{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "145c6b0c-3bf2-45de-95e7-8875a28d95f8", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexcptrestbpscholfbsrestecgthalachexangoldpeakslopecathaltarget
063131452331015002.30011
137121302500118703.50021
241011302040017201.42021
356111202360117800.82021
457001203540116310.62021
\n", "
" ], "text/plain": [ " age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n", "0 63 1 3 145 233 1 0 150 0 2.3 0 \n", "1 37 1 2 130 250 0 1 187 0 3.5 0 \n", "2 41 0 1 130 204 0 0 172 0 1.4 2 \n", "3 56 1 1 120 236 0 1 178 0 0.8 2 \n", "4 57 0 0 120 354 0 1 163 1 0.6 2 \n", "\n", " ca thal target \n", "0 0 1 1 \n", "1 0 2 1 \n", "2 0 2 1 \n", "3 0 2 1 \n", "4 0 2 1 " ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "### Reading Data and Checking for Missing Values\n", "\n", "import numpy as np\n", "import pandas as pd\n", "from scipy import stats\n", "import seaborn as sns\n", "from IPython.core.display import HTML\n", "import matplotlib.pyplot as plt\n", "from scipy.stats import uniform\n", "\n", "# Loading dataset into a DataFrame\n", "df = pd.read_csv('heart.csv')\n", "# Preview the first 5 rows\n", "df.head()" ] }, { "cell_type": "code", "execution_count": 3, "id": "4e5d33b1-c4ef-4328-ad17-a6aaa84a7168", "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
agesexcptrestbpscholfbsrestecgthalachexangoldpeakslopecathaltarget
count303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000303.000000
mean54.3663370.6831680.966997131.623762246.2640260.1485150.528053149.6468650.3267331.0396041.3993400.7293732.3135310.544554
std9.0821010.4660111.03205217.53814351.8307510.3561980.52586022.9051610.4697941.1610750.6162261.0226060.6122770.498835
min29.0000000.0000000.00000094.000000126.0000000.0000000.00000071.0000000.0000000.0000000.0000000.0000000.0000000.000000
25%47.5000000.0000000.000000120.000000211.0000000.0000000.000000133.5000000.0000000.0000001.0000000.0000002.0000000.000000
50%55.0000001.0000001.000000130.000000240.0000000.0000001.000000153.0000000.0000000.8000001.0000000.0000002.0000001.000000
75%61.0000001.0000002.000000140.000000274.5000000.0000001.000000166.0000001.0000001.6000002.0000001.0000003.0000001.000000
max77.0000001.0000003.000000200.000000564.0000001.0000002.000000202.0000001.0000006.2000002.0000004.0000003.0000001.000000
\n", "
" ], "text/plain": [ " age sex cp trestbps chol fbs \\\n", "count 303.000000 303.000000 303.000000 303.000000 303.000000 303.000000 \n", "mean 54.366337 0.683168 0.966997 131.623762 246.264026 0.148515 \n", "std 9.082101 0.466011 1.032052 17.538143 51.830751 0.356198 \n", "min 29.000000 0.000000 0.000000 94.000000 126.000000 0.000000 \n", "25% 47.500000 0.000000 0.000000 120.000000 211.000000 0.000000 \n", "50% 55.000000 1.000000 1.000000 130.000000 240.000000 0.000000 \n", "75% 61.000000 1.000000 2.000000 140.000000 274.500000 0.000000 \n", "max 77.000000 1.000000 3.000000 200.000000 564.000000 1.000000 \n", "\n", " restecg thalach exang oldpeak slope ca \\\n", "count 303.000000 303.000000 303.000000 303.000000 303.000000 303.000000 \n", "mean 0.528053 149.646865 0.326733 1.039604 1.399340 0.729373 \n", "std 0.525860 22.905161 0.469794 1.161075 0.616226 1.022606 \n", "min 0.000000 71.000000 0.000000 0.000000 0.000000 0.000000 \n", "25% 0.000000 133.500000 0.000000 0.000000 1.000000 0.000000 \n", "50% 1.000000 153.000000 0.000000 0.800000 1.000000 0.000000 \n", "75% 1.000000 166.000000 1.000000 1.600000 2.000000 1.000000 \n", "max 2.000000 202.000000 1.000000 6.200000 2.000000 4.000000 \n", "\n", " thal target \n", "count 303.000000 303.000000 \n", "mean 2.313531 0.544554 \n", "std 0.612277 0.498835 \n", "min 0.000000 0.000000 \n", "25% 2.000000 0.000000 \n", "50% 2.000000 1.000000 \n", "75% 3.000000 1.000000 \n", "max 3.000000 1.000000 " ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Get descriptive statistics for numerical columns\n", "df.describe()" ] }, { "cell_type": "code", "execution_count": 11, "id": "3bb01c8d-b6f5-4339-aeeb-363e6c5b9ca4", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "age int64\n", "sex int64\n", "cp int64\n", "trestbps int64\n", "chol int64\n", "fbs int64\n", "restecg int64\n", "thalach int64\n", "exang int64\n", "oldpeak float64\n", "slope int64\n", "ca int64\n", "thal int64\n", "target int64\n", "dtype: object" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.dtypes" ] }, { "cell_type": "code", "execution_count": 19, "id": "a5b51641-1b2c-4af2-ac3e-56194ccb9974", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Missing Values Per Column:\n", "age 0\n", "sex 0\n", "cp 0\n", "trestbps 0\n", "chol 0\n", "fbs 0\n", "restecg 0\n", "thalach 0\n", "exang 0\n", "oldpeak 0\n", "slope 0\n", "ca 0\n", "thal 0\n", "target 0\n", "dtype: int64\n" ] } ], "source": [ "# Step 1: Check for missing values\n", "print(\"Missing Values Per Column:\")\n", "print(df.isnull().sum())" ] }, { "cell_type": "code", "execution_count": 27, "id": "90c52d02-decf-444c-8719-7ad22be58a60", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " age sex cp trestbps chol fbs restecg thalach exang oldpeak slope \\\n", "0 63 1 3 145 233 1 0 150 0 2.3 0 \n", "1 37 1 2 130 250 0 1 187 0 3.5 0 \n", "2 41 0 1 130 204 0 0 172 0 1.4 2 \n", "3 56 1 1 120 236 0 1 178 0 0.8 2 \n", "4 57 0 0 120 354 0 1 163 1 0.6 2 \n", "\n", " ca thal target \n", "0 0 1 1 \n", "1 0 2 1 \n", "2 0 2 1 \n", "3 0 2 1 \n", "4 0 2 1 \n" ] } ], "source": [ "# Step 2: Convert categorical features to numerical data\n", "## numerical_features = ['age', 'trestbps', 'chol', 'thalach', 'oldpeak']\n", "## categorical_features = ['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal']\n", "\n", "from sklearn.preprocessing import LabelEncoder\n", "# Identify categorical features\n", "categorical_features = ['sex', 'cp', 'fbs', 'restecg', 'exang', 'slope', 'ca', 'thal']\n", "\n", "# Apply LabelEncoder to each categorical feature\n", "label_encoders = {}\n", "for feature in categorical_features:\n", " label_encoders[feature] = LabelEncoder()\n", " df[feature] = label_encoders[feature].fit_transform(df[feature])\n", "\n", "# Verify the transformed data\n", "print(df.head())" ] }, { "cell_type": "code", "execution_count": 55, "id": "7f426e3d-52e1-4ec7-a273-e875fc936296", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Training Logistic Regression...\n", "Best hyperparameters found by GridSearchCV: Logistic Regression: {'C': 1, 'max_iter': 100, 'solver': 'liblinear'}\n", "\n", "Training Random Forest...\n", "Best hyperparameters found by GridSearchCV: Random Forest: {'max_depth': 5, 'min_samples_leaf': 1, 'min_samples_split': 10, 'n_estimators': 50}\n", "\n", "Training SVM...\n", "Best hyperparameters found by GridSearchCV: SVM: {'C': 1, 'class_weight': None, 'degree': 3, 'gamma': 'scale', 'kernel': 'rbf'}\n", "\n", "Training KNN...\n", "Best hyperparameters found by GridSearchCV: KNN: {'algorithm': 'auto', 'metric': 'manhattan', 'n_neighbors': 5, 'weights': 'uniform'}\n", "\n", "Training Gradient Boosting...\n", "Best hyperparameters found by GridSearchCV: Gradient Boosting: {'learning_rate': 0.2, 'max_depth': 5, 'n_estimators': 50}\n", "\n", "Evaluating Logistic Regression...\n", "Accuracy for Logistic Regression: 0.85\n", "Precision for Logistic Regression: 0.87\n", "Recall for Logistic Regression: 0.84\n", "F1 for Logistic Regression: 0.86\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.86 0.85 29\n", " 1 0.87 0.84 0.86 32\n", "\n", " accuracy 0.85 61\n", " macro avg 0.85 0.85 0.85 61\n", "weighted avg 0.85 0.85 0.85 61\n", "\n", "------------------------------\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluating Random Forest...