{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "view-in-github"
   },
   "source": [
    "<a href=\"https://colab.research.google.com/github/smart-stats/ds4bio_book/blob/main/book/basic_regression_pytorch.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a> "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Basic regression in pytorch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 192
    },
    "colab_type": "code",
    "id": "6nKZWgTDvTTK",
    "outputId": "b31d9b45-3526-4922-f687-6ead41d98990"
   },
   "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>FLAIR</th>\n",
       "      <th>PD</th>\n",
       "      <th>T1</th>\n",
       "      <th>T2</th>\n",
       "      <th>FLAIR_10</th>\n",
       "      <th>PD_10</th>\n",
       "      <th>T1_10</th>\n",
       "      <th>T2_10</th>\n",
       "      <th>FLAIR_20</th>\n",
       "      <th>PD_20</th>\n",
       "      <th>T1_20</th>\n",
       "      <th>T2_20</th>\n",
       "      <th>GOLD_Lesions</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.143692</td>\n",
       "      <td>1.586219</td>\n",
       "      <td>-0.799859</td>\n",
       "      <td>1.634467</td>\n",
       "      <td>0.437568</td>\n",
       "      <td>0.823800</td>\n",
       "      <td>-0.002059</td>\n",
       "      <td>0.573663</td>\n",
       "      <td>0.279832</td>\n",
       "      <td>0.548341</td>\n",
       "      <td>0.219136</td>\n",
       "      <td>0.298662</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.652552</td>\n",
       "      <td>1.766672</td>\n",
       "      <td>-1.250992</td>\n",
       "      <td>0.921230</td>\n",
       "      <td>0.663037</td>\n",
       "      <td>0.880250</td>\n",
       "      <td>-0.422060</td>\n",
       "      <td>0.542597</td>\n",
       "      <td>0.422182</td>\n",
       "      <td>0.549711</td>\n",
       "      <td>0.061573</td>\n",
       "      <td>0.280972</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.036099</td>\n",
       "      <td>0.262042</td>\n",
       "      <td>-0.858565</td>\n",
       "      <td>-0.058211</td>\n",
       "      <td>-0.044280</td>\n",
       "      <td>-0.308569</td>\n",
       "      <td>0.014766</td>\n",
       "      <td>-0.256075</td>\n",
       "      <td>-0.136532</td>\n",
       "      <td>-0.350905</td>\n",
       "      <td>0.020673</td>\n",
       "      <td>-0.259914</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.037692</td>\n",
       "      <td>0.011104</td>\n",
       "      <td>-1.228796</td>\n",
       "      <td>-0.470222</td>\n",
       "      <td>-0.013971</td>\n",
       "      <td>-0.000498</td>\n",
       "      <td>-0.395575</td>\n",
       "      <td>-0.221900</td>\n",
       "      <td>0.000807</td>\n",
       "      <td>-0.003085</td>\n",
       "      <td>-0.193249</td>\n",
       "      <td>-0.139284</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      FLAIR        PD        T1        T2  FLAIR_10     PD_10     T1_10  \\\n",
       "0  1.143692  1.586219 -0.799859  1.634467  0.437568  0.823800 -0.002059   \n",
       "1  1.652552  1.766672 -1.250992  0.921230  0.663037  0.880250 -0.422060   \n",
       "2  1.036099  0.262042 -0.858565 -0.058211 -0.044280 -0.308569  0.014766   \n",
       "3  1.037692  0.011104 -1.228796 -0.470222 -0.013971 -0.000498 -0.395575   \n",
       "\n",
       "      T2_10  FLAIR_20     PD_20     T1_20     T2_20  GOLD_Lesions  \n",
       "0  0.573663  0.279832  0.548341  0.219136  0.298662             0  \n",
       "1  0.542597  0.422182  0.549711  0.061573  0.280972             0  \n",
       "2 -0.256075 -0.136532 -0.350905  0.020673 -0.259914             0  \n",
       "3 -0.221900  0.000807 -0.003085 -0.193249 -0.139284             0  "
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import torch\n",
    "import statsmodels.formula.api as smf\n",
    "import statsmodels as sm\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "## Read in the data and display a few rows\n",
    "dat = pd.read_csv(\"https://raw.githubusercontent.com/bcaffo/ds4bme_intro/master/data/oasis.csv\")\n",
    "dat.head(4)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 301
    },
    "colab_type": "code",
    "id": "LtzlgJCu4zbX",
    "outputId": "8d58679e-d010-4145-c01e-272b05542f61"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<Axes: xlabel='T2', ylabel='PD'>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.scatterplot(x = dat['T2'], y = dat['PD'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 435
    },
    "colab_type": "code",
    "id": "ehiVfmYHJ4EL",
    "outputId": "b671b7a2-a869-46ab-88da-aa1fade74ae1"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table class=\"simpletable\">\n",
       "<caption>OLS Regression Results</caption>\n",
       "<tr>\n",
