diff --git "a/anemia.ipynb" "b/anemia.ipynb"
--- "a/anemia.ipynb"
+++ "b/anemia.ipynb"
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 55,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,7 +12,7 @@
     "from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier\n",
     "from sklearn.linear_model import LogisticRegression\n",
     "from sklearn.svm import SVC\n",
-    "from sklearn.metrics import accuracy_score,RocCurveDisplay,PrecisionRecallDisplay,ConfusionMatrixDisplay\n",
+    "from sklearn.metrics import accuracy_score,RocCurveDisplay,PrecisionRecallDisplay,classification_report\n",
     "from sklearn.pipeline import Pipeline\n",
     "from sklearn.preprocessing import StandardScaler\n",
     "from sklearn.model_selection import train_test_split,GridSearchCV\n"
@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -181,7 +181,7 @@
        "max       1.000000  "
       ]
      },
-     "execution_count": 21,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -192,7 +192,265 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Hemoglobin</th>\n",
+       "      <th>MCH</th>\n",
+       "      <th>MCHC</th>\n",
+       "      <th>MCV</th>\n",
+       "      <th>Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>14.9</td>\n",
+       "      <td>22.7</td>\n",
+       "      <td>29.1</td>\n",
+       "      <td>83.7</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>15.9</td>\n",
+       "      <td>25.4</td>\n",
+       "      <td>28.3</td>\n",
+       "      <td>72.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>21.5</td>\n",
+       "      <td>29.6</td>\n",
+       "      <td>71.2</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>14.9</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>31.4</td>\n",
+       "      <td>87.5</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>1</td>\n",
+       "      <td>14.7</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>28.2</td>\n",
+       "      <td>99.5</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Gender  Hemoglobin   MCH  MCHC   MCV  Result\n",
+       "0       1        14.9  22.7  29.1  83.7       0\n",
+       "1       0        15.9  25.4  28.3  72.0       0\n",
+       "2       0         9.0  21.5  29.6  71.2       1\n",
+       "3       0        14.9  16.0  31.4  87.5       0\n",
+       "4       1        14.7  22.0  28.2  99.5       0"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Hemoglobin</th>\n",
+       "      <th>MCH</th>\n",
+       "      <th>MCHC</th>\n",
+       "      <th>MCV</th>\n",
+       "      <th>Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1416</th>\n",
+       "      <td>0</td>\n",
+       "      <td>10.6</td>\n",
+       "      <td>25.4</td>\n",
+       "      <td>28.2</td>\n",
+       "      <td>82.9</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1417</th>\n",
+       "      <td>1</td>\n",
+       "      <td>12.1</td>\n",
+       "      <td>28.3</td>\n",
+       "      <td>30.4</td>\n",
+       "      <td>86.9</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1418</th>\n",
+       "      <td>1</td>\n",
+       "      <td>13.1</td>\n",
+       "      <td>17.7</td>\n",
+       "      <td>28.1</td>\n",
+       "      <td>80.7</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1419</th>\n",
+       "      <td>0</td>\n",
+       "      <td>14.3</td>\n",
+       "      <td>16.2</td>\n",
+       "      <td>29.5</td>\n",
+       "      <td>95.2</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1420</th>\n",
+       "      <td>0</td>\n",
+       "      <td>11.8</td>\n",
+       "      <td>21.2</td>\n",
+       "      <td>28.4</td>\n",
+       "      <td>98.1</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "      Gender  Hemoglobin   MCH  MCHC   MCV  Result\n",
+       "1416       0        10.6  25.4  28.2  82.9       1\n",
+       "1417       1        12.1  28.3  30.4  86.9       1\n",
+       "1418       1        13.1  17.7  28.1  80.7       1\n",
+       "1419       0        14.3  16.2  29.5  95.2       0\n",
+       "1420       0        11.8  21.2  28.4  98.1       1"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.tail()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Hemoglobin</th>\n",
+       "      <th>MCH</th>\n",
+       "      <th>MCHC</th>\n",
+       "      <th>MCV</th>\n",
+       "      <th>Result</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "Empty DataFrame\n",
+       "Columns: [Gender, Hemoglobin, MCH, MCHC, MCV, Result]\n",
+       "Index: []"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[(data[\"Hemoglobin\"] < 1) | (data[\"MCV\"] < 1) | (data[\"MCH\"] < 1) | (data[\"MCHC\"] < 1)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -201,7 +459,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [
     {
@@ -224,7 +482,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -236,7 +494,7 @@
        "Name: count, dtype: int64"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -247,7 +505,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -262,7 +520,7 @@
        "dtype: int64"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -273,51 +531,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "y = data[\"Result\"]\n",
-    "x = data.drop([\"Result\",\"MCH\",\"MCHC\"],axis=1)\n",
-    "# x_dropped = data.drop([\"MCH\",\"MCHC\"])"
-   ]
+   "source": []
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "xtrain,xtest,ytrain,ytest = train_test_split(x,y,test_size=0.2,random_state=42)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# scaler = StandardScaler()\n",
-    "\n",
-    "# X_train = scaler.fit_transform(xtrain)\n",
-    "\n",
-    "# X_test = scaler.transform(xtest)\n",
-    "\n",
-    "X_train = xtrain\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "X_test = xtest"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
@@ -341,112 +562,77 @@
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
-       "      <th>Gender</th>\n",
+       "      <th></th>\n",
        "      <th>Hemoglobin</th>\n",
+       "      <th>MCH</th>\n",
+       "      <th>MCHC</th>\n",
        "      <th>MCV</th>\n",
        "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>906</th>\n",
-       "      <td>0</td>\n",
-       "      <td>11.7</td>\n",
-       "      <td>71.6</td>\n",
-       "    </tr>\n",
        "    <tr>\n",
-       "      <th>716</th>\n",
-       "      <td>1</td>\n",
-       "      <td>15.2</td>\n",
-       "      <td>90.2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>943</th>\n",
-       "      <td>1</td>\n",
-       "      <td>12.1</td>\n",
-       "      <td>86.9</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>930</th>\n",
-       "      <td>1</td>\n",
-       "      <td>11.6</td>\n",
-       "      <td>96.7</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>729</th>\n",
-       "      <td>1</td>\n",
-       "      <td>14.0</td>\n",
-       "      <td>71.1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>71</th>\n",
-       "      <td>1</td>\n",
-       "      <td>11.2</td>\n",
-       "      <td>93.9</td>\n",
+       "      <th>Gender</th>\n",
+       "      <th>Result</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
        "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
        "    <tr>\n",
-       "      <th>106</th>\n",
-       "      <td>0</td>\n",
-       "      <td>14.8</td>\n",
-       "      <td>91.1</td>\n",
+       "      <th rowspan=\"2\" valign=\"top\">0</th>\n",
+       "      <th>0</th>\n",
+       "      <td>167</td>\n",
+       "      <td>167</td>\n",
+       "      <td>167</td>\n",
+       "      <td>167</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>474</th>\n",
-       "      <td>1</td>\n",
-       "      <td>10.6</td>\n",
-       "      <td>83.7</td>\n",
+       "      <th>1</th>\n",
+       "      <td>88</td>\n",
+       "      <td>88</td>\n",
+       "      <td>88</td>\n",
+       "      <td>88</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>852</th>\n",
-       "      <td>1</td>\n",
-       "      <td>10.8</td>\n",
-       "      <td>99.6</td>\n",
+       "      <th rowspan=\"2\" valign=\"top\">1</th>\n",
+       "      <th>0</th>\n",
+       "      <td>120</td>\n",
+       "      <td>120</td>\n",
+       "      <td>120</td>\n",
+       "      <td>120</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>102</th>\n",
-       "      <td>1</td>\n",
-       "      <td>10.4</td>\n",
-       "      <td>90.6</td>\n",
+       "      <th>1</th>\n",
+       "      <td>159</td>\n",
+       "      <td>159</td>\n",
+       "      <td>159</td>\n",
+       "      <td>159</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>427 rows × 3 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "     Gender  Hemoglobin   MCV\n",
-       "906       0        11.7  71.6\n",
-       "716       1        15.2  90.2\n",
-       "943       1        12.1  86.9\n",
-       "930       1        11.6  96.7\n",
-       "729       1        14.0  71.1\n",
-       "..      ...         ...   ...\n",
-       "71        1        11.2  93.9\n",
-       "106       0        14.8  91.1\n",
-       "474       1        10.6  83.7\n",
-       "852       1        10.8  99.6\n",
-       "102       1        10.4  90.6\n",
-       "\n",
-       "[427 rows x 3 columns]"
+       "               Hemoglobin  MCH  MCHC  MCV\n",
+       "Gender Result                            \n",