\n", "Accuracy for Random Forest: 0.87\n", "Precision for Random Forest: 0.88\n", "Recall for Random Forest: 0.88\n", "F1 for Random Forest: 0.88\n", " precision recall f1-score support\n", "\n", " 0 0.86 0.86 0.86 29\n", " 1 0.88 0.88 0.88 32\n", "\n", " accuracy 0.87 61\n", " macro avg 0.87 0.87 0.87 61\n", "weighted avg 0.87 0.87 0.87 61\n", "\n", "------------------------------\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAA2kAAAHnCAYAAAAirRUnAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABxkElEQVR4nO3deZyN9f//8eeZfbUMZhNjHTtDskwx9i1KUfZ9KbTYy0eFkkFlSaFkrSFCypLI1oKiKKGQJWVEtjLDmBnv3x/zm/N1zAwzY8a54nF3O7ebeZ/3uc7rXOe6znVe5/263pfNGGMEAAAAALAEF2cHAAAAAAD4PyRpAAAAAGAhJGkAAAAAYCEkaQAAAABgISRpAAAAAGAhJGkAAAAAYCEkaQAAAABgISRpAAAAAGAhJGkAAAAAYCHZStJ++ukn9ejRQ8WLF5eXl5f8/PxUrVo1TZw4UWfPns3pGB3s2rVLUVFRyps3r2w2m6ZMmZLjz2Gz2TR69OgcX+7NzJs3TzabTTabTZs3b05zvzFGpUqVks1mU7169bL1HNOnT9e8efOy9JjNmzdnGFN2LV68WBUqVJC3t7dsNpt2796dY8u+Xmr8qTdXV1cVKlRIrVq10s6dO3PteW8m9f0+evSo0547vdvQoUNvezyZMW7cOK1YsSLD+w8fPqynnnpK4eHh8vb2lo+PjypUqKAXXnhBf/75p71f9+7dVaxYsdwPOANHjx6VzWZLsx+mt0+MHj1aNpst12Jp2LChnnzyyVxbvjPdjvf5xIkTGj16dLqfX927d5efn1+uPn9G+/D48eNz9XlvxNn7lxVltM//V6X3HhcrVkzdu3e3/32jfSO79u7dq/79+6t27dry9fW96feSDz/8UBEREfLy8lJoaKgGDhyoixcv5lg8VpHRsTE3vrtlVnx8vEaPHu2U575V3bt3T/dztWzZsun2nzZtmsqWLStPT08VL15cY8aMUWJiYo7E4pbVB8yaNUv9+/dXmTJlNGzYMJUvX16JiYnauXOnZs6cqW3btunjjz/OkeDS07NnT8XFxenDDz9U/vz5c+VgsG3bNt1zzz05vtzM8vf31+zZs9MkYlu2bNFvv/0mf3//bC97+vTpKliwoMOH6c1Uq1ZN27ZtU/ny5bP9vNc6ffq0unTpombNmmn69Ony9PRUeHh4jiz7RsaNG6f69esrMTFRu3bt0pgxYxQVFaXdu3erdOnSuf78VjR37tw0HzyhoaFOiubGxo0bp7Zt26p169Zp7lu1apXat2+vggUL6qmnnlLVqlVls9m0Z88ezZkzR6tXr9auXbtuf9DpCAkJ0bZt21SyZEl7W0b7RO/evdWsWbNcieOTTz7RN998owULFuTK8u8GJ06c0JgxY1SsWDFFREQ4JYa2bdtqyJAhDm1FixZ1SiyS9OKLL+rZZ5912vPDOT7++GPlyZPH/ndu7Bs7d+7UihUrVLVqVTVs2FArV67MsG9MTIw6d+6s3r17a/LkyTpw4ICee+457du3T+vWrcuReKwio2NjTn93y4r4+HiNGTNGkrI9qOBM3t7e2rhxY5q267366qt68cUX9fzzz6tJkybasWOH/Yfhd99995bjyFKStm3bNvXr10+NGzfWihUr5Onpab+vcePGGjJkiNauXXvLQd3Izz//rD59+qh58+a59hy1atXKtWVnRrt27RQTE6O3337b4UNv9uzZql27tv7555/bEkdiYqJsNpvy5MmTo+vkwIEDSkxMVOfOnRUVFZUjy4yPj5ePj88N+5QuXdr+OurUqaN8+fKpW7du+uCDD+wfJnebihUrqnr16jm+3My8HznlyJEjat++vcLDw7Vp0yblzZvXfl+DBg30zDPP5OoPR1nl6emZZn/KaJ/w8fHJ0R+Mrn1fxo0bp0ceeUSFCxfOseXj9gsKCnL6Meta1/74gLtH1apVc/05unTpom7dukmSli5dmmGSlpycrGHDhqlJkyaaNWuWJKl+/fry9/dXp06d9Nlnn+Xqd0iryOnvblZw6dIleXl55WqFiSS5uLjcdN2dOXNGY8eOVZ8+fTRu3DhJKQlpYmKiXnjhBQ0cOPCWE+QslTuOGzdONptN7777rkOClsrDw0MPPfSQ/e+rV69q4sSJ9mHAwMBAde3aVX/88YfD4+rVq6eKFStqx44dqlOnjnx8fFSiRAmNHz9eV69elfR/5VlJSUmaMWOGffhRUoYlQemVk23cuFH16tVTgQIF5O3traJFi6pNmzaKj4+390mv3PHnn3/Www8/rPz588vLy0sRERGaP3++Q5/UoeVFixZp5MiRCg0NVZ48edSoUSP9+uuvmVvJkjp06CBJWrRokb3twoULWrZsmXr27JnuY8aMGaOaNWsqICBAefLkUbVq1TR79mwZY+x9ihUrpr1792rLli329Zc6Epka+/vvv68hQ4aocOHC8vT01KFDh9IMmf/9998qUqSIIiMjHYZ09+3bJ19fX3Xp0iXD19a9e3c98MADklKS0etLNz/99FPVrl1bPj4+8vf3V+PGjbVt2zaHZaS+3z/88IPatm2r/PnzZ+uLQWpy8tdff2V5XUop67Nly5Zau3atqlWrJm9vb5UtW1Zz5sxJ81zbt2/X/fffby+7GDFiRLrD4VndZ7Zt26bIyEh5e3urWLFimjt3riRp9erVqlatmnx8fFSpUqVs/3hyq++HMUbTp09XRESEvL29lT9/frVt21aHDx92WMauXbvUsmVLBQYGytPTU6GhoXrwwQftr9tmsykuLk7z58+3b7up282kSZMUFxen6dOnOyRoqWw2mx599NEbvs63335bdevWVWBgoHx9fVWpUiVNnDgxzXt0szgl6aOPPlLNmjWVN29e+2fZtfvt9aVPN9onMvpsW7x4sb3kx8/PT02bNk0zUphabrdnzx41adJE/v7+atiwof11fPfdd2n21dTPzI0bN6pPnz4qUKCA8uTJo65duyouLk4nT57U448/rnz58ikkJERDhw5Ns44ys/98/fXXcnd3T1Nam/r8s2fPzvC9Ss+8efNUpkwZeXp6qly5chmODl65ckVjx46171+FChVSjx49dPr0aYd+qfv2xx9/rMqVK8vLy0slSpTQm2++ae+zefNm3XfffZKkHj162LfL648dhw4dUosWLeTn56ciRYpoyJAhSkhIyNLru51sNpueeuopzZ07V2XKlJG3t7eqV6+u7du3yxij1157TcWLF5efn58aNGigQ4cOOTw+vVK41GW+//77KleunHx8fFSlShWtWrUqy/HNmDFDVapUkZ+fn/z9/VW2bFn973//s99/+vRp9e/fX+XLl5efn58CAwPVoEEDffXVVw7LSd0PX3vtNU2YMEHFihWTt7e36tWrZ//R5Pnnn1doaKjy5s2rRx55RKdOnXJYRma2kxs5ePCgOnbsaP88KVeunN5++22HPlevXtXYsWPt70W+fPlUuXJlTZ06NUfXW+q+t379evXo0UMBAQHy9fVVq1at0nxep+facsfM7htZ5eKSua+s27dvV2xsrHr06OHQ/thjj8nPzy/bP9pl5Zh/M7fj2JheuWPqceGXX35R06ZN5evrq5CQEHuJ9Pbt2/XAAw/I19dX4eHhab7nZmb/Onr0qAoVKiQp5XiQGte1FVxff/21GjZsKH9/f/n4+CgyMlKrV692eK7UbXLdunXq2bOnChUqJB8fHyUkJOj06dPq27evihQpYv8sv//++/XFF19k+b3IrrVr1+ry5ctptrMePXrIGHPD0zMyzWRSUlKS8fHxMTVr1szsQ0zfvn2NJPPUU0+ZtWvXmpkzZ5pChQqZIkWKmNOnT9v7RUVFmQIFCpjSpUubmTNnmvXr15v+/fsbSWb+/PnGGGNOnTpltm3bZiSZtm3bmm3btplt27YZY4wZNWqUSe+lzJ0710gyR44cMcYYc+TIEePl5WUaN25sVqxYYTZv3mxiYmJMly5dzLlz5+yPk2RGjRpl//uXX34x/v7+pmTJkmbBggVm9erVpkOHDkaSmTBhgr3fpk2bjCRTrFgx06lTJ7N69WqzaNEiU7RoUVO6dGmTlJR0w/WVGu+OHTtMly5dTI0aNez3zZgxw/j6+pp//vnHVKhQwURFRTk8tnv37mb27Nlm/fr1Zv369eaVV14x3t7eZsyYMfY+P/zwgylRooSpWrWqff398MMPDrEXLlzYtG3b1nz66adm1apV5syZM/b7Nm3aZF/W119/bdzc3MygQYOMMcbExcWZ8uXLm7Jly5qLFy9m+BoPHTpk3n77bSPJjBs3zmzbts3s3bvXGGNMTEyMkWSaNGliVqxYYRYvXmzuvfde4+HhYb766iv7MlLf77CwMPPcc8+Z9evXmxUrVmT4nKnxf/TRRw7tq1atMpLMG2+8keV1aYwxYWFh5p577jHly5c3CxYsMJ9//rl57LHHjCSzZcsWe7+9e/caHx8fU758ebNo0SLzySefmKZNm5qiRYs6bJ/GZH2fKVOmjJk9e7b5/PPPTcuWLY0kM2bMGFOpUiWzaNEis2bNGlOrVi3j6elp/vzzT/vjU7e17du3m8TERIdbqpx4P/r06WPc3d3NkCFDzNq1a83ChQtN2bJlTVBQkDl58qQxxpiLFy+aAgUKmOrVq5slS5aYLVu2mMWLF5snn3zS7Nu3zxhjzLZt24y3t7dp0aKFfdtN3W7Cw8NNUFBQhu//9bp162bCwsIc2gYNGmRmzJhh1q5dazZu3GgmT55sChYsaHr06GHvk5k4t27damw2m2nfvr1Zs2aN2bhxo5k7d67p0qWLfTlHjhwxkszcuXONMTfeJ9L7bHv11VeNzWYzPXv2NKtWrTLLly83tWvXNr6+vvbHpb5Od3d3U6xYMRMdHW02bNhgPv/8c2OMMS+//LJxdXU1//77r8OyU7eL4sWLmyFDhph169aZCRMmGFdXV9OhQwdTrVo1M3bsWLN+/Xrz3HPP3dL+M378eCPJfPLJJ8YYY37++Wfj4+NjOnfunKn38fqYH374YbNy5UrzwQcfmFKlSpkiRYo4vM/JycmmWbNmxtfX14wZM8asX7/evPfee6Zw4cKmfPnyJj4+3t43LCzMFC5c2BQtWtTMmTPHrFmzxnTq1MlIMq+99poxxpgLFy7Yn/uFF16wb5fHjx+3r38PDw9Trlw58/rrr5svvvjCvPTSS8Zms6VZF0lJSWn2w/RuycnJDo+TZPLnz2+8vLyMh4eHqVatmpkzZ06W1t/1UvflyMhIs3z5cvPxxx+b8PBwExAQYAYNGmQefvhhs2rVKhMTE2OCgoJM5cqVzdWrV+2PT2//Sj0u1qhRwyxZssSsWbPG1KtXz7i5uZnffvst07EtWrTISDJPP/20Wbdunfniiy/MzJkzzTPPPGPv88svv5h+/fqZDz/80GzevNmsWrXK9OrVy7i4uDgcw1L3w7CwMNOqVSuzatUq88EHH5igoCATHh5uunTpYnr27Gk+++wzM3PmTOPn52datWrlEE9mtpNrnyt1nzcm5biQN29eU6lSJbNgwQKzbt06M2TIEOPi4mJGjx5t7xcdHW1cXV3NqFGjzIYNG8zatWvNlClTHPrkxHpL3ZaLFClif93vvvuuCQwMNEWKFHH4jpTeexwWFma6detmjLn5vnH16tVMbe/XHo+u99FHH6X5XpJq5syZRpLD52Gq6tWrm9q1a2d63V3/GjNzzM+M23FsTO+727WfS1OnTjXr1683PXr0MJLMiBEjTHh4eJrvFDt37rQ/PjP71+XLl83atWuNJNOrVy97XIcOHTLGGLN582bj7u5u7r33XrN48WKzYsUK06RJE2Oz2cyHH35of67Ubahw4cKmb9++5rPPPjNLly41SUlJpmnTpqZQoULm3XffNZs3bzYrVqwwL730ksPjk5OTM7WNXf/dvFu3bsbFxcUEBQUZFxcXU7hwYTNgwABz5swZh37PP/+8kZTud96CBQuaDh06ZGmbSE+mk7STJ08aSaZ9+/aZ6r9//34jyfTv39+h/dtvvzWSzP/+9z97W1RUlJFkvv32W4e+5cuXN02bNnUMWDIDBgxwaMtskrZ06VIjyezevfuGsV+fpLVv3954enqa33//3aFf8+bNjY+Pjzl//rwx5v92iBYtWjj0W7JkiZFkTyozcm2Slrqsn3/+2RhjzH333We6d+9ujDHpJmnXSt0wX375ZVOgQAGHA2hGj019vrp162Z43/UfhhMmTDCSzMcff2y6detmvL29zU8//XTD13jt8q5NmpKTk01oaKipVKmSwxeRf//91wQGBprIyEh7W+r7/dJLL930ua59vsWLF5vExEQTHx9vvvnmG1OmTBlTvnx5h4PP9W60LsPCwoyXl5c5duyYve3SpUsmICDAPPHEE/a2du3aGW9vb/sHrzEpX8rKli3rsH1mZ5+59sPzzJkzxtXV1Xh7ezskZLt37zaSzJtvvmlvS93W0rulfhm81fcj9UeV67/EHz9+3Hh7e5vhw4cbY4zZuXOnkXTDRNsYY3x9fe1fAq7l5eVlatWqdcPHXiu9LxjXSn3PFyxYYFxdXc3Zs2czHefrr79uJNk/E9KT3he2jH5IuP6z7ffffzdubm7m6aefduj377//muDgYPP44487vE5J6X5pb968uSlbtmya9tTt4vrlt27d2kgykyZNcmiPiIgw1apVy/C13mj/uXr1qmnRooXJly+f+fnnnzP1I096yw8NDTXVqlVzWPbRo0eNu7u7w/uc+kV12bJlDsvYsWOHkWSmT59ubwsLCzM2my3NsaJx48YmT548Ji4uzuGx176XqVLX/5IlSxzaW7RoYcqUKePQFhYWluH+eO3t2uOSMcZ07NjRxMTEmC+//NIsXbrUNG/e3P7FOLskmeDgYIf3YcWKFUaSiYiIcFjPU6ZMMZIcPvczStKCgoLMP//8Y287efKkcXFxMdHR0ZmO7amnnjL58uXL0utJTYAbNmxoHnnkEXt76n5YpUoVh8+41Nf00EMPOSxn4MCBRpK5cOGCvS2z20l6+3zTpk3NPffc47C81Nfo5eVl/9xp2bKliYiIyNJrvl5m1lvqvn/tOjLGmG+++cZIMmPHjrW33SxJM+bG+8aNjj/X3zJyoyTt1VdfNZJMbGxsmvuaNGliwsPDM1zujWT2mH8zt+vYmFGSdv3nYGJioilUqJCRZP/h3pj/+04xePDgDJ87o/3r9OnT6X5mGWNMrVq1