       "  <th>Dep. Variable:</th>           <td>PD</td>        <th>  R-squared:         </th> <td>   0.661</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.657</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   190.9</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Date:</th>             <td>Mon, 29 Jan 2024</td> <th>  Prob (F-statistic):</th> <td>9.77e-25</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Time:</th>                 <td>07:02:58</td>     <th>  Log-Likelihood:    </th> <td> -57.347</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>No. Observations:</th>      <td>   100</td>      <th>  AIC:               </th> <td>   118.7</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Residuals:</th>          <td>    98</td>      <th>  BIC:               </th> <td>   123.9</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Intercept</th> <td>    0.3138</td> <td>    0.052</td> <td>    6.010</td> <td> 0.000</td> <td>    0.210</td> <td>    0.417</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>T2</th>        <td>    0.7832</td> <td>    0.057</td> <td>   13.815</td> <td> 0.000</td> <td>    0.671</td> <td>    0.896</td>\n",
       "</tr>\n",
       "</table>\n",
       "<table class=\"simpletable\">\n",
       "<tr>\n",
       "  <th>Omnibus:</th>       <td> 1.171</td> <th>  Durbin-Watson:     </th> <td>   1.501</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Prob(Omnibus):</th> <td> 0.557</td> <th>  Jarque-Bera (JB):  </th> <td>   0.972</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Skew:</th>          <td> 0.241</td> <th>  Prob(JB):          </th> <td>   0.615</td>\n",
       "</tr>\n",
       "<tr>\n",
       "  <th>Kurtosis:</th>      <td> 2.995</td> <th>  Cond. No.          </th> <td>    1.89</td>\n",
       "</tr>\n",
       "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/latex": [
       "\\begin{center}\n",
       "\\begin{tabular}{lclc}\n",
       "\\toprule\n",
       "\\textbf{Dep. Variable:}    &        PD        & \\textbf{  R-squared:         } &     0.661   \\\\\n",
       "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.657   \\\\\n",
       "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     190.9   \\\\\n",
       "\\textbf{Date:}             & Mon, 29 Jan 2024 & \\textbf{  Prob (F-statistic):} &  9.77e-25   \\\\\n",
       "\\textbf{Time:}             &     07:02:58     & \\textbf{  Log-Likelihood:    } &   -57.347   \\\\\n",
       "\\textbf{No. Observations:} &         100      & \\textbf{  AIC:               } &     118.7   \\\\\n",
       "\\textbf{Df Residuals:}     &          98      & \\textbf{  BIC:               } &     123.9   \\\\\n",
       "\\textbf{Df Model:}         &           1      & \\textbf{                     } &             \\\\\n",
       "\\textbf{Covariance Type:}  &    nonrobust     & \\textbf{                     } &             \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lcccccc}\n",
       "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
       "\\midrule\n",
       "\\textbf{Intercept} &       0.3138  &        0.052     &     6.010  &         0.000        &        0.210    &        0.417     \\\\\n",
       "\\textbf{T2}        &       0.7832  &        0.057     &    13.815  &         0.000        &        0.671    &        0.896     \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "\\begin{tabular}{lclc}\n",
       "\\textbf{Omnibus:}       &  1.171 & \\textbf{  Durbin-Watson:     } &    1.501  \\\\\n",
       "\\textbf{Prob(Omnibus):} &  0.557 & \\textbf{  Jarque-Bera (JB):  } &    0.972  \\\\\n",
       "\\textbf{Skew:}          &  0.241 & \\textbf{  Prob(JB):          } &    0.615  \\\\\n",
       "\\textbf{Kurtosis:}      &  2.995 & \\textbf{  Cond. No.          } &     1.89  \\\\\n",
       "\\bottomrule\n",
       "\\end{tabular}\n",
       "%\\caption{OLS Regression Results}\n",
       "\\end{center}\n",
       "\n",
       "Notes: \\newline\n",
       " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
      ],
      "text/plain": [
       "<class 'statsmodels.iolib.summary.Summary'>\n",
       "\"\"\"\n",
       "                            OLS Regression Results                            \n",
       "==============================================================================\n",
       "Dep. Variable:                     PD   R-squared:                       0.661\n",
       "Model:                            OLS   Adj. R-squared:                  0.657\n",
       "Method:                 Least Squares   F-statistic:                     190.9\n",
       "Date:                Mon, 29 Jan 2024   Prob (F-statistic):           9.77e-25\n",
       "Time:                        07:02:58   Log-Likelihood:                -57.347\n",
       "No. Observations:                 100   AIC:                             118.7\n",
       "Df Residuals:                      98   BIC:                             123.9\n",
       "Df Model:                           1                                         \n",
       "Covariance Type:            nonrobust                                         \n",
       "==============================================================================\n",
