx47pNDXoKoypazBPIhHR+0KQivHzGHaA+aC7d+/OjUoUAiHuHpwyZUrdkYNl0IqJj/EhbNmyZUifkoiIyCUmT54sf//9t7Ro0UI7CKdOnZrvBBE5FcaoYiobDK0zoBcMhtyxMzBRGGVaK1eurNnWXr16ya1bt+Tp06eybds2+eKLL+TSpUs6sToREZEnwL7s6NGjOtUEA1YicqbXr1/LkCFDtELRCFijR48uY8eO1WF2DFiJwjDTiu5m+KA1btxY9u7dq8umTp2qDSwwgDxevHghfUoiIiKXiB07Nrc8ETndhQsXdO7nXbt2mZflz59f5syZIzly5OAWJwqPKW8QoKJhBTKrmCgd0wTgDFKBAgVC83REREThpnfv3prtGDlypPn3oC64DxFRSMycOVPnfDYCVh8fH+1IjusMWInCKdNqKX369Hqh97Nh/ToZMWyoXL16RTJlyiy9+vSXwkWKcLOGM19fH2ldt7TULJ9PYseKLmt3nJSBk1fK8xcvQ3QfCns3btyQ3j26yd69uyVe3HjSsHFTadW6DTc9OaR+/fpSpEgRyZ49u44pw+9BwX2IiEICw+eePXumv2fMmFGzq8WKFeNGJArPoHX9+vXy119/BXl7+fLlQzSu1WQyycGDB3XKHJyV8ja7d+2Szz+tKr369JMqVavLnNmzpHKFsrJr70HJkjWrq1fPq8z9sZl8mDmVdBqxQM5evisVi+eQ1vVKy8iZa0N0HwpbAQEB+hnJkCGjzJk3X86fPyfftvhag4/v2rXn5ieHqoVwATRhihUrltUUbgbcdvXqVT3oJCJyVNeuXfX7I1euXFqtwWEIRC4IWtGy+969e1bLcDZp9+7d+qHElAGOBqujR4/W8bD//POPHhTs379fvM3I4UOldJmy0qVbD70+bMQoWb9ujYwbM0omTpnm6tXzGp+VzSPVy+SWQrWHyskLt3TZlPlbrTpkO3IfCnt//TlfLl+6JJu37ZKECRNKvvz55czpUzJi2BBp3fY7iRw5Mt8GctjWrVslfvz4doNW3Iap3OzdRkQET548kU2bNum8zgYkYjZs2KBDDIjIRWNaq1evrplWywsaMJ09e1bixInjcPkDsiI3b96UFStWaFMnb7Vt6xYp+0l5q2XlK1SS7du3umydvFHNCvnlwImr5mDU8uRKSO5D4fOZyZe/gAaslp8ZnPw6feoU3wJyCuyjMGdr0qRJuUWJyC6c2MqdO7dWGBrNSQ0MWIncaEyrpSRJksjnn3+uAWzmzJnfef+oUaPKqFGjxJv5+fnpGbpkyZJbLU+aLJncvHHDZevljTKlTSpHzlyT3t9W1fGqT/1fyqY9p2XYz2vk6fMAh+9DYe/GjeuSLLn1ZyZZsmT68+bNG5Lzww/5NtA79e3bV/dBL1++1GqJQYMGvVVVlChRIpkxYwa3JhG9NUwFTdxQ+mucuG7durXs27eP1VdE7h60AjIdMWPGlLD8ksDFgIDPk71588ZcRmIpim8UCQwMdNFaeacovpHlqyqFZOainVL3h58lacI4Mq57HcmVJZXUaDvZ4ftQ+HxubD8zvlGi6E9+bshRderUkXz58mmDFIxpxVzjBgSxKBnG9BSoICIiMmBe5wYNGmglhqFkyZIye/ZsBqxE7hS0omkSyiEs4UARH97ffvtNdu7cKWFl6NCh0r9/f4kocDAULVo0uW8zRvj+/XuSOEkSl62XN/rngZ8kiBtDOg5boNdPX7wtvX5aKn+NbanB6d0Hfg7dh8IePhu3b1mXaBufocSJ+bkhx2DaCVwQuGIcdOrUqbnpiChIONZFL5ZevXpphYZRNYgqjY4dO7KfApG7Ba04w/Tzzz9bP4mvr6RNm1aWLVsmBQsWlLDSvXt3/WKwzLSmSZNGPBXm7cpfoKDs2rXDarqOHdu3ScFChV26bt5m77HLkipZfKtlfs9e6M/o0aI4fB8KewULFpaB/fto1QVO+hifGVR5sDSYQipdunTcaEQUrMuXL0ujRo1k27Zt5mXoDDx37lwd00pEbtiIqUmTJnL8+HGry+HDhzVgrVSpkoQlHKDGjRvX6uLpWn7bRpYtWSybN23U6wv/WiA7d2yXlq1au3rVvMrMRTskdbIE8lXVQno9dsxo0rHJJ3LkzHW5euuBw/ehsFe3Xn094TOgXx95/fq1XLlyRcaNHaVztcaIEYNvAb0TxqKhSQrGoxm/B3XBfYjIu6Ec2AhYMXygc+fOOn6VASuRG2daFyxYIA8fPpQWLVqEzRp5mTp1v5KrVy5L7Zo1dKweAvOfJkyWUqU5xUJ4QtBZq8M0Gd+zjozpWluiRoks2w9ekDodp4foPhT20PTtryXLpVXzZjJl0gTt8vplrToydNgIbn5ySP369aVIkSKSPXt2/f/B70HBfYjIu02cOFEKFSokKVOm1LGrH3/8satXicjrhDhoffDggWZWneHQoUM6xyumvnn69Kls375dl2OuV2RSvEXnrt2lQ6fOejIA03hwnknX2LjntOT8tL8kjBdLnjzzl9ev34TqPhT2SpQoKcdPndM5o9FEhxlWCols2bLpxfI6EZHh+fPnVo1F8+TJI0uXLpXixYtHiCo/Ik8U4siwbNmysnHjRqd07h0zZox069ZNg9bEiRPr77hYdgj2FhgXjAwSA1bXe/D42TuDUUfuQ2EP3xsMWOl9/fTTT3L69Gn9/eLFi5I3b16d7mbYsGHcuEReBAkUVBKWKFHC3GzJULlyZQasRJ6Uab17966WsOLMdPXq1TXQsoQPuqNjW1FiQURE5CoYl/bHH3/I999/b56/FQ3+2rVrJx06dJDPPvuMmVgiL4DZLxo2bKgnrgCzVQwePNjVq0VEIQ1aV69eLY8fP9bfUcKKy5kzZ/RiKVWqVI4+JRERkUtt2rRJSpcurb+bTCb5+++/Zffu3ZI5c2YdsoILy4eJIi5kVBGg/vjjj9pbBDDsJEOGDK5eNSIKTdCKLsG3b9/WToqYlJ2IiMjToROoMdzlwIEDOo4NAStguAYCWSKKmE6cOKHZVfRYMaCvCioBM2bM6NJ1I6L3LA8mIiKKKNCnAZnWpEmTysqVK+XLL7/U5QhWd+3apSXCRBSxIKOKseyWfVTQW2TAgAHSpUsX9hchckMMWomIyGsVKFBAxo8fL3PmzJEPP/xQ+vXrp8s3b94sJUuW5JQ3RBFMYGCgNlVat26deVmOHDlk7ty5ki9fPpeuGxE5qXvwqFGjtJQquMsPP/wQkqckIiJyqSZNmsiGDRtkxowZEi9ePF1WpkwZmTRpEt8ZoggGZf8FCxY0X0c1BYYGMGAlikCZ1goVKkitWrWCvU/u3Lnfd52IiIjCnZ+fn9y6dUsbCqIRCxFFTKiowHhWdAnHEAEiimBBa65cueSbb74Ju7UhIiIKZ/v375fvvvtOuwYbMM4VZcMoGSYiz7VmzRq5cuWKzr9qiBo1qixdutSl60VEYVgeTEREFJHcvHlTMy3p0qXTMW7Hjh3TKd7ixo2rJcIPHz509SoSUSg8f/5c2rZtK5UqVdKfR44c4XYk8mAMWomIyGv99ddfUqJECfnjjz/kk08+0cxqxYoVZcmSJZIlSxZZsWKFq1eRiEJo7969OkZ14sSJev3Vq1c6Zp2IvKA8uFOnTpyvjoiIIpR79+5Jnjx53lqOxoIYEoPbicgzIDgdMmSIDBw4ULsEQ4wYMWTEiBHSunVrV68eEYVHphU7cB8fJmaJiCjiwFQXixYtksePH1stv3Pnjs7bituJyP2dPXtWqybQZMkIWAsVKiSHDh2SNm3a6HEsEXkuRqFEROS1atasKfHjx5dMmTJpo5bevXvL119/LdmyZZOsWbNq13wicl8mk0mnp8qbN6+WBRvT2iB43bFjh36OicjLugcTERFFJFGiRJFt27bJ5MmTtcvovn37JHXq1DJ06FBp3rw5szNEbu7FixcyduxY8ff31+sYiz5nzhwpXLiwq1eNiJyIQSsREXkldBNFNubSpUt6oDtmzBhmZYg8DMasIkhFaXDLli1l+PDhEjNmTFevFhE5GYNWIiLyOg8ePJBSpUpJmjRptMvonj179PqFCxckVqxYrl49IgrCo0ePxM/PTz+7hiJFisiZM2ckQ4YM3G5EERTHtBIRkdfBlDaY3gbZ1tmzZ+v8rEmSJNESYSJyTxs3btSu3nXq1JHXr19b3caAlShiY9BKRERe58qVK1K+fHlzV/yoUaPqPK1YTkTuN261Y8eOUq5cObl+/brs2rVLRo0a5erVIqJwxPJgIiLyOgEBAdo12FK0aNF0ORG5D0xZ06BBAzl58qR5WdmyZaVevXouXS8iCl8MWomIyCvNnz9fjh8/br5++PBh7SZsuaxu3bpSrVo1F60hkffCXKtoqtS3b1959eqV+cTSjz/+KN9//725SoKIvAODViIi8jqZM2eW/fv3y+3bt83LkidPrj8tlz19+tQl60fkzdAQrVGjRrJz507zMjRMQ5fgnDlzunTdiMg1GLQSEZHX+frrr/VCRO7lzp07GqCiQzAgo9qtWzfNuGLsORF5J9ZWEBEREZFbSJYsmTRt2tTcEXjbtm0yePBgBqxEXo6ZViIiIiJyGZPJJJEiRTJfx7jVePHiSZcuXSR27Nh8Z4iImVYiIiIiCn9PnjzRrOrkyZOtlseIEUMGDBjAgJWIzFgeTEREREThauvWrZI7d26ZNWuW/PDDD3LmzBm+A0QUJAatRERETrJy5Urp0aOHDB06VM6fP+/w4968eSP9+vWT9u3by+vXr/l+UISFuZBR9lu6dGm5cuWKLvP19ZVz5865etWIyI0xaCUiIq+GLqUIGKtWrSrz5s0zz9m6Zs2aED1Pq1attNQR4/OOHTsmuXLlks2bNzv02CFDhsikSZNk3LhxDFopwjp69KgUKlRIRowYoZ8T+Pjjj3U550MmouCwERMREXmtly9fSvHixXXsXGBgoFy7dk2Xp0uXTmrXrq1zucaNG/edz7N3716ZOnWqdjotUaKELmvSpIm0bdtWjh8/Huxjd+zYITNmzJD+/ftL69atnfTKiNwHPlujR4+WXr166WcOMH0NugJ36NBBIkeO7OpVJCI3x0wrERF5rUWLFmmXUgSOZcuWNS9PkCCBZkpR7uuIpUuXaqBrBKzQqFEjOXHiRLBljw8fPpQGDRrIzJkz9W8SRTQ3b97UzxZKgo2AFWNZ9+3bp2NZGbASkSMYtBIRkddC8xccUGO6DcspNyBFihRy69Yth57n7NmzkjFjRqtlxvXggtZvvvlGatWqJWXKlHF4PCA6rlpeiNxZrFix5PLly/o7PmMIXlGZgMCViMhRDFqJiMhrJU6cWC5evKi/WwatKGfcvn27Zk8d8fz5c4kTJ47VMqOsGLfZM3HiRP3bgwYNcnh90eAJmWHjkiZNGocfS+QK+D+dPXu2fPDBBzrGe9iwYRItWjS+GUQUIgxaiYjIa33xxRdaAvzrr7+Kv7+/dvE9efKk1K9fX27fvi2VKlVy6HkQsD569Oit0l/jNnt69+4tqVKl0swTugbjwB46d+4s69ats/uY7t27y+PHj80XYwwukbvA58n2/7JUqVJa1YCmS0REocFGTERE5LVQArxgwQIdf4qxd9CzZ09JmzatLFu2TEsbHZEjRw6ddxIdUY2M7enTp/Vn9uzZ7T4GGVZjjJ9lkIvsLrJT9iBDxSwVuaOnT59Kp06dZNq0aVKuXDlZu3at+Pj8lxuJEiWKS9ePiDwbg1YiIvJqOMC+dOmSjrO7c+eOJEuWTIoUKRKig+wvv/xSu/+iIVONGjU0eJ0yZYoULVpUA2C4d++eBqotWrTQINe2U/Aff/yh2VZ0HI4ePbrTXydRWNm5c6ee+Llw4YJe37Bhg34WPv/8c250InIKBq1EROT1MP2GZeffkEIQOmDAAO0EXL16dbl69ao2Z8LBuwHlw5iH9ZNPPtH7E3k6VArgZM2PP/6opfWA6oQxY8boyRsiImdh0EpERF5r/fr12nApKAgwHQ1mUVb86aefatYJ41grV65sNY1NkiRJ9GA+Z86cdh+fP39+vZ1llOQJMPYbJ2kOHTpkXlasWDGZM2fOW520iYjeF4NWIiLyWufPn9fA1RKmkTl16pQkTZpUMmfOHKIMLOZ2xcUejFNFw6WgZMmSRS9E7gwZ1Z9++km6deumUzCBr6+vZlzRVAy/ExE5G79ZiIjIa7Vq1Uovto4eParzpyJbSkT/2bFjh3To0MF8HY3G5s6dq5UCRERhhVPeEBER2cidO7eULFnyrSwskbfD5+Kbb77R31E5cODAAQasRBTmmGklIiKy4/nz59rxl8iboVweY7SNqZxg9OjROpdx6dKlXbpuROQ9GLQSEZHXQhkwGspYev36tWaPFi5cKN27dxePcWKxyKYhIgFPRZ7edvXaUASwZs0aadq0qQwZMkSaNGliXo4glgErEYUnBq1EROS1MJckpqGxhO69GTJk0HlTg2qq5JYQsN47a70sWmxXrQ15eJUBmipNnDhRr3///fcapKZPn97Vq0ZEXopBKxERea3evXvrJUJAhhUi+YjETv5vwFqmp6vXijzM3r17pWHDhjrPsOVUNpjLmIjIVRi0EhGR15o/f77EihVLqlWrJhEGAtZOp1y9FuRhXr16JYMHD5ZBgwZJYGCgLosRI4aMGDFCWrdubTWmlYgovDFoJSIir3XmzBmddzJCBa1EofgcILu6b98+87JChQrJnDlzJGvWrNyeRORyDFopzNzZ9RO3rptKULS9q1eBbJgCA7hNXKBUqVLStWtX6dOnj/j4cBY48s5mS59//rn4+/vr9ciRI0uvXr2kZ8+eOr6biMgdMGglIiKvhXF6Dx8+lMKFC0v16tUlUaJEVrd/9NFHnIOSIrSCBQtKvHjxNGjNnDmzzJ07Vz8PRETuhEErERF5ndWrV+t4PUxtg7F6T58+ld9///2t+0WLFo1BK0VoOFEzc+ZMWb58uY5fxRhvIiJ3w6CViIi8zubNmyV+/PjSrVs36dixo6tXhyhcPHr0SHr06CF9+/aVZMmSmZdXrlxZL0RE7opBKxEREVEEt3HjRmncuLFcv35drl27JsuWLWNHYCLyGAxaiYiIiCIojFVFdnXs2LHmZdu2bZMLFy5IpkyZXLpung5TA2GqICJvEyVKFG3aFp4YtBIRkVfCnJSWB/L2oItq27Ztw22diJzp0KFD0qBBAzl58qR5WdmyZWXWrFmSJk0abuxQMplMcvv2bS23JvJW8ePHl+TJk4dbxQaDViIi8kroDFyyZMlg75M/f/5wWx8iZ3n9+rUMHz5cx67id6Op2I8//ijff/89p3d6T0bAmjRpUokZMybLrMnrTto8f/5c7t69q9dTpEgRLn+XQSsREXmlMmXKaCMmoogEZb8NGzaUXbt2mZfly5dP5syZIzlz5nTpukWUkmAjYLWdIovIW8SIEUN/InDFZyE8SoU5kzoRERFRBLFv3z5zwOrj46PjWXfv3s2A1UmMMazIsBJ5s5j//wyE17huZlqJiIiIIoi6detqZ+A9e/ZodhVl8OR84TWOj8hdRQrnzwCDViIi8jrIPvGgkyKC/fv3S8GCBa2WTZ48Wcv1YseO7bL1Is/04MEDHbObI0cO8SRYZ4zfTp06tatXJUK4deuWvHnzRlKlSiXuguXBRETkdeLGjStx4sRx9WoQhdqTJ0/k66+/lkKFCsmCBQusbosXLx4DVgrSy5cv5fz583LlyhUNTCwtWrRIqlSp4tKth3LTM2fOyJ07dxy6P4JVdMU+deqU3THeJ06csPs4PL+92zBu+fDhw/L48eMQbbuwbHx0/Phx/ZvO3IbB3Qd/q3jx4jpllrtg0EpERETkQTDPap48eWTmzJl6vVWrVnLv3j1Xrxa5OTSQat68uSRMmFA++eQTbUaHaUvatGkj//zzj7iDJUuWaDdaBKHp0qWTTz/9VJ49exbsY6ZPn66vo3z58lbLEXChCuHDDz+Uc+fO2X1cuXLl3lru5+enzcvWrVvn0m2H9UcX8MyZM0vhwoWla9euTtuG77pP0aJF9e/+9NNP4i4YtBIRERF5gICAAD1wLVWqlFy+fFmXoWJg1KhR7GRLwUJAgv+bo0ePysGDB/X/5+LFi9r9NXfu3HaDOiOjj6wjLmfPng2y6Q6yk8jOoaw0JLdZwjphTDbmx75x44Zcu3ZNM6E//PBDsI8bN26cVh3YWrhwoTYLQsbQOMETntvufWF7ISBevXq1BpeOcGQbOrqdmzZtKpMmTQq3jPK7MGglIiIicnPHjh3TbAsyLygXBMwzjAPpJk2acIw2BWvChAly+vRp+f333yVLlizm5dGjR5eWLVsG2bDryJEj+v+FC8qGUXo+ZMgQq/ugW3XGjBmlWLFimqHLmzev/r++6zZbs2fP1ufHXMKQJEkS/R3LX7x4YfcxJ0+e1BLXihUrvnXbzz//LM2aNZNvv/1Wfv31V/OcxeG17TCXqRHwB3W5efNmkH83Q4YMMmLECMmUKZPD6+rINnR0O1eoUEGuXr2q4+bdARsxEREREbkpZKnGjBkjPXv21PF0EDVqVBk0aJB07NgxXOZHJM+HctDSpUtrIBQSODGC4MqA35F1LFGihHz88ce6rFOnTvLll1/KyJEj9TrGXyIrmytXrmBvs3XgwAEt58VUTQYEuwj+EJiiJN4WumSjZNe2ARPGnW7fvl1mzZqlZbDt2rWTlStXymeffSbhte0wnhbBfnAaN24sHTp0EGc54MA2dHQ7J06cWLcrTjzghJmrMWglIiIiclN9+vSxymzhYH/u3Llalkjuofr47fKPX0C4/90kcaLJ8u9KOHRfZMwwbjG0Hj58aM4KIqjZuHGjOWhFsBMrVizzfTGGFJd33Wbr/v37bwWGiRIl0p9BjdlGEyHjPpZmzJihY0/Tp0+v1xs2bKjLQhO0hnbb4bNqGfCHh/sObMOQbGdkYdGZ2R0waCUiIiJyU23btpUpU6Zo0IAxZwMHDpRo0aK5erXIAgLW20/sl6+6C2Tnnz59GuLHXb9+XerVq6clopj+BAEoxqdmy5bNfB+cVEFQiDGkCBQRGKJR0btusxUlShQdt23JuI7b7MFnwahAMKAMGOXAaJJkBI1FihSR8ePHa+CdMmVKh167MS1aaLcdAnZklYOTNGlSh9fHEY5sw5BsZyx3l+8bBq1EREREbgLjVS3nEEZpI8aaoeGSkdki94KMp7v/XWRHMf45pFCCjinCkIFDUyPA2FbL5jy4jqZBO3bs0I67NWvWlBYtWsiPP/4Y7G220qRJY24wZjCyu7jNHmRSjTlafX3/DWv+/vtvbSCFqaAsp4NKkCCBBrPdu3c3ZxdxMsj2M4dMpHH7+2w7V5QHp3FgGzq6nbFdsDykZdFhhUErERERkRtYsWKF9O3bVw/uMU7PULVqVZeuFwXP0RJdV0LDIASQf/31l44xtYUGPGgsZAuZQgReRsCKYHDv3r1So0aNtx6LDCou+N+dNm2aBqbB3WYLHXIR0D548MD8/4/PxAcffKCXoMbcoqPxoUOHdM5iowET1hkNlCzh76KxUbdu3TRIRYk9srTGGE/Dzp07dax4jhw53mvbhUd5sL+/v45DxfQ0yII7sg0d3c6Y9xZT/QSVGQ9v7B5MRERE5EIoPcSBcfXq1XVKjdatW/P9IKeqXLmy9OjRQxo1aqRTnWzZskXn+0WAh+63uB5UUDhx4kRZtWqVrFmzRv9HHz9+bHUfPB7B4NatW/V+8+bN08e96zZbKENGd15kY3HiBnOE4m+jJD4oaBZUrVo1DSgBWV38Hcug2oDSZExVs3nzZr2OqXDw2Pr168sff/yhDYcwdyvK8JFhRunu+2w7Z0CGF4HvkydPNIDE75iexoDfMacsgnZHt6Gj23nRokUasAaV5Q5vkUxG33QPhDcQLZvv3H+spQvkXl6+do95nehtyUp05GZxM6bAAAk4PEUPBvh9RiHdD+aYUEROvHgs4ndTJE5KkU6nuBE9BLI6OBhGKaEBWR2MAbSXvSHXQlbt0qVLmpHyxPcHwRZKZJFFw/hFjE3FtDBGd9jFixdr4IYSW2OOUgQzeBxeL4JWlIzGjh1bm4QBynPR4Xr37t06/hGZPHTrjREjRrC32YN5SQcMGCD79u3Tct5vvvlGg6vgINj8/PPPNSDF+iPDiiDZ3jhYBGx4zca6o6wYY8Y3bNigTZ0QoH3xxRdSp06dEG+7sICxuLbjTxMnTizr1683T/mD14QuyZhOyNFt+K77IHuNwBbbxt50Qu/6LBj7Jmce0zBopTDDoNV9MWh1PwxaKTQYtHoulCX2799fyySN8YEowcQBfvPmzTnvqpvy9KA1omrfvr3OA1u3bl1Xr0qEsHLlSj0BgGxyUMI7aOWYViIiIqJwhOxIgwYNzCV9gAPuOXPmSKZMmfheEIXQ2LFjuc2cCOPo3W0sPce0EhEREYWTqVOnSv78+c0BKzqeDho0SEsPGbASEdnHTCsRERFROEGQaoxRy549u2ZXCxQowO1PRBQMBq1ERERE4QSNW5YvX67zSw4dOjTIhjRERPQfBq1EREREYQDzIC5ZskQDVQPmh0RnYMwDSUREjuGYViIiIiInw5yWuXLlkq+//lo7cVpiwEpEFDIMWomIiIic5Pnz59K2bVupVKmSzmcJXbp0MU9rQ0REIceglYiIiMgJ9u3bJ/ny5ZOJEyeal1WoUEHWrl0rPj485CIiCi1+gxIRERG9h1evXkn//v2lWLFicvbsWV2GBksTJkyQ1atXS6pUqbh9iYjeA4NWIiIiolBCkFqiRAnp16+fBAYG6rJChQrpPKxt2rTRxktEnuK3337T/19P89VXX8ncuXNdvRoRxtKlS6VatWriThi0EhEREYVShw4dZO/eveYGS3379pUdO3ZI1qxZuU3J7aBzdfXq1SVTpkw6T3CNGjV0CibLMdn//POPy9bv6NGj8u2330rq1KmlVatWDj1m/fr1snPnTqlTp47VcpPJJIULF5a0adPKo0eP3nrc2LFjJXfu3G8tf/LkiSRPnlxWrFgRom0XFi5duiS1a9eWDz74QPLnzy+TJk1652OWLVsm5cqV08d89NFH8ueff4b4Pnid58+f19fsLhi0EhEREYUSDiLjxo0rmTNn1gNnZFyjRInC7Ulup2XLlvLNN9/oOGsEZMimobv1zJkz3wrQXOHUqVPSoEED+fDDD/XzZC/QtGf48OH6Omw/d1u2bJHjx4/rePJ58+a99binT5/K3bt331qOpml37tyRFy9euHTbPXv2TMqUKSOvX7/WILNr167yww8/WI2Zt7Vo0SL54osv5Msvv9RgvmPHjtKiRQv566+/QnQfbDO8vlGjRom74DytRERERCGYezVhwoTm6+nSpTNPbxMrVixuR3JLyKRNmzZN1q1bJ5988ol5eZYsWTSrFlR3awQ1CCQhZsyYki1bNunVq5dm5wzIzPbs2VO2bdsmUaNGlcqVK0ufPn30/sHdZgvVCci0wqpVqxx6XQgusY6jR49+67aff/5Zs5RYZ/yOcv3w3Hbva86cOfr6Zs+eLbFjx9bvmCNHjsiQIUOkdevWdoceYD0/++wzzVZDxowZdagCTqYhSHX0PvD5559r5/MLFy7ofVyNmVYiIiKid0DWp2HDhlKwYEEtH7RUtGhRBqzk1mbNmqVjVS2DLktBdbcuWbKkHD58WC/ogo3MH57j8uXL5vsg+MH1P/74Qy+JEyeWyZMnv/M2R9chOFu3btWmZzly5Hjr84qMIjKITZs2lRMnTsiBAwckPLfdwYMHtcw4uMuAAQOCfW1o7oaA1VCxYkWdSgulu/b4+/tb3R9wHa//3r17Dt8HUAadKFEi2bx5s7gDZlqJiIiIgrFx40Zp0qSJXLt2zTyOdcaMGdxm9K+ppUSevl1mGuZiJxVpucWhuyIgQcAZUtGiRdPgytC5c2ftiI3sI7JwgBLcTp06SZ48efQ6xntiPOm7bnOGq1evSrJkyd4KHFEOnCFDBnNGGJlFfGYLFCgQ4r8R2m2HzCiC/eAEV51x48YNSZkypdWyZMmS6U8EriihtlWlShUZPHiwZpUxnhdZ0unTp5ufDycNHLmPIUWKFHLlyhVxBwxaiYiInOD27dvSvXt3bcITJ04cadSokbRr1y7I+798+VJ+/fVXPfjDgRcOsNq2bStVq1bl++EmMKatR48eMmbMGPMyjF8tXbq0S9eL3AwCVr+b4s7Q2RrluSGF76mRI0fqGE4ESpje6fHjx1aNxurWravjLc+cOaPZyFKlSmn28123OQPGe6IBmi0EqM2bNzdfR8a1Vq1aOkYzpH8/tNsOY2wtA/6QQnDv62sdqvn+/7rRqdwWThAgW2pkhREUo5QYJdnGyQJH7mPAtsU2dgcMWomIiN4TDuTKly+vZ8F///13PTONzBzKsLp162b3MYMGDdLxSjigS5MmjY7hQjYAJXSW44rINTDGC2P5Tp48aV6GbAtKBdGNlMgq4+nmfxcnxYIqKQ0Oxq+iCRBO3GAMJwIclNsimDVgLCS+/3A/nOS5ePGifk7QXTe425wBmUjbZkooy8XnF9/DQ4cO1WUIxhBso9kQyvwB42rRLdleAyTLLGhotx3WA1nN4BjBoj1JkiSxKtcFo7Nz0qT233sEtSNGjNALSqRxkg3TGIHxveXIfQzYtrbZXldh0EpERPSeFi9erMENGoIgcEUJGubvHDZsmHZmtHeWHlOjWGYIkLlAsxI0DGHQ6jrIYKAbKd4fnIwwSiRx8IvMeWjG3VEE52CJrivhOwXfRSh1zZkzp8OPw3caOueigRKg6dC5c+ckVapUVvcrXry4XvCdh7JhBKhGYBrcbe8L48kxxhxBJcZgAr5D8fy2Y2cnTJigtxlBK8pr/fz8tCTW8vWcPn3afPv7bLv3LQ9G6S62GTKdvv/PsGKca7x48RyaUit+/Pj6E4E6xsZaNpBz5D6oHrp165a+d+6A37xERETvCVMrYL4/Y7wRVKpUSc9iG90wbdkraUOQxOlSXAfZGLxvOKg2Ata8efNqAxeMY2XASp4Kc54iwEMAtn37dnMZ6PXr17UZEMZt24MqEASuqBrBZwKZV4yBtISpYI4dO6bPGRAQoGO/jbLY4G5zBgSW+Iwa3Yaxnsga4nXaNj1CqTKCPgTdgOlrEOjiZNTDhw91GdYPrxHZYSMIDu22M8qDg7tgKElQGjdurAGrcQLtzJkzMm7cOC11NvYT6CaM5zHmisZrGz9+vA5twGMxFy22DbKqBkfuA1hmbF93wKCViIjoPeHgxfZAzAhgcRbfETgYWrlypdSrVy/I++CgD1kFyws5D6aQwBQWgAAVY5T37NkTouwKkTtCtQembMH8nAje0C0WAVOJEiX0dnTHtQeBDL7DEiRIoBk+lLzaNiVCFhal9Cgzxf2QncO0Ku+6zZ706dPrdykCZYyjxe84IRgcnFBCBtXIGKLk115vAMz/ikDUaKKGCgoEZgjeEJzj9SE7iilyLOd1De22e1947cuXL5cFCxbo9kMzq2rVqunQEgOCWQwzMcq1MQUXyqJR0ovHoBQbr9EyW+rIfQBz0H7//fd2p9ZxhUgmZ7bwCmfYWeMf7M79x7rRPRlS8NevXZMPMmTQ9tIRwcvXYTNvVXjCF9m5s2ckQYKEkip1arf54L6vZCU6iqfxjewj2T5IJo/9/OXaHesJxzOnSypJ4luX2Dx++kJOXLglnsIUGCABh6fomBtP/z7zRkaggwMMA8YiYUzSwoUL9WAnOCglxtQSOCAJristxof179//reU5JhSREy8e/9sMJk5KkU6n3uv1eDOUP6IcEmOS3aUsjtzruODSpUvywQcfSPTo0cVToSwWJae2TYmQqXz69Kl+d9neH9k9vGbsp3A8ZLuvQrCIAM+2edC7brOEAMxeMyDb9bH9zBYpUkT7ByB7ipN7lh1wLaH6Bc+PANoSluE1OrL/DWrbhaVHjx7pGFzboSbIlGJfg9jBskoHwSy2g+3UNpaCuw9OGnz33XdaKRRU9U9wnwUjRnPmMQ3HtLoYPmjft/lW5s75VTJkzCgXL1yQdh06Sf+Bg129al4NZSID+vaUhQvmS5o0aeXWrZuSOk1amTbjV8mW3XouMAp7X1UpKMM71pCHj5/L68A3cuH6PWnWe474PQvQ23u3rCQl82eSi9f/a1hw7NxNaT/sL749FC5wQHXqlHWgaDTQCO5gCzAWq2zZslqOZkw7EBRk/jC2yvLAABkCCp0lS5Zo6WLv3r3Ny5Bhfdf7QOTpgipLRSBmLxizvD+CEXsQVAUluNssWQ6xcBQ+s5hLFOPRsZ7BldwaYzht2QvCgxLc84eV+EGsN4Jne+XWCDTfNdQkuPvgJABKjt1puIpLg9b79+/rDgOdxLDTrV27tt1BwhHZtCmT5a8F82XP/sOSNVs22b1rl1QoV0ry5S8gNT4P/sw8hZ07t2/Jh7lyy7CRY/WsFs5ENWlQRxrVqy17Dx3npg9HlUvkkGl9vpJGPWfL4g1HdFmFj7JLwnixzEErrNp+QloPms/3hlwCDTPQ9RddJ43GGmiqhO8PY35CezA2DKV2H3/8sU5/864xkyhnw4XeD4L99u3byy+//KLXUeYXmnkYicg9BNfQiELOFYG5245pRafFggULyq5du/TsC4JXtJRGi2pvMnvWTPmiZi0NWKFosWJSpmw5XU6ug2zq181bmcswcJDYoFFTOXP6lDx48IBvTTjq3aqyLNl41Bywwtqdp+TKTev3IWb0qJI/expJm8K7TnyRe6hTp47uy3r27KklVxjjiq6P6FJpnL2/fPmypE6dWjZs2KDXUVZlBKxz5syx25iJnA+NWHAiwQhYASXcRETkvlyWaUVTg+PHj1udGUEdOurR16xZI94AZQzHjx+Tpl//N/kxFCxUWH6Z+e+AcnIfBw/slwQJE741DoLCToK4MSVftjTy07zNEi92DMmQOpHcuPtI7j54+tZ9a5TNI9kzJJeUSePJk6cvpNXAP2TbgZDPq0YUqv/VBAlkxYoVOn8hmoxgnBHGsaLTowHL0NAEY8YAU6igU+WmTZu0MYYB44OQpSXnQsUM5kNEYxljzByyCT/99JN26SQiIvflsqAVExTbQscubwlYjYHcOCOf0KbxUsKEieQhs3luF7BOGDda+vQfHGGaMXmC5In/zVAVzf2BDG33mdy691gyp00qm/adlaa95sgz/3+75S3ZcES+H7pAHvn5a8OmUZ1ryvwRzSR/rR/l9n12V6XwgSkRMK4VQ18wJsx2DBeCUQSpRoMQZGLtTSr/rkYlFHJoJoKst+X0Q2h8NXv2bO1WSkRE7s1tprzBOCC0qUaZlLe0+jcGNwe8eGG13P+Fv92J6Mk1UBJc+4vqUvur+tL6u3Z8G8LRq9eB+rNE/oySr9ZQ+ajBKMn1+WDJny2N9P22ivl+izYc0YAV0Kipy+jFEjtmNCn/0b9l90ThCV0c7TUdQfkvyoONLovIzuK67cWZcxh6O1Q0jRw5UqekMAJW7F+HDx+uGW4GrEREnsHHXTroNmrUSMt1MElvUFBKhY5lxsXTOyaiNBoHNzduWs/hd/PGDe1YS6539sxpqV75E6lYqYr8NHEqs6zh7PqdRxIY+Eb+WnvIHJQic7p8yzH5KG+GIB8X8PK1lgijVJiIvBeOKzDHoTGHISq69u3bJ507d+YYYiIiD+LjDgHr119/LTt37tSJe4OaV8lo9Y/5fowLyqw8XdlPysvfK5ZbnRVevWqlLifXwvys1SqVk0/KV5Txk6czYHWBFwGvZPuhC28Fn6mSxZd7D5/p75Ej+0gUX+sGNnmzppZE8WPJyfO3w3V9ici9oNQaTa4wDyECVQSsuXPndvVqERFRCPm6+gxo8+bNZdWqVVqmkzVrVq9r9d+9R28p+VFhafttS6lctZr8Nm+OPPXz07layXWuX7sm1St9IilTppb6jZrInl07zbflyZff4fnG6P31nbhSlk9oJVdvPZRDp67JxwUySeXiOaRa2yl6e7zY0WXN1Lbyy+LdcubyHcmQOrF0+7q8bNl/TlZu4/RERN4Ec+P+888/kj17dqseGphaKGnSpC5dNyIi8sBMKwLWFi1ayN9//60Bq+UOxptkz5FDNm/bpaVLE34aKwkTJJQt23dLqlSpXL1qXu3G9WuSLv0HepJkQJ9e0q93D/Pl7t07rl49r7Ln2GWp1GqiZE2fVDo2KiuJE8SWko3HaFAKDx4/l5rtp0vqZPHl+/qlpVieD6T/lFVSpfUkefPm3w6hRBTx4Xjiww8/lM8//1yeP39udRsDViLHp4T64YcfPG5zoWv7ypUrXb0aEcbGjRutut+7g