TGBgoMOPhElJSaZixYrmnnvusX/GpG4nXbt2TbMMPz8/M3DgwAzjMub/jp83u12/LU+aNMlMmjTJrFu3zqxbt86MHDnS+Pj4mLJlyzrE3KdPH+Pp6Znuc4eHh5smTZrcML7MyLUp+Ddt2iRJaSaoqFGjhsqVK6cNGzY4tAcHB6tGjRoObZUrV9axY8dyLKaIiAh5eHiob9++mj9/fqaG8KWUEsmGDRuqSJEiDu3du3dXfHx8mvKva0s+pZTXISlLryUqKkolS5bUnDlztGfPHu3YsSPDUsfUGBs1aqS8efPK1dVV7u7ueumll3TmzJk0JRo30qZNm0z3HTZsmB588EF16NBB8+fP17Rp01SpUqVMP/5av/76q06cOKEuXbo4lDT4+fmpTZs22r59u0NJalZjlVJKydzd3eXj46P7779f//zzj1avXq18+fI59MvKuoyIiHA4Sd/Ly0vh4eEO7/WmTZvUsGFDBQUF2dtcXV3Vrl07h2VldZ8JCQnRvffea/87ICBAgYGBioiIcJj8o1y5cpLS3/4WLFigHTt2ONzc3Nxy5P1YtWqVbDabOnfurKSkJPstODhYVapUsZdglCpVSvnz59dzzz2nmTNnat++fWnizG27du3SQw89pAIFCtjf865duyo5OVkHDhzIdJypJT6PP/64lixZ4jCrZE74/PPPlZSUpK5duzqsUy8vL0VFRaU7k1Z6+8mJEycUGBiY4fO0bNnS4e/UbejBBx9M0379dpXZ/cdms2nBggXy9/dX9erVdeTIES1ZskS+vr43XQ+pUrfTjh07OpSFhoWFKTIy0qHvqlWrlC9fPrVq1cph3UVERCg4ODjNuqtQoYKqVKni0NaxY0f9888/+uGHHzIVn81mU6tWrRza0juurVy5Ms1+mN6tb9++Do+LiYlRx44dVadOHbVp00Zr1qxRy5YtNX78+DQlnFlRv359h/ch9f1v3ry5w3q+0WdLesu8dtKroKAgBQYGZum4WKNGDZ0/f14dOnTQJ598or///jvdfjNnzlS1atXk5eUlNzc3ubu7a8OGDdq/f3+avi1atHD4jLvRti5Jv//+u0N7draTy5cva8OGDXrkkUfk4+PjsD22aNFCly9f1vbt2+2v+ccff1T//v31+eefZ+uc9MyuN0nq1KmTw9+RkZEKCwuzH59yQqtWrTK1ve/YseOWniej85Zu5XymzBzzb8bZx0abzaYWLVrY/3Zzc1OpUqUUEhLicG5h6neK619bVvav68XFxenbb79V27ZtHWa/dXV1VZcuXfTHH3+kOT0ovWNYjRo1NG/ePI0dO1bbt29P9/SRvn37Zmobu/7cxkGDBmnQoEFq3LixGjdurLFjx2rBggX65Zdf7Oc4XrsuM5IT581lOkkrWLCgfHx8dOTIkUz1P3PmjKSUL5LXCw0Ntd+fqkCBAmn6eXp66tKlS5kN8aZKliypL774QoGBgRowYIBKliypkiVL3rS2+8yZMxm+jtT7r3X9a0k9fy8rr8Vms6lHjx764IMPNHPmTIWHh6tOnTrp9v3uu+/UpEkTSSmzb37zzTfasWOHRo4cmeXnTe913ijG7t276/LlywoODr7huWg3c7Pt5erVqzp37ly2Y5WkCRMmaMeOHdqyZYtGjhypv/76S61bt3Y4PySr6zIz2+2ZM2cUHBycpt/1bVndZwICAtL08/DwSNPu4eEhKeWLwfXKlSun6tWrO9wyE0tm3o+//vpLxhgFBQXJ3d3d4bZ9+3b7F4W8efNqy5YtioiI0P/+9z9VqFBBoaGhGjVqVKamsS1atGimP5fS8/vvv6tOnTr6888/NXXqVH311VfasWOH/dyQ1PcyM3HWrVtXK1assCdS99xzjypWrOhwfumtSD1/8r777kuzThcvXpzmy5ePj4/D5EOpUk++zkhG21B67dduV9nZfx566CFdvnxZzZo1y/KPPKnbaWb2r7/++kvnz5+Xh4dHmnV38uTJNOvuRsu8fl/MiI+PT5r17OnpmWZfLF++vCIiIm56Sy+m66V+8buVy4tk5f2X0v9suV5OHOO7dOmiOXPm6NixY2rTpo0CAwNVs2ZNrV+/3t5n0qRJ6tevn2rWrKlly5Zp+/bt2rFjh5o1a5buc93qa83OdnLmzBklJSVp2rRpabbF1C/PqdvjiBEj9Prrr2v79u1q3ry5ChQooIYNG2bp/c3MervZ68nsNp8ZAQEBmdreszsrZOq2ll7MZ8+eTffYmdVlXyur2/HtOjZmJL3PpfS+O6S2X7vNZ3X/ut65c+dkjMnSd+r0+i5evFjdunXTe++9p9q1aysgIEBdu3bVyZMn7X2Cg4MztY1lZnKPRx55RL6+vvYfT6SUbeHy5ctpfrCWbn07S5Xp2R1dXV3VsGFDffbZZ/rjjz9uOuNY6oYcGxubpu+JEydUsGDBbISbvtSNLSEhwWFCk/R+LapTp47q1Kmj5ORk7dy5U9OmTdPAgQMVFBSk9u3bp7v8AgUKKDY2Nk37iRMnJClHX8u1unfvrpdeekkzZ87Uq6++mmG/Dz/8UO7u7lq1apXDjpedkxazkvnHxsZqwIABioiI0N69ezV06NBMnzB9vWu3l+udOHFCLi4uyp8/f7ZjlaQSJUrYk5C6devK29tbL7zwgqZNm2afwCAn12WqAgUKOHxwpLq+7XbuMzeTE+9HwYIFZbPZ9NVXX6U70dC1bZUqVdKHH34oY4x++uknzZs3Ty+//LK8vb31/PPP3zDWpk2batq0adq+fXu2ZrJasWKF4uLitHz5coWFhdnb07u+T2bifPjhh/Xwww8rISFB27dvV3R0tDp27KhixYqpdu3aWY7vWqnbwNKlSx1izUhG+0jBggVz5ZqWWd1/1q9frxkzZqhGjRr6+OOPtWzZsiyNkKdup5nZvwoWLKgCBQpkOInO9Zc2udEy0/uiditKliyZqV/iR40addPJF8z/n6Als5Ms/Nf06NFDPXr0UFxcnL788kuNGjVKLVu21IEDBxQWFqYPPvhA9erV04wZMxwe9++//+ZKPNnZTvLnz28fORgwYEC6fYoXLy4pZZRj8ODBGjx4sM6fP68vvvhC//vf/9S0aVMdP34807Po3my93ez1lCpVKlPPkxnz589PM9lCRlK356xI/bFnz549Dl/Ak5KS9Msvv9gnZ3OW23VszA23un/lz59fLi4uWfpOnd5xrGDBgpoyZYqmTJmi33//XZ9++qmef/55nTp1yv4Z//LLL2dq5u6wsLBMXa/WGOPwuXrtdlazZk17e+qPfhUrVrzpMm8mS5/iI0aMkDFGffr00ZUrV9Lcn5iYaB82bNCggaSUN/RaO3bs0P79++2zjOWE1JmkfvrpJ4f2G11Dw9XVVTVr1rT/Wn6j8pWGDRtq48aN9g0o1YIFC+Tj45NrU5wWLlxYw4YNU6tWrezTzqbHZrPJzc1Nrq6u9rZLly7p/fffT9M3p0Ynk5OT1aFDB9lsNn322WeKjo7WtGnTtHz58mwtr0yZMipcuLAWLlzo8KEcFxenZcuW2WcYzEnDhw9XqVKlNH78ePsHTFbWZWbVr19fGzZscJhFMjk5WYsXL3bodzv3mZvJifejZcuWMsbozz//TDNaV7169XRHTWw2m6pUqaLJkycrX758DvtlRtvuoEGD5Ovrq/79++vChQtp7jfG3HA2r9QDwLUHRmNMmrKGzMZ5bbxRUVGaMGGCJOXIddqaNm0qNzc3/fbbb+mu08xeTqFs2bKZLvfOiqzsP7GxsfZLDmzdulUPPfSQevXqlaVR0TJlyigkJESLFi1y2E6PHTumrVu3OvRt2bKlzpw5o+Tk5HTXW5kyZRz67927Vz/++KND28KFC+Xv769q1apJyl6VRHqyW+6Ynvfff1/u7u4OpdB3Il9fXzVv3lwjR47UlStXtHfvXkkp2+D1X3x/+umnNKcl5JTMbCfX8/HxUf369bVr1y5Vrlw53e0xvQQvX758atu2rQYMGKCzZ89m6ovl9TJab6liYmIc/t66dauOHTuW5Wtd3WjfyO1yx5o1ayokJCTNxcOXLl2qixcv3nS239x2u46NuSGz+1dG77+vr69q1qyp5cuXO9x39epVffDBB7rnnnuyfN3cokWL6qmnnlLjxo0d1kt2yx3Ts3TpUsXHxzt832/WrJm8vLzSbGeps1Kmd03XrMrSddJq166tGTNmqH///rr33nvVr18/VahQwX5x4HfffVcVK1ZUq1atVKZMGfXt21fTpk2Ti4uLmjdvrqNHj+rFF19UkSJFNGjQoFsOPlWLFi0UEBCgXr166eWXX5abm5vmzZun48ePO/SbOXOmNm7cqAcffFBFixbV5cuX7VOnNmrUKMPljxo1SqtWrVL9+vX10ksvKSAgQDExMVq9erUmTpyY7rTfOSV1WtQbefDBBzVp0iR17NhRffv21ZkzZ/T666+n+wtN6q8yixcvVokSJeTl5ZWt88hGjRqlr776SuvWrVNwcLCGDBmiLVu2qFevXqpatar9V8DMcnFx0cSJE9WpUye1bNlSTzzxhBISEvTaa6/p/PnzmVoPWeXu7q5x48bp8ccf19SpU/XCCy9kaV1m1gsvvKBPP/1UDRo00EsvvSQfHx+9/fbbiouLc+h3O/eZm8mJ9+P+++9X37591aNHD+3cuVN169aVr6+vYmNj9fXXX6tSpUrq16+fVq1apenTp6t169YqUaKEjDFavny5zp8/r8aNG9uXV6lSJW3evFkrV65USEiI/P39VaZMGRUvXlwffvih2rVrp4iICPvFrKWUy0LMmTNHxhg98sgj6cbZuHFjeXh4qEOHDho+fLguX76sGTNmpCnnzEycL730kv744w81bNhQ99xzj86fP6+pU6fK3d09R64JWKxYMb388ssaOXKkDh8+rGbNmil//vz666+/9N1338nX1zdTvxzWq1dPc+bM0YEDB3L0QvKZ3X+u/ZFn4cKFcnV11bx58xQREaF27drp66+/tpeX3YiLi4teeeUV9e7dW4888oj69Omj8+fPa/To0WnKttq3b6+YmBi1aNFCzz77rGrUqCF3d3f98ccf2rRpkx5++GGHbSQ0NFQPPfSQRo8erZCQEH3wwQdav369JkyYYP+BomTJkvL29lZMTIzKlSsnPz8/hYaGZvmC8Nn5DH7ttde0b98++7Z26tQpzZ49W+vWrdPo0aMdfo0+evSoihcvrm7duqX5QvFf0qdPH3l7e+v+++9XSEiITp48qejoaOXNm9d+PmjLli31yiuvaNSoUYqKitKvv/6ql19+WcWLF1dSUlKOx5SZ7SQ9U6dO1QMPPKA6deqoX79+KlasmP79918dOnRIK1eutF9It1WrVvbrWRYqVEjHjh3TlClTFBYWptKlS2cqxsyst1Q7d+5U79699dhjj+n48eMaOXKkChcurP79+2dpvdxo3yhQoEC2RqPj4+O1Zs0aSbKXnW3ZskV///23PfmUUn6Enzhxorp06aInnnhCHTp00MGDBzV8+HA1btxYzZo1c1iuzWbL8Jze3HC7jo25IbP7l7+/v8LCwvTJJ5+oYcOGCggIUMGCBVWsWDFFR0ercePGql+/voYOHSoPDw9Nnz5dP//8sxYtWnTTKqkLFy6ofv366tixo8qWLSt/f3/t2LFDa9eudUjAs/NZfOzYMXXs2FHt27dXqVKlZLPZtGXLFk2ZMkUVKlRQ79697X0DAgL0wgsv6MUXX1RAQID9YtajR49W7969HUZxs/0ZnJ3ZRnbv3m26detmihYtajw8PIyvr6+pWrWqeemll8ypU6fs/ZKTk82ECRNMeHi4cXd3NwULFjSdO3e2T8OaKioqylSoUCHN82Q0S9T1szsaY8x3331nIiMjja+vrylcuLAZNWqUee+99xxmz9u2bZt55JFHTFhYmPH09DQFChQwUVFR5tNPP03zHNfPSLNnzx7TqlUrkzdvXuPh4WGqVKmSZtaijGZoS29mp/RcO7vjjaQ3Q+OcOXNMmTJljKenpylRooSJjo42s2fPdnj9xqTMetakSRPj7+/vMKtNRrFfe1/qDEHr1q0zLi4uadbRmTNnTNGiRc19991nEhISMoz/Rs+1YsUKU7NmTePl5WV8fX1Nw4YNzTfffOPQJ3XGnmunpL+RGz2fMcbUrFnT5M+f3z4jX2bXZVhYmHnwwQfTLC8qKirN+/PNN9/Yp8IPDg42w4YNM++++26aZd7qPpNRTNfvN5nd1nLi/ZgzZ46pWbOm8fX1Nd7e3qZkyZKma9eu9pkpf/nlF9OhQwdTsmRJ4+3tbfLmzWtq1Khh5s2b57Cc3bt3m/vvv9/4+PgYSWnW8W+//Wb69+9vSpUqZTw9PY23t7cpX768GTx4sMM6Tu9zZeXKlaZKlSrGy8vLFC5c2AwbNsx89tlnDtt9ZuJctWqVad68uSlcuLDx8PAwgYGBpkWLFg6XLLiV2R2vfV/q169v8uTJYzw9PU1YWJhp27at+eKLLxxep6+vb7rvyYULF4yfn5+ZOHGiQ3tG20VG73F6z5GZ/WfkyJHGxcXFbNiwweGxW7duNW5ububZZ59NN+6MvPfee6Z06dLGw8PDhIeHmzlz5qT7PicmJprXX3/d/l77+fmZsmXLmieeeMIcPHjQ3i91P1q6dKmpUKGC8fDwMMWKFUszu6UxKbNGli1b1ri7uzscOzJa/xm9p1n16aefmgceeMAUKlTIuLm5GX9/f1OnTh2zaNGiNH337NljJJnnn3/+pstN7xibus1eO628Melvt1k5bl8/I+DNzJ8/39SvX98EBQUZDw8PExoaah5//HGH2SUTEhLM0KFDTeHChY2Xl5epVq2aWbFiRZq4svKajEl/38jsdpLRd4AjR46Ynj17msKFCxt3d3dTqFAhExkZ6TCT4htvvGEiIyNNwYIFjYeHhylatKjp1auXOXr0aI6ut9TXt27dOtOlSxeTL18++9Tu1+4bxmRudkdjMt43sit1PaZ3S2/G3oULF5rKlSsbDw8PExwcbJ555pk0lx35999/jZS5mcuzcszPjNw+NmY0u2N6n0uZ/U6R2f3LGGO++OILU7VqVePp6WkkOWwfX331lWnQoIH9tdeqVcusXLnS4fEZHY8uX75snnzySVO5cmWTJ08e4+3tbcqUKWNGjRpln1E1u86ePWseeeQRU6xYMePt7W08PDxM6dKlzfDhwzOctXnq1KkmPDzcvn+OGjXKXLlyxaFPVj6Dr2UzJhsFvwCA/7Snn35aGzZs0N69e3NkFqo7SbFixVSxYsVsXWzZiqZPn67hw4frt99+c5hlFrfmTtpO5s2bpx49emjHjh2ZLpu+E6TOiPrjjz9me3Zq4Gay+xl8Z55ZDAC4oRdeeEF//vmnli1b5uxQkMs2bdqkZ555hgQNuM6mTZvUvn17EjTkqux+BmfpnDQAwJ0hKChIMTExac69s4qrV6/q6tWrN+zj5sYhLDM++ugjZ4dwUzc7X8zFxeWOnbHyVrDebs1rr72Wo8vj/UB6svsZTLkjAMByunfvrvnz59+wD4evO0PqSfU3kpnLD9xtWG/Wc7PS8f/65D24vUjSAACWc/To0XSvdXmtu+ncmTvZlStX0lxC53rZmantTsd6s56bXWQ8dYZDIDNI0gAAAADAQiiMBQAAAAALIUkDAOD/O3r0qGw223/2vJH4+HiNHj36li7Me+LECY0ePVq7d+/Osbiy67333pPNZpOfn59De3JysiZNmqRmzZrpnnvukY+Pj8qVK6fnn39e58+fd+h74MABeXh46IcffriNkQPArSFJAwDgDhEfH68xY8bccpI2ZswYpydpf/75p4YOHZruOVWXLl3S6NGjFRYWpilTpmjNmjXq06eP3n33Xd1///26dOmSvW94eLg6deqkQYMG3c7wAeCWMH8xAMCy4uPj5ePj4+ww4ARPPvmk6tatq4CAAC1dutThPm9vbx05ckQFChSwt9WrV09FixbVY489pmXLlqlz5872+5566ilVr15dW7duVWRk5G17DQCQXYykAQAsoV69eqpYsaK+/PJLRUZGysfHRz179pQkLV68WE2aNFFISIi8vb3tpW1xcXEOy+jevbv8/Px06NAhtWjRQn5+fipSpIiGDBmihIQEh74nTpzQ448/Ln9/f+XNm1ft2rXTyZMn043t008/Ve3ateXj4yN/f381btxY27Ztc+gzevRo2Ww2/fTTT3rssceUN29eBQQEaPDgwUpKStKvv/6qZs2ayd/fX8WKFdPEiROzvI42btyoevXqqUCBAvL29lbRokXVpk0bxcfH6+jRoypUqJAkacyYMbLZbLLZbOrevbsk6dChQ+rRo4dKly4tHx8fFS5cWK1atdKePXvsy9+8ebPuu+8+SVKPHj3sy7h2GvedO3fqoYceUkBAgLy8vFS1alUtWbIky6/lRj744ANt2bJF06dPT/d+V1dXhwQtVY0aNSRJx48fd2i/9957Va5cOc2cOTNH4wSA3EKSBgCwjNjYWHXu3FkdO3bUmjVr1L9/f0nSwYMH1aJFC82ePVtr167VwIEDtWTJErVq1SrNMhITE/XQQw+pYcOG+uSTT9SzZ09NnjxZEyZMsPe5dOmSGjVqpHXr1ik6OlofffSRgoOD1a5duzTLW7hwoR5++GHlyZNHixYt0uzZs3Xu3DnVq1dPX3/9dZr+jz/+uKpUqaJly5apT58+mjx5sgYNGqTWrVvrwQcf1Mcff6wGDRroueee0/LlyzO9bo4ePaoHH3xQHh4emjNnjtauXavx48fL19dXV65cUUhIiNauXStJ6tWrl7Zt26Zt27bpxRdflJSSlBYoUEDjx4/X2rVr9fbbb8vNzU01a9bUr7/+KkmqVq2a5s6dK0l64YUX7Mvo3bu3JGnTpk26//77df78ec2cOVOffPKJIiIi1K5duzTn8SUlJWXqdv0k06dOndLAgQM1fvx43XPPPZleP1JKEitJFSpUSHNfvXr19Nlnn3F9PQD/DQYAAAuIiooyksyGDRtu2O/q1asmMTHRbNmyxUgyP/74o/2+bt26GUlmyZIlDo9p0aKFKVOmjP3vGTNmGEnmk08+cejXp08fI8nMnTvXGGNMcnKyCQ0NNZUqVTLJycn2fv/++68JDAw0kZGR9rZRo0YZSeaNN95wWGZERISRZJYvX25vS0xMNIUKFTKPPvroTdbK/1m6dKmRZHbv3p1hn9OnTxtJZtSoUTddXlJSkrly5YopXbq0GTRokL19x44dDuvgWmXLljVVq1Y1iYmJDu0tW7Y0ISEh9nV05MgRIylTt02bNjksq02bNiYyMtJcvXrVGJPynvr6+t709fzxxx8mKCjIVK9e3eG9SjVr1iwjyezfv/+mywIAZ2MkDQBgGfnz51eDBg3StB8+fFgdO3ZUcHCwXF1d5e7urqioKEnS/v37HfrabLY0I2yVK1fWsWPH7H9v2rRJ/v7+euihhxz6dezY0eHvX3/9VSdOnFCXLl3k4vJ/h0w/Pz+1adNG27dvV3x8vMNjWrZs6fB3uXLlZLPZ1Lx5c3ubm5ubSpUq5RDTzURERMjDw0N9+/bV/Pnzdfjw4Uw/VkoZ2Ro3bpzKly8vDw8Pubm5ycPDQwcPHkyzDtNz6NAh/fLLL+rUqZN9eam3Fi1aKDY21j4iFxoaqh07dmTqdu+999qfY9myZVq5cqVmzZolm82W6dd29uxZtWjRQsYYLV682OG9ShUYGCgpZUISALA6Jg4BAFhGSEhImraLFy+qTp068vLy0tixYxUeHi4fHx8dP35cjz76qMNMfpLk4+MjLy8vhzZPT09dvnzZ/veZM2cUFBSU5rmCg4Md/j5z5kyGcYWGhurq1as6d+6cw+QmAQEBDv08PDzSjcnDw0P//PNPmuVmpGTJkvriiy80ceJEDRgwQHFxcSpRooSeeeYZPfvsszd9/ODBg/X222/rueeeU1RUlPLnzy8XFxf17t07zTpMz19//SVJGjp0qIYOHZpun7///tv+2iIiIjL1ulxdXSWlvM8DBgzQ008/rdDQUPtU+leuXJEknT9/Xu7u7vL19XV4/Llz59S4cWP9+eef2rhxo0qUKJHu86Su/8y8VgBwNpI0AIBlpDd6snHjRp04cUKbN2+2j55JSnM9rKwoUKCAvvvuuzTt108ckjo5RWxsbJq+J06ckIuLi/Lnz5/tOLKqTp06qlOnjpKTk7Vz505NmzZNAwcOVFBQkNq3b3/Dx37wwQfq2rWrxo0b59D+999/K1++fDd97oIFC0qSRowYoUcffTTdPmXKlJGUcv5c8eLFM/GKUkY169Wrp7///lt//fWX3njjDb3xxhtp+uXPn18PP/ywVqxYYW87d+6cGjVqpCNHjmjDhg2qXLlyhs9z9uxZh9cBAFZGkgYAsLTUxM3T09Oh/Z133sn2MuvXr68lS5bo008/dSh5XLhwoUO/MmXKqHDhwlq4cKGGDh1qjyUuLk7Lli2zz/h4u7m6uqpmzZoqW7asYmJi9MMPP6h9+/b2dZTeaJHNZkuzDlevXq0///xTpUqVsrdltIwyZcqodOnS+vHHH9MketdLLXfMjNTELjg4WJs2bUpz//jx47VlyxZ99tlnDglWaoJ2+PBhrV+/XlWrVr3h8xw+fFguLi725wMAKyNJAwBYWmRkpPLnz68nn3xSo0aNkru7u2JiYvTjjz9me5ldu3bV5MmT1bVrV7366qsqXbq01qxZo88//9yhn4uLiyZOnKhOnTqpZcuWeuKJJ5SQkKDXXntN58+f1/jx42/15WXazJkztXHjRj344IMqWrSoLl++rDlz5kiSGjVqJEny9/dXWFiYPvnkEzVs2FABAQEqWLCgihUrppYtW2revHkqW7asKleurO+//16vvfZamhkUS5YsKW9vb8XExKhcuXLy8/NTaGioQkND9c4776h58+Zq2rSpunfvrsKFC+vs2bPav3+/fvjhB3300UeSUsodq1evnqXX5+XlpXr16qVpnzdvnlxdXR3uu3Tpkpo2bapdu3ZpypQpSkpK0vbt2+33FypUSCVLlnRYzvbt2xUREXFbRz4BILuYOAQAYGkFChTQ6tWr5ePjo86dO6tnz57y8/PT4sWLs71MHx8fbdy4UY0aNdLzzz+vtm3b6o8//tCHH36Ypm/Hjh21YsUKnTlzRu3atVOPHj2UJ08ebdq0SQ888MCtvLQsiYiIUFJSkkaNGqXmzZurS5cuOn36tD799FM1adLE3m/27Nny8fHRQw89pPvuu89+jbOpU6eqc+fOio6OVqtWrfTpp59q+fLlaZIZHx8fzZkzR2fOnFGTJk1033336d1335WUMgL53XffKV++fBo4cKAaNWqkfv366YsvvrAnirfDX3/9pR07dsgYo2effVa1a9d2uL3yyisO/S9evKgNGzbYJz0BAKuzGcMFQwAAwJ1r9uzZevbZZ3X8+HFG0gD8JzCSBgAA7lhJSUmaMGGCRowYQYIG4D+Dc9IAAHCy5ORk3aiwxWaz2aeqR9YcP35cnTt31pAhQ5wdCgBkGuWOAAA4WbFixW54YeuoqCht3rz59gUEAHAqRtIAAHCylStXKiEhIcP7/f39b2M0AABnYyQNAAAAACyEiUMAAAAAwEJI0gAAAADAQjgnDbhLeD/ynrNDAHLduY96OzsEINd55eK3N++qT+XYsi7teivHlgXcbUjSAAAAkMJGkRVgBeyJAAAAAGAhjKQBAAAghc3m7AgAiCQNAAAAqSh3BCyBPREAAAAALISRNAAAAKSg3BGwBJI0AAAApKDcEbAE9kQAAAAAsBBG0gAAAJCCckfAEkjSAAAAkIJyR8AS2BMBAAAAwEIYSQMAAEAKyh0BSyBJAwAAQArKHQFLYE8EAAAAAAthJA0AAAApKHcELIEkDQAAACkodwQsgT0RAAAAACyEkTQAAACkoNwRsASSNAAAAKSg3BGwBPZEAAAAALAQRtIAAACQgpE0wBJI0gAAAJDChXPSACvg5xIAAAAAsBBG0gAAAJCCckfAEkjSAAAAkIIp+AFL4OcSAAAAALAQRtIAAACQgnJHwBJI0gAAAJCCckfAEvi5BAAAAAAshJE0AAAApKDcEbAEkjQAAACkoNwRsAR+LgEAAAAAC2EkDQAAACkodwQsgSQNAAAAKSh3BCyBn0sAAAAAwEIYSQMAAEAKyh0BSyBJAwAAQArKHQFL4OcSAAAAALAQRtIAAACQgnJHwBJI0gAAAJCCJA2wBPZEAAAAALAQRtIAAACQgolDAEsgSQMAAEAKyh0BS2BPBAAAgFNFR0frvvvuk7+/vwIDA9W6dWv9+uuvDn26d+8um83mcKtVq5aTIgZyF0kaAAAAUthsOXfLgi1btmjAgAHavn271q9fr6SkJDVp0kRxcXEO/Zo1a6bY2Fj7bc2aNTn56gHLoNwRAAAAKZxU7rh27VqHv+fOnavAwEB9//33qlu3rr3d09NTwcHBtzs84LZjJA0AAAA5LiEhQf/884/DLSEhIVOPvXDhgiQpICDAoX3z5s0KDAxUeHi4+vTpo1OnTuV43IAVkKQBAAAgRQ6WO0ZHRytv3rwOt+jo6JuGYIzR4MGD9cADD6hixYr29ubNmysmJkYbN27UG2+8oR07dqhBgwaZTvyA/xKbMcY4OwgAuc/7kfecHQKQ68591NvZIQC5zisXT1bxaTMnx5Z1bmGnNAmUp6enPD09b/i4AQMGaPXq1fr66691zz33ZNgvNjZWYWFh+vDDD/Xoo4/mSMyAVXBOGgAAAHJcZhKy6z399NP69NNP9eWXX94wQZOkkJAQhYWF6eDBg7cSJmBJJGkAAACQJNmcdDFrY4yefvppffzxx9q8ebOKFy9+08ecOXNGx48fV0hIyG2IELi9OCcNAAAAKWw5eMuCAQMG6IMPPtDChQvl7++vkydP6uTJk7p06ZIk6eLFixo6dKi2bdumo0ePavPmzWrVqpUKFiyoRx555JZfNmA1jKQBAADAqWbMmCFJqlevnkP73Llz1b17d7m6umrPnj1asGCBzp8/r5CQENWvX1+LFy+Wv7+/EyIGchdJGgAAACQ5t9zxRry9vfX555/fpmgA5yNJAwAAgCTnJWkAHHFOGgAAAABYCCNpAAAAkMRIGmAVJGkAAACQRJIGWAXljgAAAABgIYykAQAAIAUDaYAlkKQBAABAEuWOgFVQ7ggAAAAAFsJIGgAAACQxkgZYBUkaAAAAJJGkAVZBuSMAAAAAWAgjaQAAAJDESBpgFSRpAAAASEGOBlgC5Y6ARX311Vfq3LmzateurT///FOS9P777+vrr792cmQAAADITSRpgAUtW7ZMTZs2lbe3t3bt2qWEhARJ0r///qtx48Y5OToAwJ3KZrPl2A1A9pGkARY0duxYzZw5U7NmzZK7u7u9PTIyUj/88IMTIwMA3MlI0gBrIEkDLOjXX39V3bp107TnyZNH58+fv/0BAQAA4LYhSQMsKCQkRIcOHUrT/vXXX6tEiRJOiAgAcDdgJA2wBpI0wIKeeOIJPfvss/r2229ls9l04sQJxcTEaOjQoerfv7+zwwMA3KlsOXgDkG1MwQ9Y0PDhw3XhwgXVr19fly9fVt26deXp6amhQ4fqqaeecnZ4AAAAyEUkaYBFvfrqqxo5cqT27dunq1evqnz58vLz83N2WACAOxhlioA1kKQBFjR//ny1bdtWvr6+ql69urPDAQDcJUjSAGvgnDTAgoYOHarAwEC1b99eq1atUlJSkrNDAgAAwG1CkgZYUGxsrBYvXixXV1e1b99eISEh6t+/v7Zu3ers0AAAdzBmdwSsgSQNsCA3Nze1bNlSMTExOnXqlKZMmaJjx46pfv36KlmypLPDAwDcoUjSAGvgnDTA4nx8fNS0aVOdO3dOx44d0/79+50dEgAAAHIRI2mARcXHxysmJkYtWrRQaGioJk+erNatW+vnn392dmgAgDsV10kDLIGRNMCCOnTooJUrV8rHx0ePPfaYNm/erMjISGeHBQC4w1GmCFgDSRpgQTabTYsXL1bTpk3l5sZuCgAAcDfh2x9gQQsXLnR2CACAuxAjaYA1kKQBFvHmm2+qb9++8vLy0ptvvnnDvs8888xtigoAcDchSQOsgSQNsIjJkyerU6dO8vLy0uTJkzPsZ7PZSNIAAADuYCRpgEUcOXIk3f8DAHDbMJAGWAJT8AMW9PLLLys+Pj5N+6VLl/Tyyy87ISIAwN2Ai1kD1kCSBljQmDFjdPHixTTt8fHxGjNmjBMiAgAAwO1CuSNgQcaYdH+F/PHHHxUQEOCEiJCeoY9WUetaxRR+T15dupKsb3/5SyMX7NDBExfsfd59uq66NAh3eNx3v55S1POf3u5wgVwxe9Y7enPKJHXq3FXDR4x0dji4RYyAAdZAkgZYSP78+e1lIuHh4Q4Hy+TkZF28eFFPPvmkEyPEtepUCNbMz/bp+0On5ebqotGdqmvVqGaq+swyxSck2ft9/sNxPTHtS/vfV5KuOiNcIMf9vOcnLf1oscLDyzg7FOQQkjTAGkjSAAuZMmWKjDHq2bOnxowZo7x589rv8/DwULFixVS7dm0nRohrPfzK5w5/PzHtSx2f31lVSxbUN/tO2tuvJCbrr/OXbnd4QK6Kj4vTiOeGadSYsZr1zgxnhwMAdxSSNMBCunXrJkkqXry4IiMj5e7u7uSIkBV5fDwkSecuJji016kYomPzOulC3BV9tTdWo2N26vSFy84IEcgx48a+rLp1o1SrdiRJ2h2EkTTAGkjSAAuKioqy///SpUtKTEx0uD9Pnjy3OyRkwoQeNfXNvpPa9/s5e9u6H/7Q8q1H9PvpiyoW6K+XOt6rz15uocghKyh7xH/WZ2tWa//+fVq4eKmzQ0FOI0cDLIEkDbCg+Ph4DR8+XEuWLNGZM2fS3J+cnHzDxyckJCghwXE0xyQnyubKyFxumdw3UpWKBajh/1Y6tC/95rD9//t+P6cffjutX99pr+bVi+qT7Udvc5TArTsZG6uJ41/VzHfnyNPT09nhAMAdiSn4AQsaNmyYNm7cqOnTp8vT01PvvfeexowZo9DQUC1YsOCmj4+OjlbevHkdbkkHPrsNkd+dJvWurZb3FVXTF1frzzNpr293rZPnLun30xdVKoTRUPw37du3V2fPnFGHxx9VtcrlVa1yee3c8Z0WxryvapXL3/RHJFgb10kDrIGRNMCCVq5cqQULFqhevXrq2bOn6tSpo1KlSiksLEwxMTHq1KnTDR8/YsQIDR482KEtsHNMboZ815rcp7YeqllMTV5crWOn0l7b7noB/p66p6CvYs/dOJkDrKpmrVpausJxxHjUyBEqVqKEevTqI1dXVydFhpxAcgVYA0kaYEFnz55V8eLFJaWcf3b27FlJ0gMPPKB+/frd9PGenp5pypAodcx5U/pGql3dknoser0uXkpUUD5vSdKF+Cu6fCVZvl5ueqFdNa3YflSxZ+MVFuivlztX15l/EvTp9mNOjh7IHl9fP5Uu7XjtP28fH+XLmy9NOwAge0jSAAsqUaKEjh49qrCwMJUvX15LlixRjRo1tHLlSuXLl8/Z4eH/e6J5eUnS+rEtHdr7vLlFH2w6qOSrRhXCAtSxfmnl8/HQyXPx2vJzrLq8vlEXLyemt0gAcCoG0gBrsBljjLODAOBo8uTJcnV11TPPPKNNmzbpwQcfVHJyspKSkjRp0iQ9++yzWV6m9yPv5UKkgLWc+6i3s0MAcp1XLv7EXnrY2hxb1sHXmuXYsoC7DSNpgAUNGjTI/v/69evrl19+0c6dO1WyZElVqVLFiZEBAAAgt5GkAf8BRYsWVdGiRZ0dBgDgDke5I2ANJGmABb355pvptttsNnl5ealUqVKqW7cus6gBAHIUszsC1kCSBljQ5MmTdfr0acXHxyt//vwyxuj8+fPy8fGRn5+fTp06pRIlSmjTpk0qUqSIs8MFAABADuJi1oAFjRs3Tvfdd58OHjyoM2fO6OzZszpw4IBq1qypqVOn6vfff1dwcLDDuWsAANwqmy3nbgCyj5E0wIJeeOEFLVu2TCVLlrS3lSpVSq+//rratGmjw4cPa+LEiWrTpo0TowQA3GlcXMiuACtgJA2woNjYWCUlJaVpT0pK0smTJyVJoaGh+vfff293aAAAAMhlJGmABdWvX19PPPGEdu3aZW/btWuX+vXrpwYNGkiS9uzZo+LFizsrRADAHYhyR8AaSNIAC5o9e7YCAgJ07733ytPTU56enqpevboCAgI0e/ZsSZKfn5/eeOMNJ0cKAACAnMY5aYAFBQcHa/369frll1904MABGWNUtmxZlSlTxt6nfv36TowQAHAnYgp+wBpI0gALK1GihGw2m0qWLCk3N3ZXAEDuIkcDrIFyR8CC4uPj1atXL/n4+KhChQr6/fffJUnPPPOMxo8f7+ToAAAAkJtI0gALGjFihH788Udt3rxZXl5e9vZGjRpp8eLFTowMAHAns9lsOXYDkH3UTwEWtGLFCi1evFi1atVyONCVL19ev/32mxMjAwDcyUiuAGtgJA2woNOnTyswMDBNe1xcHAdQAACAOxxJGmBB9913n1avXm3/OzUxmzVrlmrXru2ssAAAdziukwZYA+WOgAVFR0erWbNm2rdvn5KSkjR16lTt3btX27Zt05YtW5wdHgDgDkW1BmANjKQBFhQZGalvvvlG8fHxKlmypNatW6egoCBt27ZN9957r7PDAwAAQC5iJA2wqEqVKmn+/PnODgMAcBdhIA2wBpI0wEJcXFxuWmpis9mUlJR0myICANxNKHcErIEkDbCQjz/+OMP7tm7dqmnTpskYcxsjAgAAwO1GkgZYyMMPP5ym7ZdfftGIESO0cuVKderUSa+88ooTIgMA3A0YSAOsgYlDAIs6ceKE+vTpo8qVKyspKUm7d+/W/PnzVbRoUWeHBgC4Q9lsthy7Acg+kjTAYi5cuKDnnntOpUqV0t69e7VhwwatXLlSFStWdHZoAADkiujoaN13333y9/dXYGCgWrdurV9//dWhjzFGo0ePVmhoqLy9vVWvXj3t3bvXSREDuYskDbCQiRMnqkSJElq1apUWLVqkrVu3qk6dOs4OCwBwl3DWxay3bNmiAQMGaPv27Vq/fr2SkpLUpEkTxcXF2ftMnDhRkyZN0ltvvaUdO3YoODhYjRs31r///pvDawFwPpthFgLAMlxcXOTt7a1GjRrJ1dU1w37Lly/P8rK9H3nvVkID/hPOfdTb2SEAuc4rF2cUqBm9JceW9e2IqGw/9vTp0woMDNSWLVtUt25dGWMUGhqqgQMH6rnnnpMkJSQkKCgoSBMmTNATTzyRU2EDlsDEIYCFdO3alTp+AMAdISEhQQkJCQ5tnp6e8vT0vOljL1y4IEkKCAiQJB05ckQnT55UkyZNHJYVFRWlrVu3kqThjkOSBljIvHnznB0CAOAulpO/E0ZHR2vMmDEObaNGjdLo0aNv+DhjjAYPHqwHHnjAfj72yZMnJUlBQUEOfYOCgnTs2LGcCxqwCJI0AAAASMrZi1mPGDFCgwcPdmjLzCjaU089pZ9++klff/31TeMzxlCBgjsSSRoAAAByXGZLG6/19NNP69NPP9WXX36pe+65x94eHBwsKWVELSQkxN5+6tSpNKNrwJ2A2R0BAAAgyXmzOxpj9NRTT2n58uXauHGjihcv7nB/8eLFFRwcrPXr19vbrly5oi1btigyMjInXjpgKYykAQAAQFLOljtmxYABA7Rw4UJ98skn8vf3t5+DljdvXnl7e8tms2ngwIEaN26cSpcurdKlS2vcuHHy8fFRx44dnRIzkJtI0gAAAOBUM2bMkCTVq1fPoX3u3Lnq3r27JGn48OG6dOmS+vfvr3PnzqlmzZpat26d/P39b3O0QO4jSQMAAICknJ3dMSsyc9lem82m0aNH33R2SOBOQJIGAAAASc4rdwTgiIlDAAAAAMBCGEkDAACAJEbSAKsgSQMAAIAk552TBsAR5Y4AAAAAYCGMpAEAAEAS5Y6AVZCkAQAAQBLljoBVUO4IAAAAABbCSBoAAAAkUe4IWAVJGgAAACRR7ghYBeWOAAAAAGAhjKQBAABAkuTCUBpgCSRpAAAAkES5I2AVlDsCAAAAgIUwkgYAAABJzO4IWAVJGgAAACRJLuRogCVQ7ggAAAAAFsJIGgAAACRR7ghYBUkaAAAAJDG7I2AVlDsCAAAAgIUwkgYAAABJkk0MpQFWQJIGAAAASczuCFgF5Y4AAAAAYCGMpAEAAEASszsCVkGSBgAAAEnM7ghYBeWOAAAAAGAhjKQBAABAkuTCUBpgCSRpAAAAkES5I2AVlDsCAAAAgIUwkgYAAABJzO4IWAVJGgAAACRR7ghYBeWOAAAAAGAhjKQBAABAErM7AlZBkgYAAABJEikaYA2UOwIAAACAhTCSBgAAAEnM7ghYBUkaAAAAJEku5GiAJVDuCAAAAAAWwkgaAAAAJFHuCFgFSRoAAAAkcTFrwCoodwQAAAAAC2EkDQAAAJIodwSsgiQNAAAAkpjdEbAKyh0BAAAAwEJI0oAc8P777+v+++9XaGiojh07JkmaMmWKPvnkEydHBgBA5tlsthy7Acg+kjTgFs2YMUODBw9WixYtdP78eSUnJ0uS8uXLpylTpjg3OAAAssCWgzcA2UeSBtyiadOmadasWRo5cqRcXV3t7dWrV9eePXucGBkAAAD+i5g4BLhFR44cUdWqVdO0e3p6Ki4uzgkRAQCQPS6UKQKWwEgacIuKFy+u3bt3p2n/7LPPVL58+dsfEAAA2WSz5dwNQPYxkgbcomHDhmnAgAG6fPmyjDH67rvvtGjRIkVHR+u9995zdngAAAD4jyFJA25Rjx49lJSUpOHDhys+Pl4dO3ZU4cKFNXXqVLVv397Z4QEAkGnMyghYA0kakAP69OmjPn366O+//9bVq1cVGBjo7JAAAMgycjTAGkjSgBxUsGBBZ4cAAACA/ziSNOAWFS9e/IblIYcPH76N0QAAkH3M7ghYA0kacIsGDhzo8HdiYqJ27dqltWvXatiwYc4JCgCAbCBHA6yBJA24Rc8++2y67W+//bZ27tx5m6MBAADAfx3XSQNySfPmzbVs2TJnhwEAQKbZbLYcuwHIPkbSgFyydOlSBQQEODsMu3Mf9XZ2CECuy3/fU84OAch1l3a9lWvL5td7wBpI0oBbVLVqVYdfDI0xOnnypE6fPq3p06c7MTIAAAD8F5GkAbeodevWDn+7uLioUKFCqlevnsqWLeucoAAAyAbKFAFrIEkDbkFSUpKKFSumpk2bKjg42NnhAABwS1zI0QBLoPQYuAVubm7q16+fEhISnB0KAAAA7hAkacAtqlmzpnbt2uXsMAAAuGUutpy7Acg+yh2BW9S/f38NGTJEf/zxh+699175+vo63F+5cmUnRQYAQNZwThpgDSRpQDb17NlTU6ZMUbt27SRJzzzzjP0+m80mY4xsNpuSk5OdFSIAAAD+g0jSgGyaP3++xo8fryNHjjg7FAAAcgRlioA1kKQB2WSMkSSFhYU5ORIAAHIG1Y6ANTBxCHALqN0HAABATmMkDbgF4eHhN03Uzp49e5uiAQDg1rjw4yNgCSRpwC0YM2aM8ubN6+wwAADIEc4qsfryyy/12muv6fvvv1dsbKw+/vhjtW7d2n5/9+7dNX/+fIfH1KxZU9u3b7/NkQK3B0kacAvat2+vwMBAZ4cBAMB/WlxcnKpUqaIePXqoTZs26fZp1qyZ5s6da//bw8PjdoUH3HYkaUA2cT4aAOBO46xDW/PmzdW8efMb9vH09FRwcPBtighwLpI0IJtSZ3cEAOBOkZPnpCUkJCghIcGhzdPTU56entla3ubNmxUYGKh8+fIpKipKr776KtUsuGMxuyOQTVevXuXgAABABqKjo5U3b16HW3R0dLaW1bx5c8XExGjjxo164403tGPHDjVo0CBNEgjcKRhJAwAAgKScLXccMWKEBg8e7NCW3VG0du3a2f9fsWJFVa9eXWFhYVq9erUeffTRW4oTsCKSNAAAAEiSXHIwSbuV0sabCQkJUVhYmA4ePJgrywecjXJHAAAA/KecOXNGx48fV0hIiLNDAXIFI2kAAACQ5LyLWV+8eFGHDh2y/33kyBHt3r1bAQEBCggI0OjRo9WmTRuFhITo6NGj+t///qeCBQvqkUcecUq8QG4jSQMAAIAk503Bv3PnTtWvX9/+d+q5bN26ddOMGTO0Z88eLViwQOfPn1dISIjq16+vxYsXy9/f3zkBA7mMJA0AAABOVa9evRte2ubzzz+/jdEAzkeSBgAAAEk5O3EIgOwjSQMAAIAkySayNMAKmN0RAAAAACyEkTQAAABIotwRsAqSNAAAAEgiSQOsgnJHAAAAALAQRtIAAAAgSbI560JpAByQpAEAAEAS5Y6AVVDuCAAAAAAWwkgaAAAAJElUOwLWQJIGAAAASZILWRpgCZQ7AgAAAICFMJIGAAAASUwcAlgFSRoAAAAkcU4aYBWUOwIAAACAhTCSBgAAAEmSixhKA6yAJA0AAACSKHcErIJyRwAAAACwEEbSAAAAIInZHQGrIEkDAACAJC5mDVgF5Y4AAAAAYCGMpAEAAEASE4cAVkGSBgAAAEmUOwJWQbkjAAAAAFgII2kAAACQRLkjYBUkaQAAAJBEiRVgFeyLAAAAAGAhjKQBAABAkmSj3hGwBJI0AAAASJJI0QBroNwRAAAAACyEkTQAAABI4jppgFWQpAEAAEAS5Y6AVVDuCAAAAAAWwkgaAAAAJHExa8AqSNIAAAAgiSn4Aaug3BEAAAAALISRNAAAAEji13vAKkjSAAAAIIlyR8Aq+MEEAAAAACyEkTQAAABI4jppgFWQpAEAAEAS5Y6AVVDuCAAAAAAWwkgaAAAAJPHrPWAVJGkAAACQRLkjYBX8YAIAAAAAFsJIGgAAACQxuyNgFSRpAAAAkCRR7QhYA+WOAAAAAGAhjKQBAABAkuRCwSNgCSRpAAAAkES5I2AVlDsCFvX+++/r/vvvV2hoqI4dOyZJmjJlij755BMnRwYAAIDcRJIGWNCMGTM0ePBgtWjRQufPn1dycrIkKV++fJoyZYpzgwMA3LFsOfgPQPaRpAEWNG3aNM2aNUsjR46Uq6urvb169eras2ePEyMDANzJbLacuwHIPpI0wIKOHDmiqlWrpmn39PRUXFycEyICAADA7UKSBlhQ8eLFtXv37jTtn332mcqXL3/7AwIA3BVcZMuxG4DsY3ZHwIKGDRumAQMG6PLlyzLG6LvvvtOiRYsUHR2t9957z9nhAQDuUJQpAtZAkgZYUI8ePZSUlKThw4crPj5eHTt2VOHChTV16lS1b9/e2eEBAAAgF5GkARbVp08f9enTR3///beuXr2qwMBAZ4cEALjDMZIGWAPnpAEWNGbMGP3222+SpIIFC5KgAQBuC6bgB6yBJA2woGXLlik8PFy1atXSW2+9pdOnTzs7JAAAANwmJGmABf3000/66aef1KBBA02aNEmFCxdWixYttHDhQsXHxzs7PADAHcrFlnM3ANlHkgZYVIUKFTRu3DgdPnxYmzZtUvHixTVw4EAFBwc7OzQAwB2KckfAGkjSgP8AX19feXt7y8PDQ4mJic4OBwAAALmIJA2wqCNHjujVV19V+fLlVb16df3www8aPXq0Tp486ezQAAB3KJst524Aso8p+AELql27tr777jtVqlRJPXr0sF8nDQCA3ESZImANJGmABdWvX1/vvfeeKlSo4OxQAAAAcJuRpAEWNG7cOGeHAAC4CzErI2ANJGmARQwePFivvPKKfH19NXjw4Bv2nTRp0m2KCgBwN6HcEbAGkjTAInbt2mWfuXHXrl1OjgY5Yfasd/TmlEnq1Lmrho8Y6exwgGwZ2rOJWjeoovBiQbqUkKhvfzyskVM/0cFjp+x9fL09NPaZh9WqfmUF5PXVsRNnNf3DzZr10ddOjBwA/rtI0gCL2LRpU7r/x3/Tz3t+0tKPFis8vIyzQwFuSZ1qpTRz8Zf6fu8xubm5avSAVlo14ylVfXSs4i9fkSRNHNpGUdXD1WPkAh07cUaNapfT1BGPK/b0Ba3avMfJrwBZ4axZGb/88ku99tpr+v777xUbG6uPP/5YrVu3tt9vjNGYMWP07rvv6ty5c6pZs6befvttzt3GHYsp+AEL6tmzp/7999807XFxcerZs6cTIkJWxMfFacRzwzRqzFjlyZvX2eEAt+Thp6brg5Xfav/hk9pz4E89MfoDFQ0JUNXyRex9alYurg9Wfauvvj+o32PPas7yb/TTgT9VrXxRJ0aO7LDl4C0r4uLiVKVKFb311lvp3j9x4kRNmjRJb731lnbs2KHg4GA1btw43WMlcCcgSQMsaP78+bp06VKa9kuXLmnBggVOiAhZMW7sy6pbN0q1akc6OxQgx+Xx85IknbsQb2/buvuwWkZVUmihlB8l6lYvrdJhgfpi636nxIj/nubNm2vs2LF69NFH09xnjNGUKVM0cuRIPfroo6pYsaLmz5+v+Ph4LVy40AnRArmPckfAQv755x8ZY2SM0b///isvLy/7fcnJyVqzZo0CAwNvupyEhAQlJCQ4tBlXT3l6euZ4zHD02ZrV2r9/nxYuXursUIBcMWFIG33zwyHt+y3W3jZkwkea/lJH/bbuVSUmJuuquap+Ly/U1t2HnRgpssMlB+sd0zsWeXpm/Vh05MgRnTx5Uk2aNHFYTlRUlLZu3aonnngiR+IFrISRNMBC8uXLp4CAANlsNoWHhyt//vz2W8GCBdWzZ08NGDDgpsuJjo5W3rx5HW6vTYi+Da/g7nYyNlYTx7+qceNfIyHGHWny84+rUulQdRsxz6F9QId6qlGpmNo8O1ORnSbo+Ukfa+qIdqpfk3My/2tystwxvWNRdHTWj0UnT56UJAUFBTm0BwUF2e8D7jSMpAEWsmnTJhlj1KBBAy1btkwBAQH2+zw8PBQWFqbQ0NCbLmfEiBFppvE3riQNuW3fvr06e+aMOjz+f+U6ycnJ+n7nDn24KEY7du2Rq6urEyMEsm/Sc4+pZVQlNeo1RX+eOm9v9/J015inW6nd4Fla+/VeSdLPB0+ocpl7NLBLQ2369lcnRQxnS+9YdCs/YNmuG+UzxqRpA+4UJGmAhURFRUlKKe0oWrRotg8+6ZWTXE665fBwEzVr1dLSFSsd2kaNHKFiJUqoR68+JGj4z5r83GN6qEEVNekzVcdOnHG4z93NVR7ubrpqjEN7cvJVuXBl5P+eHHzLslPamJ7g4GBJKSNqISEh9vZTp06lGV0D7hQkaYBF/PTTT6pYsaJcXFx04cIF7dmT8bTVlStXvo2RIbN8ff1UunS4Q5u3j4/y5c2Xph34r5gy4nG1a15djw16VxfjLiuogL8k6cLFy7qckKh/4y7ry50HNW5ga126nKjfY8+qzr2l1KllDT03abmTo0dWWfFi1sWLF1dwcLDWr1+vqlWrSpKuXLmiLVu2aMKECU6ODsgdJGmARUREROjkyZMKDAxURESEbDabzHW/TEsp5R7JyclOiBDA3eiJx+tKkta/N9Chvc9L7+uDld9Kkro+P0cvP/2w5o3rpvx5fPR77FmNfnsVF7NGpl28eFGHDh2y/33kyBHt3r1bAQEBKlq0qAYOHKhx48apdOnSKl26tMaNGycfHx917NjRiVEDucdm0vsWCOC2O3bsmL3E8dixYzfsGxYWluXlU+6Iu0H++55ydghArru0K/1rieWE7w5fyLFl1SiR+etEbt68WfXr10/T3q1bN82bN89+Met33nnH4WLWFStWzLF4ASshSQPuEiRpuBuQpOFukJtJ2o4cTNLuy0KSBsARU/ADFjR//nytXr3a/vfw4cOVL18+RUZG3nSUDQAAAP9tJGmABY0bN07e3t6SpG3btumtt97SxIkTVbBgQQ0aNMjJ0QEA7lg5eaE0ANnGxCGABR0/flylSpWSJK1YsUJt27ZV3759df/996tevXrODQ4AcMey4uyOwN2IkTTAgvz8/HTmTMq1iNatW6dGjRpJkry8vHTp0iVnhgYAAIBcxkgaYEGNGzdW7969VbVqVR04cEAPPvigJGnv3r0qVqyYc4MDANyxbAykAZbASBpgQW+//bZq166t06dPa9myZSpQoIAk6fvvv1eHDh2cHB0AAAByE1PwA3cJpuDH3YAp+HE3yM0p+H84+k+OLatasTw5tizgbkO5I2BR58+f1+zZs7V//37ZbDaVK1dOvXr1Ut68XHcGAJBLKHcELIFyR8CCdu7cqZIlS2ry5Mk6e/as/v77b02ePFklS5bUDz/84OzwAAAAkIsYSQMsaNCgQXrooYc0a9Ysubml7KZJSUnq3bu3Bg4cqC+//NLJEQIA7kRMwQ9YA0kaYEE7d+50SNAkyc3NTcOHD1f16tWdGBkA4E7G7I6ANVDuCFhQnjx59Pvvv6dpP378uPz9/Z0QEQAAAG4XkjTAgtq1a6devXpp8eLFOn78uP744w99+OGH6t27N1PwAwByjS0HbwCyj3JHwIJef/11ubi4qGvXrkpKSpk7393dXf369dP48eOdHB0A4I5FdgVYAkkaYCHx8fEaNmyYVqxYocTERLVu3VpPPfWU8ubNq1KlSsnHx8fZIQIAACCXkaQBFjJq1CjNmzdPnTp1kre3txYuXKirV6/qo48+cnZoAIC7ALM7AtZAkgZYyPLlyzV79my1b99ektSpUyfdf//9Sk5Olqurq5OjAwDc6ZjdEbAGJg4BLOT48eOqU6eO/e8aNWrIzc1NJ06ccGJUAAAAuJ0YSQMsJDk5WR4eHg5tbm5u9slDAADITQykAdZAkgZYiDFG3bt3l6enp73t8uXLevLJJ+Xr62tvW758uTPCAwDc6cjSAEsgSQMspFu3bmnaOnfu7IRIAAAA4CwkaYCFzJ0719khAADuYszuCFgDSRoAAAAkMbsjYBXM7ggAAAAAFsJIGgAAACQxbwhgFSRpAAAASEGWBlgC5Y4AAAAAYCGMpAEAAEASszsCVkGSBgAAAEnM7ghYBeWOAAAAAGAhjKQBAABAEvOGAFZBkgYAAIAUZGmAJVDuCAAAAAAWwkgaAAAAJDG7I2AVJGkAAACQxOyOgFVQ7ggAAAAAFsJIGgAAACQxbwhgFSRpAAAASEGWBlgC5Y4AAAAAYCGMpAEAAEASszsCVkGSBgAAAEnM7ghYBeWOAAAAAGAhjKQBAABAEvOGAFZBkgYAAIAUZGmAJVDuCAAAAAAWwkgaAAAAJDG7I2AVJGkAAACQxOyOgFVQ7ggAAAAAFsJIGgAAACQxbwhgFSRpAAAAkES5I2AVlDsCAAAAgIUwkgYAAID/j6E0wApI0gAAACCJckfAKih3BAAAAAALYSQNAAAAkih2BKyCJA0AAACSKHcErIJyRwAAAACwEEbSAAAAIEmyUfAIWAJJGgAAAFKQowGWQLkjAAAAAFgII2kAAACQxEAaYBUkaQAAAJDE7I6AVVDuCAAAAAAWwkgaAAAAJDG7I2AVJGkAAABIQY4GWALljgAAAABgIYykAQAAQBIDaYBVkKQBAABAErM7AlZBuSMAAAAAWAhJGgAAACSlzO6YU/+yYvTo0bLZbA634ODgXHqVgPVR7ggAAABJzi13rFChgr744gv7366urs4LBnAykjQAAAA4nZubG6NnwP9HuSMAAACc7uDBgwoNDVXx4sXVvn17HT582NkhAU7DSBoAAAAk5Wy5Y0JCghISEhzaPD095enpmaZvzZo1tWDBAoWHh+uvv/7S2LFjFRkZqb1796pAgQI5FxTwH8FIGgAAAHJcdHS08ubN63CLjo5Ot2/z5s3Vpk0bVapUSY0aNdLq1aslSfPnz7+dIQOWwUgaAAAAJCnLszLeyIgRIzR48GCHtvRG0dLj6+urSpUq6eDBgzkWD/BfQpIGAAAASTlb7phRaWNmJCQkaP/+/apTp07OBQT8h1DuCAAAAKcaOnSotmzZoiNHjujbb79V27Zt9c8//6hbt27ODg1wCkbSAAAAIEk5WOyYNX/88Yc6dOigv//+W4UKFVKtWrW0fft2hYWFOSkiwLlI0gAAAJDCSVnahx9+6JwnBiyKckcAAAAAsBBG0gAAACApZ2d3BJB9JGkAAACQlLOzOwLIPsodAQAAAMBCGEkDAACAJOfN7gjAEUkaAAAAUpClAZZAuSMAAAAAWAgjaQAAAJDE7I6AVZCkAQAAQBKzOwJWQbkjAAAAAFiIzRhjnB0EANxpEhISFB0drREjRsjT09PZ4QC5gu0cAHIHSRoA5IJ//vlHefPm1YULF5QnTx5nhwPkCrZzAMgdlDsCAAAAgIWQpAEAAACAhZCkAQAAAICFkKQBQC7w9PTUqFGjmEwBdzS2cwDIHUwcAgAAAAAWwkgaAAAAAFgISRoAAAAAWAhJGgAAAABYCEkaAFhAsWLFNGXKFGeHAdzU0aNHZbPZtHv37hv2q1evngYOHHhbYgKAOw1JGoA7Xvfu3WWz2TR+/HiH9hUrVshms93WWObNm6d8+fKlad+xY4f69u17W2PBnS11u7fZbHJ3d1eJEiU0dOhQxcXF3dJyixQpotjYWFWsWFGStHnzZtlsNp0/f96h3/Lly/XKK6/c0nMBwN2KJA3AXcHLy0sTJkzQuXPnnB1KugoVKiQfHx9nh4E7TLNmzRQbG6vDhw9r7Nixmj59uoYOHXpLy3R1dVVwcLDc3Nxu2C8gIED+/v639FwAcLciSQNwV2jUqJGCg4MVHR2dYZ+tW7eqbt268vb2VpEiRfTMM884jDrExsbqwQcflLe3t4oXL66FCxemKVOcNGmSKlWqJF9fXxUpUkT9+/fXxYsXJaWMOPTo0UMXLlywj3CMHj1akmO5Y4cOHdS+fXuH2BITE1WwYEHNnTtXkmSM0cSJE1WiRAl5e3urSpUqWrp0aQ6sKdxJPD09FRwcrCJFiqhjx47q1KmTVqxYoYSEBD3zzDMKDAyUl5eXHnjgAe3YscP+uHPnzqlTp04qVKiQvL29Vbp0afu2d22549GjR1W/fn1JUv78+WWz2dS9e3dJjuWOI0aMUK1atdLEV7lyZY0aNcr+99y5c1WuXDl5eXmpbNmymj59ei6tGQCwNpI0AHcFV1dXjRs3TtOmTdMff/yR5v49e/aoadOmevTRR/XTTz9p8eLF+vrrr/XUU0/Z+3Tt2lUnTpzQ5s2btWzZMr377rs6deqUw3JcXFz05ptv6ueff9b8+fO1ceNGDR8+XJIUGRmpKVOmKE+ePIqNjVVsbGy6oxqdOnXSp59+ak/uJOnzzz9XXFyc2rRpI0l64YUXNHfuXM2YMUN79+7VoEGD1LlzZ23ZsiVH1hfuTN7e3kpMTNTw4cO1bNkyzZ8/Xz/88INKlSqlpk2b6uzZs5KkF198Ufv27dNnn32m/fv3a8aMGSpYsGCa5RUpUkTLli2TJP3666+KjY3V1KlT0/Tr1KmTvv32W/3222/2tr1792rPnj3q1KmTJGnWrFkaOXKkXn31Ve3fv1/jxo3Tiy++qPnz5+fGqgAAazMAcIfr1q2befjhh40xxtSqVcv07NnTGGPMxx9/bFI/Brt06WL69u3r8LivvvrKuLi4mEuXLpn9+/cbSWbHjh32+w8ePGgkmcmTJ2f43EuWLDEFChSw/z137lyTN2/eNP3CwsLsy7ly5YopWLCgWbBggf3+Dh06mMcee8wYY8zFixeNl5eX2bp1q8MyevXqZTp06HDjlYG7xrXbvTHGfPvtt6ZAgQKmbdu2xt3d3cTExNjvu3LligkNDTUTJ040xhjTqlUr06NHj3SXe+TIESPJ7Nq1yxhjzKZNm4wkc+7cOYd+UVFR5tlnn7X/XblyZfPyyy/b/x4xYoS577777H8XKVLELFy40GEZr7zyiqldu3ZWXjYA3BEYSQNwV5kwYYLmz5+vffv2ObR///33mjdvnvz8/Oy3pk2b6urVqzpy5Ih+/fVXubm5qVq1avbHlCpVSvnz53dYzqZNm9S4cWMVLlxY/v7+6tq1q86cOZOlyRrc3d312GOPKSYmRpIUFxenTz75xD7isG/fPl2+fFmNGzd2iHfBggUOIxXAqlWr5OfnJy8vL9WuXVt169bV008/rcTERN1///32fu7u7qpRo4b2798vSerXr58+/PBDRUREaPjw4dq6destx9KpUyf7Nm2M0aJFi+zb9OnTp3X8+HH16tXLYZseO3Ys2zSAu9KNz/oFgDtM3bp11bRpU/3vf/+znzsjSVevXtUTTzyhZ555Js1jihYtql9//TXd5Rlj7P8/duyYWrRooSeffFKvvPKKAgIC9PXXX6tXr15KTEzMUpydOnVSVFSUTp06pfXr18vLy0vNmze3xypJq1evVuHChR0e5+npmaXnwZ2tfv36mjFjhtzd3RUaGip3d3f9+OOPkpRmZlNjjL2tefPmOnbsmFavXq0vvvhCDRs21IABA/T6669nO5aOHTvq+eef1w8//KBLly7p+PHj9nMvU7fpWbNmqWbNmg6Pc3V1zfZzAsB/FUkagLvO+PHjFRERofDwcHtbtWrVtHfvXpUqVSrdx5QtW1ZJSUnatWuX7r33XknSoUOHHKYd37lzp5KSkvTGG2/IxSWlUGHJkiUOy/Hw8FBycvJNY4yMjFSRIkW0ePFiffbZZ3rsscfk4eEhSSpfvrw8PT31+++/KyoqKkuvHXcXX1/fNNt0qVKl5OHhoa+//lodO3aUlDIxzc6dOx2ua1aoUCF1795d3bt3V506dTRs2LB0k7TU7fJm2/U999yjunXrKiYmRpcuXVKjRo0UFBQkSQoKClLhwoV1+PBh++gaANzNSNIA3HUqVaqkTp06adq0afa25557TrVq1dKAAQPUp08f+fr6av/+/Vq/fr2mTZumsmXLqlGjRurbt699ZGLIkCHy9va2jz6ULFlSSUlJmjZtmlq1aqVvvvlGM2fOdHjuYsWK6eLFi9qwYYOqVKkiHx+fdKfet9ls6tixo2bOnKkDBw5o06ZN9vv8/f01dOhQDRo0SFevXtUDDzygf/75R1u3bpWfn5+6deuWS2sOdwJfX1/169dPw4YNU0BAgIoWLaqJEycqPj5evXr1kiS99NJLuvfee1WhQgUlJCRo1apVKleuXLrLCwsLk81m06pVq9SiRQt5e3vLz88v3b6dOnXS6NGjdeXKFU2ePNnhvtGjR+uZZ55Rnjx51Lx5cyUkJGjnzp06d+6cBg8enLMrAQAsjnPSANyVXnnlFYdSxcqVK2vLli06ePCg6tSpo6pVq+rFF19USEiIvc+CBQsUFBSkunXr6pFHHlGfPn3k7+8vLy8vSVJERIQmTZqkCRMmqGLFioqJiUkz5X9kZKSefPJJtWvXToUKFdLEiRMzjLFTp07at2+fChcu7HD+UGr8L730kqKjo1WuXDk1bdpUK1euVPHixXNi9eAON378eLVp00ZdunRRtWrVdOjQIX3++ef2cyw9PDw0YsQIVa5cWXXr1pWrq6s+/PDDdJdVuHBhjRkzRs8//7yCgoIcZkS93mOPPaYzZ84oPj5erVu3drivd+/eeu+99zRv3jxVqlRJUVFRmjdvHts0gLuSzVz7LQUAkGl//PGHihQpYj9nBwAAICeQpAFAJm3cuFEXL15UpUqVFBsbq+HDh+vPP//UgQMH5O7u7uzwAADAHYJz0gAgkxITE/W///1Phw8flr+/vyIjIxUTE0OCBgAAchQjaQAAAABgIUwcAgAAAAAWQpIGAAAAABZCkgYAAAAAFkKSBgAAAAAWQpIGAPjPGT16tCIiIux/d+/ePc3FkW+Ho0ePymazaffu3bf9uQEAdy6SNABAjunevbtsNptsNpvc3d1VokQJDR06VHFxcbn6vFOnTtW8efMy1ZfECgBgdVwnDQCQo5o1a6a5c+cqMTFRX331lXr37q24uDjNmDHDoV9iYmKOXWMub968ObIcAACsgJE0AECO8vT0VHBwsIoUKaKOHTuqU6dOWrFihb1Ecc6cOSpRooQ8PT1ljNGFCxfUt29fBQYGKk+ePGrQoIF+/PFHh2WOHz9eQUFB8vf3V69evXT58mWH+68vd7x69aomTJigUqVKydPTU0WLFtWrr74qSSpevLgkqWrVqrLZbKpXr579cXPnzlW5cuXk5eWlsmXLavr06Q7P891336lq1ary8vJS9erVtWvXrhxccwAApGAkDQCQq7y9vZWYmChJOnTokJYsWaJly5bJ1dVVkvTggw8qICBAa9asUd68efXOO++oYcOGOnDggAICArRkyRKNGjVKb7/9turUqaP3339fb775pkqUKJHhc44YMUKzZs3S5MmT9cADDyg2Nla//PKLpJREq0aNGvriiy9UoUIFeXh4SJJmzZqlUaNG6a233lLVqlW1a9cu9enTR76+vurWrZvi4uLUsmVLNWjQQB988IGOHDmiZ599NpfXHgDgbkSSBgDINd99950WLlyohg0bSpKuXLmi999/X4UKFZIkbdy4UXv27NGpU6fk6ekpSXr99de1YsUKLV26VH379tWUKVPUs2dP9e7dW5I0duxYffHFF2lG01L9+++/mjp1qt566y1169ZNklSyZEk98MADkmR/7gIFCig4ONj+uFdeeUVvvPGGHn30UUkpI2779u3TO++8o27duikmJkbJycmaM2eOfHx8VKFCBf3xxx/q169fTq82AMBdjnJHAECOWrVqlfz8/OTl5aXatWurbt26mjZtmiQpLCzMniRJ0vfff6+LFy+qQIEC8vPzs9+OHDmi3377TZK0f/9+1a5d2+E5rv/7Wvv371dCQoI9McyM06dP6/jx4+rVq5dDHGPHjnWIo0qVKvLx8clUHAAAZBcjaQCAHFW/fn3NmDFD7u7uCg0NdZgcxNfX16Hv1atXFRISos2bN6dZTr58+bL1/N7e3ll+zNWrVyWllDzWrFnT4b7UskxjTLbiAQAgq0jSAAA5ytfXV6VKlcpU32rVqunkyZNyc3NTsWLF0u1Trlw5bd++XV27drW3bd++PcNlli5dWt7e3tqwYYO9RPJaqeegJScn29uCgoJUuHBhHT58WJ06dUp3ueXLl9f777+vS5cu2RPBG8UBAEB2Ue4IAHCaRo0aqXbt2mrdurU+//xzHT16VFu3btULL7ygnTt3SpKeffZZzZkzR3PmzNGBAwc0atQo7d27N8Nlenl56bnnntPw4cO1YMEC/fbbb9q+fbtmz54tSQoMDJS3t7fWrl2rv/76SxcuXJCUcoHs6OhoTZ06VQcOHNCePXs0d+5cTZo0SZLUsWNHubi4qFevXtq3b5/WrFmj119/PZfXEADgbkSSBgBwGpvNpjVr1qhu3brq2bOnwsPD1b59ex09elRBQUGSpHbt2umll17Sc889p3vvvVfHjh276WQdL774ooYMGaKXXnpJ5cqVU7t27XTq1ClJkpubm95880298847Cg0N1cMPPyxJ6t27t9577z3NmzdPlSpVUlRUlObNm2efst/Pz08rV67Uvn37VLVqVY0cOVITJkzIxbUDALhb2QxF9gAAAABgGYykAQAAAICFkKQBAAAAgIWQpAEAAACAhZCkAQAAAICFkKQBAAAAgIWQpAEAAACAhZCkAQAAAICFkKQBAAAAgIWQpAEAAACAhZCkAQAAAICFkKQBAAAAgIWQpAEAAACAhfw/IPSBoVHK/+MAAAAASUVORK5CYII=", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluating SVM...\n", "Accuracy for SVM: 0.87\n", "Precision for SVM: 0.90\n", "Recall for SVM: 0.84\n", "F1 for SVM: 0.87\n", " precision recall f1-score support\n", "\n", " 0 0.84 0.90 0.87 29\n", " 1 0.90 0.84 0.87 32\n", "\n", " accuracy 0.87 61\n", " macro avg 0.87 0.87 0.87 61\n", "weighted avg 0.87 0.87 0.87 61\n", "\n", "------------------------------\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluating KNN...\n", "Accuracy for KNN: 0.84\n", "Precision for KNN: 0.84\n", "Recall for KNN: 0.84\n", "F1 for KNN: 0.84\n", " precision recall f1-score support\n", "\n", " 0 0.83 0.83 0.83 29\n", " 1 0.84 0.84 0.84 32\n", "\n", " accuracy 0.84 61\n", " macro avg 0.84 0.84 0.84 61\n", "weighted avg 0.84 0.84 0.84 61\n", "\n", "------------------------------\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" }, { "name": "stdout", "output_type": "stream", "text": [ "Evaluating Gradient Boosting...\n", "Accuracy for Gradient Boosting: 0.80\n", "Precision for Gradient Boosting: 0.86\n", "Recall for Gradient Boosting: 0.75\n", "F1 for Gradient Boosting: 0.80\n", " precision recall f1-score support\n", "\n", " 0 0.76 0.86 0.81 29\n", " 1 0.86 0.75 0.80 32\n", "\n", " accuracy 0.80 61\n", " macro avg 0.81 0.81 0.80 61\n", "weighted avg 0.81 0.80 0.80 61\n", "\n", "------------------------------\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "## Step 3 Apply machine learning models with a grid search optimizer to the cleaned datasets and evaluate the models' performance.\n", "\n", "from sklearn.model_selection import train_test_split, GridSearchCV\n", "from sklearn.preprocessing import StandardScaler\n", "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.svm import SVC\n", "from sklearn.metrics import classification_report, accuracy_score\n", "from sklearn.neighbors import KNeighborsClassifier\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report\n", "\n", "\n", "# Create a copy of the DataFrame\n", "data = df.copy()\n", "\n", "# Define features and target variable\n", "X = data.drop('target', axis=1)\n", "y = data['target']\n", "\n", "# Split into training and testing sets\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Define models and their parameter grids\n", "models = {\n", " \"Logistic Regression\": {\n", " \"model\": LogisticRegression(max_iter=1000),\n", " \"params\": {\n", " \"C\": [0.1, 1, 10, 100],\n", " \"solver\": ['liblinear', 'lbfgs'],\n", " \"max_iter\": [100, 200, 300]\n", " }\n", " },\n", " \"Random Forest\": {\n", " \"model\": RandomForestClassifier(random_state=42),\n", " \"params\": {\n", " \"n_estimators\": [50, 100, 200],\n", " \"max_depth\": [5, 10, 20, None],\n", " \"min_samples_split\": [2, 5, 10],\n", " \"min_samples_leaf\": [1, 2, 4]\n", " }\n", " },\n", " \"SVM\": {\n", " \"model\": SVC(),\n", " \"params\": {\n", " \"C\": [0.1, 1, 10, 100],\n", " \"kernel\": [\"linear\", \"rbf\"],\n", " \"gamma\": ['scale', 'auto'],\n", " \"degree\": [3, 4, 5],\n", " \"class_weight\": [None, 'balanced']\n", " }\n", " },\n", " \"KNN\": {\n", " \"model\": KNeighborsClassifier(),\n", " \"params\": {\n", " \"n_neighbors\": [3, 5, 7, 9],\n", " \"weights\": [\"uniform\", \"distance\"],\n", " \"metric\": ['euclidean', 'manhattan'],\n", " \"algorithm\": ['auto', 'ball_tree', 'kd_tree', 'brute']\n", " }\n", " },\n", " \"Gradient Boosting\": {\n", " \"model\": GradientBoostingClassifier(random_state=42),\n", " \"params\": {\n", " \"n_estimators\": [50, 100, 200],\n", " \"learning_rate\": [0.01, 0.1, 0.2],\n", " \"max_depth\": [3, 5, 10]\n", " }\n", " }\n", "}\n", "\n", "# Scale the data using StandardScaler\n", "scaler = StandardScaler()\n", "X_train_scaled = scaler.fit_transform(X_train) # Fit and transform training data\n", "X_test_scaled = scaler.transform(X_test) # Transform test data\n", "\n", "# Perform Grid Search for each model\n", "best_models = {}\n", "for name, model_info in models.items():\n", " print(f\"Training {name}...\")\n", " grid_search = GridSearchCV(model_info['model'], model_info['params'], cv=5, scoring='accuracy')\n", " grid_search.fit(X_train_scaled, y_train) # Use X_train for unscaled models\n", " best_models[name] = grid_search.best_estimator_\n", " print(f\"Best hyperparameters found by GridSearchCV: {name}: {grid_search.best_params_}\")\n", " print()\n", "\n", "# Evaluate each best model on the test set\n", "for name, model in best_models.items():\n", " print(f\"Evaluating {name}...\")\n", " y_pred = model.predict(X_test_scaled)\n", " print(f\"Accuracy for {name}: {accuracy_score(y_test, y_pred):.2f}\")\n", " print(f\"Precision for {name}: {precision_score(y_test, y_pred):.2f}\")\n", " print(f\"Recall for {name}: {recall_score(y_test, y_pred):.2f}\")\n", " print(f\"F1 for {name}: {f1_score(y_test, y_pred):.2f}\")\n", " print(classification_report(y_test, y_pred))\n", " print(\"-\" * 30)\n", "\n", "# Plot Confusion Matrix\n", " cm = confusion_matrix(y_test, y_pred)\n", "\n", "# Create a heatmap to visualize the confusion matrix\n", " plt.figure(figsize=(6, 5))\n", " sns.heatmap(cm, annot=True, fmt='d', cmap='Blues', xticklabels=['Negative', 'Positive'], yticklabels=['Negative', 'Positive'])\n", " plt.xlabel('Predicted')\n", " plt.ylabel('True')\n", " plt.title(f'Confusion Matrix for {model}')\n", " plt.show()" ] }, { "cell_type": "code", "execution_count": 77, "id": "c4052688-3d67-4a75-afd0-8ec0933ec8e0", "metadata": {}, "outputs": [], "source": [ "## 4.Use two feature selection methods to identify the most important features from the datasets.