       "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
       "------------------------------------------------------------------------------\n",
       "Intercept      0.3138      0.052      6.010      0.000       0.210       0.417\n",
       "T2             0.7832      0.057     13.815      0.000       0.671       0.896\n",
       "==============================================================================\n",
       "Omnibus:                        1.171   Durbin-Watson:                   1.501\n",
       "Prob(Omnibus):                  0.557   Jarque-Bera (JB):                0.972\n",
       "Skew:                           0.241   Prob(JB):                        0.615\n",
       "Kurtosis:                       2.995   Cond. No.                         1.89\n",
       "==============================================================================\n",
       "\n",
       "Notes:\n",
       "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
       "\"\"\""
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fit = smf.ols('PD ~ T2', data = dat).fit()\n",
    "fit.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 287
    },
    "colab_type": "code",
    "id": "F6gUNlf6LbJc",
    "outputId": "dc8f04ff-b6a7-4460-abc9-bedcea4077b0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x783ee16ecca0>]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# The in sample predictions\n",
    "yhat = fit.predict(dat['T2'])\n",
    "\n",
    "# Make sure that it's adding the intercept\n",
    "#test = 0.3138 + dat['T2'] * 0.7832\n",
    "#sns.scatterplot(yhat,test)\n",
    "\n",
    "## A plot of the in sample predicted values\n",
    "## versus the actual outcomes\n",
    "sns.scatterplot(x = yhat, y = dat['PD'])\n",
    "plt.plot([-1, 3], [-1, 3], linewidth=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "9LZ4MgGEPxEN",
    "outputId": "48c41eae-7b0b-4479-e613-7af18724ddce"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[torch.Size([100, 1]), torch.Size([100, 1]), [100, 1]]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "n = dat.shape[0]\n",
    "\n",
    "## Get the y and x from \n",
    "xtraining = torch.from_numpy(dat['T2'].values)\n",
    "ytraining = torch.from_numpy(dat['PD'].values)\n",
    "\n",
    "## PT wants floats\n",
    "xtraining = xtraining.float()\n",
    "ytraining = ytraining.float()\n",
    "\n",
    "## Dimension is 1xn not nx1\n",
    "## squeeze the second dimension\n",
    "xtraining = xtraining.unsqueeze(1)\n",
    "ytraining = ytraining.unsqueeze(1)\n",
    "\n",
    "## Show that everything is the right size\n",
    "[xtraining.shape, \n",
    " ytraining.shape,\n",
    " [n, 1]\n",
    " ]\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "OZKrXwTjPdrB"
   },
   "outputs": [],
   "source": [
    "## Show that linear regression is a pytorch \n",
    "model = torch.nn.Sequential(\n",
    "    torch.nn.Linear(1, 1)\n",
    ")\n",
    "\n",
    "## MSE is the loss function\n",
    "loss_fn = torch.nn.MSELoss(reduction='sum')\n",
    "\n",
    "## Set the optimizer\n",
    "## There are lots of choices\n",
    "optimizer = torch.optim.SGD(model.parameters(), lr=1e-4)\n",
    "\n",
    "## Loop over iterations\n",
    "for t in range(10000):\n",
    "\n",
    "    ## Forward propagation\n",
    "  y_pred = model(xtraining)\n",
    "    \n",
    "  ## the loss for this interation\n",
    "  loss = loss_fn(y_pred, ytraining)\n",
    "\n",
    "  #print(t, loss.item() / n)\n",
    "\n",
    "  ## Zero out the gradients before adding them up \n",
    "  optimizer.zero_grad()\n",
    "  \n",
    "  ## Backprop\n",
    "  loss.backward()\n",
    "  \n",
    "  ## Optimization step\n",
    "  optimizer.step()\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 287
    },
    "colab_type": "code",
    "id": "fd1wjXgukgqs",
    "outputId": "c46bf0da-1478-4fff-8866-992019038021"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x783ee986a710>]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAi8AAAGdCAYAAADaPpOnAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAABJgklEQVR4nO3de1iUZd4H8O8AwzCcBmHkpIgohAfEEEpRsMyN1DfLsjJtfbU23yy1lNxMazfb3UI7Z1rmvm6ta2oHtOzVTHcVNMUSBTEPqHkAkYOcZoBhTszz/kFMjgzDQebI93Ndc10799yP83t6tubrcx8ekSAIAoiIiIichJu9CyAiIiLqDIYXIiIicioML0RERORUGF6IiIjIqTC8EBERkVNheCEiIiKnwvBCREREToXhhYiIiJyKh70L6G4GgwFXr16Fn58fRCKRvcshIiKiDhAEAXV1dQgPD4ebm+V7Ky4XXq5evYqIiAh7l0FERERdUFxcjL59+1rs43Lhxc/PD0Dzyfv7+9u5GiIiIuoIpVKJiIgI4++4JS4XXlqGivz9/RleiIiInExHpnxwwi4RERE5FYYXIiIicioML0RERORUGF6IiIjIqTC8EBERkVNheCEiIiKnwvBCREREToXhhYiIiJwKwwsRERE5FauGl48++gjx8fHG3W6Tk5Px3XffWTwmOzsbiYmJ8PLywoABA7B27VprlkhEREROxqrhpW/fvlixYgVyc3ORm5uLu+66C/fffz9Onjxptv/FixcxadIkpKamIi8vD8uWLcOzzz6LzMxMa5ZJRERETkQkCIJgyy8MDAzEm2++iT/84Q+tPluyZAm2b9+O06dPG9vmzp2L48ePIycnp0N/vlKphEwmg0Kh4LONiIiIuplCpUNFnRoxIe0/QLEzOvP7bbM5L01NTdiyZQsaGhqQnJxstk9OTg7S0tJM2u655x7k5uZCp9OZPUaj0UCpVJq8iIiIqPvlFdVg0qoDePzTI1A0mv9dtgWrh5cTJ07A19cXEokEc+fOxbZt2zBkyBCzfcvKyhASEmLSFhISAr1ej8rKSrPHZGRkQCaTGV8RERHdfg5EREQ9mSAI+Pv+C3h4bQ5KahtxpaYRf