0gmo+97OBs7dqx06NBBKleubNVJGB0XMXbVEWjEhLGtd+4/Ns+DR+7j5es3rl4FCkKyEh25bdyMKTBAAg5P0aEP/D4jRxn7wRwTisiJF49F/G6KxEkp0umU12zEp0+f6kH21KlTzcu6dOmi3ZmJnO3Fixc6xzK6gRtN1TzJ3bt3dZw3Op2jISiqHGvXri0JE/47x/nPP/8sgwYN0nmlXeHEiROydOlSuXnzpmTKlEmno3rXVIOopChcuLC+JtsTVL169dLXPGnSpLc6sy9fvlzWr1//VnCGk16tW7eWtm3bSsGCBR3edmEBU6Why/m+fft0O6AL+rsSfVjPX3/9VS5evCgpUqTQqdhs+wC96z44FsH2x/bBvNYh/SwY+yZnHtO4LNOKTn5jxozRuVnRvc+4pE3LBkRERET0brt375Z8+fJZBaxVq1bVk+JEZO3PP/+UDBkyaFUCAhIEG8eOHdPADJ8lV/vxxx+lXr16OqMIAjNkTpHYQmD1rsd9+eWXbwWs58+f10TYb7/9ZjcLe+TIEZk/f/5by1H9iIDOMnB3xbZDXrFGjRoyZMgQ/du3bt3S77vg5vFGQI1ttmPHDq08uXr1qgadx48fD9F9EHA2aNDA4URihB7TWrx4cb0QERERhQTmOMdsAziYQ0NHoyP/6NGjtVcG59Mmsnbo0CENQgYOHChdu3Z9q1oBgaI9COyQZAL088iWLZtm5eLEiWO+Dz6DS5Ys0WAKU0qhirJ06dLvvM1WrVq1dN2Mz2+rVq00mELVhOWJKdus6Lx587Q/ji1kjcuUKaMZUfz+2Wefheu2e18rVqzQIPnMmTOSOXNmc3azY8eOmnm1p3///hrwY5tbZmtRjbJ69WqH7wN169bV+awfPHgQptlkR3EGcyIiIvIYyBLgAPLgwYPmZcWKFdMSOmRAiOhtCDzRL6VTp7cbfaK7Ni72YGpGI8hEgLZs2TL56aefdN5joyklSnDnzp0rbdq00cB08ODBcu7cOT2BFNxttjJmzPjW3NbIaKK5WlCQLcRJLJQHW0IQhmwphiMiQMufP7+WHKdMmTLcth3KlhHoBgdBfJ06dezehuww1tsIWOGrr77S4Pv27dt25/S+cuWKTu1lCdfxHiDAx3vmyH2gQIECWgaN3kM1a9YUV2PQSkRERB7h0aNHUrRoUR0vBRijhqwBxrDajlcjov/s2bNHA7uQfk5Sp04tTZo0MV/HWE9MG4WppFq2bKnLFi9eLP369ZNmzZrpdZTnI0B8123vgqAPYypHjhwZ5H1Onz6twRt64tgGfAhc0ZgNwTLKeGfNmiU9evSQ8Np2GMsZVFY5qEDdtrwZQyctpf//dWwbe0Fr3rx5dQpRZH9RfYKpNJGtxU+MP82ZM6dD9wG8Xrz/OFHoDvgNT0RERB4hfvz40q1bNz3wRPYEmQFkIohcqc6KOnLP/164/93EMRLL/Gpvj8m0Byd6kiRJEqq/g6oGozkSspoIdhAsGjAuEuW76EtTokQJbcpjZDSDuy04aOCDgBM9cIzg2B4/Pz8NvGyhHBhNnBCwAmYswXCC7t27h3j4QGi3HR5jGfCHlL+//1uzicT5f1k2brMHwyZ27dqlZdyoQMG4W6MCBaXFjt7HgCwytrE7YNBKREREbgtj4nx8/usbiawqsio4kLXNrhC5AgLWu8/vuvXGT5YsmTbcCSlkVDG29JtvvtEMHQLEkydPWgUyM2bMkBEjRmj5LEp/y5cvL6NGjdJAKLjbgoLnrlSpkk47iA6/wWU4Ub788OFDq2VoWIQxrgEBAeagEWWvyE5u3rxZx7kCnhfZWFsIzAGlse+z7d63PBiZWlSXWHrw4IG5UVJQgTJOMqA5FNYZJ/muX7+u42ONwNuR+xjw97GN3QGDViIiInI7ODhDKSK6XCIzYDnOrX379i5dNyLbjKe7/10Ei8g+hrSpzpQpUzSo6d27t9Uy2+AKwRkud+7c0VJgXDDna3C3BRWwVqxYUQNHlAYHFZwZEEhj+pZ79+5J4sT/bo9ffvlFx2iiE7ElZBGN5kxGqS22h+U4TkAAZ9z+PtvufcuD8RoWLVpktez48eMabKO5VFBwku+jjz7SC6AsOl26dFYztDhyH4xhxvhXjG11BwxaiYiIyK2sXbtWO5SiHBFBapUqVXQsK5E7crRE15XQcRaNib799lsNUCyrFDBmE2WgxlhGSyiltcxkYiwk7o+yX8Mff/yhnX/xWUVWEiW9RrAV3G22ECQh84gpZ/B3MBzgXTBWFc+LZkH4O5gmZubMmdr4ybY0F/OQVqtWTV8P5jwtVaqUZo4nTpwonTt31vvg8biOKWaM+VBDu+3etzwY3Xsxnhfjc6tWrarbZfLkyfoajLlPMS0Pxgz37NlTGzahQRMCeOP9QfdnZLvRWd3gyH0AHZ9Rjuwus70waCUiIiK3gIwHppSYMGGCeRkOzu7fv+/S9SLydClSpNDADuM8jfGlyLZhOhVkMxGU2YNyfJSvnjhxQu9/4MABczBnQNYUY0UxhyjGu6LsFMHdu26zheAQ3YDRHddyrmV0EO7bt6/dxyAYRvky1h9BK8p/UZaL+U1tIUhFwIkpctq2bavbBFlZDDVYuHChZhrxOrGemNvVGA8b2m33vjBeHxnq2rVra8YWrwvNkhYsWGC+D4JP/H2UbyNoRUkzOjPjexPrj/VGZYrluGBH7mOUhuPkIcYhu4NIJpxS8FAYGI1/ljv3H5vPOJD7ePn637nzyP0kK9HR1atANkyBARJweIo2n+D3GYV0P5hjQhE58eKxiN9NkTgpRTq5R7fHkMC8gw0bNtQDQUOFChU0a2LbjITIVVBiig6rCKTc5WA+pFBiio6wCF7QjAcXA8adIvP25ZdfmpehRHTv3r36ejFvJ27HY43SUqOkFp9hjENFVYRlGW1wt1lCwInMoS2U/SK7GBTsN/EaMMcogjq8hqDGiaKKA+W1ZcuWtfoexVysKF9GNhYBdlDvbXDbLqygi/D+/fs1O4zgFdvRgBN6GPeLapSkSZPqMpRWI0uKcmZsb3QAtvWu+yBAxnIE8cbzhuSzYOybnHlMw6CVwgyDVvfFoNX9MGil0DAODEqMzyrb7t8RMb3xuKAVjVDQ1RPjVnHACciGoHkLxrSGtNMnUViKCEFrRISgGllXdxl/6emOHj2q+xdklYMS3kEry4OJiIg8nI+8+TdghWj2J7p3R+jyiTI+HHBajlFDWVp4ZDCIKGLAPKrkPJiL193810OeiIiIPBcyrImziJTp6eo1cRjKBI15AZEl6dOnj+zcuZMBKxERWWGmlYiIyMO9wTloDyoJNmBs1ty5c6V+/foyffp0KVKkiKtXiYiI3BCDViIiIgoX6HqJsl/MP2jA74cPH9ZunERERPZwD0FERERh6tGjR9oZGFM34GdAQID1wQgDViIiCgaDViIiIgozGzdu1KYeKAMGTJdhOc8gERHRuzBoJSIiIqdDg6WOHTtKuXLl5Nq1a7oMUyAYY1iJiIgcxTGtRERE5FSHDh2SBg0ayMmTJ83LypYtK7NmzZI0adJwaxMRUYgw00pEREROERgYKEOHDtUuwEbAig7BY8aMkXXr1jFgJfJiu3btkv3794s727Ztm550c9XfevLkiaxevVr++OMP7QWwfv16q5N/3oyZViIiInKKY8eOSa9eveTNmzd6PV++fDJnzhzJmTMntzCRC12/fl22b9+uv0eKFEmSJk2qY80TJUoUbuswbtw4iR8/vhQsWFBc5fXr1xoo3rhxQ5IkSSI5cuSQBAkSmG8fNmyYZMqUSb+7wprt37p7967kyZNHsmTJIilSpJBixYrp92m1atV0Pb0dg1YiIiJyirx580r37t0129qtWzfp27evRI0alVuXyMV2794tX331ldSsWVN8fX3l8uXLepIJgeQ333wj3mDhwoXSrl07/U5CcPjgwQM5f/68fPbZZzJp0qRwX5+PP/5YkidPbr6+ZMkSiRMnjmzZssW8rHz58jzp938MWomIiChU/vnnH0mYMKFEjhzZvKxPnz5So0YNl2ZTiMg+jCuPHTu2/t67d29p27atfPnll5oBhX379smFCxf098SJE2twh4ykbUdwLEubNq1mLVFZUbRoUYkZM6bV/fz8/GTr1q0SN27cIDOXL1++lJ07d2opLOZszpgxo92/lTp1av1byJSWKlVKhx3cu3dPS46x7h999JHV95Ct5cuXS61atWT8+PHSunVrzTbDq1evZMaMGUE+zpHtAWfOnJGzZ89KqlSp9OSd5TReQd2GTKrxXiALvmHDBjGZTFoabECVStasWa3+Fu6DMuubN29KhgwZrOa9ttxmKVOmlD179uj7Urp0afF0DFqJiIgoxJAVaNGihXTq1Em6du1qXo4sBgNWIvdXuXJlGTRokJw+fVqDTkBgiKAHbt++LQcOHJDJkydrYzXDgAEDdPz6rVu3JFu2bBqQ4TqyuUZAd/z4cfnkk0+0/BjB08WLFzVAQ6BmGcxVqlRJokSJIh988IHs2LFDmjdvrmPgLf/W8+fPdV1Qznz06FGJESOGdO7cWdf9ww8/1HVGcLdmzRpzMGoL98frbdOmjdVy/O1WrVoFuY0c2R4tW7aUv/76S4oXLy537tzR51y6dKm+9uBusywPRnB56tQpefjwoX63GjCmtX379ubyYGzzTz/9VB4/fizZs2eXw4cP63uwePFi80kDbDME9yiBxnbBNmfQSkRERF4FjUI6dOggM2fONGdrKlasqBkEIvIcRgYR41sNOBGFi2HZsmXSsGFDLaFF6aoBZbUImJIlS6bZUmT7pkyZot8HgOAQ5a/IGiKziOZCCBotg1YEiwg6EXChZHnv3r2aMUUgi+8Uy/G4mN8ZAfH9+/c1wztw4EANKFHpgYxj+vTpZdOmTdql3NaVK1c0QEbgGlLv2h547mnTpmngnjlzZnN21t/fP9jbbOHkH5avWLHCKtNqnEwwNGnSRINcbGts14CAAM08DxkyRIN4w4kTJ7T8GxnqiIKZViIiInK422WjRo10PJyhSpUqmkkh8majR4/Wy7vkz59fAx9LyJwdPHjwnY/FvMe4vO+4TpTW4jM8atQoHc+KElNLKLtFRhM/kbF7+vSpZmMLFSpkvs/nn3+uAatRXYFgE4GhkZFEWTAyr0YpLAJRZEoNyDpu3rxZ74eAFQoXLqxjOOfPn28VtOJvGRlcZCjRqAjBKQJWwPdPunTpNDi0F7RifQDBbmgEtz3w2vEacbsRmBrbCVnRoG4LjZs3b8ratWtl+PDhsmjRIi0TxgXvHwJ2S9hmESlgBQatREREFCyczUdTJRws4SAJUOqHJi5NmzYNsiSPyJsqEFCO+S725inG2HBHHou/8b4wthOBFMp3UWaLhmmWMOYTzdQQYKKDLcpZjc62loyA0YBAGGNY4erVq/oT2U9LKAE2IAsJtgEzxrSiTNaSZXdf42/ZW/bixQu7r9nIECNLG1Lv2h5Yhqznd999p02eypQpI40bN9bS6OBuC43L/z9ZiDJqlClbsg2G8bcjGgatREREFCQc3GL8FsrzDCVKlJDZs2dbHYQSeTM0G0KjnXex18QHyxx5LP6Gsxox4eRTnTp1pHr16lrmi4whxo6i9B/lulgOyCoi82mcrHKEMY0Oxmca2VjjutEtF02NAB18LV87rhu3OQsys/HixdPMb926dR1+nKPbA+NwkbHGdyWy6FWrVpXff/9dvvjii2BvC6m4/3//e/TooVnp4ETEE4n/tbYiIiIisoAGJAUKFDAHrMgyoHkIyvoYsBL9B2W7GHv5rottaTBgmSOPfd/SYNugZuLEifq8P/30ky5D+SsaKll2q0UToZBChhWlqZYNhVDaiqDRgHJeZJ1R5mpAphbNlHBSzJlQfvz999/L1KlT38riwrVr1+w+zpHtgUAcwS22J8b19uzZU8eh4rUGd1to5MiRQ7cZsre2HMnUezpmWomIiMguHGAhOMVYNTRMmTt3rk75QESeDxleNCdCEx9kAxEQYcwtSlhxHc2WMB2M5fQtjsDUM3jOr7/+WrvcIoDFPKjG9C7GfTAGuF69ehqsoovuzz//rFlXdNx1NkzFhcZT+E7DeuF7DEElmjlh2hyMh7XlyPZAwIspg3BBRhdBMRpK4fUHd1to+Pj4aAM8NIHCuqOxFX6ieROW/fDDD++1jdwdM61ERERkF6ZQmDNnjh4MoeslA1Yiz4QADOXAxphMA7K3KFnFXKnICK5bt06DoS1btujtWF6/fn2rEl40O7JsqmSMqbTMkKLDLsbPYrwugkWMDcW4eMuxlwjm0IgJc6UicEQAi/GaKFUO7m+hWROmcrGEdbadz9Q22zpv3jztYhw9enStIkGWGQ2f0GnXgI7HCFTBke2BdUPlCcbN4rUgGMd3Jaa4Ce42278FeE14bcG91k8++UTXFx2Esa1wUgC9BiwDVnvbLCKIZApJkbqbwYB01Kjfuf/YKXX+5FwvX7/hJnVTyUo4r8SInMMUGCABh6foDojfZxTS/WCJ8VllW9vT77XhUAqHZiH9+vUzd7okImto9nPp0iWtQEDwQ+StXgTzWTD2Tc48pmF5MBERkZdbuXKllsxhGgpkRbZv326ehoKIiMjVWB5MRETkpdAJE+PHqlWrpgErYNyWvfFdRERErsKglYiIyAthDFnevHll2rRp5mVVqlTRqRnQpZKIiMhdMGglIiLyIi9fvpRevXpp0xSUAhsNlzCNArpQGvMoEhERuQsOWCEiIvISmHKhQYMGcvDgQfMyTAExe/ZsNl8iIiK3xUwrERGRl7h165Y5YEWjpYEDB8q2bdsYsBKFkAdPvkHkkZ8BBq1EREReAvP3dejQQbJlyya7d+/WMmF2CSZynDHP6fPnz7nZyKs9//9nwHbu37DC8mAiIqIIat26dVKuXDnx8fnvHPWQIUNk8ODBEiNGDJeuG5Enihw5ssSPH1/u3r1rHg8eKVIkV68WUbhmWBGw4jOAzwI+E+GBQSsREVEE8+DBA2ndurXMnz9fxo8fL23btjXfZjsJPBGFjNGszAhcibxR/Pjxw7VxH4NWIiIiJ3nx4oWcPHlS4sSJ4/A40dA8Jjhr166Vpk2bys2bN/V6586d5fPPP5dUqVK993MTkWhmNUWKFJI0aVJ59eoVNwl5nShRooRbhtXAoJWIiMgJli1bJk2aNJFEiRLJvXv3dNzo0qVL9cDWmY8JCsq1unbtKhMmTDAvS5AggUyePJkBK1EYwEF7eB+4E3krNmIiIiJyQlfer776Srp37y7nzp2TGzdu6HyorVq1cupjguJ35YXkz5/fKmCtUKGCHDt2TOrUqRPq10VEROQOGLQSERG9pz/++EO78LZr187cnKVjx46aSb1//77THhOUI6OuyJkzZ/R3NFhC8Lp69WpmWImIKELwjQjzA/k9eeLqVSE7Xr5+w+3ipkyBAa5eBbJhCnz570/O/eeRDh06JLly5ZKoUaOalxUuXFgCAwPl6NGjUqZMGac8JiAgQC+Gx48f//vL/6fLy5cvn0ybNk2yZMkifn5+Tn6VRERE7/bk/7GZM49pPDpoNXbImT5I4+pVISJy2vdavHjxuDU9sFsvxqVaMq7jNmc9ZujQodK/f/8g1wOBcKFChUK8/kRERM6GqiFnHdN4dNCaMmVKuXbtmnZc9PQ5snBGIk2aNPp64saN6+rVIQt8b9xXRHpvcDYSASu+18gzOykaE60b/P399adlJvV9H4PxryghNjx69EjSpUsnV69e5ckOJ4lI3yvugNuT29Td8X/U+VAFlDZtWkmYMKHTntOjg1ZMlp46dWqJSLCD5E7SPfG9cV8R5b1hhtVzIXBcv3691TI0VgLsuJ31mGjRounF3v9ORPgMuJOI8r3iLrg9uU3dHf9HwyZWc9pzOe2ZiIiIvFT58uXlxIkTcuHCBfMyTF2DidcxbtWYj3X79u3y8OFDhx9DREREHp5pJSIicgdVqlSRUqVKSc2aNaV3795y5coVGTFihEyZMsV8pvn69etSsmRJWb58uVSrVs2hxxARERGDVreBcq++ffvaLfsi1+J747743pC7QF+FlStXmoNO9Fr4888/pUaNGub7YCqa4sWLm8f4OPKYd+FnwPm4Tbk93R3/R7k9vfF/NJKJ8ysQERERERGRm2L9EREREREREbktBq1ERERERETkthi0EhERERERkdti0Oombt++Lfv27ZP79++7elXIxtmzZ3WaCg7/di///POPHDp0SB49euTqVSEKU/fu3dP9w507d8L0Md4C3+UnT56Uw4cPy+vXrx16jL+/v94fHaDpbfge3r9/f6i2z65du+TgwYPcrHaOPbBdAgICHN42mFYL+0UcU5I1Pz8//R+9fPlyiL5H8R5gWrI3b95wk9pAx3scH+P70VEXL16UAwcOyLNnzyTE0IiJXCcwMNDUokULU7Ro0Uw5cuTQnz169OBb4gYWL15sKlGihClBggQmfFT8/f1dvUpkMpl2795t+vjjj01JkiQx5c2b1xQjRgxTs2bNTC9fvuT2oQina9euVvuH1q1bm968eeP0x3iLc+fO6XbB90fatGlNKVKkMG3fvj3I+9+9e9f09ddfm+LFi2fKkyePKWHChKYiRYro89C/RowYYYoePbope/bs+n1cp04dU0BAgEObZ9y4cSYfHx9T1qxZuTn/79atW6bChQub4sePb8qQIYP+z61YseKd22fUqFGmOHHimHLmzGnKmDGjqUmTJtwv/t/06dNNMWPG1P+zWLFimSpXrmx6+vRpkNsS/7/16tXTx+TPn1+/JzJlymTau3cv/09NJtPmzZt1GyZKlEiPj0+dOvXO7fLo0SNTmTJl9H80S5Ys+nPevHkh2p4MWl1swoQJujM03vCdO3eaokSJYlq4cKGrV83rDRo0yLRlyxbTggULGLS6kTlz5pi2bt1qvo6DR3xx9u/f36XrReRsf/zxhwadxoHSsWPH9IBr6tSpTn2MNylUqJCpSpUqptevX+v1Nm3amJInT2569uyZ3fsfOHDANGPGDPPBP+5Xvnx5fR769+A1UqRIpjVr1ujmuHLliilp0qQOfR8fOnTIlCZNGg2uGLT+p1q1anpi5Pnz53p94MCBptixY5vu3LkT5LacMmWKnjDA+2G5r3z8+LHX/5sePXpUT4z89ttv5hNR6dOnN3333XdBbptJkyZpwHr+/Hm9ju+LGjVq6IkrMpnGjx+vJ1L27NnjcNCKzzlOGCJ4hcmTJ2u8Y2xjRzBodTGcwfnmm2+sllWqVMlUtWpVl60TWWPQ6v7q1q2rB5JEEUmFChX0QMlSgwYN9IDWmY/xpoNXHGBZZlZv3rypB7T4nnfU3LlzNVB78eKFyds1atTIVLRoUatlP/zwgyldunTBPs7Pz08D1eXLl2tlAIPWf92+fVv/t/766y/ztkLwihNPCBTsQUCFTGDHjh2d8I5GPNguyJJa+vHHHzVhZJy8soWTLghsLQ0dOtSUMmXKMF1XT7Nv3z6Hglb8D6MaAydXLCtNkyVLZurbt6/Df49jWl0oMDBQjh07JgUKFLBaXrhwYR2TQESOfY7wecmUKRM3F0Uo+L+2t3/A2MqgxtiH5jHewtivWm6fFClSSOrUqUO0z8VYYTwmWrRo4u2C+n/DWLeHDx8G+bg2bdpI2bJlpVq1auGwlp7jyJEj+jm13KYxYsSQnDlzBvk/ivHZt27dkurVq2uvB4wXfPDgQTiutWf+jz5+/FjHV9rz9ddfS5QoUaR9+/ayfv16mTVrlkycOFGGDBkSTmsdsZw6dUrHW1u+Dz4+Pno9JN+9vmG0fuTgoPBXr15JokSJrJbjOr9wiBzTt29fbf7RoUMHbjKKULAfsLd/QGOW58+fS6xYsZzyGG+BbRMzZkyJHj16qPe527Ztk0mTJukBLAX9/2Zs7wQJEry1mebOnSt79+5l86Ug/kctt6Ej/6M3b97Un0uWLJG6devqiZjTp0/LV199JdOmTRNfX+8+1Md2y549e5D/o/akTJlSvv32WxkwYIBs2bJFTwoULFhQypcvHy7r7E3/15cuXXL4eZhpdSGcxQGcfbCELlxRo0Z10VoReY4JEybIiBEjZP78+ZI5c2ZXrw6R0/cR9vYPENQ+IjSP8RbYNgjebTPOju5zka3+7LPPpHXr1tK8efMwXFPPEdL/N8yQgGAA2xAZQXQexUlHPAa/B5ed9QahOS40HoMsLTKHyFzhf/Wvv/6ScePGibcLzXfi6NGjZdCgQdptGNsT/6Px48fXoBXVXeSaeIdBqwvhjDfOMty4ccNqOa6nTZvWZetF5AkmT54snTp1kgULFkjVqlVdvTpETpcuXTq7+4fkyZObDwKc8RhvgW2DA07LaYAwjQWmB3nXPhcBwSeffCL169eXsWPHhsPaeoag/t/wv4b/OVs4aM2TJ4+eaOzWrZtekMlCWSt+Rxmht29PCMlxYfr06fVno0aNtJIAsmbNKmXKlNHKAG8X1P8oBLVNV6xYIZUqVZKMGTPqdWSrW7ZsqaXYmP6Gwv7/2h4GrS6GszbLly83X8cOdeXKlSxBIArG1KlTdazJn3/+KZ9++im3FUXY/QP2B5bzAy5btsxq/4CyNWSoQvIYb1WyZEkdh4rtYUDAhDlGLbcPsiuWJWtHjx6VcuXKaenl+PHjw3293Rm229q1a63mEl26dKmULl3afJIE2VX8j758+VJSpUqlv1tecCIAB674/aOPPhJvljdvXkmcOLHV/ygC+XPnzln9j+J/8syZM/p7hgwZtNLIXkCQJEkS8XbYblu3btUxrJb/o/ny5TOXq+I2/P8Zc4diu9nOOXzt2jX9ifeH3g0B/vHjx80nVtB3xPL/GvsuDBMI0b7pvdpG0Xs7ceKEdoXDXK3Lli0z1apVS+ePu379Oreui6EN97Zt27TdPD4qGzZs0OsPHz509ap5NbTxR3fFzp076/thXA4ePOjqVSNyqqtXr+p0Tl999ZXuHzAfMea2O336tPk+6CiK76dXr145/Bhvhq6gcePGNU2bNk2nwMBcrZiP0RI637Zr1848pRb2yZiz2/L7Bhd2DzaZHjx4oNsQ0wjh/w2dWqNGjWratWvXWx34r127Zvc9Yfdga5ieCtNWjR07Vrcd5l0tW7as1X3QDRzz4RqWLFmi3XAx7y2mH2rVqpV2a0XHbG/n7++vU61gfndspz59+pgiR45sWrVqlfk+mzZt0v9RTMMEmDoIXcUxJdbq1at1nldMjVW/fn0XvhL3gc8yvgN//vln3W6YbxXXMcewAbOglCtXznwdHbF9fX1NgwcPNi1atEjnIsYMKsa+yxHePTrbDeTIkUN27dql9fMoOcLZst27d+vZSHKtxYsXa2MDKF68uPTp00d/HzVqlBQpUsTFa+e9kAHB2fidO3fqxYCzzbNnz3bpuhE5U5o0aXR/MHz4cN0/oMQK+wuU/lk2DMH3U6RIkRx+jDfD9ziyegsXLtTM3/fffy/fffed1X0KFSqk3yeALrhZsmTRcbAoX7WEMYP2SmC9CRot4Xt42LBh+v+GJkDIalnuI5GZwv9oUN2WkYWx7e7qzVq0aKHbbM6cOfL06VOpXbu2DoWxhBJrbGsDxlovWrRIpk+frqWtOJZESTv+d70dGq+hogL/o6iUQHZ13bp1Wj5tiBcvnv6Pxo4dW6+XKlVKu4SjqgvHfBjP2r9/f2nWrJkLX4n7wPbEEC3AdkNzOujcubP+LwI6XuM71lCzZk393/z5559l48aN2j28a9euIWoUFgmRq9NfDREREREREZETcEwrERERERERuS0GrUREREREROS2GLQSERERERGR22LQSkRERERERG6LQSsRERERERG5LQatRERERERE5LYYtBIREREREZHbYtBKZOPu3bvyxx9/mK/fvHlTFixY4BbrQkRE5K5Onjwp69evF0/1559/yu3bt9/7PkTkfJFMJpMpDJ6XyKl27Ngh165d09+jRo0qadOmlXz58knkyJGdvqU3b94sZcqUEeOjsWLFCvnyyy/lxYsXDj3+xo0bsnv3bqlZs6bT14WIiCisPH36VPd5tlKkSCGlSpV65+MHDRqkj8c+MCycO3dODhw4oL/7+PjoeuXNm1fixInjlOf39fXV9a9UqZJex0lj7IOTJUsW5H3CwuLFiyUgIEB/jxUrlmTMmFFy5MgR4udx5vEIkav5unoFiBwxZswY2bVrl5QsWVJevnwpe/bskbhx4+qOA1/mYSlVqlRSu3Zth++/b