\n", "## 5.Apply machine learning models to the selected features and evaluate the models." ] }, { "cell_type": "code", "execution_count": 81, "id": "fe9315c1-48ea-476c-9748-0f06881258cc", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Chi-Square Test Feature Selection Results:\n", " Feature Score\n", "9 oldpeak 626.781709\n", "7 thalach 497.335713\n", "4 chol 81.900670\n", "11 ca 66.440765\n", "2 cp 62.598098\n", "0 age 61.181942\n", "8 exang 38.914377\n", "3 trestbps 26.501471\n", "10 slope 9.804095\n", "1 sex 7.576835\n", "12 thal 5.791853\n", "6 restecg 2.978271\n", "5 fbs 0.202934\n" ] } ], "source": [ "\n", "import pandas as pd\n", "from sklearn.feature_selection import SelectKBest\n", "from sklearn.feature_selection import chi2\n", "from sklearn.model_selection import train_test_split\n", "from sklearn.preprocessing import LabelEncoder\n", "\n", "# Create a copy of the DataFrame\n", "data_FS = df.copy()\n", "\n", "# Step 1: Define features (X) and target (y)\n", "X = data_FS.drop(columns=['target'])\n", "y = data_FS['target']\n", "\n", "# Step 2: Ensure that categorical data is encoded as integers\n", "X_encoded = X.apply(LabelEncoder().fit_transform)\n", "\n", "# Step 3: Apply Chi-Square test for feature selection\n", "selector = SelectKBest(score_func=chi2, k='all') # Use k='all' to evaluate all features\n", "X_new = selector.fit_transform(X_encoded, y)\n", "\n", "# Step 4: Get the Chi-Square test scores and p-values\n", "feature_scores = pd.DataFrame({\n", " 'Feature': X.columns,\n", " 'Score': selector.scores_\n", "}).sort_values(by='Score', ascending=False)\n", "\n", "print(\"Chi-Square Test Feature Selection Results:\")\n", "print(feature_scores)" ] }, { "cell_type": "code", "execution_count": 75, "id": "f5c15897-47fb-4fb0-bcc5-f284650b8541", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fitting 5 folds for each of 324 candidates, totalling 1620 fits\n", "Model Evaluation Results with Hyperparameter Tuning:\n", " Model Name Accuracy Precision Recall F1 Score\n", "0 Random Forest with Grid Search 0.868852 0.875 0.875 0.875\n", "\n", "Best Hyperparameters from Grid Search:\n", "{'max_depth': 5, 'max_features': 'sqrt', 'min_samples_leaf': 1, 'min_samples_split': 10, 'n_estimators': 150}\n" ] } ], "source": [ "import warnings\n", "warnings.filterwarnings('ignore')\n", "\n", "# Step 1: Split the data into training and testing sets\n", "selector = SelectKBest(score_func=chi2, k=5) # Select top 5 features\n", "X_selected = selector.fit_transform(X_encoded, y)\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(X_selected, y, test_size=0.2, random_state=42)\n", "\n", "# Step 2: Define the RandomForestClassifier\n", "rf = RandomForestClassifier(random_state=42)\n", "\n", "# Step 3: Set up the hyperparameters for Grid Search\n", "param_grid = {\n", " 'n_estimators': [50, 100, 150], # Number of trees\n", " 'max_depth': [5, 10, 20, None], # Maximum depth of trees\n", " 'min_samples_split': [2, 5, 10], # Minimum samples to split a node\n", " 'min_samples_leaf': [1, 2, 4], # Minimum samples at a leaf node\n", " 'max_features': ['auto', 'sqrt', 'log2'] # Number of features to consider at each split\n", "}\n", "\n", "# Step 4: Apply GridSearchCV\n", "grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, n_jobs=-1, verbose=2, scoring='accuracy')\n", "grid_search.fit(X_train, y_train)\n", "\n", "# Step 5: Get the best parameters and best model\n", "best_params = grid_search.best_params_\n", "best_model = grid_search.best_estimator_\n", "\n", "# Step 6: Make predictions with the best model\n", "y_pred = best_model.predict(X_test)\n", "\n", "# Step 7: Evaluate the model\n", "accuracy = accuracy_score(y_test, y_pred)\n", "precision = precision_score(y_test, y_pred)\n", "recall = recall_score(y_test, y_pred)\n", "f1 = f1_score(y_test, y_pred)\n", "\n", "# Step 8: Store results in a dictionary or DataFrame\n", "results = {\n", " 'Model Name': ['Random Forest with Grid Search'],\n", " 'Accuracy': [accuracy],\n", " 'Precision': [precision],\n", " 'Recall': [recall],\n", " 'F1 Score': [f1]\n", "}\n", "\n", "# Create a DataFrame to display results\n", "results_df = pd.DataFrame(results)\n", "\n", "# Step 9: Display results\n", "print(\"Model Evaluation Results with Hyperparameter Tuning:\")\n", "print(results_df)\n", "\n", "# Step 10: Display the best hyperparameters\n", "print(\"\\nBest Hyperparameters from Grid Search:\")\n", "print(best_params)" ] }, { "cell_type": "code", "execution_count": 79, "id": "f8227741-e44e-46d1-9d9e-00a1bec37cbd", "metadata": {}, "outputs": [], "source": [ "## 4.Use two feature selection methods to identify the most important features from the datasets.\n", "## 5.Apply machine learning models to the selected features and evaluate the models." ] }, { "cell_type": "code", "execution_count": 87, "id": "3317b492-668f-4882-b1c2-4176e17f5115", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Selected Features: Index(['sex', 'cp', 'exang', 'oldpeak', 'thal'], dtype='object')\n" ] } ], "source": [ "from sklearn.feature_selection import RFE\n", "# Create a copy of the DataFrame\n", "data_FS1 = df.copy()\n", "\n", "# Step 1: Split the dataset into features (X) and target (y)\n", "X = data_FS1.drop('target', axis=1) # All columns except target\n", "y = data_FS1['target'] # Target column\n", "\n", "# Step 2: Split into training and test sets (80/20 split)\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n", "\n", "# Step 3: Apply RFE for feature selection (choose the number of features to select)\n", "selector = RFE(estimator=model, n_features_to_select=5) # Select top 5 features\n", "selector = selector.fit(X_train, y_train)\n", "\n", "# Step 5: Get the selected features\n", "selected_features = X.columns[selector.support_]\n", "print(\"Selected Features: \", selected_features)\n", "\n" ] }, { "cell_type": "code", "execution_count": 101, "id": "4d5b04fd-143e-4b21-8748-5e9307d8af26", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "Best hyperparameters found by GridSearchCV: {'max_depth': None, 'min_samples_leaf': 1, 'min_samples_split': 10, 'n_estimators': 100}\n", "\n", "Model Name: RandomForestClassifier\n", "Accuracy: 0.8197\n", "Precision: 0.8889\n", "Recall: 0.7500\n", "F1 Score: 0.8136\n" ] } ], "source": [ "## Apply machine learning models to the selected features and evaluate the model\n", "import pandas as pd\n", "from sklearn.model_selection import train_test_split, GridSearchCV\n", "from sklearn.ensemble import RandomForestClassifier\n", "from sklearn.feature_selection import RFE\n", "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, classification_report\n", "from sklearn.impute import SimpleImputer\n", "\n", "# Selected features\n", "X_train_selected = X_train[selected_features]\n", "X_test_selected = X_test[selected_features]\n", "\n", "# Hyperparameter tuning using GridSearchCV\n", "param_grid = {\n", " 'n_estimators': [100, 200, 300],\n", " 'max_depth': [None, 10, 20, 30],\n", " 'min_samples_split': [2, 5, 10],\n", " 'min_samples_leaf': [1, 2, 4]\n", "}\n", "\n", "grid_search = GridSearchCV(\n", " estimator=RandomForestClassifier(random_state=42),\n", " param_grid=param_grid,\n", " cv=5,\n", " scoring='accuracy',\n", " n_jobs=-1\n", ")\n", "\n", "grid_search.fit(X_train_selected, y_train)\n", "\n", "# Best parameters from GridSearch\n", "best_params = grid_search.best_params_\n", "print(\"\\nBest hyperparameters found by GridSearchCV: \", best_params)\n", "\n", "# Train the final model with the best parameters\n", "best_rf_model = grid_search.best_estimator_\n", "best_rf_model.fit(X_train_selected, y_train)\n", "\n", "# Evaluate the model\n", "y_pred = best_rf_model.predict(X_test_selected)\n", "\n", "accuracy = accuracy_score(y_test, y_pred)\n", "precision = precision_score(y_test, y_pred)\n", "recall = recall_score(y_test, y_pred)\n", "f1 = f1_score(y_test, y_pred)\n", "\n", "print(\"\\nModel Name: RandomForestClassifier\")\n", "print(f\"Accuracy: {accuracy:.4f}\")\n", "print(f\"Precision: {precision:.4f}\")\n", "print(f\"Recall: {recall:.4f}\")\n", "print(f\"F1 Score: {f1:.4f}\")\n", "\n", "#print(\"\\nClassification Report:\")\n", "#print(classification_report(y_test, y_pred))" ] }, { "cell_type": "code", "execution_count": null, "id": "7602ee56-0e9c-47b4-a068-de6afd55b465", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.7" } }, "nbformat": 4, "nbformat_minor": 5 }