{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "#################################################################\n",
        "## مشروع ماجستير ذكاء اصطناعي - المرحلة الثانية: NLP\n",
        "##  الطالب:  أحمد منير مزيك\n",
        "#################################################################\n",
        "\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import re\n",
        "import nltk\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "from nltk.corpus import stopwords\n",
        "from nltk.stem import WordNetLemmatizer\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
        "from imblearn.over_sampling import SMOTE\n",
        "from tqdm import tqdm\n",
        "print(\"Step 1: Downloading NLTK resources...\")\n",
        "nltk.download('punkt')\n",
        "nltk.download('punkt_tab')\n",
        "nltk.download('stopwords')\n",
        "nltk.download('wordnet')\n",
        "nltk.download('omw-1.4')\n",
        "\n",
        "file_path = 'unbalanceddataset (1).csv'\n",
        "print(f\"\\nStep 2: Loading dataset from {file_path}...\")\n",
        "df = pd.read_csv(file_path)\n",
        "\n",
        "\n",
        "print(\"\\nClasses distribution before balancing:\")\n",
        "print(df['sentiment'].value_counts())\n",
        "\n",
        "lemmatizer = WordNetLemmatizer()\n",
        "stop_words = set(stopwords.words('english'))\n",
        "\n",
        "def clean_text(text):\n",
        "    text = str(text).lower()\n",
        "    text = re.sub(r'https?://\\S+|www\\.\\S+', '', text)\n",
        "    text = re.sub(r'[^a-zA-Z\\s]', '', text)\n",
        "\n",
        "    tokens = nltk.word_tokenize(text)\n",
        "    cleaned_tokens = [lemmatizer.lemmatize(w) for w in tokens if w not in stop_words]\n",
        "    return ' '.join(cleaned_tokens)\n",
        "\n",
        "print(\"\\nStep 3: Starting Preprocessing... (This might take a moment)\")\n",
        "tqdm.pandas()\n",
        "df['cleaned_text'] = df['text'].progress_apply(clean_text)\n",
        "\n",
        "X = df['cleaned_text']\n",
        "y = df['sentiment']\n",
        "X_train_raw, X_test_raw, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
        "\n",
        "print(\"\\n--- Phase A: Applying Word Features (CountVectorizer) + SMOTE ---\")\n",
        "\n",
        "count_vec = CountVectorizer(max_features=2500)\n",
        "X_train_word = count_vec.fit_transform(X_train_raw)\n",
        "X_test_word = count_vec.transform(X_test_raw)\n",
        "\n",
        "smote = SMOTE(random_state=42)\n",
        "X_train_word_res, y_train_word_res = smote.fit_resample(X_train_word, y_train)\n",
        "print(f\"Distribution after SMOTE (Word Features): {pd.Series(y_train_word_res).value_counts().to_dict()}\")\n",
        "\n",
        "model_word = RandomForestClassifier(n_estimators=100, random_state=42)\n",
        "model_word.fit(X_train_word_res, y_train_word_res)\n",
        "y_pred_word = model_word.predict(X_test_word)\n",
        "\n",
        "print(\"\\n--- Phase B: Applying TF-IDF Features + SMOTE ---\")\n",
        "# استخراج الميزات (Lec 7)\n",
        "tfidf_vec = TfidfVectorizer(max_features=2500)\n",
        "X_train_tfidf = tfidf_vec.fit_transform(X_train_raw)\n",
        "X_test_tfidf = tfidf_vec.transform(X_test_raw)\n",
        "\n",
        "X_train_tfidf_res, y_train_tfidf_res = smote.fit_resample(X_train_tfidf, y_train)\n",
        "print(f\"Distribution after SMOTE (TF-IDF): {pd.Series(y_train_tfidf_res).value_counts().to_dict()}\")\n",
        "\n",
        "model_tfidf = RandomForestClassifier(n_estimators=100, random_state=42)\n",
        "model_tfidf.fit(X_train_tfidf_res, y_train_tfidf_res)\n",
        "y_pred_tfidf = model_tfidf.predict(X_test_tfidf)\n",
        "\n",
        "def show_results(name, y_true, y_pred):\n",
        "    print(f\"\\n\" + \"=\"*50)\n",
        "    print(f\" FINAL RESULTS FOR: {name} \")\n",
        "    print(\"=\"*50)\n",
        "    print(f\"Overall Accuracy: {accuracy_score(y_true, y_pred):.4f}\")\n",
        "    print(\"\\nDetailed Classification Report:\")\n",
        "    print(classification_report(y_true, y_pred))\n",
        "\n",
        "    cm = confusion_matrix(y_true, y_pred)\n",
        "    plt.figure(figsize=(6,5))\n",
        "    sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
        "                xticklabels=['negative', 'positive'],\n",
        "                yticklabels=['negative', 'positive'])\n",
        "    plt.title(f'Confusion Matrix: {name}')\n",
        "    plt.ylabel('Actual Sentiment')\n",
        "    plt.xlabel('Predicted Sentiment')\n",
        "    plt.show()\n",
        "\n",
        "show_results(\"Word Features (CountVectorizer) + SMOTE\", y_test, y_pred_word)\n",
        "show_results(\"TF-IDF Features + SMOTE\", y_test, y_pred_tfidf)\n",
        "\n",
        "print(\"\\n\" + \"#\"*50)\n",
        "print(\"Project Execution Finished. Ready for PDF Export.\")\n",
        "print(\"#\"*50)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "YO9q-OQJRYEz",
        "outputId": "f51381dd-c9e3-42fc-e25f-44c658a003a7"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Step 1: Downloading NLTK resources...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "[nltk_data] Downloading package punkt to /root/nltk_data...\n",
            "[nltk_data]   Package punkt is already up-to-date!\n",
            "[nltk_data] Downloading package punkt_tab to /root/nltk_data...\n",
            "[nltk_data]   Unzipping tokenizers/punkt_tab.zip.\n",
            "[nltk_data] Downloading package stopwords to /root/nltk_data...\n",
            "[nltk_data]   Package stopwords is already up-to-date!\n",