98+ady4MXcSRETkUZBB/Oqrr6RcuXKSOHFi83IEho4ErWFtzZo10qFDB92/vnnzRk6dOqXVULNmzZLq1au/9/PXqVNHA2EDtsW6deusglbb+4SF5s2bS5o0aSRr1qx6ImHbtm1SpEgRWb58uUSLFs3h5+HxCEUkDFrJYyCzapTKPnv2TAoUKCA//PCDLFy4UMt1PvnkE3n48KEcP35cz0jiyx6wQ9u/f7/EixdP8ufPb/eMLL7YUYr74YcfvnUbdlb2dobYueN5EyRIIIULF5YoUaLIvXv3ZPv27fL69WvzumbLlk13+M5YFyIiorDWr18/KVGihNWyixcvyt69e/X32LFjS86cOeWDDz5453PdunVLDh8+rPs77LdjxIhhdfuZM2c0+EQgiP08qqmCg6DN2L+iCgkniZs0aSL//POPZl/v37+vJ7nxe7FixXQfbQnBLl4H7o/XkCFDBvNtn332mTlARbbTqHjCvh3rX7VqVav7IIhOmTKl5MqVy+pvrF69Wk94G8ufP3+u64Tsae7cuSV16tTv3G7169fXYxy4cOGCruukSZM0aAcc7+DvG9skc+bMVscNzjgeIXInDFrJI6Fcpnz58pppReYVZ0OrVKkip0+f1p0edmAIWrHjHTdunBQtWlTPVp49e1Z+//13KVu2rHnnhbOmOJOKnRvG49iW4Bw8eFAaNmwotWrVMi/r27evjBgxQgoWLKjX/f39dV0ePXqkWeDAwEBZsmSJ3oaAFzsJZ6wLERGRK1y5csW8X3vy5Ilm/1q2bCkjR44M8jFTp07VwAv7NOwXESj99ttvup/Gvhv76g0bNuiJXzz/q1evZNmyZRqAOSJSpEgaRM6ZM0eHEO3cuVO++eYbfX7sU48dOya//vqrfPHFF3p/7KNLly6tQST2rwiWcSwxYcIEvb1evXrm0t9Vq1aZhyedP39ekidPrkGr5X3wE38Dga0BwTD2+ytXrtSgdePGjXqMgqowBNBYx/bt2+txhKPw2CxZssiRI0fMyxC0Gu8HjkFQBoxjEizDSXQE76E9HiFySxjTSuTuatasaapatarVsooVK5qKFStm8vf3x4BPU9myZU0BAQHm2xctWmRKnjy56dq1a+ZlU6ZMMaVMmdJ8v3nz5plix45tunjxol5/8uSJ6cMPP9TnMyxfvtwULVo08/X58+ebfH19Tdu2bTMvO3z4sOnSpUv6++LFi02xYsWyWldnrQsREVFYOXfunO5z+vXrZ/r999/Nl1u3br113wsXLug+a/fu3eZlAwcONBUpUsR8Hfu92bNnm69fv37dtGfPHv29T58+psKFC5uePXtmvr1Vq1amcuXKBbl+48ePf2v/OnToUJOPj4/pypUrprhx45rGjh1rvm3QoEGmhAkTmh48eGDe72bJksX06tUrq/2zIXLkyKZVq1aZr2NbrFu3zurvWd5n165dpkiRIpmuXr1qtY543a9fvzbdv3/fFD9+fNOCBQvMt58/f163m+UxhK1EiRKZRowYYb6O4xy8js6dOwf5GBwz4LXhNRpCezxC5I6YaSWPgTO0KHHBmVic1Vy7dq2WBhtwxteyrOiXX37RUhmcfcS+BxfcjudBORLOgKKsGE2WjBInlMe0bt1aL0HBWdsaNWpYlU7lyZMn2HUPq3UhIiJyNmRRkYU0ZM+eXTONyOihERKGx6DsFMtQaovxlvagFBhVQ7gvGhihZBYXY79YsWJF+fvvv837xaRJk8rMmTPN97fHKHfF/bGOo0ePlu+//142bdqkt7dp08Z8306dOmlzKFQwoTcF1gdZ4suXL0umTJn0Pp9//nmotxMylciCIkvZpUsXXTZv3jzNrKJRJDKcyPiCMQsB1hvNJLG+tiXYllBSjdeJ4VB4fqx727Ztre6D58b7cf36dS09xvPi/cDx0PscjxC5Iwat5DHu3LljLntBg4JDhw5psGh09bVtjICdEr6M//rrL6vlKMFFSRFcvXpVy4gsvWuMDh7z6aefhmjdw2pdiIiIwmNMK4IsBH4IVDEOFEHU48ePtQdDcAESTrxOmTJFGymigRKG22B/iHJeDOnx8/OzegyCSATHQY2xNMpdMWYVY0tRbox98oABAzRoswx2o0ePrkEySo8BwSTKfVEii9eAXhhYPyOADQ2UCyNQRdCKcb8IBidOnGje92M9bff9CAzfNa71xIkTGqA/ePBATyJgSBJen+HSpUtSoUIFvQ9KnbG9cByB1/y+xyNE7ohBK3lkIyZ7bL9s0V0YY0Bw1jYoiRIl0nEhlmyv24ofP76OFQmJsFoXIiKi8ICsZYsWLWTw4MHmZcjYBTclGzoOI/hC0IimQd26ddPrw4cP194U6BWBLGlIWDZisoRuxwjwbGGZ0QkZJ70xzhbjOTHec/r06dqECGM6EYyHRoMGDTRgRhNING9CVhrPaez7cWwSmvnWLRsxIVOMMbRopIRAFQYOHKjHFRg7a7kuGLf7vscjRO7Ix9UrQBRW8AW/aNGit84CY94yA84ko5ECzlQa8JjgYIeBHZPl2WE0lEDJkdFVEWU6ljvysFoXIiKi8ICSYKMrPyD4RKY0KChdxWMgXbp0GvA2atTIPIcr9os///yz1T7Pdr8YEsWLF9dOxZZzxKLJE7LBaAQFKIEFZCMRUE+bNk335ShhtgeB9bvmaEfTqEKFCmm2FRcEjgaUP+PkM4b/WMJzhuTkN5pFYdshwDe2l+37gWMQBLeWQns8QuSOmGmlCKtjx456BhI7E5T/IEOKsR9oO49uf9CuXTs904odC0pj0NXPsgugPWg3j9IkjOHBXGqA8qTZs2frGUyU/WAsC84oIzuMM6NhtS5EREThAb0cevXqpUEeuu+OHTtWg7qgoIwXJcE40YvMI4I0BKkoPYZRo0bp7QgoUTKMjOTWrVv1p22Q5wgMF0LnYKxn586dNWgeNmyYjgPFfhgQrCGwNKatwb48ffr05pkAbGH5Tz/9pNlLdP5F92B7EKj27NlTx58iQ2rA8UDv3r014MT+HplplBCjH8fcuXO1wspRyOYiQzpjxgwds4rXiex3kiRJ9NgDGWScQLcU2uMRInfEoJU8ArKQtl/GBnwhI8jDF7elmDFj6g4QDQwwVxnuh0Bz/Pjx5vvgyxpNC7AMP7FjxZlMlC4ZMB4G43gsz1xiTAwaMqG8CH8X43ZQEgTYEeJsJ5ouLF26VHfcGD/jjHUhIiIKKxgXaW9/CiipRdCFucQRJM2fP1+nczECQsBcosjsGaW4mKIF+0pkPxHgokwWWUMj+2pMSYOmQ3hOjA9FMBYUBG1oWBgUjJ0tU6aMZlgR/GJeU8vp6hDAYnodBK/nzp3TYwsEgfjbgNdu2R8DAe7kyZO1tBkBJoJW2/tA3bp19UQzXhMutsEmXjMqtLD/R3Z0/fr1wY5pxRQ9ltsV0MsDgT6aJQEy1wik0ZQS42YxhQ6mr0H/D0Noj0eI3FEktBB29UoQERERERER2cMxrUREREREROS2GLQSERERERGR22LQSkRERERERG6LQSsRERERERG5LQatRERERERE5LYYtBIREREREZHbYtBKREREREREbotBKxEREREREbktBq1ERERERETkthi0EhERERERkdti0EpERERERERui0ErERERERERibv6H7FbZF9Fh667AAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "from chemml.visualization import ClassificationPlots\n",
    "\n",
    "\n",
    "plotter = ClassificationPlots().plot(targets, y_pred, y_pred_proba)\n",
    "display(plotter)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "nitin_py312_env",
   "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": "3.12.13"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}