/u/U3arx+rhJTY2Fvn5+Th8+DCefvppzJo1C6dOtX3CNz4Ku2VUq61HZC9duhQKhcL4Ki4u7r7iiYiIeriaBi2e/GcuXtt5GnpD829yUmQvLLr7FrvV5GHtL/D09ER0dDQAICkpCUeOHMH777+Pjz/+uFXf0NBQlJWVmbRVVFTAw8MDQUFBZv98iUQCiUTS/YUTERH1cLmXqrFgcx5KFWpj29N3DkT63bdA7G6/3VasHl5uJAgCNBqN2c+Sk5Px7bffmrTt3r0bSUlJEIvFtiiPiIioxzMYBKzd/wve3n0WTb/ebQn08cQ7jwzHnbHBdq7OyuFl2bJlmDhxIiIiIlBXV4ctW7YgKysLu3btAtA85FNSUoINGzYAaF5ZtHr1aqSnp2POnDnIycnB+vXrsXnzZmuWSURERL+qqtcg/YvjyD57zdg2MioQq6YnIMTfy46V/caq4aW8vBwzZ85EaWkpZDIZ4uPjsWvXLtx9990AgNLSUhQVFRn7R0VFYefOnVi0aBHWrFmD8PBwrFq1ClOnTrVmmURERATg8IUqPLclD+XK5hESkQhYMC4az46PgYcdh4luZPN9XqyN+7wQERF1TpNBwJp95/Hev8/i11EiyH0leG/arUiJkdukhs78ftt8zgsRERE5joo6NRZ9no+D56uMbWOig/DutFsR7OcYw0Q3YnghIiLqoQ6er8RzW/JRWd88TOQmAhb+7hbMGxcNdzfzW5Q4AoYXIiKiHqbJIOD9f5/FB/vOo2XySLCfBKumJ2DUAPNbkzgShhciIqIepFypxrOb8/DjxWpj29hbeuOdR4ZD7usc+6YxvBAREfUQ2WevYdHn+ahu0AIA3N1EeD7tFswdOxBuDjxMdCOGFyIiIhenbzLg7T1n8VHWL8a2MJkXVk1PwG39A+1YWdcwvBAREbmwq7WNeHZzHnIv1xjbxg8KxlsPD0cvH087VtZ1DC9EREQuau+ZcqR/cRy1Kh0AwMNNhCUTBuHJ1Kg2H3jsDBheiIiIXIxWb8Cb35/B3w9cNLb1CZDigxkJGNGvlx0r6x4ML0RERC6kuFqFBZvzkF9ca2xLGxKCNx8aDpm3azzkmOGFiIjIRXx/sgx//PI4lGo9AEDsLsKySYMxe3R/px4muhHDCxERkZPT6JuQsfMMPj10ydjWL9Abq2ckIL5vgN3qshaGFyIiIid2uaoB8zfl4USJwtg2aVgoVkyNh7+XawwT3YjhhYiIyEntKCjFi5kFqNM0DxN5erjhT/cOwe9H9nOpYaIbMbwQERE5GbWuCX/bcQobDxcZ26LkPlg9IwFDw2V2rMw2GF6IiIicyMXKBsz77BhOlSqNbfcND8frDw6Dr6Rn/Kz3jLMkIiJyAd/kl2DZ1hNo0DYBACQebnj1vqGYdluESw8T3YjhhYiIyMGpdU1Yvv0kthwpNrYN7O2DNY+NwKBQfztWZh8ML0RERA7sfEUd5n2Wh8LyOmPb1BF98dcpQ+Ht2TN/xnvmWRMRETmBr45ewZ++/hmNuuZhIqnYHX+dEoeHEvvauTL7YnghIiJyMCqtHn/6+iQyj10xtt0S4os1M0YgJsTPjpU5BoYXIiIiB1JYVod5m47hfEW9se3R2yLwyuShkHq627Eyx8HwQkRE5AAEQcAXucX48zcnodEbAAA+nu54/cFhuP/WPnauzrEwvBAREdlZvUaPl7edwNf5V41tg8P8sWZGAgb09rVjZY6J4YWIiMiOTl1VYv6mY7hQ2WBse2xkP/zp3iHwEnOYyByGFyIiIjsQBAGf/ViEv/zfKWh/HSbylXhgxdRhuDc+3M7VOTaGFyIiIhtTqnVYuvUEdhSUGtvi+vhjzYwRiAzysWNlzoHhhYiIyIoUKi0q67VQqnXwl4pRoVDjxW0ncLlKZewze3R/LJ00CBIPDhN1BMMLERGRlVytbcSSzAIcOFdpbBOJAEFo/t/+Xh5446HhmBAXaqcKnRPDCxERkRUoVNpWwQX4LbjEhfvjo98nIiLQ2w7VOTc3exdARETkiirrta2Cy/Xeeng4g0sXWTW8ZGRk4LbbboOfnx+Cg4MxZcoUFBYWWjwmKysLIpGo1evMmTPWLJWIiKhbKRq1Fj9X//q8Iuo8q4aX7OxszJs3D4cPH8aePXug1+uRlpaGhoaGdo8tLCxEaWmp8RUTE2PNUomIiLpNTYMWb3xv+S/rfl5iG1Xjeqw652XXrl0m7z/55BMEBwfj6NGjGDt2rMVjg4ODERAQYMXqiIiIut/Ry9VYsCkPVxXqNvuMjZFD7utpw6pci03nvCgUCgBAYGBgu30TEhIQFhaG8ePHY9++fW3202g0UCqVJi8iIiJbMxgEfJT1Cx75+LAxuARIxYgL9zfpNzZGjpVT4yHzZnjpKputNhIEAenp6UhJSUFcXFyb/cLCwrBu3TokJiZCo9HgX//6F8aPH4+srCyzd2syMjLw6quvWrN0IiIii6rqNUj/4jiyz14ztt0eFYhVjyZAKnZDZb0WdWod/LzEkPt6MrjcJJEgtCzasq558+Zhx44d+OGHH9C3b99OHTt58mSIRCJs37691WcajQYajcb4XqlUIiIiAgqFAv7+/q36ExERdacfL1Th2S15KFc2/xaJRMD8cdF4bnwMPNy5qLejlEolZDJZh36/bXLnZcGCBdi+fTv279/f6eACAKNGjcLGjRvNfiaRSCCRSG62RCIiok5pMgj4cN95vPvvszD8ehtA7ivBe9NuRUqM3L7FuTirhhdBELBgwQJs27YNWVlZiIqK6tKfk5eXh7CwsG6ujoiIqGuu1Wmw6PN8/HD+t31cRg8MwnuP3opgPy87VtYzWDW8zJs3D5s2bcI333wDPz8/lJWVAQBkMhmkUikAYOnSpSgpKcGGDRsAAO+99x769++PoUOHQqvVYuPGjcjMzERmZqY1SyUiIuqQg+cr8dyWfFTWNw8TuYmA58bfgvl3RcPdTWTn6noGq4aXjz76CABw5513mrR/8sknmD17NgCgtLQURUVFxs+0Wi0WL16MkpISSKVSDB06FDt27MCkSZOsWSoREZFFTQYB7//nHD7Ye864xX+wnwTvP5qA5IFB9i2uh7HZhF1b6cyEHyIioo4oV6rx3JY8HL5QbWxLjZHj3Wm3Qu7LeZfdweEm7BIRETmr7LPXkP55Pqoamrf7d3cTIf3uW/D0HQPhxmEiu2B4ISIiMkPfZMA7e87iw6xfjG2h/l74YEYCbuvf/marZD0ML0RERDcoVTTi2c15OHKpxth216BgvPXwcAT6cIM5e2N4ISIius7eM+V4/ovjqFHpAAAebiK8MCEWT6YM4DCRg2B4ISIiAqBrMuDN7wuxbv8FY1ufACk+mJGAEf162bEyuhHDCxER9XhXalRYsDkPeUW1xra7h4TgzYfiEcDnEDkchhciIurRvj9Zhj9+eRxKtR4AIHYXYenEwXh8TH+IRBwmckQML0RE1CNp9QZkfHcanxy8ZGyLCJRi9fQRGB4RYLe6qH0ML0RE1OMUVakwf/MxFFxRGNsmDQvFiqnx8PcS27Ey6giGFyIi6lF2nijFkq8KUKdpHibydHfDn+4djN+PiuQwkZNgeCEioh5BrWvCaztO41+HLxvb+gd5Y/WMEYjrI7NjZdRZDC9EROTyLlY2YN5nx3CqVGlsu294OF5/cBh8JfwpdDa8YkRE5NK+yS/Bsq0n0KBtAgBIPNyw/L6hePS2CA4TOSmGFyIicklqXRNe/fYkNv9UbGwb0NsHa2aMwOAwy08tJsfG8EJERC7nfEU95m86hjNldca2BxP64K9T4uDDYSKnxytIREQuJfPoFbz89c9o1DUPE0nF7vjL/UPxcFKEnSuj7sLwQkRELkGl1ePP35zEV0evGNtuCfHFmhkjEBPiZ8fKqLsxvBARkdM7W16HeZ8dw7mKemPbtKQILL9vKKSe7nasjKyB4YWIiJyOQqVFZb0WikYtDv5ShTV7z0OtNwAAvD3d8foDwzAloY+dqyRrYXghIiKncrW2EUsyC3DgXGWrzwaF+mHNYyMwsLevHSojW2F4ISIip6FQadsMLmEyL/zz8dsQIpPaoTKyJTd7F0BERNRR1+o0ZoMLAJQq1KjXNNm4IrIHhhciInIKdWodXtl+st0+5Po4bERERA7v5xIF5m06hstVKov9/LzENqqI7InhhYiIHErLSiKlWgc/Lw/8+1Q53tlzDtqm5tVE7m4iNBmEVseNjZFD7utp63LJDhheiIjIYVhaSQQAw/vK8Kd7h2DVf85h/3V9xsbIsXJqPGTeDC89AcMLERE5BEsriQBg5qh++NO9Q+Hp4YYPpiegsl6LOrUOfl5iyH09GVx6EIYXIiJyCJX12jaDCwDMHh0FT4/mdSYyb4aVnoyrjYiIyCGU1FqejMuVRNSC4YWIiOzu6OVqLP6ywGIfriSiFhw2IiIiuzEYBKw7cAFvfl9odgVRC64koutZ9c5LRkYGbrvtNvj5+SE4OBhTpkxBYWFhu8dlZ2cjMTERXl5eGDBgANauXWvNMomIyEYUKi1+qahHXlENjl6uxn//40es+O6MMbgM7yvDyKheJsdwJRHdyKp3XrKzszFv3jzcdttt0Ov1eOmll5CWloZTp07Bx8fH7DEXL17EpEmTMGfOHGzcuBEHDx7EM888g969e2Pq1KnWLJeIiKzI0jJokQiYPy4az42PQYNGz5VEZJFIEIS279N1s2vXriE4OBjZ2dkYO3as2T5LlizB9u3bcfr0aWPb3Llzcfz4ceTk5LT7HUqlEjKZDAqFAv7+/t1WOxERdZ1CpcX8zXlmg4vYXYQPHk3AhGFhdqiMHEVnfr9tOmFXoVAAAAIDA9vsk5OTg7S0NJO2e+65B7m5udDpWs8012g0UCqVJi8iInIslpZB65oExIT42bgicmY2Cy+CICA9PR0pKSmIi4trs19ZWRlCQkJM2kJCQqDX61FZ2fr/+BkZGZDJZMZXREREt9dOREQ354fzbe/fAnAZNHWOzcLL/PnzUVBQgM