            "[nltk_data] Downloading package wordnet to /root/nltk_data...\n",
            "[nltk_data]   Package wordnet is already up-to-date!\n",
            "[nltk_data] Downloading package omw-1.4 to /root/nltk_data...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Step 2: Loading dataset from unbalanceddataset (1).csv...\n",
            "\n",
            "Classes distribution before balancing:\n",
            "sentiment\n",
            "positive    2000\n",
            "negative     600\n",
            "Name: count, dtype: int64\n",
            "\n",
            "Step 3: Starting Preprocessing... (This might take a moment)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "100%|██████████| 2600/2600 [00:07<00:00, 327.34it/s] \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "--- Phase A: Applying Word Features (CountVectorizer) + SMOTE ---\n",
            "Distribution after SMOTE (Word Features): {'positive': 1596, 'negative': 1596}\n",
            "\n",
            "--- Phase B: Applying TF-IDF Features + SMOTE ---\n",
            "Distribution after SMOTE (TF-IDF): {'positive': 1596, 'negative': 1596}\n",
            "\n",
            "==================================================\n",
            " FINAL RESULTS FOR: Word Features (CountVectorizer) + SMOTE \n",
            "==================================================\n",
            "Overall Accuracy: 0.8000\n",
            "\n",
            "Detailed Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "    negative       0.54      0.65      0.59       116\n",
            "    positive       0.89      0.84      0.87       404\n",
            "\n",
            "    accuracy                           0.80       520\n",
            "   macro avg       0.72      0.75      0.73       520\n",
            "weighted avg       0.81      0.80      0.81       520\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x500 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhgAAAHWCAYAAAA1jvBJAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAbCRJREFUeJzt3XdcU+fbBvArrLADqCwHIk6cOKqIihvFWfdG66gW96jS1j2o1llbV7VurFvrquJEFPdeqIjSKogTBJT5vH/4cn5GEIMeDITr208+Nc85OefOILlzPyMKIYQAERERkYz0tB0AERER6R4mGERERCQ7JhhEREQkOyYYREREJDsmGERERCQ7JhhEREQkOyYYREREJDsmGERERCQ7JhhEREQkuzyXYNy5cwdNmzaFSqWCQqHAjh07ZD3+/fv3oVAosGrVKlmPm5fVr18f9evX13YYWsHXQ8777rvv0KRJE22HQRpQKBSYNGnSFz/vuHHjULNmzS9+Xvo8n5RghIWF4dtvv0WJEiVgbGwMS0tLeHh4YMGCBXj9+rXcMarx8fHB1atXMX36dKxduxbVq1fP0fN9Sb1794ZCoYClpWWmj+OdO3egUCigUCgwe/bsbB//0aNHmDRpEi5duiRDtPI5c+YMFAoF5s2bl2FbmzZtoFAosHLlygzb6tWrh8KFC3+JED/q6NGj0nPz/qVLly45cs4bN25g0qRJuH//fo4c/0sIDw/H8uXL8cMPP2TYFhsbi8mTJ6Ny5cowNzeHiYkJKlSogLFjx+LRo0daiDajvXv3ZvjA3bZtGxQKBZYvX/7B2wUGBkKhUODXX3/N8Xh0wfDhw3H58mX8/fffWjn/rl274OnpCVtbW5iamqJEiRLo1KkT/vnnH2mf9C8jCoUC06ZNy/Q43bt3h0KhgLm5eYZtQgisXbsW9erVg5WVFUxNTVGxYkVMmTIF8fHx0n6rVq364HvNu5fixYsDACZNmpTlflFRUfI+WO8wyO4N9uzZg44dO0KpVKJXr16oUKECkpKSEBwcjDFjxuD69etYtmxZTsSK169fIyQkBD/++CMGDx6cI+dwcnLC69evYWhomCPH/xgDAwMkJCRg165d6NSpk9q29evXw9jYGG/evPmkYz969AiTJ09G8eLFUaVKFY1vd+DAgU86n6aqVq0KU1NTBAcHY8SIEWrbTp48CQMDA5w4cQJ9+vSR2pOSknD27Fm0atUqR2PLrqFDh6JGjRpqbel/6HK7ceMGJk+ejPr16+fYOXLaggUL4OzsjAYNGqi137t3D40bN0ZERAQ6duyIAQMGwMjICFeuXMGKFSuwfft23L59W0tR/8/evXvx+++/q32ot2jRAiqVCgEBAejXr1+mtwsICIC+vr7syWdm8cjp9evXMDDI9sfGZ7O3t0ebNm0we/ZstG7d+ouee/bs2RgzZgw8PT3h5+cHU1NT3L17FwcPHsRff/2FZs2aqe1vbGyMDRs24KefflJrj4+Px86dO2FsbJzhHKmpqejWrRs2bdqEunXrYtKkSTA1NcXx48cxefJkbN68GQcPHoSdnR3q1auHtWvXqt2+X79++OqrrzBgwACp7f0kZvHixZkmNlZWVtl9SDQnsuHevXvC3NxclC1bVjx69CjD9jt37oj58+dn55DZ8uDBAwFA/PLLLzl2Dm3y8fERZmZmomnTpqJt27YZtpcqVUq0b9/+kx+Ds2fPCgBi5cqVGu0fHx+f7XN8qgYNGgg7Ozu1tlu3bgkAolu3bqJMmTJq206ePCkAiAULFnz2ubO6n+Hh4Ro9ZkeOHBEAxObNmz87Hk1t3rxZABBHjhyR9bhxcXGyHu9DkpKSRMGCBcVPP/2k1p6cnCwqV64sTE1NxfHjxzPcLiYmRvzwww9fJMaP8fX1FZm9jfbt21fo6emJhw8fZtj2+vVroVKpRLNmzb5YPJ8jNTVVvH79WtZjaurd1+KWLVuEQqEQYWFh2T5O+t9xdv9WkpOThaWlpWjSpEmm2x8/fpzhHO3atRMAxKVLl9T2Xb9+vTA0NBStWrUSZmZmattmzJghAIjRo0dnOMfff/8t9PT0sny9mJmZCR8fn0y3TZw4UQAQT548+eDtc0q2XokDBw4UAMSJEyc02j85OVlMmTJFlChRQhgZGQknJyfh5+cn3rx5o7afk5OTaNGihTh+/LioUaOGUCqVwtnZWaxevVraJ/1Bevfi5OQkhHj7wZz+73el3+ZdBw4cEB4eHkKlUgkzMzNRunRp4efnJ23/0AfKoUOHRJ06dYSpqalQqVSidevW4saNG5me786dO8LHx0eoVCphaWkpevfurdGHdXqCsWrVKqFUKsWLFy+kbWfOnBEAxNatWzMkGM+ePROjRo0SFSpUEGZmZsLCwkI0a9ZM7QWe/gH4/iX9fnp6eory5cuLc+fOibp16woTExMxbNgwaZunp6d0rF69egmlUpnh/jdt2lRYWVmpvanevXtX3L1796P3ffz48dJjl27FihXC0tJSHD16NMMfyC+//CIAiPPnz0ttv//+u3B1dRVGRkbCwcFBfPfdd2qP4cfu54sXL4SPj4+wtLQUKpVK9OrVS1y8eFHWBOPUqVPCy8tLWFpaChMTE1GvXj0RHBysts/9+/fFoEGDROnSpYWxsbGwsbERHTp0EOHh4dI+K1euzPT5TH8DBSAmTpyY4fxOTk5qb0Tpxzl69KgYNGiQKFSokLCyspK27927V3rdm5ubC29vb3Ht2jW1Y0ZGRorevXuLwoULCyMjI2Fvby9at26tFm9mDh8+LJ37XX/99ZcAIKZPn57l7d+1adMmUbVqVWFsbCwKFCggunfvLv777z+1fd5/Had7//0j/T3gl19+EUuXLpXev6pXry7OnDmjdrvMngMh/vd6mDNnTobzbdmyRQAQa9euldrWrl0rxW9tbS06d+4sIiIiMtz21KlTonnz5sLKykqYmpqKihUrSl/qsopHiLcf1iNHjhRFihQRRkZGonTp0uKXX34RaWlpaucAIHx9fcW6deuEq6urMDAwENu3b5e2pb+u0h+nD13ej/tjr/v098/r16+Lrl27CisrK1GlShVp+8uXL4VCoRBz587N8Lh8zKcmGJGRkQKAmDRpksbn+OWXX4Szs7P4/vvv1bZ7e3uLVq1aSe/z6RISEoS1tbUoXbq0SE5OzvTYffr0EQBESEhIpttza4KRrVrXrl27UKJECdSuXVuj/fv164fVq1ejQ4cOGDVqFE6fPg1/f3/cvHkT27dvV9v37t276NChA/r27QsfHx/8+eef6N27N6pVq4by5cujXbt2sLKywogRI9C1a1d4e3tnWu7JyvXr19GyZUtUqlQJU6ZMgVKpxN27d3HixIksb3fw4EE0b94cJUqUwKRJk/D69WssXLgQHh4euHDhQobydKdOneDs7Ax/f39cuHABy5cvh62tLWbOnKlRnO3atcPAgQOxbds2fPPNNwDellTLli2LqlWrZtj/3r172LFjBzp27AhnZ2c8fvwYS5cuhaenJ27cuAFHR0eUK1cOU6ZMwYQJEzBgwADUrVsXANSey2fPnqF58+bo0qULevToATs7u0zjW7BgAQ4fPgwfHx+EhIRAX18fS5cuxYEDB7B27Vo4OjpK+zZq1AgAPjpOoE6dOgCA4OBglCxZEgBw4sQJ1KpVCzVr1oShoSFOnjwplUdPnDgBCwsLVK5cGcDbfsbJkyejcePGGDRoEEJDQ7F48WKcPXsWJ06cUOvyyux+CiHQpk0bBAcHY+DAgShXrhy2b98OHx+fLON+36tXr/D06VO1NhsbG+jp6eHw4cNo3rw5qlWrhokTJ0JPTw8rV65Ew4YNcfz4cXz11VcAgLNnz+LkyZPo0qULihQpgvv372Px4sWoX78+bty4AVNTU9SrVw9Dhw7Fr7/+ih9++AHlypUDAOn/2fXdd9+hUKFCmDBhgtTfu3btWvj4+MDLywszZ85EQkICFi9ejDp16uDixYvS6759+/a4fv06hgwZguLFiyM6OhqBgYGIiIjIsuvm5MmTUCgUcHNzU2tP72fv2bOnRrGvWrUKffr0QY0aNeDv74/Hjx9jwYIFOHHiBC5evPjJJeCAgAC8evUK3377LRQKBWbNmoV27drh3r17MDQ0xLfffotHjx4hMDAwQ8m6Xr16KFKkCAICAjBy5MgMxzU1NUXbtm0BANOnT8f48ePRqVMn9OvXD0+ePMHChQtRr149tfgDAwPRsmVLODg4YNiwYbC3t8fNmzexe/duDBs2LMt4hBBo3bo1jhw5gr59+6JKlSrYv38/xowZg4cPH2YY/3T48GFs2rQJgwcPRsGCBTN9HgsVKpThPMnJyRgxYgSMjIzUjqXJ6z5dx44dUapUKcyYMQNCCKldpVLBxcUFJ06cyNCVmlNsbW1hYmKCXbt2YciQIbCxsdHodl27dsW6devw888/Q6FQ4OnTp9L747vjNoC373kvXrzAsGHDPtj91KtXL6xcuRK7d+9GrVq1Pum+PH/+PEObgYFB7ugiiYmJEQBEmzZtNNr/0qVLAoDo16+fWvvo0aMFAHH48GGpzcnJSQAQQUFBUlt0dLRQKpVi1KhRUtu7GeK7NK1gzJs376OZXGYVjCpVqghbW1vx7Nkzqe3y5ctCT09P9OrVK8P5vvnmG7Vjfv3116JAgQIfPOe79yM9s+3QoYNo1KiREOJtidLe3l5Mnjw508fgzZs3IjU1NcP9UCqVYsqUKVJbVl0knp6eAoBYsmRJptve/+a3f/9+AUBMmzZN6jrLrFvHyckp0+fmfbGxsUJfX1/07dtXaitTpoyYPHmyEEKIr776SowZM0baVqhQIalsGR0dLYyMjETTpk3VHofffvtNABB//vnnR+/njh07BAAxa9YsqS0lJUXUrVs3WxWMzC7h4eEiLS1NlCpVSnh5eal9Y0xISBDOzs5qJdiEhIQMxw8JCREAxJo1a6S2rLpIkM0KRp06dURKSorU/urVK2FlZSX69++vdvuoqCihUqmk9hcvXnxyl12PHj0y/btwc3MTKpVKo2MkJSUJW1tbUaFCBbUy/u7duwUAMWHCBKktuxWMAgUKiOfPn0vtO3fuFADErl27pLasuiTGjBkjAIjQ0FCpLSYmRhgbG4uuXbsKId5Wq/T19TNUa65evSoMDAyk9pSUFOHs7CycnJwyVOXefT19KJ701/e0adPU2jt06CAUCoValRGA0NPTE9evX89wnA+9rtJ99913Ql9fX3p/z87rPv39M/2xyUzTpk1FuXLlPrj9Qz61giGEEBMmTBAAhJmZmWjevLmYPn26WuX0/XP88ssv4tq1awKA1MX3+++/C3NzcxEfH5+hgjF//nwBQKoSZeb58+dS90tmNKlgZHZ5v+tZbhrPIomNjQUAWFhYaLT/3r17ASBD9j5q1CgAbweLvsvV1VX6Vg28zY7LlCmDe/fuaRriR6Vnajt37kRaWppGt4mMjMSlS5fQu3dvtey1UqVKaNKkiXQ/3zVw4EC163Xr1sWzZ8+kx1AT3bp1w9GjRxEVFYXDhw8jKioK3bp1y3RfpVIJPb23T2VqaiqePXsGc3NzlClTBhcuXND4nEqlUm0gZVaaNm2Kb7/9FlOmTEG7du1gbGyMpUuXZtjv/v37Gs1ysLCwQKVKlRAcHAwAePr0KUJDQ6UKi4eHh1Rpun37Np48eSJVPQ4ePIikpCQMHz5cehwAoH///rC0tMzwWsvsfu7duxcGBgYYNGiQ1Kavr48hQ4Zo8Gj8z4QJExAYGKh2sbe3x6VLl3Dnzh1069YNz549w9OnT/H06VPEx8ejUaNGCAoKkl6TJiYm0vGSk5Px7NkzlCxZElZWVtl6PrOjf//+0NfXl64HBgbi5cuX6Nq1qxTr06dPoa+vj5o1a+LIkSNSrEZGRjh69ChevHiRrXM+e/YM1tbWGdpjY2M1fp85d+4coqOj8d1336kNnmvRogXKli2b4bnPjs6dO6vFl/7+pOl7Uo8ePQC8rVik27p1K968eYPu3bsDeDvjJC0tDZ06dVJ7nO3t7VGqVCnpcb548SLCw8MxfPjwDN84FQrFR2PZu3cv9PX1MXToULX2UaNGQQiBffv2qbV7enrC1dVVo/uZbs2aNVi0aBFmzZolDdrNzus+3fvvn++ytrbOUCHMTFxcnNrjmf7ajImJUWuPiYn56LEmT56MgIAAuLm5Yf/+/fjxxx9RrVo1VK1aFTdv3sz0NuXLl0elSpWwYcMGAG9fA23atIGpqWmGfV+9egUg68/W9G3Z+Qx539atWzO8N2U2O09OGneRWFpaAvjfg/ExDx48gJ6enlTuTmdvbw8rKys8ePBArb1YsWIZjmFtbZ3tN62sdO7cGcuXL0e/fv0wbtw4NGrUCO3atUOHDh3UPpjevx8AUKZMmQzbypUrh/379yM+Ph5mZmZS+/v3Jf1N6sWLF9Lj+DHe3t6wsLDAxo0bcenSJdSoUQMlS5bM9MM6LS0NCxYswKJFixAeHo7U1FRpW4ECBTQ6HwAULlxYrbT5MbNnz8bOnTtx6dIlBAQEwNbWVuPbZqZOnTpYuHAhnj59ipMnT0JfX18qB9auXRuLFi1CYmKilGikJxgfeo6MjIxQokSJDK+1zO7ngwcP4ODgkKHbLbPnPSsVK1ZE48aNM7TfuXMHALLscomJiYG1tTVev34Nf39/rFy5Eg8fPlQrE2vyhvgpnJ2dM423YcOGme6f/jpWKpWYOXMmRo0aBTs7O9SqVQstW7ZEr169YG9v/9Hzvnvf3j22ph/iWf19li1bVkpYP0VWf8eaqFSpEipUqIANGzZIszoCAgJQsGBBeHl5AXj7OAshUKpUqUyPkd61FxYWBgCoUKFCtu8H8PZxcnR0zPAhlt6l9v7fyPuvh4+5dOkSBg4ciK5du6p9qczO616TcwshNEqoBg8ejNWrV2doT++WSufp6YmjR49+9Hhdu3ZF165dERsbi9OnT2PVqlUICAhAq1atcO3atUxnhnTr1g1z5szBiBEjcPLkyUynYgP/Sx6y+mzVJAn5mHr16qFgwYKffPtPka0Ew9HREdeuXcvWCTR5MQBQ+/b0rszegDQ9x7sftMDbb1tBQUE4cuQI9uzZg3/++QcbN25Ew4YNceDAgQ/GkF2fc1/SKZVKtGvXDqtXr8a9e/eynHY2Y8YMjB8/Ht988w2mTp0q9fkPHz5c40oNoP7NWRMXL15EdHQ0AODq1avo2rVrtm7/vvQE48SJEzh58iQqVqwofeDXrl0biYmJOHv2LIKDg2FgYPDJfZHZvZ9ySH8efvnllw9OEU6/r0OGDMHKlSsxfPhwuLu7S4vKdenSJVvPZ2be/5tI9/5jkn6etWvXZpoovNtXPHz4cLRq1Qo7duzA/v37MX78ePj7++Pw4cMZxle8q0CBApl+WJctWxYXL17Ev//+i6JFi2p0vzShUCgy/Rv80GMix99xjx49MG7cOJw7dw5FihTBkSNH8O2330qPX1paGhQKBfbt25fp+bI7zkwu2fkbefHiBdq3b4/SpUtnWPsjO697Tc794sULjT4kv//+e6mCBACPHz9Gjx49MHv2bGncFoBMK2hZsbS0RJMmTdCkSRMYGhpi9erVOH36NDw9PTPs27VrV/j5+aF///4oUKAAmjZtmukx05O8K1euZEiA0l25cgUAsl1V0rZsDfJs2bIlli1bhpCQELi7u2e5r5OTE9LS0nDnzh21gWePHz/Gy5cv4eTk9GkRZ8La2hovX77M0P5+Vg4Aenp6aNSoERo1aoS5c+dixowZ+PHHH3HkyJFMv3mmxxkaGpph261bt1CwYEG16oWcunXrhj///BN6enpZzpffsmULGjRogBUrVqi1v3z5Uu2PUdNkTxPx8fHo06cPXF1dUbt2bcyaNQtff/11hjUgsuPdgZ4hISHw8PCQtjk6OsLJyQknTpzAiRMn4ObmJpUb332OSpQoId0mKSkJ4eHhmT6v73NycsKhQ4cQFxen9oaX2fP+KVxcXAC8fYP6WDxbtmyBj48P5syZI7W9efMmw2s8q+czs7+JpKQkREZGZiteW1tbjR4/FxcXjBo1CqNGjcKdO3dQpUoVzJkzB+vWrfvgbcqWLYv169cjJiYGKpVKam/VqhU2bNiAdevWwc/PL8vzvvvcv19tCQ0NVXufsba2zrQyktn7hKY+9jeV/iETEBAAJycnpKamSt0jwNvHTQgBZ2dnlC5d+oPHSX8+rl27luXz8aF4nJyccPDgQbx69UrtW/CtW7ek7Z8iLS0N3bt3x8uXL3Hw4MEMXQDZed1rIjw8XC1B+BBXV1e1D+P0ym+1atVkW5W4evXqWL169Qf/pooVKwYPDw8cPXoUgwYN+uAAzjp16sDKygoBAQH48ccfM00016xZA+DtZ3Bekq2VPL///nuYmZmhX79+ePz4cYbtYWFhWLBgAYC3JX4AmD9/vto+c+fOBfC2j1QuLi4uiImJkbI84O3YifdnqmQ2ijY9q05MTMz02A4ODqhSpQpWr16t9oZ97do1HDhwQLqfOaFBgwaYOnUqfvvttyzLzfr6+hm+VW3evBkPHz5Ua0tPhDJLxrJr7NixiIiIwOrVqzF37lwUL14cPj4+GR7HsLAwqbz7MY6OjnB2dsahQ4dw7ty5DLOVateujR07diA0NFRKRgCgcePGMDIywq+//qr2OKxYsQIxMTEavda8vb2RkpKCxYsXS22pqalYuHChRrF/TLVq1eDi4oLZs2cjLi4uw/YnT55I/87s+Vy4cGGGb9pZPZ8uLi4ICgpSa1u2bNkHv62/z8vLC5aWlpgxYwaSk5M/GG9CQkKGhd9cXFxgYWHxwb+pdO7u7hBC4Pz582rtHTp0QMWKFTF9+nSEhIRkuN2rV6/w448/Anj7Jm9ra4slS5aonW/fvn24efOm2nPv4uKCW7duqT3Wly9f/ugssqx87G+qWLFiqFu3LjZu3Ih169bB2dlZ7XXdrl076OvrY/LkyRmecyEEnj17BuDtYnTOzs6YP39+hnO9e7sPxePt7Y3U1FT89ttvau3z5s2DQqFA8+bNNb7P75o8eTL279+PDRs2ZNq1kZ3X/cfExMQgLCxM41mMckhISMj0NQhAGreSVTfqtGnTMHHixCzHcpmammL06NEIDQ2VXtfv2rNnD1atWgUvL69PrtpqS7YqGC4uLggICEDnzp1Rrlw5tZU8T548ic2bN6N3794AgMqVK8PHxwfLli3Dy5cv4enpiTNnzmD16tVo27ZthpX7PkeXLl0wduxYfP311xg6dKg0na506dJqg+KmTJmCoKAgtGjRAk5OToiOjsaiRYtQpEgRtQ+s9/3yyy9o3rw53N3d0bdvX2maqkqlytFlefX09DKsBpeZli1bYsqUKejTpw9q166Nq1evYv369Wrf5oG3z5+VlRWWLFkCCwsLmJmZoWbNmtnubz18+DAWLVqEiRMnStNmV65cifr162P8+PGYNWuWtK+m01TT1alTR5r69m4FA3ibYKQPmnr3+SpUqBD8/PwwefJkNGvWDK1bt0ZoaCgWLVqEGjVqqJVKP6RVq1bw8PDAuHHjcP/+fbi6umLbtm2yjXnQ09PD8uXL0bx5c5QvXx59+vRB4cKF8fDhQxw5cgSWlpbYtWsXgLfP59q1a6FSqeDq6oqQkBAcPHgww3iaKlWqQF9fHzNnzkRMTAyUSiUaNmwIW1tb9OvXDwMHDkT79u3RpEkTXL58Gfv379e4D9bS0hKLFy9Gz549UbVqVXTp0gWFChVCREQE9uzZAw8PD/z222+4ffs2GjVqhE6dOsHV1RUGBgbYvn07Hj9+/NFVKuvUqYMCBQrg4MGDatUHQ0NDbNu2DY0bN0a9evXQqVMneHh4wNDQENevX0dAQACsra0xffp0GBoaYubMmejTpw88PT3RtWtXaZpq8eLF1aYzfvPNN5g7dy68vLzQt29fREdHY8mSJShfvvwnD56rVq0agLcruHp5eWW6OmePHj0wYMAAPHr0KMMHiIuLC6ZNmwY/Pz/cv38fbdu2hYWFBcLDw7F9+3YMGDAAo0ePhp6eHhYvXoxWrVqhSpUq6NOnDxwcHHDr1i1cv34d+/fvzzKeVq1aoUGDBvjxxx9x//59VK5cGQcOHMDOnTsxfPhwqdKQHVevXsXUqVNRr149REdHZ6hW9ejRI1uv+485ePCgNJ38S0lISEDt2rVRq1YtNGvWDEWLFsXLly+xY8cOHD9+HG3bts2yG9DT0zPT7pP3jRs3DhcvXsTMmTMREhKC9u3bw8TEBMHBwVi3bh3KlSuX6ZiS7NiyZUumXW5NmjT54JIEn+1Tpp7cvn1b9O/fXxQvXlwYGRkJCwsL4eHhIRYuXKi2iFZycrKYPHmycHZ2FoaGhqJo0aJZLrT1vvenlX1omqoQbxfQqlChgjAyMhJlypQR69atyzBN9dChQ6JNmzbC0dFRGBkZCUdHR9G1a1dx+/btDOd4f1riwYMHhYeHhzAxMRGWlpaiVatWH1xo6/1psOlTAT+28ND705cy86FpqqNGjRIODg7CxMREeHh4iJCQkEyn5e3cuVNaPOfd+5m+AFVm3j1ObGyscHJyElWrVs2wKMyIESOEnp6e2mIwmk5TTbd06VIBQBQuXDjDtgsXLkjTq95dQS/db7/9JsqWLSsMDQ2FnZ2dGDRo0AcX2srMs2fPRM+ePaWFtnr27Cn7QlsXL14U7dq1EwUKFBBKpVI4OTmJTp06iUOHDkn7vHjxQvTp00cULFhQmJubCy8vL3Hr1q0MU0yFEOKPP/4QJUqUEPr6+mrT8FJTU8XYsWNFwYIFhampqfDy8hJ379794DTVs2fPfvB+eXl5CZVKJYyNjYWLi4vo3bu3OHfunBBCiKdPnwpfX19RtmxZYWZmJlQqlahZs6bYtGlTlo9DuqFDh4qSJUtmuu3FixdiwoQJomLFisLU1FQYGxuLChUqCD8/PxEZGam278aNG4Wbm5tQKpXCxsYm04W2hBBi3bp10sJZVapUEfv3789yoa334b1pmikpKWLIkCGiUKFCQqFQZDpF9Pnz50KpVAoAGd4z0m3dulXUqVNHmJmZCTMzM1G2bFnh6+urNsVVCCGCg4NFkyZNhIWFhTAzMxOVKlUSCxcu1CieV69eiREjRghHR0dhaGgoSpUqleVCW5l59/5nNTX7/cdBk9f9xxaE6ty5s6hTp06m2z7mc1by/OOPP0Tbtm2Fk5OTUCqVwtTUVLi5uYlffvlFJCYmZjjHx6Zsf+h9PjU1VaxcuVJ4eHgIS0tLYWxsLMqXLy8mT5780dV1P3Wa6qc8JtmhECIbI5aIiGR07949lC1bFvv27ZOqXUTvi4qKgrOzM/76668vWsGgz8MEg4i0atCgQbh79y4CAwO1HQrlUuPGjcPhw4dx5swZbYdC2cAEg4iIiGSXrVkkRERERJpggkFERESyY4JBREREsmOCQURERLJjgkFERESyy9ZKngQ8eJb18sdEusBOpdR2CEQ5zjgHPwFN3AbLerzXF3/7+E65DBMMIiIiuSnYQcBHgIiIiGTHCgYREZHcFAptR6B1TDCIiIjkxi4SdpEQERGR/FjBICIikhu7SJhgEBERyY5dJOwiISIiIvmxgkFERCQ3dpEwwSAiIpIdu0jYRUJERETyYwWDiIhIbuwiYYJBREQkO3aRsIuEiIiI5McKBhERkdzYRcIEg4iISHbsImEXCREREcmPFQwiIiK5sYuECQYREZHs2EXCLhIiIiKSHysYREREcmMFgwkGERGR7PQ4BoMpFhEREcmOFQwiIiK5sYuECQYREZHsOE2VXSREREQkP1YwiIiI5MYuEiYYREREsmMXCbtIiIiISH6sYBAREcmNXSRMMIiIiGTHLhJ2kRAREZH8WMEgIiKSG7tImGAQERHJjl0k7CIhIiIi+bGCQUREJDd2kTDBICIikh27SNhFQkRERPJjBYOIiEhu7CJhgkFERCQ7JhjsIiEiIiL5sYJBREQkNw7yZIJBREQkO3aRsIuEiIiI5McKBhERkdzYRcIEg4iISHbsImEXCREREcmPCQYREZHcFAp5LxpavHgxKlWqBEtLS1haWsLd3R379u2Ttr958wa+vr4oUKAAzM3N0b59ezx+/FjtGBEREWjRogVMTU1ha2uLMWPGICUlJdsPARMMIiIimSkUClkvmipSpAh+/vlnnD9/HufOnUPDhg3Rpk0bXL9+HQAwYsQI7Nq1C5s3b8axY8fw6NEjtGvXTrp9amoqWrRogaSkJJw8eRKrV6/GqlWrMGHChOw/BkIIke1b5WMPniVqOwSiHGenUmo7BKIcZ5yDoxBN2/8p6/EStn7zybe1sbHBL7/8gg4dOqBQoUIICAhAhw4dAAC3bt1CuXLlEBISglq1amHfvn1o2bIlHj16BDs7OwDAkiVLMHbsWDx58gRGRkYan5cVDCIiIpnJXcFITExEbGys2iUxMesvvKmpqfjrr78QHx8Pd3d3nD9/HsnJyWjcuLG0T9myZVGsWDGEhIQAAEJCQlCxYkUpuQAALy8vxMbGSlUQTTHBICIikptC3ou/vz9UKpXaxd/fP9NTX716Febm5lAqlRg4cCC2b98OV1dXREVFwcjICFZWVmr729nZISoqCgAQFRWlllykb0/flh2cpkpERJTL+fn5YeTIkWptSmXmXZllypTBpUuXEBMTgy1btsDHxwfHjh37EmGqYYJBREQks+wMzNSEUqn8YELxPiMjI5QsWRIAUK1aNZw9exYLFixA586dkZSUhJcvX6pVMR4/fgx7e3sAgL29Pc6cOaN2vPRZJun7aIpdJERERDLT1iySzKSlpSExMRHVqlWDoaEhDh06JG0LDQ1FREQE3N3dAQDu7u64evUqoqOjpX0CAwNhaWkJV1fXbJ2XFQwiIiId4efnh+bNm6NYsWJ49eoVAgICcPToUezfvx8qlQp9+/bFyJEjYWNjA0tLSwwZMgTu7u6oVasWAKBp06ZwdXVFz549MWvWLERFReGnn36Cr6+vxhWUdEwwiIiIZCZ3F4mmoqOj0atXL0RGRkKlUqFSpUrYv38/mjRpAgCYN28e9PT00L59eyQmJsLLywuLFi2Sbq+vr4/du3dj0KBBcHd3h5mZGXx8fDBlypRsx8J1MLKJ62BQfsB1MCg/yMl1MFRd18p6vJgNPWU93pfAMRhEREQkO3aREBERyY2/1s4Eg4iISG7aGoORm7CLhIiIiGTHCgYREZHMWMFggkFERCQ7JhjsIiEiIqIcwAoGERGRzFjBYIJBREQkP+YX7CIhIiIi+eWbBCMpKQmhoaFISUnRdihERKTjctOvqWqLzicYCQkJ6Nu3L0xNTVG+fHlEREQAAIYMGYKff/5Zy9EREZEuYoKRDxIMPz8/XL58GUePHoWxsbHU3rhxY2zcuFGLkREREekunR/kuWPHDmzcuBG1atVSywLLly+PsLAwLUZGRES6Kq9WHeSk8wnGkydPYGtrm6E9Pj6eLwAiIsoZ/HjR/S6S6tWrY8+ePdL19KRi+fLlcHd311ZYREREOk3nKxgzZsxA8+bNcePGDaSkpGDBggW4ceMGTp48iWPHjmk7PCIi0kGskOeDCkadOnVw6dIlpKSkoGLFijhw4ABsbW0REhKCatWqaTs8IiLSQZxFkg8qGADg4uKCP/74Q9thEBER5Rs6X8Fo3LgxVq1ahdjYWG2HQkRE+QQrGPkgwShfvjz8/Pxgb2+Pjh07YufOnUhOTtZ2WEREpMOYYOSDBGPBggV4+PAhduzYATMzM/Tq1Qt2dnYYMGAAB3kSERHlEJ1PMABAT08PTZs2xapVq/D48WMsXboUZ86cQcOGDbUdGhER6SKFzJc8KF8M8kwXFRWFv/76C+vWrcOVK1fw1VdfaTskIiLSQXm1W0NOOl/BiI2NxcqVK9GkSRMULVoUixcvRuvWrXHnzh2cOnVK2+ERERHpJJ2vYNjZ2cHa2hqdO3eGv78/qlevru2QiIhIx7GCkQ8SjL///huNGjWCnp7OF2uIiCiXYIKRDxKMJk2aaDsEIiKifEcnE4yqVavi0KFDsLa2hpubW5aZ5IULF75gZERElC+wgKGbCUabNm2gVCqlf7NURUREXxI/dwCFEEJoO4i85MGzRG2HQJTj7FRKbYdAlOOMc/ArdrEhf8t6vIiFrWU93peg8yMfS5QogWfPnmVof/nyJUqUKKGFiIiISNdxqXAd7SJ51/3795GampqhPTExEf/9958WIqLM9GzXDI+jHmVob9WuM4aM/hGjfb/BlYvn1La1aNsRw74f/6VCJJLVij+W4df5c9C9Ry987/cjAGDLpo3Yt3c3bt64jvj4eBwPOQtLS0stR0qfIq8mBXLS2QTj77//V57av38/VCqVdD01NRWHDh2Cs7OzNkKjTCxcEYC0tDTp+v17dzFu2ADUa9hUamveuj18+vtK15XGxl80RiK5XLt6BVs2/4XSpcuotb958xq1Peqitkdd/Dp/jpaiI5KHziYYbdu2BfA2i/Tx8VHbZmhoiOLFi2POHP4B5xZW1jZq1zeuXQHHwkVRye1/C6MZGxvDpkDBLx0akawS4uPhN3YMJk6ehj+WLlbb1qNXbwDA2TOntRAZyYkVDB0eg5GWloa0tDQUK1YM0dHR0vW0tDQkJiYiNDQULVu21HaYlInk5GQc2r8HXi3bqv2RHj6wFx2a10P/7l9jxeIFePPmtRajJPo0M6ZNQb16nqjlXlvboVBO4o+d6W4FI114ePgn3zYxMRGJiYnvtUGaAks542TQYcTFvUJT7zZSW4Mm3rCzd0CBQoVw7+4drFg0D/9F3MdE/3lajJQoe/bt3YObN28gYOMWbYdClON0PsEAgPj4eBw7dgwRERFISkpS2zZ06NAP3s7f3x+TJ09Waxs25keMGMuBhTnpn13bUaOWBwoUspXaWrTtIP3b2aU0bAoUxNih/fHov3/hWKSoNsIkypaoyEjM+nk6lv7xJ7+k5APsIskHCcbFixfh7e2NhIQExMfHw8bGBk+fPoWpqSlsbW2zTDD8/PwwcuRItbaouJyOOH97HPkIF8+dwoQZWVcmypavCAB49F8EEwzKE27cuI7nz56hS8d2UltqairOnzuLvzasx9mLV6Gvr6/FCElOTDDyQYIxYsQItGrVCkuWLIFKpcKpU6dgaGiIHj16YNiwYVneVqlUZvim8SKZC23lpP17dsDK2gY1a9fNcr97d0IBADYFC32JsIg+W81atbBlxy61tok/+qF4iRLo07c/