+       "0      0              167  167   167  167\n",
+       "       1               88   88    88   88\n",
+       "1      0              120  120   120  120\n",
+       "       1              159  159   159  159"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "X_train"
+    "data.groupby([\"Gender\",\"Result\"]).count()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -472,172 +658,197 @@
        "      <th></th>\n",
        "      <th>Gender</th>\n",
        "      <th>Hemoglobin</th>\n",
+       "      <th>MCH</th>\n",
+       "      <th>MCHC</th>\n",
        "      <th>MCV</th>\n",
+       "      <th>Result</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
-       "      <th>222</th>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>14.9</td>\n",
+       "      <td>22.7</td>\n",
+       "      <td>29.1</td>\n",
+       "      <td>83.7</td>\n",
        "      <td>0</td>\n",
-       "      <td>11.1</td>\n",
-       "      <td>73.3</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>131</th>\n",
-       "      <td>1</td>\n",
-       "      <td>13.9</td>\n",
-       "      <td>98.5</td>\n",
+       "      <th>1</th>\n",
+       "      <td>0</td>\n",
+       "      <td>15.9</td>\n",
+       "      <td>25.4</td>\n",
+       "      <td>28.3</td>\n",
+       "      <td>72.0</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>149</th>\n",
+       "      <th>2</th>\n",
+       "      <td>0</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>21.5</td>\n",
+       "      <td>29.6</td>\n",
+       "      <td>71.2</td>\n",
        "      <td>1</td>\n",
-       "      <td>16.4</td>\n",
-       "      <td>77.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>290</th>\n",
+       "      <th>3</th>\n",
+       "      <td>0</td>\n",
+       "      <td>14.9</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>31.4</td>\n",
+       "      <td>87.5</td>\n",
        "      <td>0</td>\n",
-       "      <td>10.5</td>\n",
-       "      <td>83.2</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>84</th>\n",
+       "      <th>4</th>\n",
        "      <td>1</td>\n",
-       "      <td>12.8</td>\n",
-       "      <td>100.9</td>\n",
+       "      <td>14.7</td>\n",
+       "      <td>22.0</td>\n",
+       "      <td>28.2</td>\n",
+       "      <td>99.5</td>\n",
+       "      <td>0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>...</th>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
        "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>738</th>\n",
+       "      <th>946</th>\n",
+       "      <td>0</td>\n",
+       "      <td>11.8</td>\n",
+       "      <td>21.2</td>\n",
+       "      <td>28.4</td>\n",
+       "      <td>98.1</td>\n",
        "      <td>1</td>\n",
-       "      <td>13.2</td>\n",
-       "      <td>70.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>177</th>\n",
+       "      <th>1156</th>\n",
+       "      <td>1</td>\n",
+       "      <td>15.1</td>\n",
+       "      <td>21.3</td>\n",
+       "      <td>32.4</td>\n",
+       "      <td>100.6</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1160</th>\n",
+       "      <td>1</td>\n",
+       "      <td>14.8</td>\n",
+       "      <td>19.5</td>\n",
+       "      <td>32.2</td>\n",
+       "      <td>72.1</td>\n",
        "      <td>0</td>\n",
-       "      <td>11.5</td>\n",
-       "      <td>100.8</td>\n",
        "    </tr>\n",
        "    <tr>\n",
-       "      <th>220</th>\n",
+       "      <th>1376</th>\n",
+       "      <td>1</td>\n",
+       "      <td>13.2</td>\n",
+       "      <td>20.4</td>\n",
+       "      <td>28.0</td>\n",
+       "      <td>97.4</td>\n",
        "      <td>1</td>\n",
-       "      <td>11.4</td>\n",
-       "      <td>70.0</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1396</th>\n",
        "      <td>1</td>\n",
        "      <td>13.0</td>\n",
+       "      <td>26.0</td>\n",
+       "      <td>31.4</td>\n",
        "      <td>82.8</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>800</th>\n",
-       "      <td>0</td>\n",
-       "      <td>12.9</td>\n",
-       "      <td>81.7</td>\n",
+       "      <td>1</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>107 rows × 3 columns</p>\n",
+       "<p>534 rows × 6 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
-       "      Gender  Hemoglobin    MCV\n",
-       "222        0        11.1   73.3\n",
-       "131        1        13.9   98.5\n",
-       "149        1        16.4   77.4\n",
-       "290        0        10.5   83.2\n",
-       "84         1        12.8  100.9\n",
-       "...      ...         ...    ...\n",
-       "738        1        13.2   70.4\n",
-       "177        0        11.5  100.8\n",
-       "220        1        11.4   70.0\n",
-       "1396       1        13.0   82.8\n",
-       "800        0        12.9   81.7\n",
+       "      Gender  Hemoglobin   MCH  MCHC    MCV  Result\n",
+       "0          1        14.9  22.7  29.1   83.7       0\n",
+       "1          0        15.9  25.4  28.3   72.0       0\n",
+       "2          0         9.0  21.5  29.6   71.2       1\n",
+       "3          0        14.9  16.0  31.4   87.5       0\n",
+       "4          1        14.7  22.0  28.2   99.5       0\n",
+       "...      ...         ...   ...   ...    ...     ...\n",
+       "946        0        11.8  21.2  28.4   98.1       1\n",
+       "1156       1        15.1  21.3  32.4  100.6       0\n",
+       "1160       1        14.8  19.5  32.2   72.1       0\n",
+       "1376       1        13.2  20.4  28.0   97.4       1\n",
+       "1396       1        13.0  26.0  31.4   82.8       1\n",
        "\n",
-       "[107 rows x 3 columns]"
+       "[534 rows x 6 columns]"
       ]
      },
-     "execution_count": 31,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "X_test"
+    "pd.get_dummies(data,drop_first=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 26,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "906    1\n",
-       "716    0\n",
-       "943    1\n",
-       "930    1\n",
-       "729    0\n",
-       "      ..\n",
-       "71     1\n",
-       "106    0\n",
-       "474    1\n",
-       "852    1\n",
-       "102    1\n",
-       "Name: Result, Length: 427, dtype: int64"
-      ]
-     },
-     "execution_count": 32,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "ytrain"
+    "y = data[\"Result\"]\n",
+    "x = data.drop([\"Result\",\"MCH\",\"MCHC\"],axis=1)\n",
+    "# x_dropped = data.drop([\"MCH\",\"MCHC\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "xtrain,xtest,ytrain,ytest = train_test_split(x,y,test_size=0.2,random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "scaler = StandardScaler()\n",
+    "X_train = scaler.fit_transform(xtrain)\n",
+    "X_test = scaler.transform(xtest)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "222     1\n",
-       "131     0\n",
-       "149     0\n",
-       "290     1\n",
-       "84      1\n",
-       "       ..\n",
-       "738     1\n",
-       "177     1\n",
-       "220     1\n",
-       "1396    1\n",
-       "800     0\n",
-       "Name: Result, Length: 107, dtype: int64"
+       "(427, 3)"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 29,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "ytest"
+    "X_train.shape"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -652,7 +863,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -693,14 +904,14 @@
     "    results[name] = {\n",
     "        'best_params': grid_search.best_params_,\n",
     "        'best_score': grid_search.best_score_,\n",
-    "        # 'test_accuracy': accuracy_score(ytest, grid_search.predict(X_test))\n",
+    "        'classification_report': classification_report(ytest, grid_search.predict(X_test))\n",
     "    }\n",
     "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -708,17 +919,17 @@
      "output_type": "stream",
      "text": [
       "RandomForest:\n",
-      "  Best Parameters: {'classifier__class_weight': 'balanced', 'classifier__max_depth': None, 'classifier__min_samples_split': 2, 'classifier__n_estimators': 5}\n",
+      "  Best Parameters: {'classifier__class_weight': 'balanced', 'classifier__max_depth': None, 'classifier__min_samples_split': 2, 'classifier__n_estimators': 10}\n",
       "  Best CV Score: 0.9976744186046511\n",
       "GradientBoosting:\n",
       "  Best Parameters: {'classifier__learning_rate': 0.1, 'classifier__max_depth': 3, 'classifier__n_estimators': 5}\n",
       "  Best CV Score: 0.9953488372093023\n",
       "SVM:\n",
       "  Best Parameters: {'classifier__C': 10, 'classifier__class_weight': 'balanced', 'classifier__kernel': 'linear'}\n",
-      "  Best CV Score: 0.9859644322845418\n",
+      "  Best CV Score: 0.9906703146374829\n",
       "Logistic Regression:\n",
       "  Best Parameters: {}\n",
-      "  Best CV Score: 0.9789329685362518\n"
+      "  Best CV Score: 0.9812859097127223\n"
      ]
     }
    ],
@@ -729,12 +940,12 @@
     "    print(f\"{name}:\")\n",
     "    print(\"  Best Parameters:\", result['best_params'])\n",
     "    print(\"  Best CV Score:\", result['best_score'])\n",
-    "    # print(\"  Test Accuracy:\", result['test_accuracy'])"
+    "    print(\"classification_report\", result[\"classification_report\"])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -754,7 +965,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