2bN7fbVyQSmbxvGdm6sR0Ali5dCoVCYXwVFxd3T8FERHTTmgwC3t1zFsvbeRo0l0FTZ9hkqfSCBQuwfft27N+/H3379rXYNzQ0FGVlZSZtFRUV8PDwQFBQUKv+EokEEomkW+slIqKbV65U47kteTh8odpiPy6Dps6y6p0XQRAwf/58bN26FXv37kVUVFS7xyQnJ2PPnj0mbbt370ZSUhLEYiZzIiJnsP/sNUx6/4AxuLiJgKfGDkBqtOlfQrkMmrrCqnde5s2bh02bNuGbb76Bn5+f8Y6KTCaDVCoF0DzsU1JSgg0bNgBoXlm0evVqpKenY86cOcjJycH69es7NNxERET2pW8y4N1/n8WHWb+gZS1rqL8XVk1PwO1RgVCotFwGTTfNqkulzc1RAYBPPvkEs2fPBgDMnj0bly5dQlZWlvHz7OxsLFq0CCdPnkR4eDiWLFmCuXPndug7uVSaiMg+ShWNeHZzHo5cqjG2jYvtjbcfuRWBPgwoZFlnfr9tus+LLTC8EBHZ3r4zFUj/Ih81quZVQx5uIvzxnljMSR0ANzfzf5Elul5nfr/5bCMiIuoyXZMBb31fiI/3XzC29QmQYtX0BCRG9rJwJFHXMbwQEVGXXKlRYcHmPOQV1Rrbfjc4BG89HI8AzmMhK2J4ISKiDmmZbKtU63CiRIG3vi+EUq0H0LzF/4sTB+OJMf3bnO9I1F0YXoiIqF2WHqoYESjF6ukjMDwiwPaFUY/E8EJERG1SqLSoVenw8tcncOB8VavP5b6e2PTkSEQE+tihOuqpbPpgRiIich5Xaxsxf3Mezl+rNxtcgOYHLmr1LrVolZwA77wQEVErCpXWOEzk1s4cFj5UkWyN4YWIiACYTsiVerojMsgbP5wHss9es3gcH6pItsbwQkREZifkuotExi3+3USAwczoEB+qSPbAOS9ERD3c9UNE12v6Nbn08hbjT/cOwRg+VJEcBO+8EBH1cJX1WrNLoFv8bUoc/vhVAZ5IicITY6IAAP0CvRHsJ2FwIbvgnRcioh5O2c6EW5FIBJW2Cav3nsc/D13CkDB/xIT4MbiQ3fDOCxFRD6bS6vFx9gWLfQbIffD1M6Ph5yWG3NeToYXsjuGFiKiHOlteh3mfHcO5ivo2+4yNkSNM5sXAQg6F4YWIqAe4fhm0n5cHDp6vRMZ3Z6DWGQAAUrE7+gVKUVj+W5DhhFxyVAwvREQuztJziQBgUKgfVs8Ygd6+nqis16JOreMQETk0hhciIhdWrlRjyVfH29ze/6HEPvjblGHwErsDAMMKOQWGFyIiF3W1thGXKhvaDC4A8PQd0cbgQuQsuFSaiMgFtWw8V6pUW+zH5xKRM+KdFyIiF9Sy8VxhWZ3FfnwuETkj3nkhInIxgiBgy5EiAEBFnabNfnwuETkr3nkhInIhikYdXswswHc/lxnb+gd5I8jXE0cv1xrbUrkMmpwYwwsRkYs4XlyL+ZuPobi60aS9XKnGvcPD8cyd0dDoDQiQijEw2Bch/l52qpTo5jC8EBE5OUEQ8I+Dl7Diu9PQNTU/CVomFWPZpEHYUVCK/ecqsXrveQC/bTzH4ELOjOGFiMjJXL9bLgC8/+9zyDp7zfj5iH4BWDU9AX17eWPC0FBuPEcuh+GFiMiJtLdb7lN3DMDitFiI3ZvXY8i8GVbI9TC8EBE5iZa9W8wFFw83Ed6bNhz3Du9jh8qIbItLpYmInETL3i3m6A0CBofJbFwRkX0wvBAROYnDF9re5h/gbrnUc3DYiIjIAV0/KdfXywPf5JXgw6xfLB7D3XKpp2B4ISJyMO1NyjWHu+VST2LVYaP9+/dj8uTJCA8Ph0gkwtdff22xf1ZWFkQiUavXmTNnrFkmEZHDsDQpFwCeGNMfqdFBJm1juVsu9TBWvfPS0NCA4cOH4/HHH8fUqVM7fFxhYSH8/f2N73v37m2N8oiIHEbLMJFG32TxjstjIyMh9/Xk3i3Uo1k1vEycOBETJ07s9HHBwcEICAjo/oKIiBzQ9cNEGQ8Os9i3Tq3DwGBfhhXq0RxytVFCQgLCwsIwfvx47Nu3z2JfjUYDpVJp8iIichY3DhNl7DxtsT8n5RI5WHgJCwvDunXrkJmZia1btyI2Nhbjx4/H/v372zwmIyMDMpnM+IqIiLBhxUREN+fGvVuUan2bfTkpl6iZSBAEwSZfJBJh27ZtmDJlSqeOmzx5MkQiEbZv3272c41GA41GY3yvVCoREREBhUJhMm+GiMgR7TlVhjkbjpq0xfXxh7enO366WGNsa5mUGxYgtXWJRDahVCohk8k69Pvt8EulR40ahY0bN7b5uUQigUQisWFFRETdY9+ZCjz/xfFW7b9U1OMPqQPw1NiBkEnF6OXtyUm5RNdx+PCSl5eHsLAwe5dBRHRTrt90ztvTHZt/LMKnOZfN9m3UGbB673mMjZHjg+kJDC1EN7BqeKmvr8f58+eN7y9evIj8/HwEBgaiX79+WLp0KUpKSrBhwwYAwHvvvYf+/ftj6NCh0Gq12LhxIzIzM5GZmWnNMomIrKq9TedSouVoMhiQc6Ha2Ma9W4jaZtXwkpubi3Hjxhnfp6enAwBmzZqFTz/9FKWlpSgqKjJ+rtVqsXjxYpSUlEAqlWLo0KHYsWMHJk2aZM0yiYisxtKmcyIAz6fdgnnjoqFs1HHvFqIOstmEXVvpzIQfIiJr+6WiHuPfyW7z8/+k34GBwb42rIjIMXXm99uhlkoTEbmacxV1Fj/nk6CJOo/hhYjISnb9XIrnv2y9muh63HSOqPMcfrUREZGz0eib8PqO0/hnG6uJWnDTOaKuYXghIroJ1y+B9peKodLosXTbCfxc8tujSsYPDkajRo9DXE1E1C0YXoiIusjcEmh3NxGaDM3rIDw93LB88lBMvz2Cq4mIuhHDCxFRF7S1BLoluEQGeWPt7xMxOKx51YTMm2GFqLtwwi4RURfc+EDFG62ZPsIYXIioe/HOCxFRB10/v0VvsLxFlt5gsFFVRD0PwwsRUQeU1KhwuUqF2kYdRCIg8+gVi/25BJrIehheiIjacaVahSVbC3DwfFWH+nMJNJF1cc4LEZEFCpUWS9sILm4i4OHEPiZtXAJNZH2880JE1AaFSotShRoH2rjjYhCAabf1w+NjoqDVG7gEmshGGF6IiMxo2cMlNUZusV9FnQaxIX4YEi6zUWVExPBCRPSrltVETYKAv2z/GT/8Uo3DFyzPcwmQijm/hcjGOOeFiAjNd1rmb87D+HeycbasDj/80ryVv66p7SXRKdFBiAzy5jARkY0xvBBRj3fjbrmv/t8pk8/HxfZG8oBAk7bUGDlWPBiPPr28bVYnETXjsBER9Xg37pZ7rU5j8vmPF6vxREoUnkwdAI3egAFyH4TJvHjHhchOGF6IqMcrVTS2avOVuKNe0wQAUGmbsHrveQDNS6E/mJ7A4EJkRwwvRNTjlCvVqGnQQqnWo1TRiBXfnTH53MNNhLceHo5/Hb5ssr8L93AhcgwML0TUY1Qo1WjQ6PHnb35uc+8WANAbBKR/cRxPpERh3p3R8BK7QyblHi5EjoITdomoR7hc1YD/nC7Hy20EFz+JB16YEGt8r9I2oaC4FlFyH4yI7IWBwb4MLkQOgndeiMjlXalWYdm2E3hiTFSbzyeq0+hx16Bg3DMkFHVqHXfLJXJgDC9E5NIUKi2KqlU4eL4KwX5eFvsqG/W4PSrQYh8isj8OGxGRS6us1+JKTfNqom15JRb7+nvx73NEzoD/phKRS2nZ4l+p1sFfKkbOL5V4e8/Zdo9LiQ5CLx8OERE5A4YXInIZLQ9TvH7DOTdR89OfWyz6XQx+ulRtMvclNVqO1x6IQ4i/5WElInIMDC9E5BJu3OK/RUtwiQ31g5+XBz7efwFPpEThiTFRAIA+vaTo5e3J4ELkRBheiMgl3LjF//UmDw+DSqPH4HAZnr5jIDR6A6Rid/QL9EbfQD6biMjZMLwQkUuoUWnb/Ow/pyvwzbwxcBOJuAyayAUwvBCRU7p+Yq7eIOC1Hafb7KvSNsFNJMLAYF8bVkhE1sLwQkROx9zEXEvGxsgh9+VdFiJXYdV9Xvbv34/JkycjPDwcIpEIX3/9dbvHZGdnIzExEV5eXhgwYADWrl1rzRKJyIkoVFqcLatDcbUKz999Cx5JijD5vJe3GPF9ZSZtfJgikeux6p2XhoYGDB8+HI8//jimTp3abv+LFy9i0qRJmDNnDjZu3IiDBw/imWeeQe/evTt0PBG5JoVKizKlGldqGiESibD/3DVsOHTJZAm0mwhQ65rwwaMJ0BsEzm0hcmFWDS8TJ07ExIkTO9x/7dq16NevH9577z0AwODBg5Gbm4u33nqL4YWoh7pSrcLSrQUmD1P0cBOZBJcJQ0MwMNgXa/b9ghqVFrf262WHSonIVhxqzktOTg7S0tJM2u655x6sX78eOp0OYrG41TEajQYajcb4XqlUWr1OIrKNK9UqLNla0Ophivpfk4uvxAP1Gj0evm74yM+r9X8niMi1ONSzjcrKyhASEmLSFhISAr1ej8pK8xPzMjIyIJPJjK+IiAiz/YjIuZTUqHD51wcqtuW1KXEAAI3eAI3ewIm5RD2EQ4UXABCJRCbvBUEw295i6dKlUCgUxldxcbHVayQi61GotDhXXodqlRaKRp3FvmKP5v+ESTzcECAVc2IuUQ/hUMNGoaGhKCsrM2mrqKiAh4cHgoKCzB4jkUggkUhsUR4RWVlJjQqXq1SobdQh1F+C70+WWewv8XDDmOggVNRpcNegYG7xT9RDOFR4SU5OxrfffmvStnv3biQlJZmd70JErqOoWoWXbpiYa0lqtBzlSjUW3BWD/oHeDC5EPYhVh43q6+uRn5+P/Px8AM1LofPz81FUVASgecjnv//7v439586di8uXLyM9PR2nT5/GP/7xD6xfvx6LFy+2ZplEZGdXatoOLiIAk+PDTNpSooPw1ylxSBkox+BQP4QGSG1UKRE5AqveecnNzcW4ceOM79PT0wEAs2bNwqefforS