kwvSOTqfYFy6dAlLly6Fnp4e9PX1kZiYiBIlSmDWrFnw8fFBu3btPn4Q+iLS0tJwYM9ONGneGvoG/3tpPvrvXxwO3Iuv3OvCUqVC+N3bWLLgF1SsUg0lSpbWYsREmjMzM0epUuqvVxNTU1iprKT2p0+e4OnTp/g3IgIAcPfObZiamsHBwQEqK6svHTJ9BhYw8kGCYWhoKP1Uu62tLSIiIlCuXDmoVCr8+++/Wo6O3nXh7ClEP46EV8u2au0Ghoa4ePYUtm9chzdvXqOQrT3qNGiMbr0HaCdQohyyedNfWLLoN+l6n17dAQBTpvmjzdf8MpSXsIskH/wWSdOmTdG7d29069YN/fv3x5UrVzB06FCsXbsWL168wOnT2Ztvzt8iofyAv0VC+UFO/hZJqTH/yHq8O780k/V4X4LOroORbsaMGXBwcAAATJ8+HdbW1hg0aBCePHmCZcuWaTk6IiLSRQqFvJe8SOe7SKpX/99KkLa2tvjnH3mzSiIiovexiyQfVDCIiIjoy9P5Coabm1ummaRCoYCxsTFKliyJ3r17o0GDBlqIjoiIdBELGPmggtGsWTPcu3cPZmZmaNCgARo0aABzc3OEhYWhRo0aiIyMROPGjbFz505th0pERDpCT08h6yUv0vkKxtOnTzFq1CiMH6++vPe0adPw4MEDHDhwABMnTsTUqVPRpk2bDxyFiIiIskPnKxibNm1C165dM7R36dIFmzZtAgB07doVoaGhXzo0IiLSUZxFkg8SDGNjY5w8eTJD+8mTJ2FsbAzg7QqS6f8mIiKiz6fzXSRDhgzBwIEDcf78edSoUQMAcPbsWSxfvhw//PADAGD//v2oUqWKFqMkIiJdwmmq+WAlTwBYv349fvvtN6kbpEyZMhgyZAi6desGAHj9+rU0q+RjuJIn5QdcyZPyg5xcybPi+EBZj3d1ahNZj/cl6HwFAwC6d++O7t27f3C7iYnJF4yGiIhI9+n8GAwAePnypdQl8vz5cwDAhQsX8PDhQy1HRkREukihUMh60ZS/vz9q1KgBCwsL2Nraom3bthkmMdSvXz/D8QcOHKi2T0REBFq0aAFTU1PY2tpizJgxSElJydZjoPMVjCtXrqBx48ZQqVS4f/8++vXrBxsbG2zbtg0RERFYs2aNtkMkIiIdo60xGMeOHYOvry9q1KiBlJQU/PDDD2jatClu3LgBMzMzab/+/ftjypQp0nVTU1Pp36mpqWjRogXs7e1x8uRJREZGolevXjA0NMSMGTM0jkXnE4yRI0eid+/emDVrFiwsLKR2b29vaQwGERGRLnj/97ZWrVoFW1tbnD9/HvXq1ZPaTU1NYW9vn+kxDhw4gBs3buDgwYOws7NDlSpVMHXqVIwdOxaTJk2CkZGRRrHofBfJ2bNn8e2332ZoL1y4MKKiorQQERER6Tq518FITExEbGys2iUx8eOTDmJiYgAANjY2au3r169HwYIFUaFCBfj5+SEhIUHaFhISgooVK8LOzk5q8/LyQmxsLK5fv67xY6DzCYZSqURsbGyG9tu3b6NQoUJaiIiIiHSd3GMw/P39oVKp1C7+/v5ZxpCWlobhw4fDw8MDFSpUkNq7deuGdevW4ciRI/Dz88PatWvRo0cPaXtUVJRacgFAup6dL+Y630XSunVrTJkyRVq1U6FQICIiAmPHjkX79u21HB0REdHH+fn5YeTIkWptSmXW08l9fX1x7do1BAcHq7UPGDBA+nfFihXh4OCARo0aISwsDC4uLrLFrPMVjDlz5iAuLg62trZ4/fo1PD09UbJkSZibm2P69OnaDo+IiHSQ3F0kSqUSlpaWapesEozBgwdj9+7dOHLkCIoUKZJlrDVr1gQA3L17FwBgb2+Px48fq+2Tfv1D4zYyo/MVDJVKhcDAQJw4cQKXL19GXFwcqlatisaNG2s7NCIi0lHamkUihMCQIUOwfft2HD16FM7Ozh+9zaVLlwAADg4OAAB3d3dMnz4d0dHRsLW1BQAEBgbC0tISrq6uGsei8wkGABw6dAiHDh1CdHQ00tLScOvWLQQEBAAA/vzzTy1HR0REJA9fX18EBARg586dsLCwkMZMqFQqmJiYICwsDAEBAfD29kaBAgVw5coVjBgxAvXq1UOlSpUAAE2bNoWrqyt69uyJWbNmISoqCj/99BN8fX0/2i3zLp1PMCZPnowpU6agevXqcHBw4PrwRESU47T1UbN48WIAbxfTetfKlSvRu3dvGBkZ4eDBg5g/fz7i4+NRtGhRtG/fHj/99JO0r76+Pnbv3o1BgwbB3d0dZmZm8PHxUVs3QxM6/1skDg4OmDVrFnr27CnL8fhbJJQf8LdIKD/Iyd8iqTH9qKzHO/tjfVmP9yXo/CDPpKQk1K5dW9thEBER5Ss6n2D069dPGm9BRET0Jcg9iyQv0vkxGG/evMGyZctw8OBBVKpUCYaGhmrb586dq6XIiIhIV3G8Xz5IMK5cuYIqVaoAAK5du6a2jS8AIiKinKHzCcaRI0e0HQIREeUz/P6aDxIMIiKiL40V8nwwyJOIiIi+PFYwiIiIZMYCBhMMIiIi2bGLhF0kRERElANyVYIRFBSElJSUDO0pKSkICgrSQkRERETZx4W2clmC0aBBAzx//jxDe0xMDBo0aKCFiIiIiLJPoVDIesmLclWCIYTI9IF89uwZzMzMtBARERERfYpcMcizXbt2AN5mfL1791b7vfnU1FRcuXKFP1hGRER5Rl6tOsgpVyQYKpUKwNsKhoWFBUxMTKRtRkZGqFWrFvr376+t8IiIiLKF+UUuSTBWrlwJAChevDhGjx7N7hAiIqI8LlckGOkmTpyo7RCIiIg+G7tIctkgz8ePH6Nnz55wdHSEgYEB9PX11S5ERER5Aaep5rIKRu/evREREYHx48fDwcGBGSAREVEelasSjODgYBw/fhxVqlTRdihERESfjF+Qc1mCUbRoUQghtB0GERHRZ2F+kcvGYMyfPx/jxo3D/fv3tR0KERERfYZcVcHo3LkzEhIS4OLiAlNTUxgaGqptz2wZcSIiotxGjyWM3JVgzJ8/X9shEBERfTbmF7kswfDx8dF2CERERCSDXDUGAwDCwsLw008/oWvXroiOjgYA7Nu3D9evX9dyZERERJrhr6nmsgTj2LFjqFixIk6fPo1t27YhLi4OAHD58mWu8klERHmGnkLeS16UqxKMcePGYdq0aQgMDISRkZHU3rBhQ5w6dUqLkREREVF25KoxGFevXkVAQECGdltbWzx9+lQLEREREWVfXu3WkFOuqmBYWVkhMjIyQ/vFixdRuHBhLURERESUffwtklyWYHTp0gVjx45FVFQUFAoF0tLScOLECYwePRq9evXSdnhERESkoVyVYMyYMQNly5ZF0aJFERcXB1dXV9SrVw+1a9fGTz/9pO3wiIiINKKQ+b+8SCFy4Y9/RERE4Nq1a4iLi4ObmxtKlSql7ZAkD54lajsEohxnp1JqOwSiHGecg6MQWy87K+vx/h5QQ9bjfQm5apBnumLFiqFYsWLaDoOIiIg+Ua5KMIQQ2LJlC44cOYLo6GikpaWpbd+2bZuWIiMiItIcZ5HksgRj+PDhWLp0KRo0aAA7Ozs+QURElCfx4yuXJRhr167Ftm3b4O3tre1QiIiI6DPkqgRDpVKhRIkS2g6DiIjos/Dn2nPZNNVJkyZh8uTJeP36tbZDISIi+mRcaCuXVTA6deqEDRs2wNbWFsWLF4ehoaHa9gsXLmgpMiIiIsqOXJVg+Pj44Pz58+jRowcHeRIRUZ7Fz69clmDs2bMH+/fvR506dbQdChER0SdjfpHLxmAULVoUlpaW2g6DiIiIPlOuSjDmzJmD77//Hvfv39d2KERERJ9MT6GQ9ZIX5aoukh49eiAhIQEuLi4wNTXNMMjz+fPnWoqMiIhIc3kzJZBXrkow5s+fr+0QiIiISAa5KsHw8fHRdghERESfjbNIckGCERsbKw3sjI2NzXJfDgAlIqK8QI/5hfYTDGtra0RGRsLW1hZWVlaZZn1CCCgUCqSmpmohQiIiIsourScYhw8fho2NDQDgyJEjWo6GiIjo87GLJBckGJ6entK/nZ2dUbRo0QxPjBAC//7775cOjYiI6JMwv8hl62A4OzvjyZMnGdqfP38OZ2dnLUREREREn0LrFYx3pY+1eF9cXByMjY21EBEREVH2sYsklyQYI0eOBPD2CRk/fjxMTU2lbampqTh9+jSqVKmipeiIiIiyR1uzSPz9/bFt2zbcunULJiYmqF27NmbOnIkyZcpI+7x58wajRo3CX3/9hcTERHh5eWHRokWws7OT9omIiMCgQYNw5MgRmJubw8fHB/7+/jAw0DxtyBUJxsWLFwG8rWBcvXoVRkZG0jYjIyNUrlwZo0eP1lZ4REREecKxY8fg6+uLGjVqICUlBT/88AOaNm2KGzduwMzMDAAwYsQI7NmzB5s3b4ZKpcLgwYPRrl07nDhxAsDbL/YtWrSAvb09Tp48icjISPTq1QuGhoaYMWOGxrEohBAiR+7lJ+jTpw8WLFiQq9e7ePAsUdshEOU4O5VS2yEQ5TjjHPyK3eevq7Ieb2WXip90uydPnsDW1hbHjh1DvXr1EBMTg0KFCiEgIAAdOnQAANy6dQvlypVDSEgIatWqhX379qFly5Z49OiRVNVYsmQJxo4diydPnqgVAbKSqwZ5rly5MlcnF0RERJpQyHxJTExEbGys2iUx8eNfeGNiYgBAWg7i/PnzSE5ORuPGjaV9ypYti2LFiiEkJAQAEBISgooVK6p1mXh5eSE2NhbXr1/X+DHIVQlGfHw8xo8fj9q1a6NkyZIoUaKE2oWIiCg/8vf3h0qlUrv4+/tneZu0tDQMHz4cHh4eqFChAgAgKioKRkZGsLKyUtvXzs4OUVFR0j7vJhfp29O3aSpXjMFI169fPxw7dgw9e/aEg4MDR+ESEVGeJPdPrPv5+UkTItIplVl3Zfr6+uLatWsIDg6WNRZN5aoEY9++fdizZw88PDy0HQoREdEnk/v7sVKp/GhC8a7Bgwdj9+7dCAoKQpEiRaR2e3t7JCUl4eXLl2pVjMePH8Pe3l7a58yZM2rHe/z4sbRNU7mqi8Ta2lrqJyIiIqLsEUJg8ODB2L59Ow4fPpxhkcpq1arB0NAQhw4dktpCQ0MREREBd3d3AIC7uzuuXr2K6OhoaZ/AwEBYWlrC1dVV41hyVYIxdepUTJgwAQkJCdoOhYiI6JMpFApZL5ry9fXFunXrEBAQAAsLC0RFRSEqKgqvX78GAKhUKvTt2xcjR47EkSNHcP78efTp0wfu7u6oVasWAKBp06ZwdXVFz549cfnyZezfvx8//fQTfH19s1VFyVXTVN3c3BAWFgYhBIoXLw5DQ0O17RcuXNBSZP/DaaqUH3CaKuUHOTlN9dstms+20MTSDuU12u9DycjKlSvRu3dvAP9baGvDhg1qC2292/3x4MEDDBo0CEePHoWZmRl8fHzw888/572FttK1bdtW2yEQERHlWZrUDIyNjfH777/j999//+A+Tk5O2Lt372fFkqsSjIkTJ2o7BCIios8m9yySvChXjcEAgJcvX2L58uXw8/PD8+fPAbztGnn48KGWIyMiItKMQiHvJS/KVRWMK1euoHHjxlCpVLh//z769+8PGxsbbNu2DREREVizZo22QyQiIiIN5KoKxsiRI9G7d2/cuXNH7efZvb29ERQUpMXIiIiINKetWSS5Sa6qYJw9exZLly7N0F64cOFsLU+ak0yMclVORpQjrGsM1nYIRDnu9cXfcuzY/KTIZY+BUqlEbGxshvbbt2+jUKFCWoiIiIiIPkWuSjBat26NKVOmIDk5GcDbElNERATGjh2L9u3bazk6IiIizbCLJJclGHPmzEFcXBxsbW3x+vVreHp6omTJkrCwsMD06dO1HR4REZFG9BTyXvKiXDUGQ6VSITAwECdOnMDly5cRFxeHqlWrqv1uPREREeV+uSrBSOfh4cFfVCUiojwrr1Yd5JQrukhCQkKwe/dutbY1a9bA2dkZtra2GDBgABIT+RsgRESUN3AMRi5JMKZMmYLr1//3wzBXr15F37590bhxY4wbNw67du2Cv7+/FiMkIiKi7MgVCcalS5fQqFEj6fpff/2FmjVr4o8//sDIkSPx66+/YtOmTVqMkIiISHMc5JlLxmC8ePECdnZ20vVjx46hefPm0vUaNWrg33//1UZoRERE2ZZHezVklSsqGHZ2dggPDwcAJCUl4cKFC6hVq5a0/dWrVzA0NNRWeERERJRNuaKC4e3tjXHjxmHmzJnYsWMHTE1NUbduXWn7lStX4OLiosUIiYiINMefa88lCcbUqVPRrl07eHp6wtzcHKtXr4aRkZG0/c8//0TTpk21GCEREZHmckX3gJbligSjYMGCCAoKQkxMDMzNzaGvr6+2ffPmzTA3N9dSdERERJRduSLBSKdSqTJtt7Gx+cKREBERfTr2kOSyBIOIiEgXcAwGu4mIiIgoB7CCQUREJDMWMJhgEBERyS6vrr4pJ60nGH///bfG+7Zu3ToHIyEiIiK5aD3BaNu2rUb7KRQKpKam5mwwREREMuAgz1yQYKSlpWk7BCIiIlkxv+AsEiIiIsoBWq9gvC8+Ph7Hjh1DREQEkpKS1LYNHTpUS1ERERFpjoM8c1mCcfHiRXh7eyMhIQHx8fGwsbHB06dPYWpqCltbWyYYRESUJyjADCNXdZGMGDECrVq1wosXL2BiYoJTp07hwYMHqFatGmbPnq3t8IiIiEhDuSrBuHTpEkaNGgU9PT3o6+sjMTERRYsWxaxZs/DDDz9oOzwiIiKN6CnkveRFuSrBMDQ0hJ7e25BsbW0REREB4O2PoP3777/aDI2IiEhjTDBy2RgMNzc3nD17FqVKlYKnpycmTJiAp0+fYu3atahQoYK2wyMiIiIN5aoKxowZM+Dg4AAAmD59OqytrTFo0CA8efIEy5Yt03J0REREmlEoFLJe8qJcVcGoXr269G9bW1v8888/WoyGiIjo0+TVbg055aoKBhEREemGXFXBcHZ2zrIUdO/evS8YDRER0afJo70asspVCcbw4cPVricnJ+PixYv4559/MGbMGO0ERURElE38sbNclmAMGzYs0/bff/8d586d+8LREBER0afKE2Mwmjdvjq1bt2o7DCIiIo1wHYxcVsH4kC1btsDGxkbbYRAREWmEPSS5LMFwc3NTG+QphEBUVBSePHmCRYsWaTEyIiIiyo5clWC0adNGLcHQ09NDoUKFUL9+fZQtW1aLkREREWlOj7+mmrsSjEmTJmk7BCIios/GLpJcNshTX18f0dHRGdqfPXsGfX19LUREREREnyJXVTCEEJm2JyYmwsjI6AtHQ0RE9Gny6swPOeWKBOPXX38F8PbHYZYvXw5zc3NpW2pqKoKCgjgGg4iI8gwutJVLEox58+YBeFvBWLJkiVp3iJGREYoXL44lS5ZoKzwiIiLKplyRYISHhwMAGjRogG3btsHa2lrLEREREX06FjBySYKR7siRI9oOgYiI6LOxiySXzSJp3749Zs6cmaF91qxZ6NixoxYiIiIiok+RqxKMoKAgeHt7Z2hv3rw5goKCtBARERFR9ikU8l7yolzVRRIXF5fpdFRDQ0PExsZqISIiIqLsy1Xf3rUkVz0GFStWxMaNGzO0//XXX3B1ddVCRERERHlLUFAQWrVqBUdHRygUCuzYsUNte+/evaFQKNQuzZo1U9vn+fPn6N69OywtLWFlZYW+ffsiLi4uW3HkqgrG+PHj0a5dO4SFhaFhw4YAgEOHDmHDhg3YvHmzlqMjIiLSjEKL/Rrx8fGoXLkyvvnmG7Rr1y7TfZo1a4aVK1dK15VKpdr27t27IzIyEoGBgUhOTkafPn0wYMAABAQEaBxHrkowWrVqhR07dmDGjBnYsmULTExMUKlSJRw8eBCenp7aDo+IiEgj2hw20bx5czRv3jzLfZRKJezt7TPddvPmTfzzzz84e/YsqlevDgBYuHAhvL29MXv2bDg6OmoUR67qIgGAFi1a4MSJE4iPj8fTp09x+PBheHp64tq1a9oOjYiISCsSExMRGxurdklMTPzk4x09ehS2trYoU6YMBg0ahGfPnknbQkJCYGVlJSUXANC4cWPo6enh9OnTGp8j1yUY73r16hWWLVuGr776CpUrV9Z2OERERBrRUyhkvfj7+0OlUqld/P39Pym2Zs2aYc2aNTh06BBmzpyJY8eOoXnz5khNTQUAREVFwdbWVu02BgYGsLGxQVRUlMbnyVVdJOmCgoKwfPlybNu2DY6OjmjXrh1+//13bYdFRESkEbm7SPz8/DBy5Ei1tvfHTWiqS5cu0r8rVqyISpUqwcXFBUePHkWjRo0+K8535ZoEIyoqCqtWrcKKFSsQGxuLTp06ITExETt27OAMEiIiyteUSuUnJxQfU6JECRQsWBB3795Fo0aNYG9vj+joaLV9UlJS8Pz58w+O28hMrugiadWqFcqUKYMrV65g/vz5ePToERYuXKjtsIiIiD5JXlpo67///sOzZ8/g4OAAAHB3d8fLly9x/vx5aZ/Dhw8jLS0NNWvW1Pi4uaKCsW/fPgwdOhSDBg1CqVKltB0OERHRZ9HmNNW4uDjcvXtXuh4eHo5Lly7BxsYGNjY2mDx5Mtq3bw97e3uEhYXh+++/R8mSJeHl5QUAKFeuHJo1a4b+/ftjyZIlSE5OxuDBg9GlSxeNZ5AAuaSCERwcjFevXqFatWqoWbMmfvvtNzx9+lTbYREREeU5586dg5ubG9zc3AAAI0eOhJubGyZMmAB9fX1cuXIFrVu3RunSpdG3b19Uq1YNx48fV+uCWb9+PcqWLYtGjRrB29sbderUwbJly7IVh0IIIWS9Z58hPj4eGzduxJ9//okzZ84gNTUVc+fOxTfffAMLCwtthwcAiH6VrO0QiHKcU70R2g6BKMe9vvhbjh1748WHsh6vs1thWY/3JeSKCkY6MzMzfPPNNwgODsbVq1cxatQo/Pzzz7C1tUXr1q21HR4REZFG3l+K+3MveVGuSjDeVaZMGcyaNQv//fcfNmzYoO1wiIiIKBtyxSDPrOjr66Nt27Zo27attkMhIiLSSN6sOcgr1ycYREREeU1e7daQU67tIiEiIqK8ixUMIiIimfHbOxMMIiIi2bGLhEkWERER5QBWMIiIiGTG+gUTDCIiItmxh4RdJERERJQDWMEgIiKSmR47SZhgEBERyY1dJPmki+T48ePo0aMH3N3d8fDh21+4W7t2LYKDg7UcGRERkW7S+QRj69at8PLygomJCS5evIjExEQAQExMDGbMmKHl6IiISBcpZP4vL9L5BGPatGlYsmQJ/vjjDxgaGkrtHh4euHDhghYjIyIiXaVQyHvJi3Q+wQgNDUW9evUytKtUKrx8+fLLB0RERJQP6HyCYW9vj7t372ZoDw4ORokSJbQQERER6To9KGS95EU6n2D0798fw4YNw+nTp6FQKPDo0SOsX78eo0ePxqBBg7QdHhER6SB2keSDaarjxo1DWloaGjVqhISEBNSrVw9KpRKjR4/GkCFDtB0eERGRTlIIIYS2g/gSkpKScPfuXcTFxcHV1RXm5uafdJzoV8kyR0aU+zjVG6HtEIhy3OuLv+XYsQ/cfCLr8ZqWKyTr8b4Ena9grFu3Du3atYOpqSlcXV21HQ4REeUDeXVqqZx0fgzGiBEjYGtri27dumHv3r1ITU3VdkhEREQ6T+cTjMjISPz1119QKBTo1KkTHBwc4Ovri5MnT2o7NCIi0lF6CnkveZHOJxgGBgZo2bIl1q9fj+joaMybNw/3799HgwYN4OLiou3wiIhIB3Elz3wwBuNdpqam8PLywosXL/DgwQPcvHlT2yERERHpJJ2vYABAQkIC1q9fD29vbxQuXBjz58/H119/jevXr2s7NCIi0kFcByMfVDC6dOmC3bt3w9TUFJ06dcL48ePh7u6u7bCIiEiH5dVuDTnpfIKhr6+PTZs2wcvLC/r6+toOh4iIKF/Q+QRj/fr12g6BiIjymbw680NOOplg/PrrrxgwYACMjY3x66+/Zrnv0KFDv1BURESUX7CLREeXCnd2dsa5c+dQoEABODs7f3A/hUKBe/fuZevYXCo8ZzyJfozFC+fi9MlgvHnzBkWKFIPfxKko61oBAPDn0t9x6MA/iH4cBQNDQ5Qp54r+3w1F+QqVtBy5buJS4Z+vf8c66N+hLpwcbQAAN+9FYcayfThw4kaGfXf8NgheHuXRacQy7Dp6RWqf830H1KpcAuVLOuBW+GPU6vLzF4s/P8jJpcKP334h6/HqlraW9Xhfgk5WMMLDwzP9N+VOr2Jj8F3fnnCr/hV+WbAEVtbW+O/fB7CwtJT2KepUHCO+/wGOhYsgMTERGwPWYJTvAGzYsRfW1jZajJ4ocw8fv8T4hTtxN+IJFFCgR6ua2DxvAGp1+Rk370VJ+w3p3gBZfc1bs/MUalR0QoVShb9A1CSXvDrzQ046P011ypQpSEhIyND++vVrTJkyRQsR0fvWr/4Ttnb2+GHiNLhWqAjHwkXwVS0PFC5STNqnSbMWqF7THY5FisLZpSSGjPge8fFxCLtzW4uRE33Y3qBr2B98A2ERT3A3IhqTft+FuIREfFXpf1XVSqULY1jPhhg4aV2mxxg1awuWbgpC+H/PvlTYJBOFzJe8SOcTjMmTJyMuLi5De0JCAiZPnqyFiOh9wUFHUKZceYwfOxKtmtTDN9064O/tWz64f3JyMv7evhnm5hYoWbrMF4yU6NPo6SnQ0asazEyMcPrK26qqibEhVvn3xvCfN+Hxs1dajpBIfjrZRfIuIQQUmdSqLl++DBubrEvriYmJSExMVG9L0oNSqZQ1xvwu8uF/2Ll1Izp174Weffrj1o1rWDDbH4aGhmjeso2034njRzH5hzF48+YNChQshLm/L4OVVd7rl6T8o3xJRxxdPQrGRgaIe52IzqP+wK3/7x6ZNao9Tl0Ox+6jV7UcJeUEPfaR6G6CYW1tDYVCAYVCgdKlS6slGampqYiLi8PAgQOzPIa/v3+GKsfocT9hzA8TciTm/CotLQ1lXcvjW9/hAIDSZcvhXtgd7Ny6SS3BqFr9K/wZsBUxL19g1/YtmOg3GktXBcDapoCWIifK2u37j1Gziz9U5ib4urEb/pjSE037LYBL0UKo/1VpDtrUYUwvdDjBmD9/PoQQ+OabbzB58mSoVCppm5GREYoXL/7RFT39/PwwcuRItbaYJJ3vVfriChQsBCdn9R+ec3IugWOHD6q1mZiYokjRYihStBjKV6yMrl97Y/fObejZp/+XDJdIY8kpqbj371MAwMWb/6Ja+WLw7VofbxKTUaJIQUQF/aK2/4bZ/XDiYhi8+i/QRrhEstLZBMPHxwfA2ymrtWvXhqGhYbaPoVQqM3SHvOE0VdlVrOyGfx/cV2v798ED2Ds4ZHm7tLQ0JCcl5WBkRPLSUyigNDLAtCV7sHL7SbVt57f8iO/nbMWeY9e0FB3JiiUM3UwwYmNjYfn/Uxzd3Nzw+vVrvH79OtN9Ld+ZCkna0albTwz6pifW/LkMDZs0w83rV7Fr+xaM+XEiAOD16wSs+XMZ6tRrgAIFCyHm5Qts27QBT59Eo0FjLy1HT5S5KUNaY/+J6/g38gUszIzRuXl11KteCq2+W4THz15lOrDz38gXePDofzNGShQtCHMTJewKWsJEaYhKpd9OVb15LwrJKalf7L5Q9nGhLR1NMKytrREZGQlbW1tYWVllOsgzffBnair/SLWtXPmKmD57Ppb9tgCrly+Bg2NhDBk1Fk2btwQA6OnpI+J+OH7a/TdiXr6ApcoK5Vwr4Lc/VsPZpaSWoyfKXCEbc6yY2gv2BS0RE/cG1+48RKvvFuHw6VsaH2PxhO6oV72UdP30Rj8AQBnvCYiIfC57zERy0smVPI8dOwYPDw8YGBjg2LFjWe7r6emZrWNzJU/KD7iSJ+UHObmS55l7MbIe76sSqo/vlMvoZAXj3aQhuwkEERHR52IHST5YaOuff/5BcHCwdP33339HlSpV0K1bN7x4Ie9a8URERPSWzicYY8aMQWxsLADg6tWrGDlyJLy9vREeHp5hCioREZEsuFa4bnaRvCs8PByurq4AgK1bt6JVq1aYMWMGLly4AG9vby1HR0REuoizSPJBBcPIyEj6sbODBw+iadOmAAAbGxupskFERETy0vkKRp06dTBy5Eh4eHjgzJkz2LhxIwDg9u3bKFKkiJajIyIiXcSfIskHFYzffvsNBgYG2LJlCxYvXozChd8uVLNv3z40a9ZMy9ERERHpJp1cByMncR0Myg+4DgblBzm5DsaF+/J2wVctnvdWndb5LhLg7a+n7tixAzdv3gQAlC9fHq1bt4a+vr6WIyMiIp3ELhLdTzDu3r0Lb29vPHz4EGXKlAHw9mfYixYtij179sDFxeUjRyAiIqLs0vkxGEOHDoWLiwv+/fdfXLhwARcuXEBERAScnZ0xdOhQbYdHREQ6SCHzf3mRzicYx44dw6xZs2BjYyO1FShQAD///PNHf6eEiIjoUygU8l6yIygoCK1atYKjoyMUCgV27Nihtl0IgQkTJsDBwQEmJiZo3Lgx7ty5o7bP8+fP0b17d1haWsLKygp9+/ZFXFxctuLQ+QRDqVTi1auMP4scFxcHIyMjLURERESUc+Lj41G5cmX8/vvvmW6fNWsWfv31VyxZsgSnT5+GmZkZvLy88ObNG2mf7t274/r16wgMDMTu3bsRFBSEAQMGZCsOnZ9F0qtXL1y4cAErVqzAV199BQA4ffo0+vfvj2rVqmHVqlXZOh5nkVB+wFkklB/k5CySyxEZv9h+jsrFLD7pdgqFAtu3b0fbtm0BvK1eODo6YtSoURg9ejQAICYmBnZ2dli1ahW6dOmCmzdvwtXVFWfPnkX16tUBvP1dL29vb/z3339wdHTU6Nw6X8H49ddf4eLiAnd3dxgbG8PY2Bi1a9dGyZIlsWDBAm2HR0REukjm3yJJTExEbGys2iUxMTHbYYWHhyMqKgqNGzeW2lQqFWrWrImQkBAAQEhICKysrKTkAgAaN24MPT09nD59WuNz6XyCYWVlhZ07d+L27dvYvHkzNm/ejNu3b2P79u1QqVTaDo+IiOij/P39oVKp1C7+/v7ZPk5UVBQAwM7OTq3dzs5O2hYVFQVbW1u17QYGBrCxsZH20YTOT1MFgBUrVmDevHnSIJZSpUph+PDh6Nevn5YjIyIiXST3zA8/P78MvwCuVCplPYfcdD7BmDBhAubOnYshQ4bA3d0dwNvyz4gRIxAREYEpU6ZoOUIiItI1cv8WiVKplCWhsLe3BwA8fvwYDg4OUvvjx49RpUoVaZ/o6Gi126WkpOD58+fS7TWh8wnG4sWL8ccff6Br165SW+vWrVGpUiUMGTKECQYREeUbzs7OsLe3x6FDh6SEIjY2FqdPn8agQYMAAO7u7nj58iXOnz+PatWqAQAOHz6MtLQ01KxZU+Nz6XyCkZycrDZQJV21atWQkpKihYiIiEjXaXNprLi4ONy9e1e6Hh4ejkuXLsHGxgbFihXD8OHDMW3aNJQqVQrOzs4YP348HB0dpZkm5cqVQ7NmzdC/f38sWbIEycnJGDx4MLp06aLxDBIgHwzy7NmzJxYvXpyhfdmyZejevbsWIiIiIp0n8yyS7Dh37hzc3Nzg5uYGABg5ciTc3NwwYcIEAMD333+PIUOGYMCAAahRowbi4uLwzz//wNjYWDrG+vXrUbZsWTRq1Aje3t6oU6cOli1blr2HQNfXwRgyZAjWrFmDokWLolatWgDeroMRERGBXr16wdDQUNp37ty5Hz0e18Gg/IDrYFB+kJPrYFx7mL1VLz+mQmFzWY/3Jeh8F8m1a9dQtWpVAEBYWBgAoGDBgihYsCCuXbsm7aeQe0QOERHlW3n190PkpPMJxpEjR7QdAhER5TP8zpoPxmAQERHRl6fzFQwiIqIvjQUMJhhERETyY4bBLhIiIiKSHysYREREMuMsEiYYREREsuMsEnaREBERUQ5gBYOIiEhmLGAwwSAiIpIfMwx2kRAREZH8WMEgIiKSGWeRMMEgIiKSHWeRsIuEiIiIcgArGERERDJjAYMJBhERkfyYYbCLhIiIiOTHCgYREZHMOIuECQYREZHsOIuEXSRERESUA1jBICIikhkLGEwwiIiI5McMg10kREREJD9WMIiIiGTGWSRMMIiIiGTHWSTsIiEiIqIcwAoGERGRzFjAYIJBREQkO3aRsIuEiIiIcgArGERERLJjCYMJBhERkczYRcIuEiIiIsoBrGAQERHJjAUMJhhERESyYxcJu0iIiIgoB7CCQUREJDP+FgkTDCIiIvkxv2AXCREREcmPFQwiIiKZsYDBBIOIiEh2nEXCLhIiIiLKAaxgEBERyYyzSJhgEBERyY/5BbtIiIiISH6sYBAREcmMBQwmGERERLLjLBJ2kRAREVEOYAWDiIhIZpxFwgSDiIhIduwiYRcJERER5QAmGERERCQ7dpEQERHJjF0krGAQERHpjEmTJkGhUKhdypYtK21/8+YNfH19UaBAAZibm6N9+/Z4/PhxjsTCBIOIiEhmCpn/y47y5csjMjJSugQHB0vbRowYgV27dmHz5s04duwYHj16hHbt2sl99wGwi4SIiEh22uwiMTAwgL29fYb2mJgYrFixAgEBAWjYsCEAYOXKlShXrhxOnTqFWrVqyRoHKxhERES5XGJiImJjY9UuiYmJme57584dODo6okSJEujevTsiIiIAAOfPn0dycjIaN24s7Vu2bFkUK1YMISEhssfMBIOIiEhmCpkv/v7+UKlUahd/f/8M561ZsyZWrVqFf/75B4sXL0Z4eDjq1q2LV69eISoqCkZGRrCyslK7jZ2dHaKiomR/DNhFQkREJDeZu0j8/PwwcuRItTalUplhv+bNm0v/rlSpEmrWrAknJyds2rQJJiYm8gb1EaxgEBER5XJKpRKWlpZql8wSjPdZWVmhdOnSuHv3Luzt7ZGUlISXL1+q7fP48eNMx2x8LiYYREREMtPmLJJ3xcXFISwsDA4ODqhWrRoMDQ1x6NAhaXtoaCgiIiLg7u4ux91Wwy4SIiIimWlrFsno0aPRqlUrODk54dGjR5g4cSL09fXRtWtXqFQq9O3bFyNHjoSNjQ0sLS0xZMgQuLu7yz6DBGCCQUREpDP+++8/dO3aFc+ePUOhQoVQp04dnDp1CoUKFQIAzJs3D3p6emjfvj0SExPh5eWFRYsW5UgsCiGEyJEj66joV8naDoEoxznVG6HtEIhy3OuLv+XYsROS5P1oNTXKe2uPs4JBREQkt7yXD8iOgzyJiIhIdqxgEBERyexzZn7oCiYYREREMuPPtbOLhIiIiHIAZ5FQrpaYmAh/f3/4+flptGodUV7E1znpIiYYlKvFxsZCpVIhJiYGlpaW2g6HKEfwdU66iF0kREREJDsmGERERCQ7JhhEREQkOyYYlKsplUpMnDiRA99Ip/F1TrqIgzyJiIhIdqxgEBERkeyYYBAREZHsmGAQERGR7JhgkM6YNGkSqlSpou0wiDR29OhRKBQKvHz5Msv9ihcvjvnz53+RmIjkwkGelCcpFAps374dbdu2ldri4uKQmJiIAgUKaC8womxISkrC8+fPYWdnB4VCgVWrVmH48OEZEo4nT57AzMwMpqam2gmU6BPw11RJZ5ibm8Pc3FzbYRBpzMjICPb29h/dr1ChQl8gGiJ5sYuEsqV+/foYOnQovv/+e9jY2MDe3h6TJk2Str98+RL9+vVDoUKFYGlpiYYNG+Ly5ctqx5g2bRpsbW1hYWGBfv36Ydy4cWpdG2fPnkWTJk1QsGBBqFQqeHp64sKFC9L24sWLAwC+/vprKBQK6fq7XSQHDhyAsbFxhm+Cw4YNQ8OGDaXrwcHBqFu3LkxMTFC0aFEMHToU8fHxn/04ke6oX78+Bg8ejMGDB0OlUqFgwYIYP3480ou/L168QK9evWBtbQ1TU1M0b94cd+7ckW7/4MEDtGrVCtbW1jAzM0P58uWxd+9eAOpdJEePHkWfPn0QExMDhUIBhUIh/W2920XSrVs3dO7cWS3G5ORkFCxYEGvWrAEApKWlwd/fH87OzjAxMUHlypWxZcuWHH6kiNQxwaBsW716NczMzHD69GnMmjULU6ZMQWBgIACgY8eOiI6Oxr59+3D+/HlUrVoVjRo1wvPnzwEA69evx/Tp0zFz5kycP38exYoVw+LFi9WO/+rVK/j4+CA4OBinTp1CqVKl4O3tjVevXgF4m4AAwMqVKxEZGSldf1ejRo1gZWWFrVu3Sm2pqanYuHEjunfvDgAICwtDs2bN0L59e1y5cgUbN25EcHAwBg8eLP+DRnna6tWrYWBggDNnzmDBggWYO3culi9fDgDo3bs3zp07h7///hshISEQQsDb2xvJyckAAF9fXyQmJiIoKAhXr17FzJkzM6201a5dG/Pnz4elpSUiIyMRGRmJ0aNHZ9ive/fu2LVrF+Li4qS2/fv3IyEhAV9//TUAwN/fH2vWrMGSJUtw/fp1jBgxAj169MCxY8dy4uEhypwgygZPT09Rp04dtbYaNWqIsWPHiuPHjwtLS0vx5s0bte0uLi5i6dKlQgghatasKXx9fdW2e3h4iMqVK3/wnKmpqcLCwkLs2rVLagMgtm/frrbfxIkT1Y4zbNgw0bBhQ+n6/v37hVKpFC9evBBCCNG3b18xYMAAtWMcP35c6OnpidevX38wHspfPD09Rbly5URaWprUNnbsWFGuXDlx+/ZtAUCcOHFC2vb06VNhYmIiNm3aJIQQomLFimLSpEmZHvvIkSMCgPSaXLlypVCpVBn2c3JyEvPmzRNCCJGcnCwKFiwo1qxZI23v2rWr6Ny5sxBCiDdv3ghTU1Nx8uRJtWP07dtXdO3aNdv3n+hTsYJB2VapUiW16w4ODoiOjsbly5cRFxeHAgUKSOMhzM3NER4ejrCwMABAaGgovvrqK7Xbv3/98ePH6N+/P0qVKgWVSgVLS0vExcUhIiIiW3F2794dR48exaNHjwC8rZ60aNECVlZWAIDLly9j1apVarF6eXkhLS0N4eHh2ToX6bZatWpBoVBI193d3XHnzh3cuHEDBgYGqFmzprStQIECKFOmDG7evAkAGDp0KKZNmwYPDw9MnDgRV65c+axYDAwM0KlTJ6xfvx4AEB8fj507d0qVubt37yIhIQFNmjRRe22vWbNG+jsk+hI4yJOyzdDQUO26QqFAWloa4uLi4ODggKNHj2a4TfqHuiZ8fHzw7NkzLFiwAE5OTlAqlXB3d0dSUlK24qxRowZcXFzw119/YdCgQdi+fTtWrVolbY+Li8O3336LoUOHZrhtsWLFsnUuog/p168fvLy8sGfPHhw4cAD+/v6YM2cOhgwZ8snH7N69Ozw9PREdHY3AwECYmJigWbNmACB1nezZsweFCxdWux1/64S+JCYYJJuqVasiKioKBgYG0sDL95UpUwZnz55Fr169pLb3x1CcOHECixYtgre3NwDg33//xdOnT9X2MTQ0RGpq6kdj6t69O9avX48iRYpAT08PLVq0UIv3xo0bKFmypKZ3kfKp06dPq11PHxvk6uqKlJQUnD59GrVr1wYAPHv2DKGhoXB1dZX2L1q0KAYOHIiBAwfCz88Pf/zxR6YJhpGRkUav69q1a6No0aLYuHEj9u3bh44dO0qJv6urK5RKJSIiIuDp6fk5d5vos7CLhGTTuHFjuLu7o23btjhw4ADu37+PkydP4scff8S5c+cAAEOGDMGKFSuwevVq3LlzB9OmTcOVK1fUys+lSpXC2rVrcfPmTZw+fRrdu3eHiYmJ2rmKFy+OQ4cOISoqCi9evPhgTN27d8eFCxcwffp0dOjQQe0b3NixY3Hy5EkMHjwYly5dwp07d7Bz504O8qQMIiIiMHLkSISGhmLDhg1YuHAhhg0bhlKlSqFNmzbo378/goODcfnyZfTo0QOFCxdGmzZtAADDhw/H/v37ER4ejgsXLuDIkSMoV65cpucpXrw44uLicOjQITx9+hQJCQkfjKlbt25YsmQJAgMDpe4RALCwsMDo0aMxYsQIrF69GmFhYbhw4QIWLlyI1atXy/vAEGWBCQbJRqFQYO/evahXrx769OmD0qVLo0uXLnjw4AHs7OwAvP3A9/Pzw+jRo1G1alWEh4ejd+/eMDY2lo6zYsUKvHjxAlWrVkXPnj0xdOhQ2Nraqp1rzpw5CAwMRNGiReHm5vbBmEqWLImvvvoKV65cUXsTBt6OJTl27Bhu376NunXrws3NDRMmTICjo6OMjwrpgl69euH169f46quv4Ovri2HDhmHAgAEA3s5mqlatGlq2bAl3d3cIIbB3716popCamgpfX1+UK1cOzZo1Q+nSpbFo0aJMz1O7dm0MHDgQnTt3RqFChTBr1qwPxtS9e3fcuHEDhQsXhoeHh9q2qVOnYvz48fD395fOu2fPHjg7O8v0iBB9HFfyJK1r0qQJ7O3tsXbtWm2HQpRB/fr1UaVKFS7VTZRNHINBX1RCQgKWLFkCLy8v6OvrY8OGDTh48KC0jgYREekGJhj0RaV3o0yfPh1v3rxBmTJlsHXrVjRu3FjboRERkYzYRUJERESy4yBPIiIikh0TDCIiIpIdEwwiIiKSHRMMIiIikh0TDCIiIpIdEwyiL6R3795o27atdL1+/foYPnz4F4/j6NGjUCgUePny5Rc/tyYmTZqEKlWqaDsMIvpMTDAoX+vduzcUCgUUCgWMjIxQsmRJTJkyBSkpKTl+7m3btmHq1Kka7fulk4LLly+jdevWsLW1hbGxMYoXL47OnTsjOjpa1vMoFArs2LFDrW306NE4dOiQrOf5VMWLF+cKnkSfiAttUb7XrFkzrFy5EomJidi7dy98fX1haGgIPz+/DPsmJSXByMhIlvPa2NjIchy5PXnyBI0aNULLli2xf/9+WFlZ4f79+/j7778RHx+f4+c3NzeHubl5jp+HiHIWKxiU7ymVStjb28PJyQmDBg1C48aN8ffffwP4X7fG9OnT4ejoiDJlygB4+xPynTp1gpWVFWxsbNCmTRvcv39fOmZqaipGjhwJKysrFChQAN9//z3eX9Pu/S6SxMREjB07FkWLFoVSqUTJkiWxYsUK3L9/Hw0aNAAAWFtbQ6FQoHfv3gCAtLQ0+Pv7w9nZGSYmJqhcuTK2bNmidp69e/eidOnSMDExQYMGDdTizMyJEycQExOD5cuXw83NDc7OzmjQoAHmzZun9mNZ165dQ/PmzWFubg47Ozv07NkTT58+Vbt/Q4cOxffffw8bGxvY29tj0qRJ0vbixYsDAL7++msoFArp+vtdJOnPwYwZM2BnZwcrKyupyjRmzBjY2NigSJEiWLlypdr9+NhzlH7c2bNnw8HBAQUKFICvry+Sk5Ol+B88eIARI0ZIVS4i0hwTDKL3mJiYICkpSbp+6NAhhIaGIjAwELt370ZycjK8vLxgYWGB48eP48SJEzA3N0ezZs2k282ZMwerVq3Cn3/+ieDgYDx//hzbt2/P8ry9evXChg0b8Ouvv+LmzZtYunQpzM3NUbRoUWzduhUAEBoaisjISCxYsAAA4O/vjzVr1mDJkiW4fv06RowYgR49euDYsWMA3n7ItmvXDq1atcKlS5fQr18/jBs3Lss47O3tkZKSgu3bt2dIitK9fPkSDRs2hJubG86dO4d//vkHjx8/RqdOndT2W716NczMzHD69GnMmjULU6ZMkX535uzZswDe/hppZGSkdD0zhw8fxqNHjxAUFIS5c+di4sSJaNmyJaytrXH69GkMHDgQ3377Lf777z8A0Og5AoAjR44gLCwMR44cwerVq7Fq1SqsWrUKwNsurCJFimDKlCmIjIxEZGRklo8bEb1HEOVjPj4+ok2bNkIIIdLS0kRgYKBQKpVi9OjR0nY7OzuRmJgo3Wbt2rWiTJkyIi0tTWpLTEwUJiYmYv/+/UIIIRwcHMSsWbOk7cnJyaJIkSLSuYQQwtPTUwwbNkwIIURoaKgAIAIDAzON88iRIwKAePHihdT25s0bYWpqKk6ePKm2b9++fUXXrl2FEEL4+fkJV1dXte1jx47NcKz3/fDDD8LAwEDY2NiIZs2aiVmzZomoqChp+9SpU0XTpk3VbvPvv/8KACI0NFS6f3Xq1FHbp0aNGmLs2LHSdQBi+/btavtMnDhRVK5cWbru4+MjnJycRGpqqtRWpkwZUbduXel6SkqKMDMzExs2bBBCaPYcpR83JSVF2qdjx46ic+fO0nUnJycxb968Dz5ORPRhHINB+d7u3bthbm6O5ORkpKWloVu3bmql/IoVK6qNu7h8+TLu3r0LCwsLteO8efMGYWFhiImJQWRkJGrWrCltMzAwQPXq1T9YEbh06RL09fXh6empcdx3795FQkICmjRpotaelJQENzc3AMDNmzfV4gAAd3f3jx57+vTpGDlyJA4fPozTp09jyZIlmDFjBoKCglCxYkVcvnwZR44cyXSsRFhYGEqXLg0AqFSpkto2BweHTxooWr58eejp/a/gamdnhwoVKkjX9fX1UaBAAenYH3uO3j2uvr6+WnxXr17NdnxElBETDMr3GjRogMWLF8PIyAiOjo4wMFD/szAzM1O7HhcXh2rVqmH9+vUZjlWoUKFPisHExCTbt4mLiwMA7NmzB4ULF1bbplQqPymOdxUoUAAdO3ZEx44dMWPGDLi5uWH27NlYvXo14uLi0KpVK8ycOTPD7RwcHKR/Gxoaqm1TKBRIS0vLdiyZHSerY2v6HMkVHxFlxASD8j0zMzOULFlS4/2rVq2KjRs3wtbWFpaWlpnu4+DggNOnT6NevXoAgJSUFJw/fx5Vq1bNdP+KFSsiLS0Nx44dy/Sn69MrKKmpqVKbq6srlEolIiIiPlj5KFeunDRgNd2pU6c+ficzOb+Li4s0i6Rq1arYunUrihcvniEhyw5DQ0O1+yQXTZ4jTRgZGeVIfET5AQd5EmVT9+7dUbBgQbRp0wbHjx9HeHg4jh49iqFDh0qDDIcNG4aff/4ZO3bswK1bt/Ddd99luYZF8eLF4ePjg2+++QY7duyQjrlp0yYAgJOTExQKBXbv3o0nT54gLi4OFhYWGD16NEaMGIHVq1cjLCwMFy5cwMKFC7F69WoAwMCBA3Hnzh2MGTMGoaGhCAgIkAYxfsju3bvRo0cP7N69G7dv30ZoaChmz56NvXv3ok2bNgAAX19fPH/+HF27dsXZs2cRFhaG/fv3o0+fPtn6QC5evDgOHTqEqKgovHjxQuPbfYwmz5Gm8QUFBeHhw4dqM2SI6OOYYBBlk6mpKYKCglCsWDG0a9cO5cqVQ9++ffHmzRvp2/KoUaPQs2dP+Pj4wN3dHRYWFvj666+zPO7ixYvRoUMHfPfddyhbtiz69+8vVQwKFy6MyZMnY9y4cbCzs8PgwYMBAFOnTsX48ePh7++PcuXKoVmzZtizZ480nbRYsWLYunUrduzYgcqVK0tjKbLi6uoKU1NTjBo1ClWqVEGtWrWwadMmLF++HD179gQAODo64sSJE0hNTUXTpk1RsWJFDB8+HFZWVmpjJT5mzpw5CAwMRNGiRaVxI3LQ5DnSxJQpU3D//n24uLh8cvcXUX6lEB8adUZERET0iVjBICIiItkxwSAiIiLZMcEgIiIi2THBICIiItkxwSAiIiLZMcEgIiIi2THBICIiItkxwSAiIiLZMcEgIiIi2THBICIiItkxwSAiIiLZ/R+yWZ1SHxVCsAAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "==================================================\n",
            " FINAL RESULTS FOR: TF-IDF Features + SMOTE \n",
            "==================================================\n",
            "Overall Accuracy: 0.8635\n",
            "\n",
            "Detailed Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "    negative       0.75      0.58      0.65       116\n",
            "    positive       0.89      0.95      0.91       404\n",
            "\n",
            "    accuracy                           0.86       520\n",
            "   macro avg       0.82      0.76      0.78       520\n",
            "weighted avg       0.86      0.86      0.86       520\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 600x500 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "##################################################\n",
            "Project Execution Finished. Ready for PDF Export.\n",
            "##################################################\n"
          ]
        }
      ]
    }
  ]
}