@@ -774,14 +985,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 47,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1.0\n"
+      "100.0\n"
      ]
     }
    ],
@@ -794,7 +1005,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [
     {
@@ -814,16 +1025,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7a854452ec20>"
+       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7aa4ec671150>"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 37,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -844,22 +1055,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7a8529906d10>"
+       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7aa4ec670a60>"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 38,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcAAAAGyCAYAAABzzxS5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAABGU0lEQVR4nO3deXhMZ/8/8PckMpOJLJbIRojYtUTQRHgsrWgsVVtbS0qoBrVWUGtFKam1aQlKrX14gqCoraRokJaKKA2pJSSWxJpEFpks9+8Pv8zXyGImZjJJzvt1XXNd5j7bZ+7EvHOW+xyZEEKAiIhIYkyMXQAREZExMACJiEiSGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSRVMnYBpS0vLw93796FlZUVZDKZscshIiIdCSHw9OlTODk5wcTkNfbjhBGdOHFCvPfee8LR0VEAELt3737lMseOHRPu7u5CLpeLevXqiQ0bNui0zYSEBAGAL7744ouvcv5KSEgoWfj8f0bdA0xPT4ebmxs++eQT9O3b95Xzx8XFoUePHhg1ahS2bNmC8PBwfPrpp3B0dISPj49W27SysgIAJCQkwNra+rXqJyKi0peamgpnZ2f193lJyYQoGzfDlslk2L17N3r37l3kPFOnTsX+/ftx6dIldduAAQOQnJyMQ4cOabWd1NRU2NjYICUlBVZWVsjMzn3d0omIyMCUZqbq01Yvfo+/zo5MuToHGBkZCW9vb402Hx8ffP7550Uuk5WVhaysLPX71NRU9b8zs3PRdPZhvddJRET61bpOVewY5aXXazfK1VWgiYmJsLe312izt7dHamoqMjMzC10mKCgINjY26pezs3NplEpERHr0160nej9iV672AEti+vTpCAgIUL/PP3YMPN+ljpmr3blDIiIqfRmqXLT++qhB1l2uAtDBwQFJSUkabUlJSbC2toZSqSx0GYVCAYVCUeg0mUwGC3m56gIiItKTcnUI1MvLC+Hh4RptR44cgZeXl5EqIiKi8sqoAZiWlobo6GhER0cDeD7MITo6GvHx8QCeH74cMmSIev5Ro0bhxo0b+OKLL3DlyhWsXLkS27dvx8SJE41RPhERlWNGDcC//voL7u7ucHd3BwAEBATA3d0ds2fPBgDcu3dPHYYAULduXezfvx9HjhyBm5sbli5dih9//FHrMYBERET5jHoCrFOnTihuGOLGjRsLXeb8+fMGrIqIiKSgXJ0DJCIi0hcGIBERSRIDkIiIJIkBSEREksQAJCIiSWIAEhGRJDEAiYhIkhiAREQkSQxAIiKSJAYgERFJEgOQiIgkiQFIRESSxAAkIiJJYgASEZEkMQCJiEiSGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSQxAImISJIYgEREJEkMQCIikiQGIBERSRIDkIiIJIkBSEREksQAJCIiSWIAEhGRJDEAiYhIkhiAREQkSQxAIiKSJAYgERFJEgOQiIgkiQFIRESSxAAkIiJJYgASEZEkMQCJiEiSGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSQxAImISJIYgEREJEkMQCIikiQGIBERSRIDkIiIJIkBSEREksQAJCIiSWIAEhGRJDEAiYhIkhiAREQkSQxAIiKSJAYgERFJEgOQiIgkiQFIRESSxAAkIiJJMnoAhoSEwMXFBebm5vD09MSZM2eKnT84OBiNGjWCUqmEs7MzJk6ciGfPnpVStUREVFEYNQC3bduGgIAABAYGIioqCm5ubvDx8cH9+/cLnX/r1q2YNm0aAgMDcfnyZaxbtw7btm3DjBkzSrlyIiIq74wagMuWLYO/vz+GDRuGpk2bYvXq1bCwsMD69esLnf/06dNo164dBg0aBBcXF7z77rsYOHDgK/caiYiIXma0AFSpVDh37hy8vb3/rxgTE3h7eyMyMrLQZdq2bYtz586pA+/GjRs4cOAAunfvXuR2srKykJqaqvEiIiKqZKwNP3z4ELm5ubC3t9dot7e3x5UrVwpdZtCgQXj48CH+85//QAiBnJwcjBo1qthDoEFBQfjqq6/0WjsREZV/Rr8IRhfHjx/HggULsHLlSkRFRWHXrl3Yv38/5s2bV+Qy06dPR0pKivqVkJBQihUTEVFZZbQ9QFtbW5iamiIpKUmjPSkpCQ4ODoUu8+WXX2Lw4MH49NNPAQDNmjVDeno6RowYgZkzZ8LEpGCeKxQKKBQK/X8AIiIq14y2ByiXy9GqVSuEh4er2/Ly8hAeHg4vL69Cl8nIyCgQcqampgAAIYThiiUiogrHaHuAABAQEAA/Pz+0bt0aHh4eCA4ORnp6OoYNGwYAGDJkCGrWrImgoCAAQM+ePbFs2TK4u7vD09MT165dw5dffomePXuqg5CIiEgbRg3A/v3748GDB5g9ezYSExPRokULHDp0SH1hTHx8vMYe36xZsyCTyTBr1izcuXMHNWrUQM+ePTF//nxjfQQiIiqnZEJixw5TU1NhY2ODlJQUWFtbG7scIiIqRoYqB01nHwYAxMz1gYW8kt6+x8vVVaBERET6wgAkIiJJYgASEZEkMQCJiEiSGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSTpfDPsrKws/Pnnn7h16xYyMjJQo0YNuLu7o27duoaoj4iIyCC0DsBTp07hu+++w759+5CdnQ0bGxsolUo8fvwYWVlZcHV1xYgRIzBq1ChYWVkZsmYiIqLXptUh0Pfffx/9+/eHi4sLfv31Vzx9+hSPHj3C7du3kZGRgatXr2LWrFkIDw9Hw4YNceTIEUPXTURE9Fq02gPs0aMHdu7cCTMzs0Knu7q6wtXVFX5+foiJicG9e/f0WiQREZG+aRWAI0eO1HqFTZs2RdOmTUtcEBERUWngVaBERCRJegvACxcuwNTUVF+rIyIiMii97gEKIfS5OiIiIoPRehhE3759i52ekpICmUz22gURERGVBq0DcN++fejSpQvs7e0LnZ6bm6u3ooiIiAxN6wBs0qQJ+vXrh+HDhxc6PTo6Gr/88oveCiMiIjIkrc8BtmrVClFRUUVOVygUqF27tl6KIiIiMjSt9wBXr15d7GHOJk2aIC4uTi9FERERGZrWAahQKAxZBxERUaniQHgiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkkqUQBu3rwZe/bs0Wjbs2cPNm/erJeiiIiIDK1EATh06FBMnz5do23q1KkYNmyYXooiIiIyNK3HAb4oLy+vQNuVK1deuxgiIqLSwnOAREQkSVrtAaampmq9Qmtr6xIXQ0REVFq0CsAqVaq88ll/QgjIZDI+FomIiMoFrQLw2LFjhq6DiIioVGkVgB07djR0HURERKWqRBfBRERE4OOPP0bbtm1x584dAMBPP/2EkydP6rU4IiIiQ9E5AHfu3AkfHx8olUpERUUhKysLAJCSkoIFCxbovUAiIiJD0DkAv/76a6xevRpr166FmZmZur1du3bFPjGeiIioLNE5AGNjY9GhQ4cC7TY2NkhOTtZHTURERAancwA6ODjg2rVrBdpPnjwJV1dXvRRFRERkaDoHoL+/PyZMmIA///wTMpkMd+/exZYtWzB58mR89tlnhqiRiIhI73S+F+i0adOQl5eHzp07IyMjAx06dIBCocDkyZMxbtw4Q9RIRESkdzoHoEwmw8yZMzFlyhRcu3YNaWlpaNq0KSwtLQ1RHxERkUGU6GkQACCXy2FlZQUrKyuGHxERlTs6nwPMycnBl19+CRsbG7i4uMDFxQU2NjaYNWsWsrOzDVEjERGR3um8Bzhu3Djs2rULixYtgpeXFwAgMjISc+bMwaNHj7Bq1Sq9F0lERKRvOgfg1q1bERoaim7duqnbmjdvDmdnZwwcOJABSERE5YLOh0AVCgVcXFwKtNetWxdyuVwfNRERERmczgE4duxYzJs3T30PUADIysrC/PnzMXbsWL0WR0REZChaHQLt27evxvujR4+iVq1acHNzAwBcuHABKpUKnTt31n+FREREBqBVANrY2Gi879evn8Z7Z2dn/VVERERUCrQKwA0bNhi6DiIiolJVogfiEhERlXcluhNMWFgYtm/fjvj4eKhUKo1pfCYgERGVBzrvAX7//fcYNmwY7O3tcf78eXh4eKB69eq4ceOGxthAIiKiskznAFy5ciXWrFmD5cuXQy6X44svvsCRI0cwfvx4pKSkGKJGIiIivdM5AOPj49G2bVsAgFKpxNOnTwEAgwcPxv/+9z/9VkdERGQgJXoi/OPHjwEAtWvXxh9//AEAiIuLgxBCv9UREREZiM4B+M4772Dv3r0AgGHDhmHixIno0qUL+vfvjz59+ui9QCIiIkPQOQDXrFmDmTNnAgDGjBmD9evXo0mTJpg7d26JboQdEhICFxcXmJubw9PTE2fOnCl2/uTkZIwZMwaOjo5QKBRo2LAhDhw4oPN2iYhI2nQeBmFiYgITk//LzQEDBmDAgAEl2vi2bdsQEBCA1atXw9PTE8HBwfDx8UFsbCzs7OwKzK9SqdClSxfY2dkhLCwMNWvWxK1bt1ClSpUSbZ+IiKRLqwD8+++/tV5h8+bNtZ532bJl8Pf3x7BhwwAAq1evxv79+7F+/XpMmzatwPzr16/H48ePcfr0aZiZmQFAoU+mICIiehWtArBFixaQyWSvvMhFJpMhNzdXqw2rVCqcO3cO06dPV7eZmJjA29sbkZGRhS6zd+9eeHl5YcyYMdizZw9q1KiBQYMGYerUqTA1NS10maysLI0nV6SmpmpVHxERVWxaBWBcXJzeN/zw4UPk5ubC3t5eo93e3h5XrlwpdJkbN27gt99+g6+vLw4cOIBr165h9OjRyM7ORmBgYKHLBAUF4auvvtJ7/UREVL5pFYB16tQxdB1aycvLg52dHdasWQNTU1O0atUKd+7cweLFi4sMwOnTpyMgIED9PjU1lU+vICKikt0LVB9sbW1hamqKpKQkjfakpCQ4ODgUuoyjoyPMzMw0Dnc2adIEiYmJUKlUhT6RXqFQQKFQ6Ld4IiIq94z2NAi5XI5WrVohPDxc3ZaXl4fw8HB4eXkVuky7du1w7do15OXlqdv+/fdfODo6Fhp+RERERTHq45ACAgKwdu1abNq0CZcvX8Znn32G9PR09VWhQ4YM0bhI5rPPPsPjx48xYcIE/Pvvv9i/fz8WLFiAMWPGGOsjEBFROWW0Q6AA0L9/fzx48ACzZ89GYmIiWrRogUOHDqkvjImPj9cYc+js7IzDhw9j4sSJaN68OWrWrIkJEyZg6tSpxvoIRERUTslECW7gmZycjLCwMFy/fh1TpkxBtWrVEBUVBXt7e9SsWdMQdepNamoqbGxskJKSAmtra2OXQ0RExchQ5aDp7MMAgJi5PrCQV9Lb97jOe4B///03vL29YWNjg5s3b8Lf3x/VqlXDrl27EB8fj82bN5e4GCIiotKi8znAgIAADB06FFevXoW5ubm6vXv37vj999/1WhwREZGh6ByAZ8+exciRIwu016xZE4mJiXopioiIyNB0DkCFQlHo7cT+/fdf1KhRQy9FERERGZrOAfj+++9j7ty5yM7OBvD8/p/x8fGYOnUq+vXrp/cCiYiIDEHnAFy6dCnS0tJgZ2eHzMxMdOzYEfXr14eVlRXmz59viBqJiIj0TuerQG1sbHDkyBGcPHkSf//9N9LS0tCyZUt4e3sboj4iIiKD0DkAExIS4OzsjP/85z/4z3/+Y4iaiIiIDE7nQ6AuLi7o2LEj1q5diydPnhiiJiIiIoPTOQD/+usveHh4YO7cuXB0dETv3r0RFham8dBZIiKisk7nAHR3d8fixYsRHx+PgwcPokaNGhgxYgTs7e3xySefGKJGIiIivSvx0yBkMhnefvttrF27FkePHkXdunWxadMmfdZGRERkMCUOwNu3b2PRokVo0aIFPDw8YGlpiZCQEH3WRkREZDA6XwX6ww8/YOvWrTh16hQaN24MX19f7NmzB3Xq1DFEfURERAahcwB+/fXXGDhwIL7//nu4ubkZoiYiIiKD0zkA4+PjIZPJDFELERFRqdEqAP/++2+8+eabMDExwcWLF4udt3nz5nopjIiIyJC0CsAWLVogMTERdnZ2aNGiBWQyGV58kHz+e5lMhtzcXIMVS0REpC9aBWBcXJz6UUdxcXEGLYiIiKg0aBWAL17heevWLbRt2xaVKmkumpOTg9OnT/NqUCIiKhd0Hgf49ttv4/HjxwXaU1JS8Pbbb+ulKCIiIkPTOQDzz/W97NGjR6hcubJeiiIiIjI0rYdB9O3bF8DzC16GDh0KhUKhnpabm4u///4bbdu21X+FREREBqB1ANrY2AB4vgdoZWUFpVKpniaXy9GmTRv4+/vrv0IiIiID0DoAN2zYAOD58wAnT57Mw51ERFSu6XwnmMDAQEPUQUREVKq0CsCWLVsiPDwcVatWhbu7e7G3QouKitJbcURERIaiVQD26tVLfdFL7969DVkPERFRqdAqAF887MlDoEREVBHoPA4wISEBt2/fVr8/c+YMPv/8c6xZs0avhRERERmSzgE4aNAgHDt2DACQmJgIb29vnDlzBjNnzsTcuXP1XiAREZEh6ByAly5dgoeHBwBg+/btaNasGU6fPo0tW7Zg48aN+q6PiIjIIHQOwOzsbPUFMUePHsX7778PAGjcuDHu3bun3+qIiIgMROcAfOONN7B69WpERETgyJEj6Nq1KwDg7t27qF69ut4LJCIiMgSdA3DhwoX44Ycf0KlTJwwcOBBubm4AgL1796oPjRIREZV1Ot8JplOnTnj48CFSU1NRtWpVdfuIESNgYWGh1+KIiIgMRecABABTU1Pk5OTg5MmTAIBGjRrBxcVFn3UREREZlM6HQNPT0/HJJ5/A0dERHTp0QIcOHeDk5IThw4cjIyPDEDUSERHpnc4BGBAQgBMnTmDfvn1ITk5GcnIy9uzZgxMnTmDSpEmGqJGIiEjvdD4EunPnToSFhaFTp07qtu7du0OpVOKjjz7CqlWr9FkfERGRQei8B5iRkQF7e/sC7XZ2djwESkRE5YbOAejl5YXAwEA8e/ZM3ZaZmYmvvvoKXl5eei2OiIjIUHQ+BBocHAwfHx/UqlVLPQbwwoULMDc3x+HDh/VeIBERkSHoHIDNmjXDtWvXsHXrVly+fBkAMHDgQPj6+kKpVOq9QCIiIkPQKQD/+OMP7Nu3DyqVCu+88w4+/fRTQ9VFRERkUFoHYFhYGPr37w+lUgkzMzMsW7YMCxcuxOTJkw1ZHxERkUFofRFMUFAQ/P39kZKSgidPnuDrr7/GggULDFkbERGRwWgdgLGxsZg8eTJMTU0BAJMmTcLTp09x//59gxVHRERkKFoHYEZGBqytrdXv5XI5zM3NkZaWZpDCiIiIDEmni2B+/PFHWFpaqt/n5ORg48aNsLW1VbeNHz9ef9UREREZiEwIIbSZ0cXFBTKZrPiVyWS4ceOGXgozlNTUVNjY2CAlJUVjj5aIiMqeDFUOms5+PsY8Zq4PLOSV9PY9rvUe4M2bN0u8ESIiorJG51uhERERVQRaBWBoaKjWK0xISMCpU6dKXBAREVFp0CoAV61ahSZNmmDRokXq25+9KCUlBQcOHMCgQYPQsmVLPHr0SO+FEhER6ZPWF8Hs3bsXy5cvx2+//YbKlSvD3t4e5ubmePLkCRITE2Fra4uhQ4di4sSJhT4uqazgRTBEROWHEAKZ2bkAAKWZKWQymd6+x7UOwHwPHz7EyZMncevWLWRmZsLW1hbu7u5wd3eHiUnZP6XIACQiKt9K/SrQfLa2tujdu3eJN0hERFQWlP1dNiIiIgNgABIRkSQxAImISJLKRACGhITAxcUF5ubm8PT0xJkzZ7RaLjQ0FDKZjOckiYhIZ0YPwG3btiEgIACBgYGIioqCm5sbfHx8XvmYpZs3b2Ly5Mlo3759KVVKREQVic7DIHJzc7Fx40aEh4fj/v37yMvL05j+22+/6VSAp6cn3nrrLaxYsQIAkJeXB2dnZ4wbNw7Tpk0rsoYOHTrgk08+QUREBJKTk/Hzzz9rtT0OgyAiKt+MNgxiwoQJ2LhxI3r06IE333zzlU+IKI5KpcK5c+cwffp0dZuJiQm8vb0RGRlZ5HJz586FnZ0dhg8fjoiIiGK3kZWVhaysLPX71NTUEtdLREQVh84BGBoaiu3bt6N79+6vvfGHDx8iNze3wJ1j7O3tceXKlUKXOXnyJNatW4fo6GitthEUFISvvvrqdUslIqIKRudzgHK5HPXr1zdELa/09OlTDB48GGvXrtV4CG9xpk+fjpSUFPUrISHBwFUSEVF5oPMe4KRJk/Ddd99hxYoVr3X4E3h+VxlTU1MkJSVptCclJcHBwaHA/NevX8fNmzfRs2dPdVv+OchKlSohNjYW9erV01hGoVBAoVC8Vp1ERFTx6ByAJ0+exLFjx3Dw4EG88cYbMDMz05i+a9curdcll8vRqlUrhIeHq4cy5OXlITw8HGPHji0wf+PGjXHx4kWNtlmzZuHp06f47rvv4OzsrOvHISIiidI5AKtUqYI+ffrorYCAgAD4+fmhdevW8PDwQHBwMNLT0zFs2DAAwJAhQ1CzZk0EBQXB3Nwcb775ZoF6ABRoJyIiKo7OAbhhwwa9FtC/f388ePAAs2fPRmJiIlq0aIFDhw6pL4yJj48vF0+ZICKi8kXncYD5Hjx4gNjYWABAo0aNUKNGDb0WZigcB0hEVL7p63tc512r9PR0fPLJJ3B0dESHDh3QoUMHODk5Yfjw4cjIyChxIURERKVJ5wAMCAjAiRMnsG/fPiQnJyM5ORl79uzBiRMnMGnSJEPUSEREpHc6HwK1tbVFWFgYOnXqpNF+7NgxfPTRR3jw4IE+69M7HgIlIirfjHYINCMjo8CdWwDAzs6Oh0CJiKjc0DkAvby8EBgYiGfPnqnbMjMz8dVXX8HLy0uvxRERERmKzsMgvvvuO/j4+KBWrVpwc3MDAFy4cAHm5uY4fPiw3gskIiIyhBINg8jIyMCWLVvUN6xu0qQJfH19oVQq9V6gvvEcIBFR+Wa0xyEBgIWFBfz9/Uu8USIiImPTKgD37t2Lbt26wczMDHv37i123vfff18vhRERERmSVodATUxMkJiYCDs7u2JvSyaTyZCbm6vXAvWNh0CJiMq3Uj0Emv/IoZf/TUREVF7p5S7TycnJ+lgNERFRqdE5ABcuXIht27ap33/44YeoVq0aatasiQsXLui1OCIiIkPROQBXr16tfvDskSNHcPToURw6dAjdunXDlClT9F4gERGRIeg8DCIxMVEdgL/88gs++ugjvPvuu3BxcYGnp6feCyQiIjIEnfcAq1atioSEBADAoUOH4O3tDQAQQpT5K0CJiIjy6bwH2LdvXwwaNAgNGjTAo0eP0K1bNwDA+fPnUb9+fb0XSEREZAg6B+C3334LFxcXJCQkYNGiRbC0tAQA3Lt3D6NHj9Z7gURERIZQonuBlmccCE9EVL6V6kB43gqNiIgqGt4KjYiIyhXeCo2IiOg16OVWaEREROWNzgE4fvx4fP/99wXaV6xYgc8//1wfNRERERmczgG4c+dOtGvXrkB727ZtERYWppeiiIiIDE3nAHz06BFsbGwKtFtbW+Phw4d6KYqIiMjQdA7A+vXr49ChQwXaDx48CFdXV70URUREZGg63wkmICAAY8eOxYMHD/DOO+8AAMLDw7F06VIEBwfruz4iIiKD0DkAP/nkE2RlZWH+/PmYN28eAMDFxQWrVq3CkCFD9F4gERGRIbzWrdAePHgApVKpvh9oecCB8ERE5Zu+vsdLNA4wJycHR48exa5du5Cfn3fv3kVaWlqJCyEiIipNOh8CvXXrFrp27Yr4+HhkZWWhS5cusLKywsKFC5GVlYXVq1cbok4iIiK90nkPcMKECWjdujWePHkCpVKpbu/Tpw/Cw8P1WhwREZGh6LwHGBERgdOnT0Mul2u0u7i44M6dO3orjIiIyJB03gPMy8sr9IkPt2/fhpWVlV6KIiIiMjSdA/Ddd9/VGO8nk8mQlpaGwMBAdO/eXZ+1ERERGYzOwyASEhLQtWtXCCFw9epVtG7dGlevXoWtrS1+//132NnZGapWveAwCCKi8k1f3+MlGgeYk5ODbdu24cKFC0hLS0PLli3h6+urcVFMWcUAJCIq34wSgNnZ2WjcuDF++eUXNGnSpMQbNSYGIBFR+WaUgfBmZmZ49uxZiTdGRERUVuh8EcyYMWOwcOFC5OTkGKIeIiKiUqHzOMCzZ88iPDwcv/76K5o1a4bKlStrTN+1a5feiiMiIjIUnQOwSpUq6NevnyFqISIiKjU6B+CGDRsMUQcREVGp0vocYF5eHhYuXIh27drhrbfewrRp05CZmWnI2oiIiAxG6wCcP38+ZsyYAUtLS9SsWRPfffcdxowZY8jaiIiIDEbrANy8eTNWrlyJw4cP4+eff8a+ffuwZcsW5OXlGbI+IiIig9A6AOPj4zXu9ent7Q2ZTIa7d+8apDAiIiJD0joAc3JyYG5urtFmZmaG7OxsvRdFRERkaFpfBSqEwNChQ6FQKNRtz549w6hRozTGAnIcIBERlQdaB6Cfn1+Bto8//livxRAREZUWrQOQ4/+IiKgi0fleoERERBUBA5CIiCSJAUhERJLEACQiIkliABIRkSQxAImISJIYgEREJEkMQCIikiQGIBERSRIDkIiIJKlMBGBISAhcXFxgbm4OT09PnDlzpsh5165di/bt26Nq1aqoWrUqvL29i52fiIioMEYPwG3btiEgIACBgYGIioqCm5sbfHx8cP/+/ULnP378OAYOHIhjx44hMjISzs7OePfdd3Hnzp1SrpyIiMozmRBCGLMAT09PvPXWW1ixYgUAIC8vD87Ozhg3bhymTZv2yuVzc3NRtWpVrFixAkOGDHnl/KmpqbCxsUFKSgqsra1fu34iIipd+voeN+oeoEqlwrlz5+Dt7a1uMzExgbe3NyIjI7VaR0ZGBrKzs1GtWrVCp2dlZSE1NVXjRUREZNQAfPjwIXJzc2Fvb6/Rbm9vj8TERK3WMXXqVDg5OWmE6IuCgoJgY2Ojfjk7O7923UREVP4Z/Rzg6/jmm28QGhqK3bt3w9zcvNB5pk+fjpSUFPUrISGhlKskIqKySOsH4hqCra0tTE1NkZSUpNGelJQEBweHYpddsmQJvvnmGxw9ehTNmzcvcj6FQgGFQqGXeomIqOIw6h6gXC5Hq1atEB4erm7Ly8tDeHg4vLy8ilxu0aJFmDdvHg4dOoTWrVuXRqlERFTBGHUPEAACAgLg5+eH1q1bw8PDA8HBwUhPT8ewYcMAAEOGDEHNmjURFBQEAFi4cCFmz56NrVu3wsXFRX2u0NLSEpaWlkb7HEREVL4YPQD79++PBw8eYPbs2UhMTESLFi1w6NAh9YUx8fHxMDH5vx3VVatWQaVS4YMPPtBYT2BgIObMmVOapRMRUTlm9HGApY3jAImIyrcKMQ6QiIjIWBiAREQkSQxAIiKSJAYgERFJEgOQiIgkiQFIRESSxAAkIiJJYgASEZEkMQCJiEiSGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSQxAImISJIYgEREJEkMQCIikiQGIBERSRIDkIiIJIkBSEREksQAJCIiSWIAEhGRJDEAiYhIkhiAREQkSQxAIiKSJAYgERFJEgOQiIgkiQFIRESSxAAkIiJJYgASEZEkMQCJiEiSGIBERCRJDEAiIpIkBiAREUlSJWMXUBYJIZCTk4Pc3Fxjl0JERmZqaopKlSpBJpMZuxTSMwbgS1QqFe7du4eMjAxjl0JEZYSFhQUcHR0hl8uNXQrpEQPwBXl5eYiLi4OpqSmcnJwgl8v5Vx+RhAkhoFKp8ODBA8TFxaFBgwYwMeGZo4qCAfgClUqFvLw8ODs7w8LCwtjlEFEZoFQqYWZmhlu3bkGlUsHc3NzYJZGe8E+ZQvAvPCJ6Eb8TKib+VImISJIYgEREJEkMQNKai4sLgoODS7z8xo0bUaVKFb3VU14dP34cMpkMycnJBt/Wo0ePYGdnh5s3bxp8W+VVTEwMatWqhfT0dGOXQqWMAVhBDB06FL179zboNs6ePYsRI0ZoNW9hYdm/f3/8+++/Wm+vU6dOkMlkkMlkMDc3R8OGDREUFAQhhC5llzlt27bFvXv3YGNjY/BtzZ8/H7169YKLi0uBaT4+PjA1NcXZs2cLTBs6dKi67+VyOerXr4+5c+ciJyfHYLWuWbMGnTp1grW1tU5/IISEhMDFxQXm5ubw9PTEmTNnNKY/e/YMY8aMQfXq1WFpaYl+/fohKSlJPb1p06Zo06YNli1bps+PQ+UAA5C0VqNGjde6OlapVMLOzk6nZfz9/XHv3j3ExsZi+vTpmD17NlavXl3iGrShUqkMun65XA4HBweDD7HJyMjAunXrMHz48ALT4uPjcfr0aYwdOxbr168vdPmuXbvi3r17uHr1KiZNmoQ5c+Zg8eLFBq23a9eumDFjhtbLbNu2DQEBAQgMDERUVBTc3Nzg4+OD+/fvq+eZOHEi9u3bhx07duDEiRO4e/cu+vbtq7GeYcOGYdWqVQYNeCqDhMSkpKQIACIlJaXAtMzMTBETEyMyMzPVbXl5eSI9K9sor7y8PK0/l5+fn+jVq1eR048fPy7eeustIZfLhYODg5g6darIzs5WT09NTRWDBg0SFhYWwsHBQSxbtkx07NhRTJgwQT1PnTp1xLfffqvul8DAQOHs7CzkcrlwdHQU48aNE0II0bFjRwFA4yWEEBs2bBA2NjYade3du1e0bt1aKBQKUb16ddG7d2/1tJe3L4QQLVu2FH369FG/f/bsmZg0aZJwcnISFhYWwsPDQxw7dkxjmTVr1ohatWoJpVIpevfuLZYuXapRR2BgoHBzcxNr164VLi4uQiaTCSGEePLkiRg+fLiwtbUVVlZW4u233xbR0dHq5aKjo0WnTp2EpaWlsLKyEi1bthRnz54VQghx8+ZN8d5774kqVaoICwsL0bRpU7F//34hhBDHjh0TAMSTJ0/U6woLCxNNmzYVcrlc1KlTRyxZskTjM9SpU0fMnz9fDBs2TFhaWgpnZ2fxww8/iOLs2LFD1KhRo9Bpc+bMEQMGDBCXL18WNjY2IiMjQ2N6Yb9PXbp0EW3atCl2m/pQWP8UxcPDQ4wZM0b9Pjc3Vzg5OYmgoCAhhBDJycnCzMxM7NixQz3P5cuXBQARGRmpbsvKyhIKhUIcPXq00O0U9t1AxlPc97guOA7wFTKzc9F09mGjbDtmrg8s5K//I7pz5w66d++OoUOHYvPmzbhy5Qr8/f1hbm6OOXPmAAACAgJw6tQp7N27F/b29pg9ezaioqLQokWLQte5c+dOfPvttwgNDcUbb7yBxMREXLhwAQCwa9cuuLm5YcSIEfD39y+yrv3796NPnz6YOXMmNm/eDJVKhQMHDhQ6rxACJ0+exJUrV9CgQQN1+9ixYxETE4PQ0FA4OTlh9+7d6Nq1Ky5evIgGDRrg1KlTGDVqFBYuXIj3338fR48exZdffllg/deuXcPOnTuxa9cumJqaAgA+/PBDKJVKHDx4EDY2Nvjhhx/QuXNn/Pvvv6hWrRp8fX3h7u6OVatWwdTUFNHR0TAzMwMAjBkzBiqVCr///jsqV66MmJgYWFpaFvrZzp07h48++ghz5sxB//79cfr0aYwePRrVq1fH0KFD1fMtXboU8+bNw4wZMxAWFobPPvsMHTt2RKNGjQpdb0REBFq1alVoX27YsAEhISFo3Lgx6tevj7CwMAwePLjwH9T/p1Qq8ejRoyKnd+vWDREREUVOr1OnDv75559it6ELlUqFc+fOYfr06eo2ExMTeHt7IzIyEsDzvs3Ozoa3t7d6nsaNG6N27dqIjIxEmzZtADzfK2/RogUiIiLQuXNnvdVIZRsDUAJWrlwJZ2dnrFixAjKZDI0bN8bdu3cxdepUzJ49G+np6di0aRO2bt2q/s+/YcMGODk5FbnO+Ph4ODg4wNvbG2ZmZqhduzY8PDwAANWqVYOpqSmsrKzg4OBQ5Drmz5+PAQMG4KuvvlK3ubm5Faj9xx9/hEqlQnZ2NszNzTF+/Hh1DRs2bEB8fLy61smTJ+PQoUPYsGEDFixYgOXLl6Nbt26YPHkyAKBhw4Y4ffo0fvnlF43tqFQqbN68GTVq1AAAnDx5EmfOnMH9+/ehUCgAAEuWLMHPP/+MsLAwjBgxAvHx8ZgyZQoaN24MABrBHB8fj379+qFZs2YAAFdX1yL7YdmyZejcubM6mBs2bIiYmBgsXrxYIwC7d++O0aNHAwCmTp2Kb7/9FseOHSsyAG/dulXoz/Do0aPIyMiAj48PAODjjz/GunXrigxAIQTCw8Nx+PBhjBs3rsjP8eOPPyIzM7PI6fl/HOjLw4cPkZubC3t7e412e3t7XLlyBQCQmJgIuVxe4OIre3t7JCYmarQ5OTnh1q1beq2RyjYG4CsozUwRM9fHaNvWh8uXL8PLy0vjnFO7du2QlpaG27dv48mTJ8jOzlYHGADY2NgU+cUKPN87Cg4OhqurK7p27Yru3bujZ8+eqFRJ+1+p6OjoYvcQAcDX1xczZ87EkydPEBgYiLZt26Jt27YAgIsXLyI3NxcNGzbUWCYrKwvVq1cHAMTGxqJPnz4a0z08PAoEYJ06ddThBwAXLlxAWlqaej35MjMzcf36dQDP95o//fRT/PTTT/D29saHH36IevXqAQDGjx+Pzz77DL/++iu8vb3Rr18/NG/evNDPePnyZfTq1UujrV27dggODkZubq56j/TF5WUyGRwcHDTOdb0sMzOz0LuWrF+/Hv3791f/rAYOHIgpU6bg+vXr6voB4JdffoGlpSWys7ORl5eHQYMGqY8YFKZmzZpFTisPlEol7wEsMQzAV5DJZHo5DFnRODs7IzY2FkePHsWRI0cwevRoLF68GCdOnND6L32lUvnKeWxsbFC/fn0AwPbt21G/fn20adMG3t7eSEtLg6mpKc6dO6cOiXxFHW4sSuXKlTXep6WlwdHREcePHy8wb/7exJw5czBo0CDs378fBw8eRGBgIEJDQ9GnTx98+umn8PHxwf79+/Hrr78iKCgIS5cuLXYP6lVe7leZTIa8vLwi57e1tcWTJ0802h4/fozdu3cjOzsbq1atUrfn5uZi/fr1mD9/vrrt7bffxqpVqyCXy+Hk5PTKP25K+xCora0tTE1NNa7oBICkpCT1kQcHBweoVCokJydr7AW+OE++x48fa/wBQBUfrwKVgCZNmiAyMlJj+MCpU6dgZWWFWrVqwdXVFWZmZhqXw6ekpLxyyIJSqUTPnj3x/fff4/jx44iMjMTFixcBPD+n8qrHSTVv3hzh4eFafw5LS0tMmDABkydPhhAC7u7uyM3Nxf3791G/fn2NV/6XW6NGjQpc5l/YZf8va9myJRITE1GpUqUC67a1tVXP17BhQ0ycOBG//vor+vbtiw0bNqinOTs7Y9SoUdi1axcmTZqEtWvXFrqtJk2a4NSpUxptp06dQsOGDQsEuy7c3d0RExOj0bZlyxbUqlULFy5cQHR0tPq1dOlSbNy4UeNnVrlyZdSvXx+1a9fWas/+xx9/1Fjny6+izu+WlFwuR6tWrTR+h/Ly8hAeHg4vLy8AQKtWrWBmZqYxT2xsLOLj49Xz5Lt06RLc3d31WiOVbdy1qUBSUlIQHR2t0Va9enWMHj0awcHBGDduHMaOHYvY2FgEBgYiICAAJiYmsLKygp+fH6ZMmYJq1arBzs4OgYGBMDExKfJS/fwvS09PT1hYWOC///0vlEol6tSpA+D5OMDff/8dAwYMgEKh0AiNfIGBgejcuTPq1auHAQMGICcnBwcOHMDUqVOL/IwjR47EvHnzsHPnTnzwwQfw9fXFkCFDsHTpUri7u+PBgwcIDw9H8+bN0aNHD4wbNw4dOnTAsmXL0LNnT/z22284ePDgK4cgeHt7w8vLC71798aiRYvQsGFD3L17V33hzhtvvIEpU6bggw8+QN26dXH79m2cPXsW/fr1AwB8/vnn6NatGxo2bIgnT57g2LFjaNKkSaHbmjRpEt566y3MmzcP/fv3R2RkJFasWIGVK1cWW+Or+Pj4YPr06Xjy5AmqVq0KAFi3bh0++OADvPnmmxrzOjs7Y/r06Th06BB69OhRou297iHQxMREJCYm4tq1awCeH+K2srJC7dq1Ua1aNQBA586d0adPH4wdOxbA88PQfn5+aN26NTw8PBAcHIz09HQMGzYMwPMjCMOHD0dAQACqVasGa2trjBs3Dl5eXuoLYADg5s2buHPnjsbFMiQBr39Bavmi6zCI8sLPz6/A0AMAYvjw4UKIkg2D8PDwENOmTVPP8+IwiN27dwtPT09hbW0tKleuLNq0aaNxCXlkZKRo3ry5UCgUxQ6D2Llzp2jRooWQy+XC1tZW9O3bVz2tsGEQQggxcuRI8cYbb4jc3FyhUqnE7NmzhYuLizAzMxOOjo6iT58+4u+//1bPv2bNGlGzZk31MIivv/5aODg4qKfnD4N4WWpqqhg3bpxwcnISZmZmwtnZWfj6+or4+HiRlZUlBgwYoB4G4uTkJMaOHav+3Rk7dqyoV6+eUCgUokaNGmLw4MHi4cOHQojih0GYmZmJ2rVri8WLF2vU8mLf53NzcxOBgYEF6n6Rh4eHWL16tRBCiL/++ksAEGfOnCl03m7duqmHmLxqWI0hBAYGFvo7vGHDBvU8derUKfCZly9fLmrXri3kcrnw8PAQf/zxh8b0zMxMMXr0aFG1alVhYWEh+vTpI+7du6cxz4IFC4SPj0+RtZXn74aKSF/DIGRClPPbaugoNTUVNjY2SElJgbW1tca0Z8+eIS4uDnXr1pX8I0/S09NRs2ZNLF26tNCB1OWZv78/rly5Uuz5qopi//79mDJlCi5dusQnGhRBpVKhQYMG2Lp1K9q1a1foPPxuKFuK+x7XBQ+BEgDg/PnzuHLlCjw8PJCSkoK5c+cCQIGrE8ujJUuWoEuXLqhcuTIOHjyITZs2vfbhxfKiR48euHr1Ku7cuQNnZ2djl1MmxcfHY8aMGUWGH1VcDEBSW7JkCWJjY9UXF0RERBR67q68OXPmDBYtWoSnT5/C1dUV33//PT799FNjl1VqPv/8c2OXUKblX9xE0sMAJADPrxg8d+6cscswiO3btxu7BCIqg3hSgIiIJIkBWAiJXRdERK/A74SKiQH4gvw7bfB2SET0ovzvBH3fz5SMq0ycAwwJCcHixYuRmJgINzc3LF++XOO+lC/bsWMHvvzyS9y8eRMNGjTAwoUL0b1799euw9TUFFWqVFHfX9HCwsLgz2wjorJLCIGMjAzcv38fVapUea0781DZY/QAzH+g5erVq+Hp6Yng4GD4+PggNja20Iennj59GgMHDkRQUBDee+89bN26Fb1790ZUVFSBu1uURP4ttIq7yTARSUuVKlWKfbIJlU9GHwjv6emJt956CytWrADw/F5+zs7OGDduHKZNm1Zg/v79+yM9PV3jbv5t2rRBixYttHpSuLYDKHNzc5GdnV2CT0REFYmZmRn3/MqYCjEQXpsHWr4sMjISAQEBGm0+Pj74+eefC50/KysLWVlZ6vepqala1WZqaspfeiKiCsyoF8EU90DLlx9WmS8xMVGn+YOCgmBjY6N+8W4YREQESOAq0OnTpyMlJUX9SkhIMHZJRERUBhj1EKg2D7R8mYODg07zKxQKKBQK/RRMREQVhlED8MUHWvbu3RvA/z3QMv95Xy/z8vJCeHi4xv0Njxw5UuDhlkXJv+ZH23OBRERUtuR/f7/2NZyv91Sm1xcaGioUCoXYuHGjiImJESNGjBBVqlQRiYmJQgghBg8erPFMulOnTolKlSqJJUuWiMuXL4vAwEBhZmYmLl68qNX2EhISCn3mGF988cUXX+XrlZCQ8Fr5Y/RxgP3798eDBw8we/ZsJCYmokWLFjh06JD6Qpf4+HiN55i1bdsWW7duxaxZszBjxgw0aNAAP//8s9ZjAJ2cnJCQkAArKyvIZDKkpqbC2dkZCQkJr3U5bUXF/nk19lHx2D+vxj4q3sv9I4TA06dP4eTk9FrrNfo4QGPT13iSior982rso+Kxf16NfVQ8Q/VPhb8KlIiIqDAMQCIikiTJB6BCoUBgYCCHShSB/fNq7KPisX9ejX1UPEP1j+TPARIRkTRJfg+QiIikiQFIRESSxAAkIiJJYgASEZEkSSIAQ0JC4OLiAnNzc3h6euLMmTPFzr9jxw40btwY5ubmaNasGQ4cOFBKlRqHLv2zdu1atG/fHlWrVkXVqlXh7e39yv6sCHT9HcoXGhoKmUymvtdtRaVr/yQnJ2PMmDFwdHSEQqFAw4YN+f/sJcHBwWjUqBGUSiWcnZ0xceJEPHv2rJSqLV2///47evbsCScnJ8hksiKf7/qi48ePo2XLllAoFKhfvz42btyo+4Zf60Zq5UBoaKiQy+Vi/fr14p9//hH+/v6iSpUqIikpqdD5T506JUxNTcWiRYtETEyMmDVrlk73Gi1vdO2fQYMGiZCQEHH+/Hlx+fJlMXToUGFjYyNu375dypWXHl37KF9cXJyoWbOmaN++vejVq1fpFGsEuvZPVlaWaN26tejevbs4efKkiIuLE8ePHxfR0dGlXHnp0bWPtmzZIhQKhdiyZYuIi4sThw8fFo6OjmLixImlXHnpOHDggJg5c6bYtWuXACB2795d7Pw3btwQFhYWIiAgQMTExIjly5cLU1NTcejQIZ22W+ED0MPDQ4wZM0b9Pjc3Vzg5OYmgoKBC5//oo49Ejx49NNo8PT3FyJEjDVqnsejaPy/LyckRVlZWYtOmTYYq0ehK0kc5OTmibdu24scffxR+fn4VOgB17Z9Vq1YJV1dXoVKpSqtEo9O1j8aMGSPeeecdjbaAgADRrl07g9ZZFmgTgF988YV44403NNr69+8vfHx8dNpWhT4EqlKpcO7cOXh7e6vbTExM4O3tjcjIyEKXiYyM1JgfAHx8fIqcvzwrSf+8LCMjA9nZ2ahWrZqhyjSqkvbR3LlzYWdnh+HDh5dGmUZTkv7Zu3cvvLy8MGbMGNjb2+PNN9/EggULkJubW1pll6qS9FHbtm1x7tw59WHSGzdu4MCBA+jevXup1FzW6et72uhPgzCkhw8fIjc3V/1kiXz29va4cuVKocskJiYWOn9iYqLB6jSWkvTPy6ZOnQonJ6cCv4wVRUn66OTJk1i3bh2io6NLoULjKkn/3LhxA7/99ht8fX1x4MABXLt2DaNHj0Z2djYCAwNLo+xSVZI+GjRoEB4+fIj//Oc/EEIgJycHo0aNwowZM0qj5DKvqO/p1NRUZGZmQqlUarWeCr0HSIb1zTffIDQ0FLt374a5ubmxyykTnj59isGDB2Pt2rWwtbU1djllUl5eHuzs7LBmzRq0atUK/fv3x8yZM7F69Wpjl1ZmHD9+HAsWLMDKlSsRFRWFXbt2Yf/+/Zg3b56xS6tQKvQeoK2tLUxNTZGUlKTRnpSUBAcHh0KXcXBw0Gn+8qwk/ZNvyZIl+Oabb3D06FE0b97ckGUala59dP36ddy8eRM9e/ZUt+Xl5QEAKlWqhNjYWNSrV8+wRZeikvwOOTo6wszMDKampuq2Jk2aIDExESqVCnK53KA1l7aS9NGXX36JwYMH49NPPwUANGvWDOnp6RgxYgRmzpyp8YxUKSrqe9ra2lrrvT+ggu8ByuVytGrVCuHh4eq2vLw8hIeHw8vLq9BlvLy8NOYHgCNHjhQ5f3lWkv4BgEWLFmHevHk4dOgQWrduXRqlGo2ufdS4cWNcvHgR0dHR6tf777+Pt99+G9HR0XB2di7N8g2uJL9D7dq1w7Vr19R/GADAv//+C0dHxwoXfkDJ+igjI6NAyOX/wSB4+2b9fU/rdn1O+RMaGioUCoXYuHGjiImJESNGjBBVqlQRiYmJQgghBg8eLKZNm6ae/9SpU6JSpUpiyZIl4vLlyyIwMLDCD4PQpX+++eYbIZfLRVhYmLh375769fTpU2N9BIPTtY9eVtGvAtW1f+Lj44WVlZUYO3asiI2NFb/88ouws7MTX3/9tbE+gsHp2keBgYHCyspK/O9//xM3btwQv/76q6hXr5746KOPjPURDOrp06fi/Pnz4vz58wKAWLZsmTh//ry4deuWEEKIadOmicGDB6vnzx8GMWXKFHH58mUREhLCYRBFWb58uahdu7aQy+XCw8ND/PHHH+ppHTt2FH5+fhrzb9++XTRs2FDI5XLxxhtviP3795dyxaVLl/6pU6eOAFDgFRgYWPqFlyJdf4deVNEDUAjd++f06dPC09NTKBQK4erqKubPny9ycnJKuerSpUsfZWdnizlz5oh69eoJc3Nz4ezsLEaPHi2ePHlS+oWXgmPHjhX6vZLfJ35+fqJjx44FlmnRooWQy+XC1dVVbNiwQeft8nFIREQkSRX6HCAREVFRGIBERCRJDEAiIpIkBiAREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSQxAIkKIZPJ8PPPPwMAbt68CZlM9srHG8XGxsLBwQFPnz41fIEAXFxcEBwcXOw8c+bMQYsWLQxaR0m28WL/ltTQoUPRu3fv11pHYdq0aYOdO3fqfb1U9jAAqUwZOnQoZDIZZDIZzMzMULduXXzxxRd49uyZsUt7penTp2PcuHGwsrIC8PyRNvmfRSaTwd7eHv369cONGzf0sr2zZ89ixIgR6veFhcrkyZML3DRYyn7//Xf07NkTTk5ORYbwrFmzMG3aNI2bdVPFxACkMqdr1664d+8ebty4gW+//RY//PBDmX9Qanx8PH755RcMHTq0wLTY2FjcvXsXO3bswD///IOePXvq5ennNWrUgIWFRbHzWFpaonr16q+9rYoiPT0dbm5uCAkJKXKebt264enTpzh48GApVkbGwACkMkehUMDBwQHOzs7o3bs3vL29ceTIEfX0vLw8BAUFoW7dulAqlXBzc0NYWJjGOv755x+89957sLa2hpWVFdq3b4/r168DeL7n1KVLF9ja2sLGxgYdO3ZEVFTUa9W8fft2uLm5oWbNmgWm2dnZwdHRER06dMDs2bMRExODa9euAQBWrVqFevXqQS6Xo1GjRvjpp5/UywkhMGfOHNSuXRsKhQJOTk4YP368evqLh0BdXFwAAH369IFMJlO/f/Hw5K+//gpzc3MkJydr1DdhwgS888476vcnT55E+/btoVQq4ezsjPHjxyM9PV3rvtC2f+/du4du3bpBqVTC1dW1wM8wISEBH330EapUqYJq1aqhV69euHnzptZ1FKZbt274+uuv0adPnyLnMTU1Rffu3REaGvpa26KyjwFIZdqlS5dw+vRpjefEBQUFYfPmzVi9ejX++ecfTJw4ER9//DFOnDgBALhz5w46dOgAhUKB3377DefOncMnn3yCnJwcAM+f2u7n54eTJ0/ijz/+QIMGDdC9e/fXOncXERGh1bMR8x/WqVKpsHv3bkyYMAGTJk3CpUuXMHLkSAwbNgzHjh0DAOzcuVO9B3z16lX8/PPPaNasWaHrPXv2LABgw4YNuHfvnvr9izp37owqVaponN/Kzc3Ftm3b4OvrC+D5A327du2Kfv364e+//8a2bdtw8uRJjB07Vuu+0LZ/v/zyS/Tr1w8XLlyAr68vBgwYgMuXLwMAsrOz4ePjAysrK0RERODUqVOwtLRE165doVKpCt3uxo0bIZPJtK6zOB4eHoiIiNDLuqgMe82nWBDplZ+fnzA1NRWVK1cWCoVCABAmJiYiLCxMCCHEs2fPhIWFhTh9+rTGcsOHDxcDBw4UQggxffp0UbduXaFSqbTaZm5urrCyshL79u1TtwEQu3fvFkIIERcXJwCI8+fPF7kONzc3MXfuXI22/Ee85D/C5u7du6Jt27aiZs2aIisrS7Rt21b4+/trLPPhhx+K7t27CyGEWLp0qWjYsGGRn6NOnTri22+/LbTmfIGBgcLNzU39fsKECeKdd95Rvz98+LBQKBTqGocPHy5GjBihsY6IiAhhYmIiMjMzC63j5W28rKj+HTVqlMZ8np6e4rPPPhNCCPHTTz+JRo0aiby8PPX0rKwsoVQqxeHDh4UQBR8ztWvXLtGoUaMi63hZYf2Vb8+ePcLExETk5uZqvT4qf7gHSGVO/tPT//zzT/j5+WHYsGHo168fAODatWvIyMhAly5dYGlpqX5t3rxZfYgzOjoa7du3h5mZWaHrT0pKgr+/Pxo0aAAbGxtYW1sjLS0N8fHxJa45MzMT5ubmhU6rVasWKleuDCcnJ6Snp2Pnzp2Qy+W4fPky2rVrpzFvu3bt1HtBH374ITIzM+Hq6gp/f3/s3r1bvRdbUr6+vjh+/Dju3r0LANiyZQt69OiBKlWqAAAuXLiAjRs3avStj48P8vLyEBcXp9U2tO3fl5/e7eXlpf7sFy5cwLVr12BlZaWuo1q1anj27Jn65/yyPn364MqVK7p0R5GUSiXy8vKQlZWll/VR2VTJ2AUQvaxy5cqoX78+AGD9+vVwc3PDunXrMHz4cKSlpQEA9u/fX+B8m0KhAPB/hxmL4ufnh0ePHuG7775DnTp1oFAo4OXlVeShNW3Y2triyZMnhU6LiIiAtbU17Ozs1FeIasPZ2RmxsbE4evQojhw5gtGjR2Px4sU4ceJEkeH+Km+99Rbq1auH0NBQfPbZZ9i9ezc2btyonp6WloaRI0dqnGvMV7t2ba22oY/+TUtLQ6tWrbBly5YC02rUqKH1ekrq8ePHqFy58it/l6h8YwBSmWZiYoIZM2YgICAAgwYNQtOmTaFQKBAfH4+OHTsWukzz5s2xadMmZGdnFxoUp06dwsqVK9G9e3cAzy+2ePjw4WvV6e7ujpiYmEKn1a1bV72H9aImTZrg1KlT8PPz06itadOm6vdKpRI9e/ZEz549MWbMGDRu3BgXL15Ey5YtC6zPzMxMq6tLfX19sWXLFtSqVQsmJibo0aOHelrLli0RExOj/gOkJLTt3z/++ANDhgzReO/u7q6uY9u2bbCzs4O1tXWJaympS5cuqWuhiouHQKnM+/DDD2FqaoqQkBBYWVlh8uTJmDhxIjZt2oTr168jKioKy5cvx6ZNmwAAY8eORWpqKgYMGIC//voLV69exU8//YTY2FgAQIMGDfDTTz/h8uXL+PPPP+Hr6/vaf+n7+PggMjJSp+ENU6ZMwcaNG7Fq1SpcvXoVy5Ytw65duzB58mQAzy/qWLduHS5duoQbN27gv//9L5RKJerUqVPo+lxcXBAeHo7ExMQi90aB5wEYFRWF+fPn44MPPlDvOQPA1KlTcfr0aYwdOxbR0dG4evUq9uzZo9NFMNr2744dO7B+/Xr8+++/CAwMxJkzZ9Tb8fX1ha2tLXr16oWIiAjExcXh+PHjGD9+PG7fvl3odnfv3o3GjRsXW1taWhqio6PVNzWIi4tDdHR0gcOzERERePfdd7X+zFROGfskJNGLXr6wIV9QUJCoUaOGSEtLE3l5eSI4OFg0atRImJmZiRo1aggfHx9x4sQJ9fwXLlwQ7777rrCwsBBWVlaiffv24vr160IIIaKiokTr1q2Fubm5aNCggdixY0exF5RocxFMdna2cHJyEocOHVK3vXwRTGFWrlwpXF1dhZmZmWjYsKHYvHmzetru3buFp6ensLa2FpUrVxZt2rQRR48eVU9/uea9e/eK+vXri0qVKok6deoIIYq+QMXDw0MAEL/99luBaWfOnBFdunQRlpaWonLlyqJ58+Zi/vz5RX6Gl7ehbf+GhISILl26CIVCIVxcXMS2bds01nvv3j0xZMgQYWtrKxQKhXB1dRX+/v4iJSVFCFHwd2XDhg3iVV9p+T+Tl19+fn7qeW7fvi3MzMxEQkJCseui8k8mhBBGyl6iCiUkJAR79+7F4cOHjV0KvYapU6fiyZMnWLNmjbFLIQPjOUAiPRk5ciSSk5Px9OlTnS52obLFzs4OAQEBxi6DSgH3AImISJJ4EQwREUkSA5CIiCSJAUhERJLEACQiIkliABIRkSQxAImISJIYgEREJEkMQCIikiQGIBERSdL/AzdHcz48o9s6AAAAAElFTkSuQmCC",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -874,16 +1085,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7a85266db220>"
+       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7aa4ec614e80>"
       ]
      },
-     "execution_count": 43,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -904,16 +1115,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7a8526810190>"
+       "<sklearn.metrics._plot.precision_recall_curve.PrecisionRecallDisplay at 0x7aa4ec62ef80>"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -934,22 +1145,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/johanan/.local/lib/python3.10/site-packages/sklearn/base.py:486: UserWarning: X has feature names, but LogisticRegression was fitted without feature names\n",
+      "  warnings.warn(\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7a85267e9f30>"
+       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7aa4ec52ef20>"
       ]
      },
-     "execution_count": 45,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAcAAAAGyCAYAAABzzxS5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAABSEUlEQVR4nO3deVgT5/428DssCaAsWkAWqbgrVQG1WLGtG4rVuldRqaLHpe5WqnUHtVVsXYp1o65of/bgUrWeqrhQtYocFxA3EKuAqAWVIiCCBMnz/uFLjpHFBBMQc3+uK5fmmWdmvhlCbmbyzIxECCFARESkZwwquwAiIqLKwAAkIiK9xAAkIiK9xAAkIiK9xAAkIiK9xAAkIiK9xAAkIiK9xAAkIiK9xAAkIiK9ZFTZBVQ0hUKBv//+G+bm5pBIJJVdDhERaUgIgcePH8PBwQEGBq+xHycq0cmTJ8Wnn34q7O3tBQCxd+/eV85z/Phx4e7uLqRSqahfv77YsmWLRuu8c+eOAMAHH3zwwUcVf9y5c6d84fP/Veoe4JMnT+Dq6op//etf6Nev3yv7JyUloUePHhg7diy2b9+OiIgIjBo1Cvb29vD29lZrnebm5gCAO3fuwMLC4rXqJyKiipednQ0nJyfl53l5SYR4My6GLZFIsHfvXvTp06fUPjNmzMCBAwdw9epVZdugQYOQmZmJ8PBwtdaTnZ0NS0tLZGVllRmAQgjkFRSqXT8REemWqbEhJBKJ2p/jr1KlvgOMioqCl5eXSpu3tze+/PLLUufJz89Hfn6+8nl2dvYr1yOEwGchUYi+/ajctRIRkXbFLfSGmVR7sVWlRoGmpaWhVq1aKm21atVCdnY28vLySpwnKCgIlpaWyoeTk9Mr15NXUMjwIyJ6y1WpPcDymDVrFvz9/ZXPi44dq+vCXC+YSQ11URoREWnA1Fi7n8VVKgDt7Oxw//59lbb79+/DwsICpqamJc4jk8kgk8nKvU4zqaFWd7mJiOjNUKUOgbZt2xYREREqbUePHkXbtm0rqSIiIqqqKjUAc3JyEBsbi9jYWADPT3OIjY1FSkoKgOeHL4cNG6bsP3bsWCQmJuLrr7/G9evXsXbtWuzcuRNTp06tjPKJiKgKq9QAvHDhAtzd3eHu7g4A8Pf3h7u7OwICAgAAqampyjAEgLp16+LAgQM4evQoXF1dsXz5cmzcuFHtcwCJiIiKVOqXWx06dEBZpyGGhoaWOM/Fixe1VkNJ5/vlynn+HxHR206vR3fwfD8iIv1VpQbBaNurzvdrXaeG1ofdEhHRm0Gv9wBfVNL5fkWX3SEiorcPA/D/4/l+RET6Ra8PgRIRkf5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV5iABIRkV4yKs9MKSkpuH37NnJzc2FjY4P33nsPMplM27URERHpjNoBmJycjHXr1iEsLAx3796FEEI5TSqV4qOPPsKYMWPQv39/GBhwx5KIiN5saiXV5MmT4erqiqSkJHz77beIi4tDVlYW5HI50tLScPDgQXz44YcICAhAixYtcP78eV3XTURE9FrU2gOsVq0aEhMT8c477xSbZmtri06dOqFTp04IDAxEeHg47ty5g/fff1/rxRIREWmLWgEYFBSk9gK7detW7mKIiIgqCr+sIyIivaS1AIyPj0e9evW0tTgiIiKd0loAyuVy3L59W1uLIyIi0im1T4Pw9/cvc/rDhw9fuxgiIqKKovYe4MqVK3Hy5ElcvHixxMf169fLVcCaNWvg7OwMExMTtGnTBufOnSuzf3BwMBo3bgxTU1M4OTlh6tSpePr0abnWTURE+kvtPcAGDRpg6tSp+Pzzz0ucHhsbi1atWmm08h07dsDf3x8hISFo06YNgoOD4e3tjYSEBNja2hbr/8svv2DmzJnYvHkzPD09cePGDQwfPhwSiQQrVqzQaN1ERKTf1N4DbN26NaKjo0udLpFIVK4Oo44VK1Zg9OjRGDFiBFxcXBASEgIzMzNs3ry5xP5nzpxBu3btMGTIEDg7O6Nr164YPHjwK/caiYiIXqZ2AC5fvhxffvllqdNdXV2hUCjUXrFcLkd0dDS8vLz+V4yBAby8vBAVFVXiPJ6enoiOjlYGXmJiIg4ePIju3buXup78/HxkZ2erPIiIiNQ+BGpnZ6fVFaenp6OwsBC1atVSaa9Vq1ap3ycOGTIE6enp+PDDDyGEwLNnzzB27FjMnj271