0lJjkAGAqKgo7Ny5E4sWLcKaNWsQHh6OVatWcZk0kYsqV6pR3aCFslGH9LRYiD3OY++ZCpM+AoBZo/tjSkIfaPQGyKRiRPKBikQ9mkhomRHrIpRKJWQyGRQKBfz9/e1dDhG1oaiqAUu3nbC4mqjFlv8ZBQAwGAREBnmjTy8GFyJX05nfb4dbbURErq9cqW4zuIhEwMxRkSZtBoOAMH8vDA33Z3AhIoYXIrIdhUqLXyrqUd2gbfOOiyAAj9zW1/g+NVqOyCBvRMp9uAyaiAAwvBCRDShUWlyqbMD8Tccw/p1snLpqeSfsenUTgObg8tqDw3i3hYhMONRSaSJyPVeqVdDoDVi+/WfjaqKXvj5h8RiZVIzPnhyJyCBv9GVwIaIb8M4LEVnN5aoGLNlagEtVDSbLoNU6Q5vHpEQHQanWNa8oYnAhIjN454WIul25Uo1alRZXahrxh5QBqFfrIBI1z2dpcfeQENSrdci5UG1sS4kOwmsPDEOAVMz5LUTUJoYXIupWl6sa8PK2EyZ3WtxuCC4AkFdUg5VT47HsvwajUdsEfy8xevl4cqdcImoXh42IqNtcqVZh2Q3BBQAMvwaXQJ/f7qZU1mvxh3/m4s1dhYgN8cOgMH8GFyLqEIYXIuoWCpUWRdUqi5vOvf3wcJP3Y2PkfBI0EXUah42IqFtU1mtRo9Ja7OPuLsL6WUkAgL69pAj192JwIaJO450XIuoW5Uo1NuRctthHpzfgk4MXER3si9hQfwYXIuoS3nkhok67WtsIRaMOykYd/KViXK1R4c/bT6KkVt3mMakxckTJfbBiajyXQBPRTWF4IaJOuVzVgGU3PJdIhOanPwOAVOyOfkFSFJbVGz9PiQ7C36bEcQk0EXULhhci6rCSGhVeNvNAxZbgEhviB7mvJxIie+GFewKg0RsQIBWjX6A3+gbybgsRdQ+GFyJql0KlhaJRhzq1vtUy6Ou98VA8AqRi6A0C6tQ6+HmJIff15N0WIupWDC9EZNHVahVU+ia8sv0kZtzez2Jfta4JNYKAW/v1slF1RNQTMbwQUZuu1qigUOvw+s7TOHi+CipNk8X+flIxJO5cxEhE1sX/yhCRWeVKNdR6A6pVOuNQUV5xbZv9U6KDIAIg9+UQERFZF8MLEbVytbYRi7/IR4NGj6+OXjH5zEfijsFhfiZtqdFy/G3KMARxNRER2QCHjYjISKHSoqJOg6JqFR5O6odXtp/EsaJakz5NBgHjB4dgcVosNHoDIgO94e/lAX8GFyKyEYYXIgLQfLdlSWYBDpyrtNhPrTNg9d7zAJqHilZOjUcfbjpHRDbEYSMigkKlbTO4iN1FWPi7GIyJDjJpT42W4/UHhjG4EJHN8c4LEaGyXms2uLiJgIwHh2HXz2VI6NcLT4yJMm48F9FLioggHztUS0Q9HcMLEeHQL+aHigwC8OdvTuLLuckwCAIaNE3oEyBGLx9PhPh72bhKIqJmDC9EPZBCpUVlvRY1Ki2+LbiKf1l4GrRK24QyhRr/PHQJK6fGIyxAasNKiYhaY3gh6mEsTcx1EzXfbbleaowc0b198cH0BK4mIiKHwAm7RD2IpYm5kUHe+OuUOJO2sTFyvDE1HpFyHwYXInIYvPNC1AOUK9WoadBC22Rocyn05SoVbu8fiP+k38GHKhKRQ2N4IXJxRVUNWLrtBA6er0J0sK/Fvg0aPR+qSEQOj8NGRC6sXKk2BhcAOF9Rb7G/n5fYFmUREd0UhhciF3ZNqTYGlxaeHub/tR8bI+dDFYnIKdgkvHz44YeIioqCl5cXEhMTceDAgTb7ZmVlQSQStXqdOXPGFqUSuYyrtY14/ssCkzY3EfDG1PhWu+WOjZFj5dR4zm8hIqdg9Tkvn3/+ORYuXIgPP/wQY8aMwccff4yJEyfi1KlT6NevX5vHFRYWwt/f3/i+d+/e1i6VyGX8+1Q5Fn91HLUqnUm7QQCWbTuBJ1Ki8MSYKPh7iRHo48mJuUTkVESCIAjtd+u6kSNHYsSIEfjoo4+MbYMHD8aUKVOQkZHRqn9WVhbGjRuHmpoaBAQEdPr7lEolZDIZFAqFSfghclUtG84p1TpIPd3x2eHL+NfhIuPnEg83aPSGVselRAfh7Udu5U65ROQQOvP7bdU7L1qtFkePHsWLL75o0p6WloZDhw5ZPDYhIQFqtRpDhgzByy+/jHHjxpntp9FooNFojO+VSuXNF07kJNp7EnTakBA8Nz4aGd+dwQ/XzX1JiQ7C6w8MY3AhIqdk1fBSWVmJpqYmhISEmLSHhISgrKzM7DFhYWFYt24dEhMTodFo8K9//Qvjx49HVlYWxo4d26p/RkYGXn31VavUT+TILG04JxIBL9wTi7l3DIRIJMLbj9yKmgYtlGo9/L08+GwiInJqNtnnRSQSmbwXBKFVW4vY2FjExsYa3ycnJ6O4uBhvvfWW2fCydOlSpKenG98rlUpERER0U+VEjqutJ0EDgCAAaUNCjf+ehfh7MawQkcuw6mojuVwOd3f3VndZKioqWt2NsWTUqFE4d+6c2c8kEgn8/f1NXkQ9QWF5ncXP69Q6i58TETkrq4YXT09PJCYmYs+ePSbte/bswejRozv85+Tl5SEsLKy7yyNyWjsKSvHHL49b7MMN54jIVVl92Cg9PR0zZ85EUlISkpOTsW7dOhQVFWHu3LkAmod9SkpKsGHDBgDAe++9h/79+2Po0KHQarXYuHEjMjMzkZmZae1SiRxSy3OJlGo9vMRu+OehS8g8VmLxGG44R0SuzOrhZdq0aaiqqsJf/vIXlJaWIi4uDjt37kRkZCQAoLS0FEVFvy3r1Gq1WLx4MUpKSiCVSjF06FDs2LEDkyZNsnapRA5FodJC2aiDUq1vfjXq8Lcdp1Bc02jskzYkBPUaHQ79Um1s44ZzROTqrL7Pi61xnxdyBeW1jWjUG/DS1ydabe8PNO+Uu3TiYDyZGgVlow6V9Vo+CZqInJrD7PNCRJ2nUGlR/etdFnPBRSp2x4sTB2FkVCBEIhFk3gwrRNSz8MGMRA6msl4LATAbXACgUdeEEZEBUKr1ti2MiMhB8M4LkQO4fot/iYcb/q+g1GL/enUTenlzNRER9UwML0R2pFBpUaZU40pNI0QiEX68WIX/PXARTQbLU9FadsklIuqJGF6I7ORqbSOWfFWAA+d/2yVXKnZvN7ikRAfB38uDO+YSUY/FOS9EdqBQaVsFF6B5PgsAiN1FWDJhEFKig0w+T4kOwmsPDENEkI/NaiUicjS880JkB5X12lbB5XrLJw/Fu/8+iy+fSoZabzAug5ZJxQgPkNqwUiIix8PwQmQHynaeO9TLxxOV9VoYBGBwGPcrIiK6HoeNiGxMEARkFV6z2Efi4YZUbvFPRGQW77wQWdn1y6Dd3ERYs/c8dp8qb7P/mOggVCjVyHhgGDefIyIyg+GFyIpKalS4XKVCbaMOpQo13v/3WZPN5cIDvHC1Vm18nxodhFfuGwpvsTvCe3nbo2QiIofH8EJkBdfv3wIAm38qwoFzv03Q9XAT4c2H4nHXoGBU1GmgaNTB29MdPp4eCPAW844LEZEFDC9E3czc/i3X85V44MERfRDfN4DPJSIi6gJO2CXqJgqVFpcrG7Dkq+NtBpdbIwJQr9Hjjlt6o66dFUdERGQewwtRN7hSrcKVmkaUKdV4YcIgPJLU12y/BXdFAwA0egP8vPhsIiKiruCwEdFNKq5qQFFNIxSNOuibBLyzpxCXqlRm+2r0BgBAgFTMZdBERF3E8EJ0Ey5XNWDZthM4eL7K7OeT4kKx8+cy43uJhxtSooMQGeTNuS5ERF3EYSOiLlCotCiuasDLbQQXDzcRJg8Pw9PjBhrbxkQHoaJOgxUPxqMPl0ETEXUZwwtRJ12tbcT8zXmoVetwoI07LnqDgCm39kG9uvlBi6kxcrw2ZRgmxYWibyCDCxHRzeCwEVEnKFRaLMkswIFzlbgzNthiX43egLAAMfYsGotgPwmHiYiIugnDC1EHKFRaVNRpUKvS4fm7b0G/QG+8tuOUxWNkUjH8JR6800JE1M0YXoja0d6mc+akRAehXy8pgwsRkRVwzguRBeVKtcVN534/qh9SBgaatKXGyPHaA8MQEeRjixKJiHoc3nkhasOVahWKqlVtTsoFgN8NCkHYqEhomwxo0DQhQCpGLx9PhPh72bBSIqKeheGF6DoKlRaV9VrUqLTQNhnQqGuCmwgwCOb7q3RN+OVaA7b8VISVU+MRFiC1bcFERD0QwwvRr67WNhpXErXwcBO1GVyA5k3n+gRI8cH0BK4mIiKyEc55IULz3JZLlQ2Yfns//P2/kzAiMgBA834tQPOToG/UsulcmMyLwYWIyIZ454V6vCvVKizdWmBxbsvbD8fjqY3HjO/HRAdhwV0x6B/Ibf6JiGyN4YV6LIVKizKlGldqGvF4ygDIvD3xfwWlxs9FAEZHB+Hg+Sp4Szzw1dxk6A0CfCTu8JN4oJe3J4MLEZEdMLxQj9SRvVsEAE+MicLB81XQ6g2Yuf4npEQHYcWD8dy/hYjIjhheqMcxbvHfRnAZIPfBhcoGAM1b/KdGyxHo44lNT45EZJA3H6pIRGRnNpmw++GHHyIqKgpeXl5ITEzEgQMHLPbPzs5GYmIivLy8MGDAAKxdu9YWZVIPUVmvNVlRdKNlkwYZ/3eAVIxX7x8KmVSMoeH+DC5ERA7A6uHl888/x8KFC/HSSy8hLy8PqampmDhxIoqKisz2v3jxIiZNmoTU1FTk5eVh2bJlePbZZ5GZmWntUsmFKVRanCuvw5FL1ShXqi321TY1rzBKjZFjYLAvBvRufnF+CxGRYxAJgmBhF4ubN3LkSIwYMQIfffSRsW3w4MGYMmUKMjIyWvVfsmQJtm/fjtOnTxvb5s6di+PHjyMnJ6fd71MqlZDJZFAoFPD39++ekyCnduP8lsggb1yuUrXZf/2sJHxy8CLnthAR2VBnfr+teudFq9Xi6NGjSEtLM2lPS0vDoUOHzB6Tk5PTqv8999yD3Nxc6HS6Vv01Gg2USqXJi6iFuWcTWQouqdFBCJN5YeVUBhciIkdl1fBSWVmJpqYmhISEmLSHhISgrKzM7DFlZWVm++v1elRWtp6nkJGRAZlMZnxFRER03wmQU7ta24hfKurN7t8S4i/B8AiZSVtqjBx/nTIMfQKknNtCROTAbLLaSCQSmbwXBKFVW3v9zbUDwNKlS5Genm58r1QqGWB6OIVKi1qVDi9/fQLjB4eY7aNs1OHhpAj89f44qHUGBPl4Qu7LfVuIiJyBVcOLXC6Hu7t7q7ssFRUVre6utAgNDTXb38PDA0FBQa36SyQSSCSS7iuanFpJjQqXq1RwE4kwOFyGFbvOmO3XqDNg9d7zSIgIQP8gHwwM9rVxpURE1FVWHTby9PREYmIi9uzZY9K+Z88ejB492uwxycnJrfrv3r0bSUlJEIvFVquVnN+VahUuValQUafBh1nnsW7/Bah1hjb7tzybSO7Luy1ERM7E6sNG6enpmDlzJpKSkpCcnIx169ahqKgIc+fOBdA87FNSUoINGzYAaF5ZtHr1aqSnp2POnDnIycnB+vXrsXnzZmuXSk5IodKiqkELkQh4+eufcdDM/JY7bpFDpzfg0IVqY1tqtBzz7orms4mIiJyQ1cPLtGnTUFVVhb/85S8oLS1FXFwcdu7cicjISABAaWmpyZ4vUVFR2LlzJxYtWoQ1a9YgPDwcq1atwtSpU61dKjmZq7WNWJJZgOERATheVGM2uMQE+2BEZC+Miw3GtToNNHoDAqRiRPSSwl8qZnAhInJCVt/nxda4z0vPoFBpMX9zHg6cq8SHMxLwzKa8Nvuun5UEjd6AZz47hrExcqycGo+wAKkNqyUiovZ05vebzzYip6NQaVGqUGP67f1w95AQ/G3naYv9NXoDIgKl2LNoLIL9JLzbQkTk5BheyKm0DBVZejbRjWRSMQK9Pbl3CxGRi7DJgxmJuoPxadBmgouPp7vZY1KigxAZyCdBExG5EoYXchptPQ3aw02Etx4ZjtRouUl7aoyczyciInJBHDYipyAIAr7ILTb7md4g4PkvjuOzJ0fi6TsHQiJ2Q4CUO+YSEbkqhhdySAqVFpX1WijVOri5ibBm73nsPlXeZn+VtglSsTsGyH0YWIiIXBzDCzmcrkzKHRsjR5jMi8GFiKgH4JwXchgKlRaXKxuw5Kvjbc5tef2BOIyNMZ3b0rJ3C4MLEVHPwDsv5BBa7rbMHt0fB8zslAs0z20ZGRWE/xoWhsp6LerUOvh5iTm3hYioh2F4Ibu7fgn0qAGtnxx+vTq1DgODfRlWiIh6MA4bkd1dvwT6nd1nLfb18+KTxYmIejqGF7K7K7Uq4/9usvCorbExcsh9eceFiKin47AR2dT1S6D9pWJcqVbhj18VmPSZEBcKRaMWOb9UG9s4KZeIiFowvJDNdHQJ9P6z1/BEShSeTBkAAOgX6M0HKhIRkRGHjcgmLD2XCABu7SvDyKheAJo3nFu99zz+eegShoT5IybEj8GFiIiMeOeFbKKt5xK1ePPh4Qj2k3AJNBERtYvhhWyiRqW1+HmDRg8Z77AQEVEHMLyQVVw/MVdvELDiuzMW+3MJNBERdRTDC3W7zj6biEugiYioMzhhl7qVpYm5nu5umJMaZdLGJdBERNRZvPNC3crSxFxtkwGPJEXg0dv6cVIuERF1GcMLdavssxUWP2/Q6HFrv142qoaIiFwRwwt1C32TAe/sOYsPs36x2I8Tc4mI6GYxvNBNK1U04tnNeThyqcZiP07MJSKi7sAJu3RT9p4px6T3DxiDi4ebCPPHRSM1OsikHyfmEhFRd+GdF+oSXZMBb35fiHX7Lxjb+gRI8cGMBIzo18u4zwsn5hIRUXdjeKFOu1KjwoLNecgrqjW23T0kBG8+FI+AXwOKzJthhYiIrIPhhTpl98kyLP7yOJRqPQBA7C7C0omD8fiY/hCJRHaujoiIegKGF+oQrd6AjO9O45ODl4xtEYFSrJ4+AsMjAuxWFxER9TwML9SuoioV5m8+hoIrCmPbpGGhWDE1Hv5c+kxERDbG8EIW7TxRiiVfFaBO0zxM5Onuhj/dOxi/HxXJYSIiIrILqy6VrqmpwcyZMyGTySCTyTBz5kzU1tZaPGb27NkQiUQmr1GjRlmzTDJDrWvCn77+Gc98dswYXPoHeWPrM6MxM5nzW4iIyH6seudlxowZuHLlCnbt2gUA+J//+R/MnDkT3377rcXjJkyYgE8++cT43tOTq1Zs6WJlA+Z9dgynSpXGtvuGh+P1B4fBV8KbdUREZF9W+yU6ffo0du3ahcOHD2PkyJEAgL///e9ITk5GYWEhYmNj2zxWIpEgNDTUWqWRBd/kl2DZ1hNo0DYBACQeblh+31A8elsE77YQEZFDsNqwUU5ODmQymTG4AMCoUaMgk8lw6NAhi8dmZWUhODgYt9xyC+bMmYOKirYf9qfRaKBUKk1e1HlqXROWbi3Ac1vyjcFlQG8ffD1vDKbf3o/BhYiIHIbVwktZWRmCg4NbtQcHB6OsrKzN4yZOnIjPPvsMe/fuxdtvv40jR47grrvugkajMds/IyPDOKdGJpMhIiKi286hpzhfUY8paw5i80/FxrYHE/rg2/kpGBzmb8fKiIiIWut0eFm+fHmrCbU3vnJzcwHA7N/WBUGw+Lf4adOm4b/+678QFxeHyZMn47vvvsPZs2exY8cOs/2XLl0KhUJhfBUXF5vtR+ZlHr2CyR/8gDNldQAAL7Eb3nwoHu9MuxU+nN9CREQOqNO/TvPnz8ejjz5qsU///v1RUFCA8vLyVp9du3YNISEhHf6+sLAwREZG4ty5c2Y/l0gkkEgkHf7zqJlKq8efvzmJr45eMbbdEuKLNTNGICbEz46VERERWdbp8CKXyyGXy9vtl5ycDIVCgZ9++gm33347AODHH3+EQqHA6NGjO/x9VVVVKC4uRlhYWGdLpTacLa/DvM+O4VxFvbFtWlIElt83FFJPdztWRkRE1D6rzXkZPHgwJkyYgDlz5uDw4cM4fPgw5syZg3vvvddkpdGgQYOwbds2AEB9fT0WL16MnJwcXLp0CVlZWZg8eTLkcjkeeOABa5XaYwiCgM+PFOG+1T8Yg4u3pzvem3YrVj4Uz+BCREROwaqTGj777DM8++yzSEtLAwDcd999WL16tUmfwsJCKBTN2867u7vjxIkT2LBhA2praxEWFoZx48bh888/h58fhzJuRr1Gj5e3ncDX+VeNbYNC/bDmsREY2NvXjpURERF1jkgQBMHeRXQnpVIJmUwGhUIBf3+ulAGAU1eVmL/pGC5UNhjbHhvZD3+6dwi8xLzbQkRE9teZ328uJ3FhgiBg009FePXbU9DqDQAAX4kHMh4chsnDw+1cHRERUdcwvLioOrUOL249gR0Fpca2uD7+WD19BPrLfexYGRER0c1heHFBP5coMG/TMVyuUhnbZo/uj6WTBkHiwWEiIiJybgwvLkQQBGzIuYzXdpyGtql5mMjPywNvPhSPCXFcak5ERK6B4cVFKBp1WPJVAXad/O3RC8P7yrB6xghEBHrbsTIiIqLuxfDiAvKLazF/0zFcqWk0tj2ZEoUXJgyCp4fVtvIhIiKyC4YXJyYIAtb/cBErd52Brql5xbtMKsbbDw/H74Z0/BEMREREzoThxUnVqrRY/OVx/Pt0hbFtRL8AfDBjBPoESO1YGRERkXUxvDiho5ersWBTHq4q1Ma2p+4YgMVpsRC7c5iIiIhcG8OLEzEYBKw7cAFvfl+IJkPzMFGgjyfefmQ4xsUG27k6IiIi22B4cRJV9Ro8/+VxZBVeM7bd3j8Qq6YnIFTmZcfKiIiIbIvhxQn8eKEKz27JQ7lSAwAQiYD546Lx3PgYeHCYiIiIehiGFwdmMAj4MOs83tlzFr+OEkHu64l3p92K1Jje9i2OiIjIThheHNS1Og3Sv8jHgXOVxrbkAUF4/9FbEezPYSIiIuq5GF4c0KHzlXju83xcq/ttmOi58TFYcFcM3N1Edq6OiIjIvhheHEiTQcCq/5zDqr3nIPw6TNTbT4L3H70VowfK7VscERGRg2B4cRDlSjWe25KHwxeqjW2pMXK8O+1WyH0ldqyMiIjIsTC8OID9Z69h0ef5qGrQAgDcRMDzabF4+o6BcOMwERERkQmGFzvSNxnw7r/P4sOsX4zDRKH+Xlg1PQG3RwXatzgiIiIHxfBiJ6WKRjy7OQ9HLtUY28bF9sbbj9yKQB9PO1ZGRETk2Bhe7GDfmQqkf5GPGpUOAODhJsIf74nFnNQBHCYiIiJqB8OLDemaDHjr+0J8vP+Csa1PgBSrpicgMbKXHSsjIiJyHgwvNnKlRoUFm/OQV1RrbPvd4BC89XA8Arw5TERERNRRDC82sPtkGf74VQEUjc3DRGJ3EV6cOBhPjOkPkYjDRERERJ3B8GJFWr0BK747g38cvGhsiwiUYvX0ERgeEWC/woiIiJwYw4uVFFerMH/TMRy/ojC2TYwLxYqp8ZBJxXasjIiIyLkxvFjBdydK8UJmAerUegCAp7sbXr53MGaOiuQwERER0U1ieOlGal0TXt95GhtyLhvb+gd5Y/WMEYjrI7NjZURERK6D4aWbXKxswPxNx3DyqtLYNnl4OF5/IA5+XhwmIiIi6i4ML91g+/GrWLb1BOo1zcNEEg83vDJ5KKbfHsFhIiIiom7G8HIT1LomvPrtKWz+qcjYNqC3D9bMGIHBYf52rIyIiMh1uVnzD3/ttdcwevRoeHt7IyAgoEPHCIKA5cuXIzw8HFKpFHfeeSdOnjxpzTK75HxFPaasOWgSXB5M6INv56cwuBAREVmRVcOLVqvFww8/jKeffrrDx7zxxht45513sHr1ahw5cgShoaG4++67UVdXZ8VKO2frsSu4b/UPOFPWXJOX2A1vPBSPtx8ZDh8Jb2YRERFZk0gQBMHaX/Lpp59i4cKFqK2ttdhPEASEh4dj4cKFWLJkCQBAo9EgJCQEK1euxFNPPdXudymVSshkMigUCvj7d+8dEJVWj1e+OYkvj14xtsUE+2LNYyNwS4hft34XERFRT9KZ32+r3nnprIsXL6KsrAxpaWnGNolEgjvuuAOHDh0ye4xGo4FSqTR5WcPZ8jrcv/qgSXB5JKkvts9PYXAhIiKyIYcKL2VlZQCAkJAQk/aQkBDjZzfKyMiATCYzviIiIqxS2/v/OYdzFfUAAG9Pd7zzyHC88dBwSD3drfJ9REREZF6nw8vy5cshEoksvnJzc2+qqBuXFwuC0OaS46VLl0KhUBhfxcXFN/Xdbfnb/XEIl3lhUKgfts9PwYMj+lrle4iIiMiyTs8unT9/Ph599FGLffr379+lYkJDQwE034EJCwsztldUVLS6G9NCIpFAIpF06fs6o5ePJ/715Ej0CZDCS8y7LURERPbS6fAil8shl8utUQuioqIQGhqKPXv2ICEhAUDziqXs7GysXLnSKt/ZGQN7+9q7BCIioh7PqnNeioqKkJ+fj6KiIjQ1NSE/Px/5+fmor6839hk0aBC2bdsGoHm4aOHChXj99dexbds2/Pzzz5g9eza8vb0xY8YMa5ZKRERETsKqm5L8+c9/xj//+U/j+5a7Kfv27cOdd94JACgsLIRCoTD2eeGFF9DY2IhnnnkGNTU1GDlyJHbv3g0/P67oISIiIhvt82JL1tznhYiIiKzDafd5ISIiImoPwwsRERE5FYYXIiIicioML0RERORUGF6IiIjIqTC8EBERkVNheCEiIiKnwvBCREREToXhhYiIiJyKVR8PYA8tGwYrlUo7V0JEREQd1fK73ZGN/10uvNTV1QEAIiIi7FwJERERdVZdXR1kMpnFPi73bCODwYCrV6/Cz88PIpGoW/9spVKJiIgIFBcXu+Rzk1z9/ADXP0een/Nz9XN09fMDXP8crXV+giCgrq4O4eHhcHOzPKvF5e68uLm5oW/fvlb9Dn9/f5f8P2QLVz8/wPXPkefn/Fz9HF39/ADXP0drnF97d1xacMIuERERORWGFyIiInIqDC+dIJFI8Morr0Aikdi7FKtw9fMDXP8ceX7Oz9XP0dXPD3D9c3SE83O5CbtERETk2njnhYiIiJwKwwsRERE5FYYXIiIicioML0RERORUGF7a8dprr2H06NHw9vZGQEBAh44RBAHLly9HeHg4pFIp7rzzTpw8edK6hXZRTU0NZs6cCZlMBplMhpkzZ6K2ttbiMbNnz4ZIJDJ5jRo1yjYFd8CHH36IqKgoeHl5ITExEQcOHLDYPzs7G4mJifDy8sKAAQOwdu1aG1XaNZ05v6ysrFbXSiQS4cyZMzasuOP279+PyZMnIzw8HCKRCF9//XW7xzjT9evs+Tnb9cvIyMBtt90GPz8/BAcHY8qUKSgsLGz3OGe6hl05R2e6jh999BHi4+ONG9AlJyfju+++s3iMPa4fw0s7tFotHn74YTz99NMdPuaNN97AO++8g9WrV+PIkSMIDQ3F3XffbXzukiOZMWMG8vPzsWvXLuzatQv5+fmYOXNmu8dNmDABpaWlxtfOnTttUG37Pv/8cyxcuBAvvfQS8vLykJqaiokTJ6KoqMhs/4sXL2LSpElITU1FXl4eli1bhmeffRaZmZk2rrxjOnt+LQoLC02uV0xMjI0q7pyGhgYMHz4cq1ev7lB/Z7t+nT2/Fs5y/bKzszFv3jwcPnwYe/bsgV6vR1paGhoaGto8xtmuYVfOsYUzXMe+fftixYoVyM3NRW5uLu666y7cf//9bf4F3G7XT6AO+eSTTwSZTNZuP4PBIISGhgorVqwwtqnVakEmkwlr1661YoWdd+rUKQGAcPjwYWNbTk6OAEA4c+ZMm8fNmjVLuP/++21QYefdfvvtwty5c03aBg0aJLz44otm+7/wwgvCoEGDTNqeeuopYdSoUVar8WZ09vz27dsnABBqampsUF33AiBs27bNYh9nu37X68j5OfP1EwRBqKioEAAI2dnZbfZx5msoCB07R2e/jr169RL+93//1+xn9rp+vPPSzS5evIiysjKkpaUZ2yQSCe644w4cOnTIjpW1lpOTA5lMhpEjRxrbRo0aBZlM1m6tWVlZCA4Oxi233II5c+agoqLC2uW2S6vV4ujRoyb/7AEgLS2tzfPJyclp1f+ee+5Bbm4udDqd1Wrtiq6cX4uEhASEhYVh/Pjx2LdvnzXLtClnun43w1mvn0KhAAAEBga22cfZr2FHzrGFs13HpqYmbNmyBQ0NDUhOTjbbx17Xj+Glm5WVlQEAQkJCTNpDQkKMnzmKsrIyBAcHt2oPDg62WOvEiRPx2WefYe/evXj77bdx5MgR3HXXXdBoNNYst12VlZVoamrq1D/7srIys/31ej0qKyutVmtXdOX8wsLCsG7dOmRmZmLr1q2IjY3F+PHjsX//fluUbHXOdP26wpmvnyAISE9PR0pKCuLi4trs58zXsKPn6GzX8cSJE/D19YVEIsHcuXOxbds2DBkyxGxfe10/l3uqdEcsX74cr776qsU+R44cQVJSUpe/QyQSmbwXBKFVm7V09PyA1nUC7dc6bdo04/+Oi4tDUlISIiMjsWPHDjz44INdrLr7dPafvbn+5todRWfOLzY2FrGxscb3ycnJKC4uxltvvYWxY8datU5bcbbr1xnOfP3mz5+PgoIC/PDDD+32ddZr2NFzdLbrGBsbi/z8fNTW1iIzMxOzZs1CdnZ2mwHGHtevR4aX+fPn49FHH7XYp3///l36s0NDQwE0p9GwsDBje0VFRat0ai0dPb+CggKUl5e3+uzatWudqjUsLAyRkZE4d+5cp2vtTnK5HO7u7q3uQlj6Zx8aGmq2v4eHB4KCgqxWa1d05fzMGTVqFDZu3Njd5dmFM12/7uIM12/BggXYvn079u/fj759+1rs66zXsDPnaI4jX0dPT09ER0cDAJKSknDkyBG8//77+Pjjj1v1tdf165HhRS6XQy6XW+XPjoqKQmhoKPbs2YOEhAQAzXMVsrOzsXLlSqt85406en7JyclQKBT46aefcPvttwMAfvzxRygUCowePbrD31dVVYXi4mKTsGYPnp6eSExMxJ49e/DAAw8Y2/fs2YP777/f7DHJycn49ttvTdp2796NpKQkiMViq9bbWV05P3Py8vLsfq26izNdv+7iyNdPEAQsWLAA27ZtQ1ZWFqKioto9xtmuYVfO0RxHvo43EgShzWkBdrt+Vp0O7AIuX74s5OXlCa+++qrg6+sr5OXlCXl5eUJdXZ2xT2xsrLB161bj+xUrVggymUzYunWrcOLECWH69OlCWFiYoFQq7XEKFk2YMEGIj48XcnJyhJycHGHYsGHCvffea9Ln+vOrq6sTnn/+eeHQoUPCxYsXhX379gnJyclCnz59HOL8tmzZIojFYmH9+vXCqVOnhIULFwo+Pj7CpUuXBEEQhBdffFGYOXOmsf+FCxcEb29vYdGiRcKpU6eE9evXC2KxWPjqq6/sdQoWdfb83n33XWHbtm3C2bNnhZ9//ll48cUXBQBCZmamvU7Borq6OuO/YwCEd955R8jLyxMuX74sCILzX7/Onp+zXb+nn35akMlkQlZWllBaWmp8qVQqYx9nv4ZdOUdnuo5Lly4V9u/fL1y8eFEoKCgQli1bJri5uQm7d+8WBMFxrh/DSztmzZolAGj12rdvn7EPAOGTTz4xvjcYDMIrr7wihIaGChKJRBg7dqxw4sQJ2xffAVVVVcJjjz0m+Pn5CX5+fsJjjz3Wajnf9eenUqmEtLQ0oXfv3oJYLBb69esnzJo1SygqKrJ98W1Ys2aNEBkZKXh6egojRowwWcI4a9Ys4Y477jDpn5WVJSQkJAienp5C//79hY8++sjGFXdOZ85v5cqVwsCBAwUvLy+hV69eQkpKirBjxw47VN0xLUtKb3zNmjVLEATnv36dPT9nu37mzu3G/z46+zXsyjk603V84oknjP996d27tzB+/HhjcBEEx7l+IkH4dWYNERERkRPgUmkiIiJyKgwvRERE5FQYXoiIiMipMLwQERGRU2F4ISIiIqfC8EJEREROheGFiIiInArDCxERETkVhhciIiJyKgwvRERE5FQYXoiIiMipMLwQERGRU/l/yOc7qW2llD8AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ytest = model(xtraining).detach().numpy().reshape(-1)\n",
    "sns.scatterplot(x = ytest, y = yhat)\n",
    "plt.plot([-1, 3], [-1, 3], linewidth=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 53
    },
    "colab_type": "code",
    "id": "hZpPdBPYy53z",
    "outputId": "f2b4a179-809a-41c8-c2e2-2c205d5175c2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[0.7831]])\n",
      "tensor([0.3138])\n"
     ]
    }
   ],
   "source": [
    "for param in model.parameters():\n",
    "  print(param.data)\n"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "include_colab_link": true,
   "machine_shape": "hm",
   "name": "basicRegression",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.13"
  },
  "vscode": {
   "interpreter": {
    "hash": "ec2927a07ded3c75d927b91f94ff296a623558d55243d1c2257b781926dc480a"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}