diff --git a/Q1.ipynb b/Q1.ipynb
index ab7238e..f58e1c0 100644
--- a/Q1.ipynb
+++ b/Q1.ipynb
@@ -1816,1077 +1816,6 @@
    ],
    "execution_count": 97
   },
-  {
-   "cell_type": "code",
-   "id": "61b135564e36f71d",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.379249Z",
-     "start_time": "2026-04-26T14:56:43.348227Z"
-    }
-   },
-   "source": [
-    "poly_model = LinearRegression()\n",
-    "poly_res, y_pred_poly = evaluate_model(poly_model, X_train_p, X_test_p, y_train, y_test, \"Polynomial Regression\")\n",
-    "results.append(poly_res)"
-   ],
-   "outputs": [],
-   "execution_count": 98
-  },
-  {
-   "cell_type": "code",
-   "id": "5358eeb45dc985",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.491703300Z",
-     "start_time": "2026-04-26T14:56:43.380250Z"
-    }
-   },
-   "source": [
-    "plt.figure(figsize=(6, 6))\n",
-    "plt.scatter(y_test, y_pred_poly, alpha=0.5)\n",
-    "plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')\n",
-    "plt.title(\"Part E - Polynomial Regression: Actual vs Predicted\")\n",
-    "plt.xlabel(\"True Rating\")\n",
-    "plt.ylabel(\"Predicted Rating\")\n",
-    "plt.tight_layout()\n",
-    "plt.show()"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Figure size 600x600 with 1 Axes>"
-      ],
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAk4AAAJOCAYAAABBWYj1AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjksIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvJkbTWQAAAAlwSFlzAAAPYQAAD2EBqD+naQAAoXZJREFUeJzt3QeYU1X6BvB3esk0hg5SBQEFVMQCqChFVCy49rLY1y72VVfXtesq9rWv/Y+u2NcVkaJYsKCgAkrv0mGY3pP/8547d8hkkpnMJDNp788nhtzcTG5ubnK/nPOd78S5XC4XRERERKRR8Y2vIiIiIiIKnERERESaQC1OIiIiIn5S4CQiIiLiJwVOIiIiIn5S4CQiIiLiJwVOIiIiIn5S4CQiIiLiJwVOIiIiIn5S4CTipmfPnjjvvPOiYp/84x//QFxcXLMee8QRR5iL+If7mftbAvfKK6+Y/blmzZqY3p18/dwP3B/B+Ey31jbGAgVOUfAFY19SU1Ox11574corr8SWLVuC9jwlJSXmA/vFF1/4tT7Xc98uz8tbb70VtG2zv0jsS3p6Ovbee2/cdtttKCgoCNrziO9A033/OxwOHHTQQXjttde0y8IE3w++N88880yz/8Ynn3wSc4Ehf0C5H9tZWVnYd999MXnyZJSXlyOSPP300zEX3LSkxBb969Iq7rrrLvTq1QtlZWX4+uuvzRckv+gWLVpkAolgBE533nmn+XdTWiGuvvpqHHjggfWWDxs2DMHG15yRkYGioiJ89tlnuPfeezF79mx88803YfULrTUxeLz55ptb/Hn2228/XH/99ebfmzZtwosvvohzzz3XnFwuvvhixILS0lIkJobf1+ny5csxb948E+D+3//9Hy677LJm/R1+n/zrX/+KueApJSXFHM+0a9cuvPvuu7jhhhvMPg3mD8CW/kwzcGrXrl3UtKaHWvh90qXJjjnmGAwdOtT8+6KLLkLbtm3xyCOP4MMPP8SZZ57Z7D3qdDpRUVHR7McfdthhOOWUU9Aa+Dz8YqBLL70UJ598Mt577z189913LRKoRQKeyFvjZN61a1ecc845tbf55dy7d288+uijrR44FRcXm1av1sbW3nD0xhtvoEOHDqaVhJ8Rdq0wiBL/8PPjfmxffvnlOPjgg/Gf//zHfMd26dKl3mNcLpf5EZuWlhaxn2lpmLrqotCoUaPM9erVq831ww8/jOHDh5uAih/mAw44AO+88069x7Flht18/GW6zz77mF9bzz77LNq3b2/uZ6uT3Wwd7r88PfcBT6hsFenWrZt5Xf369TP7hV9yvqxatcq8VgYAnubOnWvue/PNN+t0Ga5YscIEDjk5OcjOzsb5559vWuzcVVVV4e6778aee+5ptoUnsltvvbVe8z+XH3fccabrk4Ex37tBgwbVdpkyMORtnrT5ni5YsKDO473lQ7z88stm3/Bkyudmt2YgXTje8Hjp378/Vq5cWS8Qf+yxx8yxxW3u2LEjLrnkEuTl5dVbj9vOkxJbTI888kj89ttv9fLP7K7qOXPmmBMaX9Mee+xRe/+0adNM8M5AKjMzE+PHj8fixYvrPNfmzZvNe8THcX907twZJ554Yp38mh9//BHjxo0zgTnfA7buXnDBBXX+jrfPBN8P/qhhFw9bQ0ePHm0CeXf2a2DL6HXXXWf2Hbf3pJNOwrZt2+qsm5+fjyVLlphrf02ZMsUETDyOeDzytjfff/89jj32WLRp08Y8/+DBg/H444+b+7jP2dpkv0774t4t79mN7y335ddff60Nqvn+d+rUyezHHTt2oKn42eXfX7t2bb37brnlFiQnJ9ceV2x14w8pPh+fl+/1GWec0aT9aIuPj69tdbePEftzOn369NrP6XPPPVfbSnXNNdfUfu/06dMHDz74oDnG3XE97hu+R/zuYIstl3nylePEAJldsvy88D08/PDDTcu7vX087vk5sd87956DYG9jLFDoGoXsExYDJeIX4AknnICzzz7btCCxifnUU0/Fxx9/bE4m7ti99fbbb5sAiicK9unzxMomfn6Z/+lPfzLr8Yu1MYWFhdi+fXu95dyulu4+c98HDI74+j///HNceOGFpmuJX3I33ngj/vjjD6+BEfELfsSIESaQvPbaa+vcx2U8GfMk6+60004zJ9b7778f8+fPN838PKHzi8jGVsFXX33VnNAYzPGkxfV///13vP/++3X+HgOxs846ywQY/OXLE8bxxx9vAloGWwwYiI/ncy9dutR8ufvC95KBC/cHf7n+97//NX+DX5JXXHEFgoGB4YYNG8wXuDu+Bp5IGaiwG5dB7VNPPWUCDAYOSUlJtSe+f/7zn+Z1MmD55ZdfzDV/xXvD7WfA8fe//90EyPT666+bL3Y+jvuewStf+6GHHmqez2514QmVJ5WrrrrKLNu6dStmzJiBdevW1d4+6qijzN9nFwlPGDxhMmhtCP8mgzYGTTfddJN5bTyZ8oTFExhbLdzx+bm/7rjjDvP3GWDyM8iWDRuPDe47Br/+dLnwuOLxw/UZSPCzy+OWx407vl6e+Bk0Tpo0yQQYPBb5/cDbfN82btxo1uN+bS4+nj9G+Br4HNxHzz//vLlmQNmU7wQe69yv/K7i59gdl/E94/7k9x2PAf4o4T7m8/Izz9fGkz6DgEC/X4mfO7buc1+xlZU/zHjMjRw50jwfl3fv3t384OLxzS5tvsfE7yd+jzDNgq3lAwYMMO81j19/8ActAyr+OGbaBt9rvvf8Lud+4PPwtTN4/9vf/mYewx8t1FrbGHVcErFefvllNpe4Zs6c6dq2bZtr/fr1rrfeesvVtm1bV1pammvDhg1mvZKSkjqPq6iocA0cONA1atSoOsv5t+Lj412LFy+us5x/m/fdcccdfm3X559/btb3ddm0aZMrWLhN/JtLly4127l69WrXc88950pJSXF17NjRVVxc7Prggw/MOvfcc0+dx55yyimuuLg414oVK2qX9ejRw3XuuefW3ubf4mN///33OvuvXbt2ddazt+OCCy6o8xwnnXSSeT9sP//8s1nvoosuqrPeDTfcYJbPnj27zrZw2dy5c2uXTZ8+3Szj+7t27dp628l977lN7jyPBRo3bpyrd+/edZaNHDnSXBrDbTzqqKPMvudl4cKFrj//+c/mea+44ora9b766iuz7P/+7//qPP7TTz+ts3zz5s2uxMRE14QJE+qs949//MOs577P7eP/0EMPdVVVVdUuLywsdOXk5LguvvjiOn+Dfzs7O7t2eV5ennn8Qw895PP1vf/++2adefPmNbgfPD8f3P7k5GTXypUra5dt3LjRlZmZ6Tr88MPrvYYxY8a4nE5n7fJrr73WlZCQ4Nq1a1e9dXntjyuvvNLVrVu32r/72WefmccvWLCgdh3ut169epn3kfvDnfv28L30drqwP+vuxx3xc+i5rd6OvTfffNOs9+WXX9Z7nfwbDRk2bJjrgAMOqLPshx9+MI997bXXzG2+Vt6eOnWqq6l4rDkcjtpjm98T9913n/nOGDx4cL3PKY9ld3fffbd5/LJly+osv/nmm817u27dOnPb/n765z//Wed9Oeyww+rtQ8/P9PLly813Nr9nqqurfb5/++yzj9fPc0tsYyxQV10UGDNmjPlFzKZWNkHzlwV/DTD3hNz72tl8zSZq/hpmi4gn/vpg900wsAWAvzI9L7m5uQg2/sLjPmBrD385sbn5f//7n2m6ZmJrQkKCaeVwx9YenvPYpdPQL1s27/OXuo2tVWxJc899sPHXmDvuZ3ZF2CP8uC3EbhnPbSFuszu+F+45WnZLBbvb+OvQczl/0TfE/VjgccDXwfecj2tO1wWxS4D7nhd2HbJVgq0KDz30UO06U6dONb/ux44da57TvrCLkccrWwNp1qxZpsXKbkmz8RezL/yFz/fXxmOMrQlsAXB/Lq7D/WQ/F/cFf52zm8mzu9DGFiZiC0VlZaVf+6O6utrskwkTJphWSxtbdNh6yF/tniM+//KXv9RpceFxw7/j3hXFViYer/60NnEfsrXq9NNPr/27dhet+7HM1je2/LGrxn6ttmC3Crsfe2w95HtyyCGHmNvevosaw9f2008/1ekS5mtmd5PdEmy3KPEz69ll7g+2YNrHNr9T2FrHz6NnyzC/d9iy5Y7HPN9Htny5H4f8vuZ7++WXX9Z+J7D11z1xn8dqQ8e87YMPPjCtxfyu9Wxp9uf9a41tjEbqqosCzD9gGQIe2GyCZRDh/iHil/4999yDn3/+uU4ejbcPFr8AgoUnUX4Am4Kj4nhx/3DaOVYN4WgXdouwS4Q5DMwfsvHkw3wZdq25Y3Ozfb8vPJmwy4i5IcxLIp54GJTaeVTu3IMZsrureGLm9vG5+N7wS9gduxD4XJ7b4vn37BMBg2Rvy30FADZ2ibE76Ntvv613ImHg1JyuCwYjPL74RcuRnPw3t4NBiY15Jvz7PHF7wy4xsl+/5/5hsO3Z9efrmOVzkbf3h/g+EE+w7MZj0MrPDU/i7LKaOHGieT+IQSW789gdwi5ddrUxIGIAxMd7w9wk7lt+Dj3xmOOJbv369abL1J/jpjkYuHE7mPfC7job88WYl8fXzePQDjoGDhyIlrZz506zH5kqYL/ftuYE7Uw34A8QBksMaBhUMhCw88rsY4PrMJGbn1sGCeym5o8ef451/mhidzbx/ebfc8+ja+h7k8ch87p8fX+5H/MMqvkDwp2348cT3z++j839sdsa2xiNFDhFAX452qPqPH311Vfmi4LJghySyoOfwQXzHrwlirbESJCmYA6PXfqAevTo4VchPL4+e1RdsPFEyi9k9v0zGPzoo49Mi4i3XCL3lg93nkno/v6a9/X3/H0ezy9ZJigzcZsnEgZfDG74a5JBgWcyqL+43+0Amb+6+fcZgDC3zm5Z49/2bO1w509w7IvnMWu/DrZ82QGQO/dRSWxpYWDMX+5slbj99ttNvhjzQ/bff3/zPnEgBXNweALlOkxo5ig1LvM8kTRXc97Phtj7mS2m3jDPikFUoHwdxwyiPXFb+BliThLzDLnv+F4dffTRzTr2+GOIgRBzmhg48f1gbpp7PiHxvWIrHUcZM6BkyzPfY67vLQjyfF/8+fHn7XuTr4ktrMzF8oY/dkMtErYxHClwinJsieGvJn7hu/9CZuDkr9asg8QghQm8wQzkGHzNnDnTJKu7tzpxhJJ9f0P4xc4TO09GbF1ha8Kf//znZm8Lv6z4S89u8SIWLGX3UmPbEgie+NniyMDPvYXD7roKFg44YEvNfffdZ7pNOUqLLYB8D5hs39B7ar9+tpK4/4pnd6e/rS92ayMDNX9OelyfrU688H3hSZ0nW45UsrE1ihfWB+MPDg60YMsJE/098VhhFzEThj3xmGPA7dliGEzsXmKQwK4sb+VAGDjwWGbgZO8rthQ2tK98fQfYLWOeo6s8W0753rEblj+K2K3k2TrYXHyN/BHDfc2WJ+53BsKe+IOHF9ZBYvDG45ADLNg62lK4b9l63tgxyGOe+4brugfi3o4fb8/B7xOOOuVx29T3rzW2MRopxynK8RcTPzTuvwDZgsNf2P6yi2i2xtBT5oTwQ2xf+AUXKA6z5uvnCC53bGXhvmHTfkPYQsF8Gf6y5agwfgH7M6rQ17aQPVrFxhYg8hzlGEx2q4Z7Kwa7SJoSRPvrr3/9qwl2XnjhhdrWBr4HdnenZz6OfWyxRYz727NEgud71xC2erGrhoGbt7wke5g/A2DPkXo8kTC4tru0ecL3bPWxT1C+qkdzP3M0E4MX99ZSBscMuvjDwO5Kagp/yxEw/4bBE0dJMnDyvLA1kD+ouP1DhgwxASqPR8/Pt/vrtmtjea7DEypfr50LY2Prtuc+8fyb3j4HTcVuVP5tdj+yVZivzb2OF3PJeHy54+eXwWtLV//mMc8ucf5o9cT9aG8XvxP4b/djnp+VJ598stHnYLcxXwtH03m22nm+f96+v1tjG6ORWpyiHE/EPCmz1YR5GeyzZk4Uc0jYt+0PthCwD52/6Nh0y3wT5kQ0lhfBbkJvQ8gZdDQ38GgO/gLlr2sOxeWJjCUW2GTPExu7atzzoRpqCXviiSdM64xnV0BT8Lk5hJfDsPnFxJaZH374wZQn4JdgMLpPfOHJnF1z3B9sCeKvRwY2bJnh0ONgYjDK44PHHk/gfJ18TnaRMNeO28IuY7Y48ITHbj2e1JlrxCHwbPFhFzOPW5YjYAI/uwT9af1kUMIveLYKMjDggAm2ArEbh8n3DMYZiC1btswEajx58PhmwMaggwEOH0N8XxgEsBQHjxO2WnKf8TnsINgbtmQwSZ1BEltE+LdZjoAna5ZaaA5/yxGwNYlD5Tk83RvuV74G7guWKOC+4jHBgJB/n935DNBYJsA+oTKJ326tYmDKYIX7iHlCzDXiCZTvDfcRcyo9c5i4v9idztfOYJY5gvwM2nXWmovHLj8zPM743rAFyh27XFnWgdvI7y6e/NmFy+1n0NWS2CXJ1l0Gc3y/uA8Z0C5cuNB0//K7iMc09z2PSZa74DIeiyx34U/eF7/H+b3GHyTstuT7yZ4FVjZnVyY/b8Tn5vvM45KP4X5jDmBrbGNUCvWwPmk+e9huY0Ol//3vf7v69u1rhuj379/fPM7bUHXPIeTuOCSeQ385xLqx0gSNlSPwt6yBP+zXweHCDeEQdQ7x7tKliyspKcnsDw5Ddx+y660cgTsO6eXQX7vMgz/b4W1odWVlpevOO+80w8C5LRwyfsstt7jKysrqbcv48ePrPZe398ke/u0+tN7be/zRRx+ZodSpqamunj17uh588EHXSy+9VG8bm1KOwNs20iuvvFJvqPLzzz9vjiOWU+DQ/EGDBrluuukmM1TffZjz7bff7urUqZNZj2UzWA6CZR0uvfRSv49/HocstcASBHy9e+65p+u8885z/fjjj+b+7du3m/3IzwSHZHO9gw8+2PX222/X/o358+e7zjzzTFf37t3N56dDhw6u4447rvZv2Lwd13wsnz8jI8OVnp7uOvLII+uUlmjoNXgb5u9POYItW7aYcg4sCeELywJweziE3fb111+7xo4da94T7gseI08++WSd9+Sqq65ytW/f3gzHdz+ueMyffPLJ5m+2adPGdckll7gWLVpUb1v5ueFzslQE9/Wpp55q3nfPfedvOQLbCy+8YNbntpeWlta5b9WqVaZECN97HgO5ubnmfWAJF3/LEQTyGeD3Dj/bffr0Md+dLGMyfPhw18MPP2zKmth27Nhh3rOsrCyzb/hvu5RCQ+UIbPwM77///uYY5XvAz+6MGTPqlOLgNnIf8fHun+1gb2MsiOP/Qh28iUQCJguztY19/dK62DrHfBr+YraL+ImIhIJynET8wGk32MXELjtp+QlzPdm5ME2ZZFpEpCWoxUmkARxtxCJ7zLlhYTgWigzXCV2jBRPweWEOEUfwsGAkk3+ZF+UtiVVEpDUpOVykAUyQ5IgVFnrjyVtBU8vjwAEmUzORmKOi7ITxlhw6LiLiL7U4iYiIiPhJOU4iIiIiflLgJCIiIuKnmMtxYnXVjRs3murArTmViIiIiIQnVmZiEVUWDvU2D2lMB04MmlpynigRERGJTOvXr2908ueYC5zsSV65c5ozX5SIiIhEF47gZaOK+0TwvsRc4GR3zzFoUuAkIiIiNn9SeJQcLiIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIiflLgJCIiIuInBU4iIiIikRA4/eMf/0BcXFydS//+/Rt8zNSpU806qampGDRoED755JNW214RERGJbSFvcdpnn32wadOm2svXX3/tc925c+fizDPPxIUXXogFCxZgwoQJ5rJo0aJW3WYRERGJTSEPnBITE9GpU6faS7t27Xyu+/jjj+Poo4/GjTfeiAEDBuDuu+/GkCFD8NRTT7XqNouIiEhsCnngtHz5cnTp0gW9e/fG2WefjXXr1vlc99tvv8WYMWPqLBs3bpxZ7kt5eTkKCgrqXERERCSCzJ0LVFUBsR44HXzwwXjllVfw6aef4plnnsHq1atx2GGHobCw0Ov6mzdvRseOHess420u9+X+++9HdnZ27aVbt25Bfx0iIiLSQt58Ezj8cODcc4HqasR04HTMMcfg1FNPxeDBg03LERO9d+3ahbfffjtoz3HLLbcgPz+/9rJ+/fqg/W0RERFpQa++CpxzjhUwJScjHCQijOTk5GCvvfbCihUrvN7PHKgtW7bUWcbbXO5LSkqKuYiIiEgEeeEF4JJLAJcL+MtfgGeeAeJDnmEU+hwnd0VFRVi5ciU6d+7s9f5hw4Zh1qxZdZbNmDHDLBcREZEo8a9/WcESg6arrgKefTYsgiYK6VbccMMNmDNnDtasWWNKDZx00klISEgwJQdo4sSJpqvNNmnSJJMPNXnyZCxZssTUgfrxxx9x5ZVXhvBViIiISFDl5ABxcQwUOKTe+neYCGlX3YYNG0yQtGPHDrRv3x6HHnoovvvuO/Nv4gi7eLcIc/jw4ZgyZQpuu+023Hrrrejbty8++OADDBw4MISvQkRERILq7LMBFsQeMiSsgiaKc7nYDhY7WI6Ao+uYKJ6VlRXqzRERERGXC3jySeCUU4AuXcI6NgiPDkMRERGJ3aDp1luZjwOMHg2UliKchdWoOhEREYmxoOn664FHH7VuMyE8LQ3hTIGTiIiItD6n0xox9/TTu0fSXX552L8TCpxERESkdVVXA5deCrz4opX8zZpNF14YEe+CAicRERFpXX//uxU0ceT8K68Af/5zxLwDSg4XERGR1nX55UC/fsCUKREVNJFanERERKR1EsHjamoyde0K/Ppr2Mw/1xRqcRIREZGWVVYGTJgAvPXW7mURGDSRAicRERFpOSUlwIknAh99ZJUb2LEjove2uupERESkZRQVAccfD3zxBeBwWMFT27YRvbcVOImIiEjwFRQAxx4LfPMNkJkJTJsGjBgR8XtagZOIiIgEV14ecPTRwA8/ANnZwPTpwMEHR8VeVuAkIiIiwfXyy1bQlJsLzJgBDBkSNXtYgZOIiIgE17XXAtu3A2ecAQweHFV7V4GTiIiIBG7rVqtbLiXFqtd0331RuVdVjkBEREQCs2EDcOihwOmnA5WVUb031eIkIiIizbdmDTBqFLB6NVBRYbU8sTJ4lFKLk4iIiDTPihXAyJFW0LTnnsCXX0Z10EQKnERERKTpliyxgqZ166wJe+fMAbp3j/o9qcBJREREmmbRIuCII4CNG4F99rGCpihvabIpcBIREZGmyc+3plPZbz9rOpWOHWNmDyo5XERERJpmxAhg5kxgr72sIpcxRIGTiIiINO6774C0NGDffa3bhxwSk3tNXXUiIiLSMI6WGzsWGDMGWLYspveWAicRERHxbdYsa8Je5jTtu2/MJIH7oq46ERGJSVVVTsxfn4cdxRVo60jGkG5tkJio9oQ6pk0DTjoJKC+3gqf33rO662KYAicREYk5s37fgle+WYM1O4pRWe1EUkI8erZ14LwRPTF6QOyMEGvQRx8Bp55qVQM/4QTg7beteehinAInERGJuaDp/mlLUFhWaVqa0pITUFpRjWVbC81yivngafZs4OST2SwHnHIKMGUKkJQU6rcuLChwEhGRmOqeY0sTg6bubdIQH291zWWmxsORnIB1eaV4de4ajOzbPra77Q46CDj4YKBHD+DVV4FEhQs27QkREYkZzGli9xxbmuygycbbXL56e7FZ76BebRGzMjKATz+18pkSEkK9NWElhsNpERGJNUwEZ04Tu+e84XLez/VizgsvAHffXTd4UtBUj1qcREQkZrBFiYngzGli95wnLuf9XC+mPPUUcNVV1r+HDbPqNYlXanESEZGYwZIDHD3HFiWn01nnPt7m8l7tHGa9mDF58u6g6cYbgdGjQ71FYU2Bk4iIxAwmfLPkQGZqkkkEZ5J4ldNprnk7KzUJ5w7vGTuJ4ffdB9xwg/Xv224DHnwQiIsL9VaFNXXViYhITLFLDdh1nHYWV5juuX4dM03QFBOlCFwu4B//AO66y7rN69tvD/VWRYQ4l4t7L3YUFBQgOzsb+fn5yMrKCvXmiIhIjFUOdzpd+GNXKYorquBITkTXHJZFaOVWnu+/3z1JL1uZbroJsaygCbGBWpxERCQmMUhq7ZIDK7YWYvqiLVi5rQhlVdVITUzAnu0zMG5gR/TpkNl6G8IaTY89Zv170qTWe94ooMBJRESklYKml79ZY7oGO2enIj05DSUVVVi0MR8b80tx/oieLRs8MRmeE/XaLSoKmJolRrLfREREQofdc2xpYtDUp73DpBjllVSYa97m8s8WbzHrtYjqauAvfwGOOALIy2uZ54gRanESERFpYcxpYvdcWlI8flq7CztLKsxovsT4eOSmJ6NTdgpWbC0y63XLTQ/uk3O+ufPPB954g+XRgW++AY47LrjPEUMUOImIiLQwJoJvLyrHjuJylFc6kZGaiKSERFOlfGthGfLLmKCeYtYLanJ5ZSVwzjnA229bVcA5Wa+CpoAocBIREWlh6UkJJnAqKa9Ch6xUVFQ5UVZZjYS4OOQ6krGloAxwWesFLbm8ogI44wzg/feBpCQTPFUddwLmr97R6iMJo4kCJxERkRZmZS7FoaLahT/ySlFW5YTT5UJ8XBxSE+PN/S7E1awXhOTysjLglFOA//0PSEkB3n0Xs3oPxSuvzDO1q9jSxdpVrKLOgqAxUbsqSBQ4iYiItLDSymqkJ8djU361aW3iZMKpCfGodLqwq7QSyYnx6JIcb9ZrLLm8b4cMxNVU92YF9IyURCzfWmSSy3u3y7C67bZuBX7+GUhLAz74ALO67Yv7py0xFdLZ0sTn57x8y7YWmuWk4Mk/ap8TERFpYeyCK6moNsnhbdKTzGi68iqnueZtLmcg46urzk4uZ0sTFZRWmq4/XhOX28nlRvfuwOzZwLRpqBo1xlRJZ9DUvU2aCbaYlM5r3ubyV+euMQVBpXFqcRIREWmlrrqkhAR0yExGZbUL1S6XyXFKSojD1sKKBrvqmAjOnKayygT8vinPlDKoqnYiMYGBWDJ6tktHXEE+nF98AfzpWOtBe+1lLsxpYvccW5riOarODW9z+ertxaaKemsXBI1ECpxERERaGLvg2mUkm/lz80oqzag6JnYz18i+zQDGV1edIznRdPH9tHYnqp0uZKQmISmVo/Jc2FZYhopt2/HQSzej+4blwEcfAePG1T6WieB8HnbPecPl7ALketI4BU4iIhKTWnOuOkdyItplpJjgaVN+uWkxKiqvMl1mHGXXKSvFtEhxPW86Z6WaMgbMh2L3mt1ylJIYh1xnMW7617XovWkFXLm5QPv2dR7L18ZEcHYFZqbWf31czvu5njROgZOIiMScWb9vMXk/rTXCjLWWWDaAI+CG9shBUXk1KqqdSE6IR0ZKAlZsK8agrtlmPW82FZQhpSY/ym6h4jan79qB2564Br03rUJBZhuUfDgNnYYMqfNYBoR8bUwEdyQn1OmuczqdJnDs1zHTrCeNU3K4iIjEXNDEkWQMJDJTE9HVJEwn1o4w4/3BxpFurLXEmk0Mkthll5OeZK55m8uP2qejz0KWzHHiyLsh3dugQ2YqyiqdiN+8CXc9dpUVNLVpj8duex67+vSv91i2ojEgZDL4urxSkwzOquW85u2s1CScO7yn6jn5SS1OIiISU91z7iPM7NYXdmGxNYaBBEeYjezbPuiBBGsssdaSXcCSRS9TEhNMSxODpoYm+HUkWzlRqUkJGNqzDaq3bMX5/7we7basRWG7Tnjtnn9jV04Xn119diua3crGnCa2WLGliUGTShH4T4GTiIjEDOY0hXKEGYOj3kdk+D9lipeuPtZxSmrfDtv23hdJzipM/eerWByfg0EdMnx29RGDIwaErZXXFa0UOImISMwIhxFmDJKaOpGv3dXHCuEsdsm6Tf+77l7Ebd+BFfEZjXb12RgkqeRAYBRmiohIzHAfYeZNOI8w67PzD9z46bMY1DEDu0oqsTqvHH+kZJuuvjrTrUiLUouTiIjEjIgdYbZoETB6NHK2bsVlndphw6S/NqmrT4JHLU4iIhIzInKE2YIFwBFHWPPP7bcf4q66ynT19e+UZa4VNLUutTiJiEhMiagRZvPmAUcdBezaBRx4IPDppwCLXErIKHASEZGYE8oRZk6ny79RdXPnAsccAxQUAMOHA598AmRnt/j2ScMUOImISEwKxQizFVsLa+s4cdJe1mZimQGOmKuT3F1UBJxwghU0HX448PHHQGZok7/9DviinAInERGRVgqaXv5mjekaZDmB9OQ0lFRUmdpMLDNQZ2RcRgbw6qvAv/4FTJ0KOBwhfY/8DvhigAInERGRVmitYeDBoIkFLOM414qpWJ6EjJREU5vps8Vb0DsrGfGpnPAXwPjxwLHHwszLEikBXwwIo2EDIiIi0YldXGytYeDBIGrZlgLMX5dnrnmby1M++S+c/fsDK1fufmCIgybPgC8zNQkJ8XHmmre5nAEf14sVanESERFpYcwLYhfXym3l+HndLnPb5bLiornJO3Dxlp9w3gt/R0J1NfD448ATT4RFnpJ7wGe3ktl4m8tXbC0y6zW1GnqkCpsWpwceeMC8Cddcc43PdV555RWzjvslNTW1VbdTRESEAcj6nSVYsrnAXDfW4uJITsQfeaWYu2I7isqrkBgfj9SkeHN95PyZuOy5203QVHzKacAjj7RYl9szX6zEozOW4YlZy801b3N5YwFfuo/Jg9OSE1BeVW3WixVh0eI0b948PPfccxg8eHCj62ZlZWHp0qW1tz0jYBERkXBLlG6fnow120tQ5QLSE+NqW3n+tPAz3PnfxxAPFz7cbyzGvfIah/uFTZ6SIznRvD6uy+45b1PUpCQmmPViRchbnIqKinD22WfjhRdeQJs2jZe4Z6DUqVOn2kvHjmFUqExERKK21cg9AGHAkZOehN7tMsw1b3O5r9abmcu2oLyqyhTarHYBFdVOnPTD/3D3R4+aoOnN/Y/BzcdejZkrt4dVnhK78hgUbsovg4t9i254m8v7dMgw68WKkIeIV1xxBcaPH48xY8bgnnvu8SvQ6tGjh5lTaMiQIbjvvvuwzz77+Fy/vLzcXGwFrIkhIiIxjQHOtIWbMG9NHorKK5GRkoQDe7bBMYM6+2w18ntkXLuMenlDm/PLwbAjJR4ornQhvqoKp/z8qbnv5QOOxyPHXArGLVwv2ALJU+LrYEsaW6X4+jpnp5ruObY0MWjKdSTjqH06xlQ9p5AGTm+99Rbmz59vuur80a9fP7z00kumSy8/Px8PP/wwhg8fjsWLF2OPPfbw+pj7778fd955Z5C3XEREIjlouvvj37DojwKTn8OWEwYQizcW4Me1ebj9uL29Bk+BBCCdslNMMnhRhdPcdiUm4oLT78KJiz7HSwecAFS6kJQQZ9YLdoL37jwl761CDIS2FJT5zFPivmBXnt09uaWgzHTPDeqabYKmWCpFENLAaf369Zg0aRJmzJjhd4L3sGHDzMXGoGnAgAEmP+ruu+/2+phbbrkF1113XZ0Wp27dugXhFYiISKRh0PH05yvw45q82qAhKT4OlU6XaUXhct7/8Kn71QtG3AMQBluFZVWmyy05IR6ZqYkNBiCj+nRAHOIweOMSLO7az/ztAkc2Xj94AhKcLpP7xOCL6zUW9H26cDMW/pGP4soqOJISTQBz9KBOPgMYRxDylPi3ex+RocrhoQycfvrpJ2zdutV0t9mqq6vx5Zdf4qmnnjLdawkJCQ3+jaSkJOy///5YsWKFz3VSUlLMRUREZN3OYny1fLsJfLLTkmqDo5T4OBNA7SqtxNcrtpv1erbLqLPDHDUByMZdJaZLbWdJBaqcTjMyLjc92bQW+QpAFm3Ox3XfvIFL5kzB7WMvw5QDxoPPzO47dtFxMxh4LdpS4HMaGAZNj81cjmVbClHtlo+0ekcxlmwpxDVj+noNnuw8JeZhsUvRvbXMzlNi8NVYnhL3VbcYKTkQlsnho0ePxsKFC/Hzzz/XXoYOHWoSxfnvxoImO9Di3+jcuXOrbLOIiEQ2K6epygQpni1KvJ2enGBakrieJwYWTATnfVsKSk05gTbpyeaat7mc99cLQFwutLvnDhM0UUZVmUkQZysTrzmvcNecVKQmxpsJh321lE35bh1+Wb8L1dUupCRY5Qx4zdtc/ub367wmeNt5SsxHYp5SYVmlCfh4zduxmKcUkS1OmZmZGDhwYJ1lDocDbdu2rV0+ceJEdO3a1eQp0V133YVDDjkEffr0wa5du/DQQw9h7dq1uOiii0LyGkREJLKUVTKnCUjwUcomPi7O3M/1vHLtviqvcqKy2gWny2UvNq1Iddd3Addei94vP21uPjL+Mvx78HjASnWqfUxltRNJCQlo60j2+rTr80rw3eqdpqWpzFltWsb4vNxeBlx8/m9X7TTr9Whbf1475SlF0ai6hqxbtw7x8bsbxfLy8nDxxRdj8+bNpnTBAQccgLlz52LvvfcO6XaKiEhk6NsxA8mJ8SitrEZiQnydGU3sgIn3cz1PTMhmwNKvUwaWbi7C9qJSE8hwaH9OWpJZnldSuTs53Onk0HHg2WfN4x/907V4su9oEzTxzGZ31VU6gS0FFejdPh1Dunkvy7N6ezG2F5WhqtplutcSEuKRyCAPMLlL7H7j/VzPW+BEylOKwsDpiy++aPD2o48+ai4iIhIdqqqcmL8+z3RRsbWFgUMi+65ayNDuuaaUwG+bCkzAkZKUYFqfql0ulFdWo8rpwj5dMs16npj0vb2o3GwrE8I7ZKaAbU1M+mbQtSm/HBVVLis5nAsuvhh46SUzr0rVcy9gypbucBVZXXHeKkaxi9BXLSkGS0zitluZSiurav/N0XhOlxNV1dyOhmtRKU8pygInERGJHbN+34JXvlmDNTuKa7qq4tGzrQPnjeiJ0QNaprgxg7LLj+yDO//7G3YWl8NVUW1anRhvMHjqkJmKy47o4zV4S0tKwPaiCuwqqTCtRWVVzjrdZWzF4t/heuaP9urFSAV47TV8OugIFL79KxLjrLwm9/CGf4vpRQWlVfhsyWYcN7hr/edOTqhpEXPWzfWFC3avIp+X64UjZxNLKIQzBU4iIhKSoOn+aUtMgjJbmuyiisu2Fprl1FLBk/13X/56talLZAdtrIB93ohePp+Xp3nWfSooqzQj8JJNaxUrgbtM6xVLGvB11IYDt90GTJgADByIjV+uNM+TEAekJiWYx9iT/LLFq6Kq2ty/cVeZ1+fOSOVoOGsEHoMuxnWmpQsuVDl3B19cLxqmqAln4beHRUQkqrF7ji1NDJq6t2HLg9W6k5kaD0dyAtblleLVuWswsm/7RrvtmtuSweDosD3bmRYelhZgKYGj+ndCcgMtNhyNxxFsdm4S85ucJnSxbidXVWDitCkoPqEvYOcZ1Qx2SmFTU02hTAZAzE9yZ0oEuFy163kqZjcek9rjrdYxXtjaZQVeVgDG+7leOFnRzDnywpkCJxERaVXMaWL3HFua3AcAEW9zOZOcuZ6vmkaBtmR4e+za7aUNPtYETi6XKTmQX1KJ/PLK2hyn7PgqPPnuvRi29AfsuugP4IuZVjRTY/8ebUzSeUWVE4lOV53gjsEfc6tSEuPNet4UV1SbLkGWH+BjK2qSxBlwJTPHyWn9m+uFC2cAU9SEMwVOIiJhJJpyQXxhcjW7pXzl43A5T7a+ahoF2pJhP3ZHUQWyUhORlZpk9jurcTf0WHaDcQTdtsIKVFUzu8hq+UmtKsXj79yDYWt+RllSCvIvuwo5Hi1KbdJSsFfHTPy+qQCllU4kJlhddAzEqqphRvj17Zhp1vOGQVNacrxJAOdcraw3Zff1uZxOJCUlIDEhzqwXLv5wm6KGCkor61Rab2iKmnCmwElEJExEWy6IL2xRYk4Rc5rYPeeJy3m/r5pGgbRk2I9dt7PEdBmy5cuu/t0mLckErL4e60hOtOooVVabBG9KryjFC+/ehWHrFqI4KRU3n38fbhg7tt42MwA+au9OKCqrxIa8UpSbP2D9kZSEOOzRJhXj9unks3p3r3YOtMtINSUHSqs5gX1VbY4UW6rY6sT7uV64BObFNVPUlFXGY8mmwnqV1nu2Szc5Y77myAtXCpxERMJANOaC+MKSAxw9x0Rw5jSxiCRbXhJqhtazpalfx0yfNY0CmWyXyxasz8O2QqsmEluRkhISTQvYtqJy06I0f12e18e6nC7TamIHTZnlxXh56j8w9I/fUZichvNOvRMrOu+N631U7+7fORNx8fHITk8ygaGV2h1nnpvL+3XK9BnEdGuTjv4dMzB9R7G57Uhm6xfzrGBacYrLq3FYnwyzXkPH2LRfN5kK54UVlchMTsKBPdvgmMGd/Tq2mhp0OZITTdck96fnvt5aWIYdxeVmH3O9SBJZWysiEoWiNRfEFyZ8s+QASwL8vrnQBExxcczZsbqu2jpScO7wnj4Tw90n2/Wmocl2mZC+bkcJqp1OtM1Iqd3XnGMu2RGPHUXlWL+zxKznaeX2IpS45RA99t+HTdCUn+LAxNPuwi9d+iGpotqs17N9Rr33mK0uDOraOZJMd18lu9ji402CfGJiApZuLsSR/Tr4fI9zHMmmi4sVy8kEcHaLUyIDMu8tdHbQdPfHv2HRHwWmlcdurVq8qQA/rsvD7cft3WDw1JzJhTtnpaK80mmKgroPAuC+TkqPM4MAOlY5zXqRJGRz1YmIiO9cEBZa5DW5t6BEix5t09GrXbo56TOAKKtymWveZhcO7/fFUTPZLlvkvGFXn6/JdpngzXpLLHzprbWKyxkccT1PK7YWm646+1EPHT4RK3O74qwz7jVBE5fzfq7n6z1un5Fsnoevla0xvGYEw+UNvcemanlJJYbv2Rb9OmYgMyXR7Cte8zaX835vj2fQ9vTsFfhxTZ7pZmQ5BOZ28Zq3ufyZz1f4LL5pTy780a8bsWJbETbtKjPXvM3lvN+bTQVlSEmKN1XVGTwxYONIQF7zdk56sgn4uF4kUYuTiEiI7c4FScDvm/KQx1yQaiYQW5PItkYuSGvmvtgtbIwZ+rR3WBW3a5KGO2enmOUNtbBx25j7xW5Mtsi5B0AcabYpv8y0hnjLF2J3EVuk2BKSkeKq91guZ+K1t3pIDAK4jqvmMUs69MJRFz6N6ngryd3ltp6vquMbd5WalkUGWPyvtCIORWVV2FpYbrbX13tsHyMMQrjNSVYhJ9Plx8CLQVB+aaXXx6/dWYyvVuww5QqyUuLNiDwGbWzpy0iOR0G509zP9Xq1y/A5uTCDnMxUdjOye9FlWuXsyYX/Nn7veu8Vt4WPOaBHrhklyeOaASlznDpkpZrgmD8OlOMkIiJN4qjJBflprTWJawZPTqnMBXGZXJydLZwL0tpJ6XaeEfNc+HpzM1JqT8Y7iiuREF/lM8+IeILmtjH3i92YbJGzC2gyaMp1JOOofTp6DboyU5LQPTfddMcxgLHybuJN3g0DGHYPdmuTZtbz1LloJz547TrcM+pCzOtm1WeygyYbgycmPntKT0owr4eBkzUtil0NyrpmK5i9njcOt3yhyiqnKb7JYIktOFsLeIxU+DxG2KJUVF5puua2FrGEwm589rSkeBMEcT3PwMmeXJij9ZisH1fbtRmHZEcythSU+5xcmNvCYyk1Kd7kUnFKGfdRdQyiGKh62+Zwpq46EZEQs3NBOIFsm/Qk0wVjavYkssUpySyvaKFcEDspna03rE/EVh5e8zaX++qGCURheaU1qq3aZYIc99fL21xu8ozK6+cZ2RjQMWF+YJds00W1ZnuxuWZLU0OJ9GzV2b9bGzO1SvvMFDOFCVtCeM3bHTJSMKR7m/qtVevX49CLT8W+m5fj3ulPI95Z7fOkmppc/9TKAIfBDd9Hzy4x3ubyvOIKs15Dx8i2wnLTvbZ5V5nZR7zmbbZm+TpGeD+DrZIKluusy0wSXOk093M9T2wp2lVaYY4Jb12b2axpVVph1vPVMshglrLSktAuI8VcE5ezWruvkYThKrLCPBGRKGTngjBIYu6HZysIu2fsXJCG6t00dcLcYCWlN7Wbj6/JKkVgnYI4ua49qo6vk/uCrRNcryEMjnofkdGk53ZvrWIi+B5t0sxIOrZ88TmZMF6vtWr1amDUKDjWrcH67I644NQ74PRoaSI+grWU8kvqbzcDC75OrsTp5lh7yWLlTDFvmvdzvZ4erT7E955D+TmJcEFZhVXDyd6fFZwrj6MTnV6PEeaSVTU896+5n+t5E2emefH1B1w+/2YgLYPhTIGTiEiI2bkgbOlYva0YWwrLa+vddMxKMbV5fOWvBDJhbiDD+uuMtlpkjbZisnZ6cs1oq4G+R1sxKOOEtIWllSbHhQUh7cly2W3ELUlPSTTrtQS7tcoeJVZSWYX0pEQM3iMb4zy3e8UKEzSxxamkey+cf9Jd2JGRi2QXTNeijV2NnPokMSEBbTPqd9VxcmAmgjNe8tbqw+UVcU6znjdsfWOwweOCQV7tAzndCotoOp3mfm+tdGyN8oe39Xq3c5hWpYKSSqRm1U2oZ5cjK6gzsOd6De1ruyuYox2ZuM9jhEFTJJbYUOAkIhJijppcENNVwhMhF3K4eM39XO5rlFggE+YGMqzffbTV0k0FKK/eHfys2lqEJZsLcc2Yvl5PjGzRYnDx+6YyE3zweVLZwuZ0mRY3ttrskZtu1mvJ3CzGHcwtYg0kTptSb1DZkiVW0LRpE9C/P/Km/heuTzdw2CPinS4kxtuVmFix25pll4FuH49SBJTjYPFM699sqzJT09kZTpx3zozIs9bzhkHm9sLymqDYqhBuZ0lxv3M57+d69fdT/W407/uz/np7tEnHIb3bYsZvW0wLXWaaVYOKz8fn4j47uHdbs14wWwbDmQInEZEQ40mEv9pn/L7FGrlkTk5WsjRHW7HS9FF7d/SaCxLIhLkOt2H93oKUhob1m9FW36/Dj2t21tYVsjErqnDNTnP/bV5GWzEPh61pCfHcxjhTioB/g60ZOWmJ5jZPzg3ldAU65QoDvmWbC00XIcMPtuht/mUjlm5xC/gmT7aCJk7UO3MmOrfvgMGLC7FxkdXyw+CFF/4JzjWXFBePwXvkeA0iSiucJtAxAZKPHq74mvW8YSI1E6v5XKz95N5AyPpXnAKG93sro5CZlmgCO/P8ptttt5p4zyzjevW2KT4OZx3c3RyH3F+FpvvUCvn4/u3bJdPc31gQxPsjaVqVhig5XEQkHNjnnZoTec2N2lwWVxAmzG0oedca6YV6w/p9Je9uyCvBnKVba0/UTOxmNxuvicu/XLrVrOcrp6t9ZjJSkxNNK03nnDRzzdvtMhqu7+OZm8Wgj3lKvOZtLmdulre6RHbAx2H0DH64valJVk0k3uZy3m8e+9RTwHXXAZ9/DnS0WuzapCUjOy3JzG/HoJMjxHjN21zOPDVvrKroDZ9yeT/X82ZnsTUqjq1cldUsXVFtAluT+F1dbZbzfq7naWy/jub1sWfRDpTsi6k95bLeP67nDYNIBpMn7NfFHA9dctLN9Yn7dfXZqhjN1OIkIhJidnFDDtnenF9u5vQqLq8yv+g7ZqehU1ZKbXFDz1/tgUyYG0jyLgsgcoQX7zN5STUnfOb58DZbcthKwfW6ewxTd8/pWrO9xLze6upq6/VmpaJn2/QGc7rcc7MY4HGIf0lltRnKz2UN5WYxkPtu1Q6rjhJzdEqr6uRXddqxEd+vTDDrme1mq5P7+1TKIpS5Zv9sLSivrf7dgcFfdqrpavT2vFbeUyMZ2rXreV+ekhBvXmedBr6aP5kY70J6ovf8Kr6OLtmpWLm9xLR4eduMrjmp9d4ndwyOLj3c0aTBB9FKgZOISIjZuUYcvcZuHs96NwxCONzeWyAR6IS5TUqUdrPDJDu74Ei0AjYW7LRzdtj6w2CipKrKrOfJUVvfJwFDfdT3YXkArtfQ/tpSUI1f1+8ywYo9Ko8tPoO75dSu52nV9mKTBG1trzWKLyHOCvT6rPgVT71xGz4echRWHf2s14DPfp/YCsfgyT1gY1Di631q50jendTtA6eB4XreMG+Kj/boFa3F5a44az1PbLljwck/8lm6oO4f4PvF1qb2makNjtr0Ngjgh647GxwEEKoCqy1NgZOISIg5PHKN7Do3ttLyKp+5Rp4T5rp31zmdzkYnzK3Fc5h9HqvJeWkIWzaYp1RaUYXyqjiT42PPf8ZuI54oeb+3FhD3yt97tmOgWFkbgDiS4xus/G3vL9Y8WrSxwDy/vbHspNpUUI28ZdsxqGuW1/1lVeuuNi1MjhSOErOWD139Kx56/W9IryjDnhtXoqSifjeh/T5t3FViWrk27iqrDfi65KSiS06az/dpwfr8Rvbo7vX6dMyqtzw3NckksTekuKzarOeJ+5cBbHvWyHI6TSubHWgyp4wtfWyV9DY/n6+cMCDOjABtaBBAIPPchTMFTiIiIRbIFCL2hLkcPcdEcPdRdQyamHvT0IS57knW/PtsSWAAt3hjgXleX0nWbNlgQjtbKeJqRpgxhYeNKmVVVhJzl4wkry0gdhfhD2t24M15G2omnbWmP2HgMbBrVoP1fTpmpGDtjuKaRGUPLiu/at2OYrOeJ5ZBYNDE7jk+J0eyDV3xEyb/3x1IrSzHt732xzVn3oHHMxw+k/g5Rxu7Ulk00m5l21bEbslinLhvF6/vU2kluwStxGJvjUZmuctaz5sX5q70+jh3zpr1rh07wOv8fGxdc1a6kJxoVRw3I/Nqamf5mp/PPSeMM8mkJCfW7r/yiqranDBvgwDqBF1bCuu0uK3eUYwl7on4EST2OidFRMKMHUgwp4i5Rvzlz5YBXvN2Y4UCWWrglmP6o2/7DNMSw+4iXu/VIQM3H9PfZx2nQJKsu2SnmbweBkvxbMdxWcPpec3bXN4+K8Ws583aHSVYvb3EdH1ZCcvW8Hre5nLe78v8DXlm2xrCoJHreWIgycll+ZKYrzR44Td45PXbTdA0p8+BuPyMfyAtJ8us5w0rnucVW7WnmFRtX3iby9fu9L7dfE57VJ03XB5Xs543yzb7V1LA23osqMpjZ1tRBYorqk25B06Zwmve5nK+797m59udE+Y0c9xtLbDm2+M1b3P596t2eB0E4D7PHYMmHlc8lnnN2/Y8d74mFw5XCpxERIKIJwFOhbFkc4G59vek0NwpRGycMPXAnrkmR4XTifB6aI9cs9wX9yRrYjFK5v/wmtyTrD2xpamNIxmds9PgSEkyJ2EGS7zmbS7nBMXeRsbZJRTYapNtususGkpmCo+UBLOcJRS4njfctyxZ0JDyKpdZzxNP2uxWY5By2G9z8a+p9yCluhIz+h6CS068FZWJfE2pXsszsBWLc8VZ3VV1xj4aXD5/bZ5ZzxMT3mu7Qn2Jq1nPizYZ/nUQeVvPkZxoWgSZ18WWJ7bUFZZZ17zN5QycuJ7XnDBO81LlNEFWUoKVRM9r3uZytrZxPU/u89zlcrShy2XVKnO5zG0ut+e5iyTqqhORFhVIUmioEkqb+7yBFmRsbqFAbzkoO4qd+N/CTVi+rchnd4id7FxWGY/fNxaYiuX2KLGOmSno1d5hutG8JTvbI+MGdsnCLxvyUVZcbloRGDw5UhKxTxcrT8fbYzkya/nWQjOMvrjcVTs/G8+pnG+NJ2V27XC9g3q1rfd4jjz0/PVvd5mRs+a2+3qeNaQYqCVXVyLB5cTH/Q7FNcffAGdiIuJZJ8lHDal5a3eaYLYhvJ/r9fTooixiXlEjfW28n+t5c/SALpjy/R8N/4Ga9TxZBVWtBDTuL3ZR2vloplu4pvq4t6OM7w2Dqzi2SCXvrhxuj54sqqg2Aa63Ofbsee4yUxKxKb/c/J3dIxgTkJ6SUDvPnecEweFMgZOItJhAAolAg5DW3uZACjIGUigwkBwUR3KiCVS+XbXDTJ3hfurbVVJhWotYr4frebIfyxYpthBZBS2tKtq8zRwpX49lGQOWG7BzhNwb5eLjXKiqZhDhMut5k8oX6h4wxXmUwfKyno2vaWthmXlvP+5/GLY62mB+1wGojk8wj7VG65V5HWHG7ih/8oy8dVst2JDXaMK9q2a94X3b17svN4u1reLMXHW+sPuN63kqqmAyOEc7MtCMQzzn2auJnDiAgNvMP8v1PKXXBEuumjepqprp9db7zL/H5byf63nD1qxthWX1RjAyoC6pYJX4yOv4UuAkIi0i0MrOwQhCmrvNZmqJ1EST58IcjoV/7GrweYM1WW5zuOegsIJ0fkF5nbpE/Ledg+I5vJ6tKsyF2pxvzR/GQIObZxK8K50mgGAxSm+tL/Zjzdxj7L5JTjSjtKprAjYub+vjsVyHo9Hcpnpzu8+6dpn7vQcJzJuyt9Os4baa/U/e7y2/yvmfN1G+Jhmu9FwTbP3QbWDtffYUJuxizSstRzfUDZx8BXKevK3HFjR/+FqvpLzaHI++5rKzjzeu54mTJTMQZWI7A2TmztktThzJmJNu5Rx5m1SZz5mbnoytRWWmuKbLrX3Pnpy4Q0aK15ywnrnp5nmY/8UyEfbnIjEuDglJ8aaMRCbnVIywiuKRF+qJSNgLtLJzcx8bjG1et6PEtIYs/KPATCfCa97mcl/P25TJcoPNMweFz84BdLxuLAflj3yroCP3rzVQ32xx7cmRy01Bx/z6281Akq1SXCcuPh7V1Zwvrdpc8zaX5xdXmPU8pSXHm0ltG8L7uZ43B/XKNVW67RjUHiDvHjQxSOB6dTz3HHpcfhFefv1mZJcWWSd+t4upyFATNC5YWz+x3EvutFfe1mMw6Q9f63EIfzn7Mht6LGtfJdV/cgbvDKQZdHH0HFPHGKDymre328nhXiZV5ueuc06qeTwDWZed38URiTUlDXzlhLF7j6U1+Let57W6CHnN2/bnmutFEgVOIhJ0gQQSoQpC+PcWrM8z3ThbOcQ+DkhJsur88DaXMzHY2/Puniw30ZxQ3JOseZvlAXzlCgWaXG7noLDbrKKyCoXllaZOD695m8vLKqzcEk/MLeFjmUeVkZJkumGsZGEXMkwSdZpJ5uV6nhiIMcBgixSDpYKySuwqqTLXvM3WptIqp9eAbXthhV/dVlzPm+65DhzZr72pn+R5yuVtLj+iX3uzXq0nngAuvdT88/PeQ7ErxWG6qLxd+NyehSJpxRb/kpi9redIbnjC4sbW435liYmGsKYV16v3N1MSzfHH1+TZ08fbXM73mev5yglji2T7jGRzjPPfvOZtljbwlRNmH1udsqw8PQZ2bDnmNW93yk4193O9lhhw0VLUVSciQbc7kEgzX3KbCkrNlz4DiM5ZaeaaXTm+ko7tx3rT0GMDwUCDQ81Ly6tN28suj6k4mFvCL22u58nhVhiRSbB5JRUmt4P5GxxZ1jk7xWdhxEDzq5hbYnWH1D/5WHuo2krE9ZGDwhYWzhvHFhwGWXYrAvNRuA3FDfROMZG8tNRlumvYsmB3dfG1F5ZWmRF23qzd7l8A4ms9nnTHD+6Cmb9vNS1q7vj83HbeX9st+tBDwE03mX8uPPsvuKvr8VY/lQ8uH/lRhX4ec97Wy0j1vv/9XW/NzqJ6QY8n3s/1hqFdneXVVSx6WTeHzR2X836u52teQQbInNonPSkRrjgX4lxxYIZaZlpC7byCnjlhDjPvYIp5rK8pahjqcr1wy3VsiAInEQk6R00gsXRzgakszFyY2ikxHMno3ynTNNFzvcaqaHtiAOZPENJUzO9gC1F5zcmD01BYSdZWlxfxS99bHohdGHHG71vMSYTbnZSaiErWvSksM/lFR+3d0Wcl7EDyujKTmTuyO8HavdfDfRnX89S7nQPZ6UkoKKlEalaCaWGzmXncSirN6+J6nljmgDlVDNiyU+PN8H/7PU5NjEN+mROZCYleyyEUVzQ8Mq2x9RiMs/6Pt4KNxOVv/rAOR/brgPj77gVuv9264/bbUXXBJODZ7xp97sFdrWlb3CUn+Bf8eFvPSwOWV77WW7rZvxwpb+v9tD7PBMVkB7c2+zbv53q9O2Z6HT3JY+/XDbvMKDhr9CSrjiehf2dHTbdwVYOFXYf2aIOi8uraSusZKQmmYGhDFeJDlevYGHXViUjQ8YuQrTZfr9iBTfml5suSrTe85m0ut9fz9WXLX6h2PoVnFW2O1mooCGkOtsgw0OEJJJWjf8xs8xw5xECALU5O04Xlq+Wm7rAutwo/HjV/vAkkr6uwwmpJYHDEa/eijPZyZ816njgv3iG925p1mRDP7hwzGq+q2tzm0x3cu61ZzxMDpKzUBBMsbSmsRF5pJQrKqsw1b1e7nMhKSTDreeqS418ysK/11mwrwlfLt9UZjVdnf7qAr5Zvx84HJu8Omu65B7jrLqz1s4t3rZeRcft09m/IvLf1GKD6w9d6G/P8K4DpbT1+ZkydrJrb3q55P9fz5KgdPVloAqg9ctLQs126uU5KjMfKrUXmxwbXa6iwK4MkHgpMROc1bzdU2DVUuY7+UOAkEgNaO0eAf5+/fCuqmaxsBR/WlBy8FWeWL91S4HU7Aq2i3VxMVmX9IF7Y/eOeyMrbXM6uJ67niXlPrN9zYM826JjFvCCnSZzmdcfsNLOc9/vKywokr4stPj4Gn9Xy1ZXHfXjWwd2xb7ccM18ZCyLuLC4317zN5bzf277m3HLcVJ5UPZ/easGwhm1xPU+jBrT3pxakWc+bz37bgnJvQ/Lc8GT+yV7Dgb32srrq/vY3s3zVtiL4w9t6rjj/Tpne1hvQOduv18z1vOGINn94W6995u6pZ9h7ys8iBxCYz2Sc9/VszF1iThIHEbBoZWYaR4pa17zN5TwGvOU4BVLYNZQDLhqjrjqRKBeKHIEf1+3EH3mlSEmwWm4YfLC4H7//mDvCpv4NO0vNeof0rpuP4f5la2+3GfKemGC+bBk0tcR2c0QRh1QzQLKHUFe6nOZLmpPnmqHbyYleRx7ZeVksN8DWGQYedpcEyxqwVYYnDF95WQHldbmsBHHGEfFuNY1Mu1dNy5NJDPcRZ3BfskDm7pnvuR0JpquqoWMkOSEO63c2fNJikM71PO0qrgR7BRvKdeb9XM+bJVvqVwT3Zn5VKibOnw84drcAbdrlX0kBb+ux5pE/vK03pm8HE6w01GXH+7meNwxk/eFtPU4CbSqH88dAzbhJ612xR1JaFd+5nq8cJ5YT4AjLjNREkwzOfCd2W7O7zleOUyCFXUOV6+gPBU4iUSx09ZCs5vusNGuqBwZKdmVnO5AqKK0y63kLnAKpot1c7ALo3jbd5COxy84kO7Pwn+m6cprXwRODt7wrz7wsPtZdaXlVg3lZno9vSl5XalKCabnj6TLBBH27q0KbfV1tVebmer5wX1/exH29cEN+460+1S6zXu/2dY+x7cUVZqQWa095+xNWq0i8Wc/r3/UxEW6cy4k7ZzyHBV364f2Bo6z13IImciT6d/x4W29nScPz4zW03sLN+TUtJ773Ge/negd7+Uy091LY0htv6zHxv0NmiqnXZYJp91ynmoCb93M9T3aO05Dubczoyq1uCd4ds1LQs53DJJY3FsA0tbCrI0S5jv5QV51IlApljgC/8HiOYMDEkwFHl/FXKq9521purefPl23/TlnmuiWnW2GgsH+3NmifmWoK+nG3VJicH+uk0iEr1Zw8WiIvK5DHswvOzBOXwE5Ql9nPTGzntanFxC7GeCuJO