PUEBQVhwYIFWq2diIiqvip1IvyJEyewePFirF27FjExMdizZw8OHDiAb775ptR5Zs2ahaysLOXjzp07FVgxERG9qcp1OyRtsLa2hqGhIe7fv6/Sfv/+/VL3NufNm4ehQ4di1KhRAIDmzZvjyZMnGDNmDObMmVPiXShkMhlv1URERMVU2h6gVCpFq1atEBERoWxTKBSIiIhA27ZtS5wnNze3WMgZGhoCgMYDcIiISL9V2h4g8Pzkej8/P7Ru3RoeHh4IDg7GkydPMGLECADAsGHD4OjoqLwYd8+ePbFixQq4u7ujTZs2uHnzJubNm4eePXsqg5CIiEgdlRqAPj4+ePjwIQICApCWlgY3NzeEh4crB8akpKSo7PHNnTsXEokEc+fOxb1792BjY4OePXti0aJFlfUSiIioipKIchw7/PPPP2FmZobWrVsr2y5cuIDc3Fx8/PHHWi1Q27Kzs2FpaYmsrCwYmZjBJeAwACBuoTfMpJX69wAREanhxc9xCwuLci+nXJ/4HTp0QJMmTRAXF6dsGzp0KG7cuIHCwsJyF0NERFRRyhWASUlJMDY2VmmLiIhAQUGBVooiIiLStXIFYJ06dYq1OTg4vHYxREREFaVKnQhPRESkLWrtAdaoUQMSiUStBWZkZLxWQURERBVBrQAMDg7WcRlEREQVS60A9PPz03UdREREFapc3wHeunULc+fOxeDBg/HgwQMAwKFDh3Dt2jWtFkdERKQrGgfgyZMn0bx5c5w9exZ79uxBTk4OAODSpUsIDAzUeoFERES6oHEAzpw5E99++y2OHj0KqVSqbO/UqRP++9//arU4IiIiXdE4AK9cuYK+ffsWa7e1tUV6erpWiiIiItI1jQPQysoKqampxdovXrwIR0dHrRRFRESkaxoH4KBBgzBjxgykpaVBIpFAoVAgMjIS06ZNw7Bhw3RRIxERkdZpHICLFy9GkyZN4OTkhJycHLi4uODjjz+Gp6cn5s6dq4saiYiItE7ja4FKpVJs2LAB8+bNw9WrV5GTkwN3d3c0bNhQF/URERHpRLlvgPfuu+/CyckJANS+TBoREdGbolwnwm/atAnNmjWDiYkJTExM0KxZM2zcuFHbtREREemMxnuAAQEBWLFiBSZNmoS2bdsCAKKiojB16lSkpKRg4cKFWi+SiIhI2zQOwHXr1mHDhg0YPHiwsq1Xr15o0aIFJk2axAAkIqIqQeNDoAUFBWjdunWx9latWuHZs2daKYqIiEjXNA7AoUOHYt26dcXa169fD19fX60URUREpGtqHQL19/dX/l8ikWDjxo04cuQIPvjgAwDA2bNnkZKSwhPhiYioylArAC9evKjyvFWrVgCe3xYJAKytrWFtbc3bIRERUZWhVgAeP35c13UQERFVqHKdB0hERFTVletKMBcuXMDOnTuRkpICuVyuMm3Pnj1aKYyIiEiXNN4DDAsLg6enJ+Lj47F3714UFBTg2rVr+OOPP2BpaamLGomIiLSuXHeD+OGHH/Cf//wHUqkUK1euxPXr1zFw4EC8++67uqiRiIhI6zQOwFu3bqFHjx4Ant8Z4smTJ5BIJJg6dSrWr1+v9QKJiIh0QeMArFGjBh4/fgwAcHR0xNWrVwEAmZmZyM3N1W51REREOqLxIJiPP/4YR48eRfPmzTFgwABMmTIFf/zxB44ePYrOnTvrokYiIiKt0zgAV69ejadPnwIA5syZA2NjY5w5cwb9+/fnHeGJiKjK0DgAa9asqfy/gYEBZs6cqdWCiIiIKoJaAZidna32Ai0sLMpdDBERUUVRKwCtrKwgkUjK7COEgEQiQWFhoVYKIyIi0iVeC5SIiPSSWgHYvn17XddBRERUoXgxbCIi0ksMQCIi0ksMQCIi0ksMQCIi0kvlCsBnz57h2LFj+Omnn5TXBf3777+Rk5Oj1eKIiIh0ReMrwdy+fRvdunVDSkoK8vPz0aVLF5ibm+O7775Dfn4+QkJCdFEnERGRVmm8BzhlyhS0bt0ajx49gqmpqbK9b9++iIiI0GpxREREuqLxHuCpU6dw5swZSKVSlXZnZ2fcu3dPa4URERHpksZ7gAqFosTLnd29exfm5uZaKYqIiEjXNA7Arl27Ijg4WPlcIpEgJycHgYGB6N69uzZrIyIi0hmND4EuX74c3t7ecHFxwdOnTzFkyBD89ddfsLa2xr///W9d1EhERKR1Ggdg7dq1cenSJYSFheHy5cvIycnByJEj4evrqzIohoiI6E2mcQA+ffoUJiYm+Pzzz3VRDxERUYXQ+DtAW1tb+Pn54ejRo1AoFLqoiYiISOc0DsCtW7ciNzcXvXv3hqOjI7788ktcuHBBF7URERHpjMYB2LdvX+zatQv379/H4sWLERcXhw8++ACNGjXCwoULdVEjERGR1pX7Ytjm5uYYMWIEjhw5gsuXL6NatWpYsGCBNmsjIiLSmXIH4NOnT7Fz50706dMHLVu2REZGBqZPn67N2oiIiHRG41Gghw8fxi+//IJ9+/bByMgIn332GY4cOYKPP/5YF/URERHphMYB2LdvX3z66afYtm0bunfvDmNjY13URUREpFMaB+D9+/d5zU8iIqry1ArA7OxsWFhYAACEEMjOzi61b1E/IiKiN5laAVijRg2kpqbC1tYWVlZWkEgkxfoIISCRSEq8UwQREdGbRq0A/OOPP1CzZk0AwPHjx3VaEBERUUVQKwDbt2+v/H/dunXh5ORUbC9QCIE7d+5otzoiIiId0fg8wLp16+Lhw4fF2jMyMlC3bl2NC1izZg2cnZ1hYmKCNm3a4Ny5c2X2z8zMxIQJE2Bvbw+ZTIZGjRrh4MGDGq+XiIj0m8ajQIu+63tZTk4OTExMNFrWjh074O/vj5CQELRp0wbBwcHw9vZGQkICbG1ti/WXy+Xo0qULbG1tsXv3bjg6OuL27duwsrLS9GUQEZGeUzsA/f39ATy/A/y8efNgZmamnFZYWIizZ8/Czc1No5WvWLECo0ePxogRIwAAISEhOHDgADZv3oyZM2cW679582ZkZGTgzJkzyvMPnZ2dNVonERERoEEAXrx4EcDzPcArV65AKpUqp0mlUri6umLatGlqr1gulyM6OhqzZs1SthkYGMDLywtRUVElzrN//360bdsWEyZMwG+//QYbGxsMGTIEM2bMgKGhYYnz5OfnIz8/X/m8rFM4iIhIf6gdgEWjP0eMGIGVK1e+9vl+6enpKCwsRK1atVTaa9WqhevXr5c4T2JiIv744w/4+vri4MGDuHnzJsaPH4+CggIEBgaWOE9QUBAv0k1ERMVoPAhmy5YtlXayu0KhgK2tLdavX49WrVrBx8cHc+bMQUhISKnzzJo1C1lZWcoHR6oSERGg5h5gv379EBoaCgsLC/Tr16/Mvnv27FFrxdbW1jA0NMT9+/dV2u/fvw87O7sS57G3t4exsbHK4c6mTZsiLS0Ncrlc5bBsEZlMBplMplZNRESkP9TaA7S0tFSO/LS0tCzzoS6pVIpWrVohIiJC2aZQKBAREYG2bduWOE+7du1w8+ZNKBQKZduNGzdgb29fYvgRERGVRq09wC1btpT4/9fl7+8PPz8/tG7dGh4eHggODsaTJ0+Uo0KHDRsGR0dHBAUFAQDGjRuH1atXY8qUKZg0aRL++usvLF68GJMnT9ZaTUREpB80Pg8wLy8PQgjlaRC3b9/G3r174eLigq5du2q0LB8fHzx8+BABAQFIS0uDm5sbwsPDlQNjUlJSYGDwv51UJycnHD58GFOnTkWLFi3g6OiIKVOmYMaMGZq+DCIi0nMSIYTQZIauXbuiX79+GDt2LDIzM9G4cWNIpVKkp6djxYoVGDdunK5q1Yrs7GxYWloiKysLRiZmcAk4DACIW+gNM6nGfw8QEVEFe/Fz/HUGZWo8CjQmJgYfffQRAGD37t2ws7PD7du3sW3bNvz444/lLoSIiKgiaRyAubm5yhviHjlyBP369YOBgQE++OAD3L59W+sFEhER6YLGAdigQQPs27cPd+7cweHDh5Xf+z148IA3wyUioipD4wAMCAjAtGnT4OzsDA8PD+UpC0eOHIG7u7vWCyQiItIFjUd9fPbZZ/jwww+RmpoKV1dXZXvnzp3Rt29frRZHRESkK+Ua9mhnZwc7OzvcvXsXAFC7dm14eHhotTAiIiJd0vgQqEKhwMKFC2FpaYk6deqgTp06sLKywjfffKNyhRYiIqI3mcZ7gHPmzMGmTZuwZMkStGvXDgBw+vRpzJ8/H0+fPsWiRYu0XiQREZG2aRyAW7duxcaNG9GrVy9lW9FVWcaPH88AJCKiKkHjQ6AZGRlo0qRJsfYmTZogIyNDK0URERHpmsYB6OrqitWrVxdrX716tcqoUCIiojeZxodAv//+e/To0QPHjh1TngMYFRWFO3fu4ODBg1ovkIiISBc03gNs3749bty4gX79+iEzMxOZmZno168fEhISlNcIJSIietNptAeYnJyMo0ePQi6XY9CgQWjWrJmu6iIiItIptQPw+PHj+PTTT5GXl/d8RiMjbN68GZ9//rnOiiMiItIVtQ+Bzps3D126dMG9e/fwzz//YPTo0fj66691WRsREZHOqB2AV69exeLFi2Fvb48aNWpg6dKlePDgAf755x9d1kdERKQTagdgdnY2rK2tlc/NzMxgamqKrKwsnRRGRESkSxoNgjl8+DAsLS2VzxUKBSIiInD16lVl24tXiCEiInpTaRSAfn5+xdq++OIL5f8lEgkKCwtfvyoiIiIdUzsAeacHIiJ6m2h8IjwREdHbQK0A/O9//6v2AnNzc3Ht2rVyF0RERFQR1ArAoUOHwtvbG7t27cKTJ09K7BMXF4fZs2ejfv36iI6O1mqRRERE2qbWd4BxcXFYt24d5s6diyFDhqBRo0ZwcHCAiYkJHj16hOvXryMnJwd9+/bFkSNH0Lx5c13XTURE9FokQgihyQwXLlzA6dOncfv2beTl5cHa2hru7u7o2LEjatasqas6tSY7OxuWlpbIysqCkYkZXAIOAwDiFnrDTKrxzTGIiKiCvfg5bmFhUe7laPyJ37p1a7Ru3brcKyQiInoTcBQoERHpJQYgERHpJQYgERHpJQYgERHppdcKwKdPn2qrDiIiogqlcQAqFAp88803cHR0RPXq1ZGYmAjg+Q1zN23apPUCiYiIdEHjAPz2228RGhqK77//HlKpVNnerFkzbNy4UavFERER6YrGAbht2zasX78evr6+MDQ0VLa7urri+vXrWi2OiIhIVzQOwHv37qFBgwbF2hUKBQoKCrRSFBERka5pHIAuLi44depUsfbdu3fD3d1dK0URERHpmsaXQgsICICfnx/u3bsHhUKBPXv2ICEhAdu2bcPvv/+uixqJiIi0TuM9wN69e+M///kPjh07hmrVqiEgIADx8fH4z3/+gy5duuiiRiIiIq0r1+0PPvroIxw9elTbtRAREVUYjfcA69Wrh3/++adYe2ZmJurVq6eVooiIiHRN4wBMTk5GYWFhsfb8/Hzcu3dPK0URERHpmtqHQPfv36/8/+HDh2Fpaal8XlhYiIiICDg7O2u1OCIiIl1ROwD79OkDAJBIJPDz81OZZmxsDGdnZyxfvlyrxREREemK2gGoUCgAAHXr1sX58+dhbW2ts6KIiIh0TeNRoElJSbqog4iIqEKV6zSIJ0+e4OTJk0hJSYFcLleZNnnyZK0URkREpEsaB+DFixfRvXt35Obm4smTJ6hZsybS09NhZmYGW1tbBiAREVUJGp8GMXXqVPTs2ROPHj2Cqakp/vvf/+L27dto1aoVli1bposaiYiItE7jAIyNjcVXX30FAwMDGBoaIj8/H05OTvj+++8xe/ZsXdRIRESkdRoHoLGxMQwMns9ma2uLlJQUAIClpSXu3Lmj3eqIiIh0ROPvAN3d3XH+/Hk0bNgQ7du3R0BAANLT0/Hzzz+jWbNmuqiRiIhI6zTeA1y8eDHs7e0BAIsWLUKNGjUwbtw4PHz4ED/99JPWCyQiItIFjfcAW7durfy/ra0twsPDtVoQERFRRdB4D7A0MTEx+PTTT7W1OCIiIp3SKAAPHz6MadOmYfbs2UhMTAQAXL9+HX369MH777+vvFwaERHRm07tQ6CbNm3C6NGjUbNmTTx69AgbN27EihUrMGnSJPj4+ODq1ato2rSpLmslIiLSGrX3AFeuXInvvvsO6enp2LlzJ9LT07F27VpcuXIFISEhDD8iIqpS1A7AW7duYcCAAQCAfv36wcjICEuXLkXt2rV1VhwREZGuqB2AeXl5MDMzA/D8noAymUx5OgQREVFVo9FpEBs3bkT16tUBAM+ePUNoaGix+wLyYthERFQVSIQQQp2Ozs7OkEgkZS9MIlGODtXEmjVrsHTpUqSlpcHV1RWrVq2Ch4fHK+cLCwvD4MGD0bt3b+zbt0+tdWVnZ8PS0hJZWVkwMjGDS8BhAEDcQm+YSct1dygiIqpAL36OW1hYlHs5an/iJycnl3slZdmxYwf8/f0REhKCNm3aIDg4GN7e3khISICtrW2Z9UybNg0fffSRTuoiIqK3m9ZOhC+vFStWYPTo0RgxYgRcXFwQEhICMzMzbN68udR5CgsL4evriwULFqBevXoVWC0REb0tKjUA5XI5oqOj4eXlpWwzMDCAl5cXoqKiSp1v4cKFsLW1xciRI1+5jvz8fGRnZ6s8iIiIKjUA09PTUVhYiFq1aqm016pVC2lpaSXOc/r0aWzatAkbNmxQax1BQUGwtLRUPpycnF67biIiqvoq/RCoJh4/foyhQ4diw4YNxUaflmbWrFnIyspSPnjPQiIiAspxNwhtsra2hqGhIe7fv6/Sfv/+fdjZ2RXrf+vWLSQnJ6Nnz57KtqLrjxoZGSEhIQH169dXmUcmk0Emk+mgeiIiqsrKtQd469YtzJ07F4MHD8aDBw8AAIcOHcK1a9c0Wo5UKkWrVq0QERGhbFMoFIiIiEDbtm2L9W/SpAmuXLmC2NhY5aNXr17o2LEjYmNjeXiTiIjUpnEAnjx5Es2bN8fZs2exZ88e5OTkAAAuXbqEwMBAjQvw9/fHhg0bsHXrVsTHx2PcuHF48uQJRowYAQAYNmwYZs2aBQAwMTFBs2bNVB5WVlYwNzdHs2bNIJVKNV4/ERHpJ40Pgc6cORPffvst/P39YW5urmzv1KkTVq9erXEBPj4+ePjwIQICApCWlgY3NzeEh4crB8akpKTAwKBKfVVJRERVgNpXgilSvXp1XLlyBXXr1oW5uTkuXbqEevXqITk5GU2aNMHTp091VatW8EowRERVm7auBKPxrpWVlRVSU1OLtV+8eBGOjo7lLoSIiKgiaRyAgwYNwowZM5CWlgaJRAKFQoHIyEhMmzYNw4YN00WNREREWqdxAC5evBhNmjSBk5MTcnJy4OLigo8//hienp6YO3euLmokIiLSOo2/9JJKpdiwYQPmzZuHq1evIicnB+7u7mjYsKEu6iMiItIJjQPw9OnT+PDDD/Huu+/i3Xff1UVNREREOqfxIdBOnTqhbt26mD17NuLi4nRRExERkc5pHIB///03vvrqK5w8eRLNmjWDm5sbli5dirt37+qiPiIiIp3QOACtra0xceJEREZG4tatWxgwYAC2bt0KZ2dndOrUSRc1EhERad1rXWKlbt26mDlzJpYsWYLmzZvj5MmT2qqLiIhIp8odgJGRkRg/fjzs7e0xZMgQNGvWDAcOHNBmbURERDqj8SjQWbNmISwsDH///Te6dOmClStXonfv3jAzM9NFfURERDqhcQD++eefmD59OgYOHKj2TWmJiIjeNBoHYGRkpC7qICIiqlBqBeD+/fvxySefwNjYGPv37y+zb69evbRSGBERkS6pFYB9+vRBWloabG1t0adPn1L7SSQSFBYWaqs2IiIinVErABUKRYn/JyIiqqo0Pg1i27ZtyM/PL9Yul8uxbds2rRRFRESkaxoH4IgRI5CVlVWs/fHjxxgxYoRWiiIiItI1jQNQCAGJRFKs/e7du7C0tNRKUURERLqm9mkQ7u7ukEgkkEgk6Ny5M4yM/jdrYWEhkpKS0K1bN50USUREpG1qB2DR6M/Y2Fh4e3ujevXqymlSqRTOzs7o37+/1gskIiLSBbUDMDAwEADg7OwMHx8fmJiY6KwoIiIiXdP4SjB+fn66qIOIiKhCqRWANWvWxI0bN2BtbY0aNWqUOAimSEZGhtaKIyIi0hW1AvCHH36Aubm58v9lBSAREVFVoFYAvnjYc/jw4bqqhYiIqMJofB5gTEwMrly5onz+22+/oU+fPpg9ezbkcrlWiyMiItIVjQPwiy++wI0bNwAAiYmJ8PHxgZmZGXbt2oWvv/5a6wUSERHpgsYBeOPGDbi5uQEAdu3ahfbt2+OXX35BaGgofv31V23XR0REpBPluhRa0R0hjh07hu7duwMAnJyckJ6ert3qiIiIdETjAGzdujW+/fZb/Pzzzzh58iR69OgBAEhKSkKtWrW0XiAREZEuaByAwcHBiImJwcSJEzFnzhw0aNAAALB79254enpqvUAiIiJd0PhKMC1atFAZBVpk6dKlMDQ01EpRREREuqZxABaJjo5GfHw8AMDFxQUtW7bUWlFERES6pnEAPnjwAD4+Pjh58iSsrKwAAJmZmejYsSPCwsJgY2Oj7RqJiIi0TuPvACdNmoScnBxcu3YNGRkZyMjIwNWrV5GdnY3JkyfrokYiIiKt03gPMDw8HMeOHUPTpk2VbS4uLlizZg26du2q1eKIiIh0ReM9QIVCAWNj42LtxsbGyvMDiYiI3nQaB2CnTp0wZcoU/P3338q2e/fuYerUqejcubNWiyMiItIVjQNw9erVyM7OhrOzM+rXr4/69eujbt26yM7OxqpVq3RRIxERkdZp/B2gk5MTYmJiEBERoTwNomnTpvDy8tJ6cURERLqiUQDu2LED+/fvh1wuR+fOnTFp0iRd1UVERKRTagfgunXrMGHCBDRs2BCmpqbYs2cPbt26haVLl+qyPiIiIp1Q+zvA1atXIzAwEAkJCYiNjcXWrVuxdu1aXdZGRESkM2oHYGJiIvz8/JTPhwwZgmfPniE1NVUnhREREemS2gGYn5+PatWq/W9GAwNIpVLk5eXppDAiIiJd0mgQzLx582BmZqZ8LpfLsWjRIlhaWirbVqxYob3qiIiIdETtAPz444+RkJCg0ubp6YnExETlc4lEor3KiIiIdEjtADxx4oQOyyAiIqpYGl8JhoiI6G3AACQiIr3EACQiIr3EACQiIr3EACQiIr1UrgA8deoUPv/8c7Rt2xb37t0DAPz88884ffq0VosjIiLSFY0D8Ndff4W3tzdMTU1x8eJF5OfnAwCysrKwePFirRdIRESkCxoH4LfffouQkBBs2LABxsbGyvZ27dohJiZGq8URERHpisYBmJCQgI8//rhYu6WlJTIzM7VRExERkc5pHIB2dna4efNmsfbTp0+jXr16WimKiIhI1zQOwNGjR2PKlCk4e/YsJBIJ/v77b2zfvh3Tpk3DuHHjdFEjERGR1ml0NwgAmDlzJhQKBTp37ozc3Fx8/PHHkMlkmDZtGiZNmqSLGomIiLRO4wCUSCSYM2cOpk+fjps3byInJwcuLi6oXr26LuojIiLSiXKfCC+VSuHi4gIPD4/XDr81a9bA2dkZJiYmaNOmDc6dO1dq3w0bNuCjjz5CjRo1UKNGDXh5eZXZn4iIqCQa7wF27NixzPv+/fHHHxotb8eOHfD390dISAjatGmD4OBgeHt7IyEhAba2tsX6nzhxAoMHD4anpydMTEzw3XffoWvXrrh27RocHR01fTlERKSnNN4DdHNzg6urq/Lh4uICuVyOmJgYNG/eXOMCVqxYgdGjR2PEiBFwcXFBSEgIzMzMsHnz5hL7b9++HePHj4ebmxuaNGmCjRs3QqFQICIiQuN1ExGR/tJ4D/CHH34osX3+/PnIycnRaFlyuRzR0dGYNWuWss3AwABeXl6IiopSaxm5ubkoKChAzZo1S5yen5+vvFoNAGRnZ2tUIxERvZ20djHszz//vNS9ttKkp6ejsLAQtWrVUmmvVasW0tLS1FrGjBkz4ODgAC8vrxKnBwUFwdLSUvlwcnLSqEYiIno7aS0Ao6KiYGJioq3FqWXJkiUICwvD3r17S133rFmzkJWVpXzcuXOnQmskIqI3k8aHQPv166fyXAiB1NRUXLhwAfPmzdNoWdbW1jA0NMT9+/dV2u/fvw87O7sy5122bBmWLFmCY8eOoUWLFqX2k8lkkMlkGtVFRERvP433AF88nGhpaYmaNWuiQ4cOOHjwIAIDAzVallQqRatWrVQGsBQNaGnbtm2p833//ff45ptvEB4ejtatW2v6EoiIiDTbAywsLMSIESPQvHlz1KhRQysF+Pv7w8/PD61bt4aHhweCg4Px5MkTjBgxAgAwbNgwODo6IigoCADw3XffISAgAL/88gucnZ2V3xVWr16dJ+MTEZHaNApAQ0NDdO3aFfHx8VoLQB8fHzx8+BABAQFIS0uDm5sbwsPDlQNjUlJSYGDwvx3VdevWQS6X47PPPlNZTmBgIObPn6+VmoiI6O2n8XeAzZo1Q2JiIurWrau1IiZOnIiJEyeWOO3EiRMqz5OTk7W2XiIi0l/luiHutGnT8PvvvyM1NRXZ2dkqDyIioqpA7T3AhQsX4quvvkL37t0BAL169VK5JJoQAhKJBIWFhdqvkoiISMvUDsAFCxZg7NixOH78uC7rISIiqhBqB6AQAgDQvn17nRVDRERUUTT6DrCsu0AQERFVJRqNAm3UqNErQzAjI+O1CiIiIqoIGgXgggULYGlpqataiIiIKoxGATho0KASb1JLRERU1aj9HSC//yMioreJ2gFYNAqUiIjobaD2IVCFQqHLOoiIiCqU1m6IS0REVJUwAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8xAImISC8ZVXYB9PYqLCxEQUFBZZdBRFWMoaEhjIyMIJFIdLoeBiDpRE5ODu7evQshRGWXQkRVkJmZGezt7SGVSnW2DgYgaV1hYSHu3r0LMzMz2NjY6PyvOCJ6ewghIJfL8fDhQyQlJaFhw4YwMNDNt3UMQNK6goICCCFgY2MDU1PTyi6HiKoYU1NTGBsb4/bt25DL5TAxMdHJejgIhnSGe35EVF662utTWYfO10BERPQGYgASEZFeYgASVSBnZ2cEBweXe/7Q0FBYWVlprZ6q6sSJE5BIJMjMzNT5uv755x/Y2toiOTlZ5+vSF4MGDcLy5csruwwGIFGR4cOHo0+fPjpdx/nz5zFmzBi1+pYUlj4+Prhx44ba6+vQoQMkEgkkEglMTEzQqFEjBAUFVfnTUzw9PZGamgpLS0udr2vRokXo3bs3nJ2di03z9vaGoaEhzp8/X2xahw4d8OWXXxZrL+mPmOzsbMyZMwdNmjSBiYkJ7Ozs4OXlhT179ujsZ5WamoohQ4agUaNGMDAwKLHWkqSkpKBHjx4wMzODra0tpk+fjmfPnqn0OXHiBFq2bAmZTIYGDRogNDRUZfrcuXOxaNEiZGVlaenVlA8DkKgC2djYwMzMrNzzm5qawtbWVqN5Ro8ejdTUVCQkJGDWrFkICAhASEhIuWtQh1wu1+nypVIp7OzsdD7QKjc3F5s2bcLIkSOLTUtJScGZM2cwceJEbN68udzryMzMhKenJ7Zt24ZZs2YhJiYGf/75J3x8fPD111/rLCTy8/NhY2ODuXPnwtXVVa15CgsL0aNHD8jlcpw5cwZbt25FaGgoAgIClH2SkpLQo0cPdOzYEbGxsfjyyy8xatQoHD58WNmnWbNmqF+/Pv7v//5P669LI0LPZGVlCQAiKytLPMkvEHVm/C7qzPhdPMkvqOzS3hp5eXkiLi5O5OXlCSGEUCgU4kl+QaU8FAqF2nX7+fmJ3r17lzr9xIkT4v333xdSqVTY2dmJGTNmiIKC/71vsrOzxZAhQ4SZmZmws7MTK1asEO3btxdTpkxR9qlTp4744YcflNslMDBQODk5CalUKuzt7cWkSZOEEEK0b99eAFB5CCHEli1bhKWlpUpd+/fvF61btxYymUy88847ok+fPsppL69fCCFatmwp+vbtq3z+9OlT8dVXXwkHBwdhZmYmPDw8xPHjx1XmWb9+vahdu7YwNTUVffr0EcuXL1epIzAwULi6uooNGzYIZ2dnIZFIhBBCPHr0SIwcOVJYW1sLc3Nz0bFjRxEbG6ucLzY2VnTo0EFUr15dmJubi5YtW4rz588LIYRITk4Wn376qbCyshJmZmbCxcVFHDhwQAghxPHjxwUA8ejRI+Wydu/eLVxcXIRUKhV16tQRy5YtU3kNderUEYsWLRIjRowQ1atXF05OTuKnn34SZdm1a5ewsbEpcdr8+fPFoEGDRHx8vLC0tBS5ubkq00va9kIU/xmOGzdOVKtWTdy7d69Y38ePH6u8x3SltFpfdvDgQWFgYCDS0tKUbevWrRMWFhYiPz9fCCHE119/Ld577z2V+Xx8fIS3t7dK24IFC8SHH35Y6rpe/hx50Yuf46+D5wGSzuUVFMIl4PCrO+pA3EJvmElf/21+7949dO/eHcOHD8e2bdtw/fp1jB49GiYmJpg/fz4AwN/fH5GRkdi/fz9q1aqFgIAAxMTEwM3NrcRl/vrrr/jhhx8QFhaG9957D2lpabh06RIAYM+ePXB1dcWYMWMwevToUus6cOAA+vbtizlz5mDbtm2Qy+U4ePBgiX2FEDh9+jSuX7+Ohg0bKtsnTpyIuLg4hIWFwcHBAXv37kW3bt1w5coVNGzYEJGRkRg7diy+++479OrVC8eOHcO8efOKLf/mzZv49ddfsWfPHhgaGgIABgwYAFNTUxw6dAiWlpb46aef0LlzZ9y4cQM1a9aEr68v3N3dsW7dOhgaGiI2NhbGxsYAgAkTJkAul+PPP/9EtWrVEBcXh+rVq5f42qKjozFw4EDMnz8fPj4+OHPmDMaPH4933nkHw4cPV/Zbvnw5vvnmG8yePRu7d+/GuHHj0L59ezRu3LjE5Z46dQqtWrUqcVtu2bIFa9asQZMmTdCgQQPs3r0bQ4cOLfkHVQqFQoGwsDD4+vrCwcGh2PTSXm9RbZ988kmZy//pp5/g6+urUU1liYqKQvPmzVGrVi1lm7e3N8aNG4dr167B3d0dUVFR8PLyUpnP29u72CFWDw8PLFq0CPn5+ZDJZFqrURMMQCI1rF27Fk5OTli9ejUkEgmaNGmCv//+GzNmzEBAQACePHmCrVu34pdffkHnzp0BAFu2bCnxQ61ISkqK8rseY2NjvPvuu/Dw8AAA1KxZE4aGhjA3N4ednV2py1i0aBEGDRqEBQsWKNtePpy1du1abNy4EXK5HAUFBTAxMcHkyZOVNWzZsgUpKSnKWqdNm4bw8HBs2bIFixcvxqpVq/DJJ59g2rRpAIBGjRrhzJkz+P3331XWI5fLsW3bNtjY2AAATp8+jXPnzuHBgwfKD7hly5Zh37592L17N8aMGYOUlBRMnz4dTZo0AQCVYE5JSUH//v3RvHlzAEC9evVK3Q4rVqxA586dlcHcqFEjxMXFYenSpSoB2L17d4wfPx4AMGPGDPzwww84fvx4qQF4+/btEn+Gx44dQ25uLry9vQEAn3/+OTZt2qRxAKanp+PRo0fK16+J1q1bIzY2tsw+LwaVNqSlpRVbZtHztLS0MvtkZ2cjLy9PeXEMBwcHyOVypKWloU6dOlqtU10MQNI5U2NDxC30rrR1a0N8fDzatm2r8p1Tu3btlNc8ffToEQoKCpQBBgCWlpalfrACz/eOgoODUa9ePXTr1g3du3dHz549YWSk/q9lbGxsmXuIAODr64s5c+bg0aNHCAwMhKenJzw9PQEAV65cQWFhIRo1aqQyT35+Pt555x0AQEJCAvr27asy3cPDo1gA1qlTRxl+AHDp0iXk5OQol1MkLy8Pt27dAvB8r3nUqFH4+eef4eXlhQEDBqB+/foAgMmTJ2PcuHE4cuQIvLy80L9/f7Ro0aLE1xgfH4/evXurtLVr1w7BwcEoLCxU7pG+OL9EIoGdnR0ePHhQ6rbLy8sr8Sokmzdvho+Pj/JnNXjwYEyfPh23bt1S1q8O8RoDXExNTdGgQYNyz1/ZioIwNze30mpgAJLOSSQSrRyGfNs4OTkhISEBx44dw9GjRzF+/HgsXboUJ0+eVB4GfBV1LjVnaWmp/KDcuXMnGjRogA8++ABeXl7IycmBoaEhoqOjlSFRpKzDbyWpVq2ayvOcnBzY29vjxIkTxfoWjYKcP38+hgwZggMHDuDQoUMIDAxEWFgY+vbti1GjRsHb2xsHDhzAkSNHEBQUhOXLl2PSpEka1fWil7erRCKBQqEotb+1tTUePXqk0paRkYG9e/eioKAA69atU7YXFhZi8+bNWLRoEQDAwsKixAEsmZmZytGrNjY2sLKywvXr1zV+LZVxCNTOzg7nzp1Tabt//75yWtG/RW0v9rGwsFB5v2ZkZACAyh9NFY2jQInU0LRpU0RFRan8xR4ZGQlzc3PUrl0b9erVg7Gxscpw+KysrFeesmBqaoqePXvixx9/xIkTJxAVFYUrV64AeD7SsbCwsMz5W7RogYiICLVfR/Xq1TFlyhRMmzYNQgi4u7ujsLAQDx48QIMGDVQeRR9ojRs3LjbMv6Rh/y9r2bIl0tLSYGRkVGzZ1tbWyn6NGjXC1KlTceTIEfTr1w9btmxRTnNycsLYsWOxZ88efPXVV9iwYUOJ62ratCkiIyNV2iIjI9GoUaNiwa4Jd3d3xMXFqbRt374dtWvXxqVLlxAbG6t8LF++HKGhocqfWePGjRETE1NsmTExMco9bgMDAwwaNAjbt2/H33//XaxvTk5OsVMMihQdAi3r0atXr3K/9pK0bdsWV65cUdlrPnr0KCwsLODi4qLs8/J78ujRo2jbtq1K29WrV1G7dm2V90KFe60hNFUQR4HqXlmjt95kfn5+okOHDuLixYsqj5SUFHH37l1hZmYmJkyYIOLj48W+ffuEtbW1CAwMVM4/atQoUbduXfHHH3+Iq1eviv79+wtzc3Px5ZdfKvu8OAp0y5YtYuPGjeLKlSvi1q1bYu7cucLU1FSkp6cLIYTo0qWL6NWrl7h79654+PChcp4XRxAeP35cGBgYiICAABEXFycuX74slixZopxe0ui+f/75R5iamopdu3YJIYTw9fUVzs7O4tdffxWJiYni7NmzYvHixeL3338XQghx+vRpYWBgIJYvXy5u3LghQkJCxDvvvCOsrKyUyywaBfoihUIhPvzwQ+Hq6ioOHz4skpKSRGRkpJg9e7Y4f/68yM3NFRMmTBDHjx8XycnJ4vTp06J+/fri66+/FkIIMWXKFBEeHi4SExNFdHS0aNOmjRg4cKDydeOFUaDR0dHCwMBALFy4UCQkJIjQ0FBhamoqtmzZUuK2L+Lq6qryM3zZ5cuXhZGRkcjIyFCZZ8aMGcX6ZmZmCqlUqtxut27dEiYmJmLSpEni0qVL4vr162L58uXCyMhIHDp0SOXn0aRJE1G7dm2xdetWce3aNXHjxg2xadMm0aBBA5WRrtpW9B5v1aqVGDJkiLh48aK4du2acvqePXtE48aNlc+fPXsmmjVrJrp27SpiY2NFeHi4sLGxEbNmzVL2SUxMFGZmZmL69OkiPj5erFmzRhgaGorw8HCVdfv5+Yl//etfpdZWEaNAGYAMQK2rygGIl049ACBGjhwphCjfaRAeHh5i5syZyj4vfgjv3btXtGnTRlhYWIhq1aqJDz74QBw7dkzZNyoqSrRo0ULIZLIyT4P49ddfhZubm5BKpcLa2lr069dPOa204e1ffPGFeO+990RhYaGQy+UiICBAODs7C2NjY2Fvby/69u0rLl++rOy/fv164ejoqDwN4ttvvxV2dnbK6SUFYNE2mTRpknBwcBDGxsbCyclJ+Pr6ipSUFJGfny8GDRqkPA3EwcFBTJw4Ufm+mThxoqhfv76QyWTCxsZGDB06VPnHQVmnQRgbG4t3331XLF26VKWW8gSgEEJ4eHiIkJAQIYQQFy5cEADEuXPnSuz7ySefqJxicu7cOdGlSxdhY2MjLC0tRZs2bcTevXuLzZeZmSlmzpwpGjZsKKRSqahVq5bw8vISe/fu1ehUHk2V9H6vU6eOcvqWLVvEy/tJycnJ4pNPPhGmpqbC2tpafPXVV8VO1Th+/LjyPVmvXj2VP0SEeP4ZYWlpKaKiokqtrSICUCJEFb8khIays7NhaWmJrKwsGJmYKYfna2u4PAFPnz5FUlIS6tatq7PbmFQFT548gaOjI5YvX17iidRV2ejRo3H9+nWcOnWqskvRuQMHDmD69Om4evVqhdyhQB+sW7cOe/fuxZEjR0rtU9bnyIuf4xYWFuWug5/4RFpy8eJFXL9+HR4eHsjKysLChQsBoNjoxKpo2bJl6NKlC6pVq4ZDhw5h69atWLt2bWWXVSF69OiBv/76C/fu3YOTk1Nll/NWMDY2xqpVqyq7DAYgkTYtW7YMCQkJkEqlaNWqFU6dOlW5X/Jryblz5/D999/j8ePHqFevHn788UeMGjWqssuqMOpeJ5PU86a8dxiARFri7u6O6Ojoyi5DJ3bu3FnZJRBpHQ9oExGRXmIAks7o2fgqItKiivj8YACS1hWdeKzrW+IQ0dur6BJp6l4VqTzeiO8A16xZg6VLlyItLQ2urq5YtWqVyjUVX7Zr1y7MmzcPycnJaNiwIb777jt07969AiumshgZGcHMzAwPHz6EsbExh44TkdqEEMjNzcWDBw9gZWX1WlfyeZVKD8AdO3bA398fISEhaNOmDYKDg+Ht7Y2EhIQSb/x55swZDB48GEFBQfj000/xyy+/oE+fPoiJiUGzZs0q4RXQyyQSCezt7ZGUlITbt29XdjlEVAVZWVmVeScUbaj0E+HbtGmD999/H6tXrwbw/P5YTk5OmDRpEmbOnFmsv4+PD548eaJyJfoPPvgAbm5uat3lmifCVxyFQsHDoESkMWNj4zL3/N6KE+Hlcjmio6Mxa9YsZZuBgQG8vLwQFRVV4jxRUVHw9/dXafP29sa+fftK7J+fn4/8/Hzl8+zs7NcvnNRiYGCg11eCIaI3W6V+OZOeno7CwsISb55YdHPFl5V2s8XS+gcFBcHS0lL54JUciIgI0INRoLNmzUJWVpbycefOHeW0ohu1xi301tqNU4mIqGqo1EOg1tbWMDQ0LPHmiaV9+VnazRZL6y+TySCTyUqcxhu1EhHpr0r99C+6XmJERAT69OkD4PnAiYiICEycOLHEeYputvjitflKutliaYrG/PC7QCKiqqno8/u1x3C+1s2UtCAsLEzIZDIRGhoq4uLixJgxY4SVlZVIS0sTQggxdOhQlfupRUZGCiMjI7Fs2TIRHx8vAgMDhbGxsbhy5Ypa67tz506J98Digw8++OCjaj3u3LnzWvlT6cf/fHx88PDhQwQEBCAtLQ1ubm4IDw9XDnRJSUlROZHa09MTv/zyC+bOnYvZs2ejYcOG2Ldvn9rnADo4OODOnTswNzeHRCJBdnY2nJyccOfOndcaTvu24vZ5NW6jsnH7vBq3Udle3j5CCDx+/BgODg6vtdxKPw+wsmnrfJK3FbfPq3EblY3b59W4jcqmq+3z1o8CJSIiKgkDkIiI9JLeB6BMJkNgYGCpp0roO26fV+M2Khu3z6txG5VNV9tH778DJCIi/aT3e4BERKSfGIBERKSXGIBERKSXGIBERKSX9CIA16xZA2dnZ5iYmKBNmzY4d+5cmf137dqFJk2awMTEBM2bN8fBgwcrqNLKocn22bBhAz766CPUqFEDNWrUgJeX1yu359tA0/dQkbCwMEgkEuW1bt9Wmm6fzMxMTJgwAfb29pDJZGjUqBF/z14SHByMxo0bw9TUFE5OTpg6dSqePn1aQdVWrD///BM9e/aEg4MDJBJJqfd3fdGJEyfQsmVLyGQyNGjQAKGhoZqv+LUupFYFhIWFCalUKjZv3iyuXbsmRo8eLaysrMT9+/dL7B8ZGSkMDQ3F999/L+Li4sTcuXM1utZoVaPp9hkyZIhYs2aNuHjxooiPjxfDhw8XlpaW4u7duxVcecXRdBsVSUpKEo6OjuKjjz4SvXv3rphiK4Gm2yc/P1+0bt1adO/eXZw+fVokJSWJEydOiNjY2AquvOJouo22b98uZDKZ2L59u0hKShKHDx8W9vb2YurUqRVcecU4ePCgmDNnjtizZ48AIPbu3Vtm/8TERGFmZib8/f1FXFycWLVqlTA0NBTh4eEarfetD0APDw8xYcIE5fPCwkLh4OAggoKCSuw/cOBA0aNHD5W2Nm3aiC+++EKndVYWTbfPy549eybMzc3F1q1bdVVipSvPNnr27Jnw9PQUGzduFH5+fm91AGq6fdatWyfq1asn5HJ5RZVY6TTdRhMmTBCdOnVSafP39xft2rXTaZ1vAnUC8OuvvxbvvfeeSpuPj4/w9vbWaF1v9SFQuVyO6OhoeHl5KdsMDAzg5eWFqKioEueJiopS6Q8A3t7epfavysqzfV6Wm5uLgoIC1KxZU1dlVqrybqOFCxfC1tYWI0eOrIgyK015ts/+/fvRtm1bTJgwAbVq1UKzZs2wePFiFBYWVlTZFao828jT0xPR0dHKw6SJiYk4ePAgunfvXiE1v+m09Tld6XeD0KX09HQUFhYq7yxRpFatWrh+/XqJ86SlpZXYPy0tTWd1VpbybJ+XzZgxAw4ODsXejG+L8myj06dPY9OmTYiNja2ACitXebZPYmIi/vjjD/j6+uLgwYO4efMmxo8fj4KCAgQGBlZE2RWqPNtoyJAhSE9Px4cffgghBJ49e4axY8di9uzZFVHyG6+0z+ns7Gzk5eXB1NRUreW81XuApFtLlixBWFgY9u7dCxMTk8ou543w+PFjDB06FBs2bIC1tXVll/NGUigUsLW1xfr169GqVSv4+Phgzpw5CAkJqezS3hgnTpzA4sWLsXbtWsTExGDPnj04cOAAvvnmm8ou7a3yVu8BWltbw9DQEPfv31dpv3//Puzs7Eqcx87OTqP+VVl5tk+RZcuWYcmSJTh27BhatGihyzIrlabb6NatW0hOTkbPnj2VbQqFAgBgZGSEhIQE1K9fX7dFV6DyvIfs7e1hbGwMQ0NDZVvTpk2RlpYGuVwOqVSq05orWnm20bx58zB06FCMGjUKANC8eXM8efIEY8aMwZw5c1TukaqPSvuctrCwUHvvD3jL9wClUilatWqFiIgIZZtCoUBERATatm1b4jxt27ZV6Q8AR48eLbV/VVae7QMA33//Pb755huEh4ejdevWFVFqpdF0GzVp0gRXrlxBbGys8tGrVy907NgRsbGxcHJyqsjyda4876F27drh5s2byj8MAODGjRuwt7d/68IPKN82ys3NLRZyRX8wCF6+WXuf05qNz6l6wsLChEwmE6GhoSIuLk6MGTNGWFlZibS0NCGEEEOHDhUzZ85U9o+MjBRGRkZi2bJlIj4+XgQGBr71p0Fosn2WLFkipFKp2L17t0hNTVU+Hj9+XFkvQec03UYve9tHgWq6fVJSUoS5ubmYOHGiSEhIEL///ruwtbUV3377bWW9BJ3TdBsFBgYKc3Nz8e9//1skJiaKI0eOiPr164uBAwdW1kvQqcePH4uLFy+KixcvCgBixYoV4uLFi+L27dtCCCFmzpwphg4dquxfdBrE9OnTRXx8vFizZg1PgyjNqlWrxLvvviukUqnw8PAQ//3vf5XT2rdvL/z8/FT679y5UzRq1EhIpVLx3nvviQMHDlRwxRVLk+1Tp04dAaDYIzAwsOILr0Cavode9LYHoBCab58zZ86INm3aCJlMJurVqycWLVoknj17VsFVVyxNtlFBQYGYP3++qF+/vjAxMRFOTk5i/Pjx4tGjRxVfeAU4fvx4iZ8rRdvEz89PtG/fvtg8bm5uQiqVinr16oktW7ZovF7eDomIiPTSW/0dIBERUWkYgEREpJcYgEREpJcYgEREpJcYgEREpJcYgEREpJcYgEREpJcYgEREpJcYgFSq0NBQWFlZVXYZ5SaRSLBv374y+wwfPhx9+vSpkHreNPPmzcOYMWMqZF0nTpyARCJBZmZmmf2cnZ0RHBys01o0XYe2fg/UeT9qKi4uDrVr18aTJ0+0ulx9wQB8yw0fPhwSiaTY4+bNm5VdGkJDQ5X1GBgYoHbt2hgxYgQePHigleWnpqbik08+AQAkJydDIpEUu0ffypUrERoaqpX1lWb+/PnK12loaAgnJyeMGTMGGRkZGi1Hm2GdlpaGlStXYs6cOSrLL6pTKpWiQYMGWLhwIZ49e/ba6/P09ERqaiosLS0BlB4q58+fr7BQrgoWLVoET09PmJmZlbi9XFxc8MEHH2DFihUVX9xbgAGoB7p164bU1FSVR926dSu7LACAhYUFUlNTcffuXWzYsAGHDh3C0KFDtbJsOzs7yGSyMvtYWlpWyF7ue++9h9TUVKSkpGDLli0IDw/HuHHjdL7e0mzcuBGenp6oU6eOSnvRe+Wvv/7CV199hfnz52Pp0qWvvT6pVAo7OztIJJIy+9nY2MDMzOy11/e2kMvlGDBgQJnvlREjRmDdunVa+UNF3zAA9YBMJoOdnZ3Kw9DQECtWrEDz5s1RrVo1ODk5Yfz48cjJySl1OZcuXULHjh1hbm4OCwsLtGrVChcuXFBOP336ND766COYmprCyckJkydPfuWhGYlEAjs7Ozg4OOCTTz7B5MmTcezYMeTl5UGhUGDhwoWoXbs2ZDIZ3NzcEB4erpxXLpdj4sSJsLe3h4mJCerUqYOgoCCVZRcdcioKfHd3d0gkEnTo0AGA6l7V+vXr4eDgoHKbHgDo3bs3/vWvfymf//bbb2jZsiVMTExQr149LFiw4JUfPkZGRrCzs4OjoyO8vLwwYMAAHD16VDm9sLAQI0eORN26dWFqaorGjRtj5cqVyunz58/H1q1b8dtvvyn30k6cOAEAuHPnDgYOHAgrKyvUrFkTvXv3RnJycpn1hIWFqdyzsEjRe6VOnToYN24cvLy8sH//fgDAo0ePMGzYMNSoUQNmZmb45JNP8NdffynnvX37Nnr27IkaNWqgWrVqeO+993Dw4EEAqodAT5w4gREjRiArK0v5WubPnw9A9fDkkCFD4OPjo1JfQUEBrK2tsW3bNgDPbysUFBSk3G6urq7YvXt3ma/9Zer+Huzbtw8NGzaEiYkJvL29cefOHZXp5XlfvMqCBQswdepUNG/evNQ+Xbp0QUZGBk6ePPla69JHDEA9ZmBggB9//BHXrl3D1q1b8ccff+Drr78utb+vry9q166N8+fPIzo6GjNnzoSxsTGA5zeC7datG/r374/Lly9jx44dOH36NCZOnKhRTaamplAoFHj27BlWrlyJ5cuXY9myZbh8+TK8vb3Rq1cv5Yfujz/+iP3792Pnzp1ISEjA9u3b4ezsXOJyz507BwA4duwYUlNTsWfPnmJ9BgwYgH/++QfHjx9XtmVkZCA8PBy+vr4AgFOnTmHYsGGYMmUK4uLi8NNPPyE0NBSLFi1S+zUmJyfj8OHDKve+UygUqF27Nnbt2oW4uDgEBARg9uzZ2LlzJwBg2rRpGDhwoMrevKenJwoKCuDt7Q1zc3OcOnUKkZGRqF69Orp16wa5XF7i+jMyMhAXF6fWvRxNTU2Vyxk+fDguXLiA/fv3IyoqCkIIdO/eHQUFBQCACRMmID8/H3/++SeuXLmC7777DtWrVy+2TE9PTwQHByv3/lNTUzFt2rRi/Xx9ffGf//xHJYwOHz6M3Nxc9O3bFwAQFBSEbdu2ISQkBNeuXcPUqVPx+eefaxQG6vwe5ObmYtGiRdi2bRsiIyORmZmJQYMGKaeX533RoUMHDB8+XO06SyOVSuHm5oZTp0699rL0zmvexYLecH5+fsLQ0FBUq1ZN+fjss89K7Ltr1y7xzjvvKJ9v2bJFWFpaKp+bm5uL0NDQEucdOXKkGDNmjErbqVOnhIGBgcjLyytxnpeXf+PGDdGoUSPRunVrIYQQDg4OYtGiRSrzvP/++2L8+PFCCCEmTZokOnXqJBQKRYnLByD27t0rhBAiKSlJABAXL15U6fPyrYp69+4t/vWvfymf//TTT8LBwUEUFhYKIYTo3LmzWLx4scoyfv75Z2Fvb19iDUI8v7ebgYGBqFatmjAxMVHe6mXFihWlziOEEBMmTBD9+/cvtdaidTdu3FhlG+Tn5wtTU1Nx+PDhEpdbdM+1lJQUlfYXl69QKMTRo0eFTCYT06ZNEzdu3BAARGRkpLJ/enq6MDU1FTt37hRCCNG8eXMxf/78EtdZdLubotv5vPyzL1KnTh3xww8/CCGe3xLI2tpabNu2TTl98ODBwsfHRwghxNOnT4WZmZk4c+aMyjJGjhwpBg8eXGIdL6+jJCX9HgBQuX1RfHy8ACDOnj0rhFDvffHi+1GIV99H8kWlba8iffv2FcOHD1drWfQ/RpUVvFRxOnbsiHXr1imfV6tWDcDzvaGgoCBcv34d2dnZePbsGZ4+fYrc3NwSv4fx9/fHqFGj8PPPPysP49WvXx/A88Ojly9fxvbt25X9hRBQKBRISkpC06ZNS6wtKysL1atXh0KhwNOnT/Hhhx9i48aNyM7Oxt9//4127dqp9G/Xrh0uXboE4PkeSZcuXdC4cWN069YNn376Kbp27fpa28rX1xejR4/G2rVrIZPJsH37dgwaNEh5d+5Lly4hMjJS5S/7wsLCMrcbADRu3Bj79+/H06dP8X//93+IjY3FpEmTVPqsWbMGmzdvRkpKCvLy8iCXy+Hm5lZmvZcuXcLNmzdhbm6u0v706VPcunWrxHny8vIAACYmJsWm/f7776hevToKCgqgUCgwZMgQzJ8/HxERETAyMkKbNm2Ufd955x00btwY8fHxAIDJkydj3LhxOHLkCLy8vNC/f3+0aNGizPrLYmRkhIEDB2L79u0YOnQonjx5gt9++w1hYWEAgJs3byI3NxddunRRmU8ul8Pd3V3t9ajze2BkZIT3339fOU+TJk1gZWWF+Ph4eHh4lOt9UXQYVxtMTU2Rm5urteXpCwagHqhWrRoaNGig0pacnIxPP/0U48aNw6JFi1CzZk2cPn0aI0eOhFwuL/EXdv78+RgyZAgOHDiAQ4cOITAwEGFhYejbty9ycnLwxRdfYPLkycXme/fdd0utzdzcHDExMTAwMIC9vT1MTU0BANnZ2a98XS1btkRSUhIOHTqEY8eOYeDAgfDy8tL4O6AX9ezZE0IIHDhwAO+//z5OnTqFH374QTk9JycHCxYsQL9+/YrNW1KgFCkaVQkAS5YsQY8ePbBgwQJ88803AJ5/Jzdt2jQsX74cbdu2hbm5OZYuXYqzZ8+WWW9OTg5atWql8odHERsbmxLnsba2BvD8O72X+xT9sSSVSuHg4AAjI/U/IkaNGgVvb28cOHAAR44cQVBQEJYvX14s6DXh6+uL9u3b48GDBzh69ChMTU3RrVs3AFAeGj1w4AAcHR1V5nvV4Kci5fk9KEl53xfakpGRofxjlNTHANRT0dHRUCgUWL58uXLvpuj7prI0atQIjRo1wtSpUzF48GBs2bIFffv2RcuWLREXF1csaF/FwMCgxHksLCzg4OCAyMhItG/fXtkeGRkJDw8PlX4+Pj7w8fHBZ599hm7duiEjIwM1a9ZUWV7R922FhYVl1mNiYoJ+/fph+/btuHnzJho3boyWLVsqp7ds2RIJCQkav86XzZ07F506dcK4ceOUr9PT0xPjx49X9nl5D04qlRarv2XLltixYwdsbW1hYWGh1rrr168PCwsLxMXFoVGjRirTSvpjCQCaNm2KZ8+e4ezZs/D09AQA/PPPP0hISICLi4uyn5OTE8aOHYuxY8di1qxZ2LBhQ4kBWNJrKYmnpyecnJywY8cOHDp0CAMGDFB+7+zi4gKZTIaUlBSV94gm1P09ePbsGS5cuKB87yUkJCAzM1N5ZENb74vyunr1Kj777LNKWXdVxkEweqpBgwYoKCjAqlWrkJiYiJ9//hkhISGl9s/Ly8PEiRNx4sQJ3L59G5GRkTh//rzyA2DGjBk4c+YMJk6ciNjYWPz111/47bffNB4E86Lp06fju+++w44dO5CQkICZM2ciNjYWU6ZMAfB89N6///1vXL9+HTdu3MCuXbtgZ2dX4mkNtra2MDU1RXh4OO7fv4+srKxS1+vr64sDBw5g8+bNysEvRQICArBt2zYsWLAA165dQ3x8PMLCwjB37lyNXlvbtm3RokULLF68GADQsGFDXLhwAYcPH8aNGzcwb948nD9/XmUeZ2dnXL58GQkJCUhPT0dBQQF8fX1hbW2N3r1749SpU0hKSsKJEycwefJk3L17t8R1GxgYwMvLC6dPn1a73oYNG6J3794YPXo0Tp8+jUuXLuHzzz+Ho6MjevfuDQD48ssvcfjwYSQlJSEmJgbHjx8v9dC3s7MzcnJyEBERgfT09DIP3w0ZMgQhISE4evSoys/D3Nwc06ZNw9SpU7F161bcunULMTExWLVqFbZu3arW61L398DY2BiTJk3C2bNnER0djeHDh+ODDz5QBmJ53hfDhg3DrFmzyqwvJSUFsbGxSElJQWFhIWJjYxEbG6syMCg5ORn37t2Dl5eXWq+ZXlDZX0KSbpU0cKLIihUrhL29vTA1NRXe3t5i27ZtpQ5UyM/PF4MGDRJOTk5CKpUKBwcHMXHiRJUBLufOnRNdunQR1atXF9WqVRMtWrQoNojlRa/6Yr+wsFDMnz9fODo6CmNjY+Hq6ioOHTqknL5+/Xrh5uYmqlWrJiwsLETnzp1FTEyMcjpeGnSwYcMG4eTkJAwMDET79u1L3T6FhYXC3t5eABC3bt0qVld4eLjw9PQUpqamwsLCQnh4eIj169eX+joCAwOFq6trsfZ///vfQiaTiZSUFPH06VMxfPhwYWlpKaysrMS4cePEzJkzVeZ78OCBcvsCEMePHxdCCJGamiqGDRsmrK2thUwmE/Xq1ROjR48WWVlZpdZ08OBB4ejoqBzcU9q2eFFGRoYYOnSosLS0VL5nbty4oZw+ceJEUb9+fSGTyYSNjY0YOnSoSE9PF0IUHwQjhBBjx44V77zzjgAgAgMDhRAlD1CJi4sTAESdOnWKDXhSKBQiODhYNG7cWBgbGwsbGxvh7e0tTp48WerreHkd6v4e/Prrr6JevXpCJpMJLy8vcfv2bZXlvup98fL7sX379sLPz6/UOoV4/jPB/x809eKj6GcvhBCLFy8W3t7eZS6HSiYRQojKCF4iqjxCCLRp00Z5KJuqJrlcjoYNG+KXX34pNmCMXo2HQIn0kEQiwfr163n1kCouJSUFs2fPZviVE/cAiYhIL3EPkIiI9BIDkIiI9BIDkIiI9BIDkIiI9BIDkIiI9BIDkIiI9BIDkIiI9BIDkIiI9BIDkIiI9NL/AxKrkPkcmlp1AAAAAElFTkSuQmCC",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -964,22 +1183,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 42,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7a8527631ab0>"
+       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7aa4ea358670>"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 42,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -994,16 +1213,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 43,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7a85265ad5d0>"
+       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7aa4ea2a3dc0>"
       ]
      },
-     "execution_count": 47,
+     "execution_count": 43,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -1024,16 +1243,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 44,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7a85265ae380>"
+       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7aa4ea0bba00>"
       ]
      },
-     "execution_count": 48,
+     "execution_count": 44,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -1054,16 +1273,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 45,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7a85267f3580>"
+       "<sklearn.metrics._plot.roc_curve.RocCurveDisplay at 0x7aa4ec7b3460>"
       ]
      },
-     "execution_count": 49,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -1084,64 +1303,49 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['models/svm.pkl']"
-      ]
-     },
-     "execution_count": 50,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import joblib\n",
-    "\n",
-    "joblib.dump(svm,\"models/svm.pkl\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 57,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "(534, 6)"
-      ]
-     },
-     "execution_count": 51,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00        61\n",
+      "           1       1.00      1.00      1.00        46\n",
+      "\n",
+      "    accuracy                           1.00       107\n",
+      "   macro avg       1.00      1.00      1.00       107\n",
+      "weighted avg       1.00      1.00      1.00       107\n",
+      "\n"
+     ]
     }
    ],
    "source": [
-    "data.shape"
+    "print(classification_report(ytest,lr_y_preds))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": 46,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(427, 3)"
+       "['models/svm.pkl']"
       ]
      },
-     "execution_count": 52,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "X_train.shape"
+    "import joblib\n",
+    "\n",
+    "joblib.dump(svm,\"models/svm.pkl\")"
    ]
   }
  ],