5j7et6anQ3e39B69mtkgnBmSgKS2HUUB3PN21zuvp4nvkf1tt9ZjQenPYGJC/5nrrvmb/W6XrmfrUbe1mtsypSG1lu6pdAc975OuvF2F7ePApjt0ut3o/m7Hj/zA7pkoVNOqqk+7p7bxNudslMwoHNWgz8KzBxz9oOoJqeOy1sigHH/TLAFz73EB2+3VK6jP9TiJBKlmpIj0JRfgv7gCBp2aXF0E0/i7s/PkyG7g9iFxfXChZ1bxZa4HYXlaJORZIowsufDWQ20zUzxmVvl/ljmYXHfsiuBv4r5Bd9YXlYgj+fIv/SURCSyjhPnDHNaLUxczm4bthbYIwSDiV2RzV2vV26GqTTOukNs5UhMcNaO1GIiPlsw2C3K9fxJGk9wVuPh/z2Kk377AlVx8bhh/DX4I7uD1+Ryf/eDt/VyHP4FL97WK62wcsEYqPB1slXTfp/YPcxWWC7jet7kZnjPIfJnPftHActksMlpR3Fl7QjIto4kdMpJa/BHARO6Z/y2xXS7ZqYl1XbVsb7ZhrxSjG1kxGhz2J+J3zcXYPpvW8zxYeP+26tjZovkOvq1ba3+jCLSKtyLMnrTlKKMTcWpPQ7t2858qTERlF1d1mgtJk1XmuWH9mlfbwqQUCfEs8tqVP8OpvzAwg0F+Hn9LnPN21zeULdmc5NgA318r3YOtM9INflUzJHhCZEvlde8zeXtMlLNesG0f/ecZq+XlZ6EvTpmmFYLTizM18m8MF7zNpf37Zhh1vNmzw6O2pNXYnUVHv/oIRM0VcYn4KoTbsJHex9h7ud6njJT/evy8rbeEV7mkPPG23rcFrb8MThisjU/D2xQM58LFqasdpkWN2/bTAf2yjUBVkMY2HA9T/y89e+ciW2FFdhVVmX+DgNUXvM2C43265TpOwixPzqewWScdbvFQ5ea57dr2jdaPbWFqcVJJEo53HIE2PrjmbDckjkC/AK+4sg+ZoTPoj/yTXN+STkLJXIy0EQM7JqNy4/cs9Ffiwx2mpPjFMhEvbOXbIUjJQGH9M41LTbMw+G+43LWJGoseOp5uAPz1+dhR3EF2jqSMaRbGyQygvFDc/K6urVh91oGVm8vMpPmmrIENQnibL2oclbhsL4ZZr1g7uthvdohPSkeJQ1kO/N+rufJVJPOTsX8dXUn5SWTg+MEOmen+WzFYJcSBxlUlZbjqY8exFHLv0N5QiKuOPEWzOx7sFmH93vrehrSMwfxX1olGnyJr1nPU//OWWjnSML2Bka48X6u56lvh0zTcriloNwqE1FTHoBBLreF/2aNM67nzYE9ctG9TRpWNlA8tHtumlnP23v7zfLtpuuZn393fF7+gJq7YrtV98rjPTcjRkutEaN2cdeimkmdO2alolNWijUtT5Bbru1UA7Y0jduno9caUC01/2NjFDiJRCk7R4ATwHI4P7/cdlezTjJffMP2bNtiOQIMAm4/bgCmLdxs8lz4ZcsA7sCeuThmUKdGW2ACCX6akxDvmRNmf1GnJSWhU1aqX1/U3rZ53uq8Jo1gbGoSrTvTJRpXU9PJrW5PY5qzrzl6kInBv28q9NoAwOfuWTPK0Nu+5tx/3E7WgmIhzdqJY+NY78uFdTuLraR3L/uaox9z0pNx6PzpNUFTEv7yp9swp/cB5n42zPB+bxPP9uuYZYbRby/xHfzwfq7n7TWfsF9XTP1xgzmePQtJ8vjm/d5ec9eaQJB5OqxF6Rm4MZ7Zo02aWc8b7ode7R1Ys6PEZ0I93w9v+2s9J4JevdP8UOrWJs20etlddWx12lpYgW9X7TTr9fBoBQ50xGgwUg3i4+ORlVY34GvJVIPGKHASiVJ28/z7P/9haiCx9YPF9djSxPnD+Gu8web5IOBJ94ojmz4yLljBj51bxdfKkxrzh3wFP/YXNadX+WntLjMyigEnA0zODs8E2oa+qEM1gpGjAFmd3cw+b050ztrcGUdyvDm5s6YW1/PWNdrc7ebwc85lZyftsm6TPXIyJTEObTNS0CUn1eswdbbIbS0sRztHssln4onZHgnIoI2tNmyZ4XoH9Wpb77k5pxoDjXcGjkHv7evxVa8h+KbnfrX3828xD8bb3GsMTJjov6PE+xQk3P6OnEPNSwBj173iti/ZlG/m5mOuD3N+ctIT0b9zts+6V9wPzDfj3G7VFZzWx+3v1lQb59/xNayfQc3GXeWm1aqssgolNTlTfKb05HikJiWa+70FPxwNt6u0Au0zUkwQkuLRAMrvBRY85Xqej3UEOGK0uVSOQERaHYOIJZsKzcmwvSPZquxcWmm6nziFBlueeEL11jwfTE1tQQlG8NOchHh+UTMA2FFcbnJOrHo1nDbFaaZNyS9j11uK11/WgWxzoBgEc2qUdpkp5gTnbb65HUUVZj3PwMl9u/u0d5hWNnbFsDWBtxtqZbOHqR++VwdTLJJBFp+byxh09GzvMMebt/3FbkwmhjNS4omcAZ7d4sT/c3JgK4nZy/D/oiKgpAzF5dXm8f888oLaAAJu18VsEfKS18btLCyvsiqqe4mcuJwV0Lmet0CzuXWvOMfhxppRk/Zz29vNw4VhJwcCeJsL0T34YeBUVMaRcdW173NmagIcqUlmOhRvwY/ZL+b5Gpqtzjv3aVN4LMd5DPTgNjc0bUpzOcK4HIFanESilB1E8ETuLceJXQ2haupuSKDBT3OL5qUnJZjAqaS8yrRI2M/NL+dkR7x5HM8vXC+Y2xyMvC4rp8maIsZ9vrmaLfD5uEBa2ewTG3OJDuqV6/X4YgDK9TyxdYzdRXwuhkpmehi79lQcUFltlVDgenXk5wPHHANHUjqcI65GXJz1Wk1HX83jbRyIsGpHMXq2rzsyj6+XVd253WyV8xzdxn/nl1SY9XwNXmhO3SsGkWzVYRI4XxvXtTso+Z5zuT3c3hd2tW8rLDPlK9NqprNh8MQ8s9LKMvNjyBvPOQk9g5+G5iQMdMRoc4UqYPOHAieRKOUeRPBLx7OJPZSVdxsSSPDjCOBXqvWb26qpzC9m95YbazRTzX1B3uZAc404Wi4nLdmMSOuYFe/1pJidlux1VF0grWzuJzYG5+7HV2Mntk6ZqaYrzSQZm9GAceAsJQx+Kk0QUW3KFHC9Wnl5wLhxwLx5yMrMQucBG1HStrt5j/im1L5sE3xxeL/TtLR52l7E4NCac5DHglWcle+sVSaAidJsReJ6wVRSVm2Vi3C5THBrbTbrOsUhITHOHJu8n+t50zM3vbaiPQNKJtBXsbI9g6ikeJPDmJkQb9bzNSchSwoweHMvKVDIukgNzEkYqkr+8SEK2PyhwEkkSjnCuKm7IY4Attv9ZM5pUjxH4jR0MmeByHYZydaEptuKUGXOX1ZnCut0MmeH93srJBnINgeaa8TRcof0ysWM37eYri229tSeFMuqzIl6WO9cr6PqAmllC+TExvnrWMm8oKzSjFqMj4s3wY6ZOoatUHFWsFk7z9327cDYscDPPwNt22LBc29i1XzrhJ/KoJYV3u22NQ7vrwa4xW0c9d+LthnJVlkApwspcJnioXarHAM+LmdZAK4XzACXrXl8Xdwd5hjyyCznct7vqzp5XLz144ddlAwId1chtwJ9dsHz2ON6DeVmLdtcaI4L+7FmTsIumT5zs0JVyT9UAZs/wusbU0Rioqm7pbY7kKJ5juREk5/DYIW/6s1ja87GCc44lJRXm/u5XjC3OdAcKXNSPKQ7thaVY+nmAvM3uOlcjYUvOVHvmT5Oiu6tbN75bmUL5MTGlia+H12yU01LmZkXsMqaF5AtQew24vNyPWzZAowZAyxaBHToAMyaBaR3QuIvP8LJyZjNlCHWFppur5rRhAweM70kh/N96pCZaupF8Xn5njJ2YnehVUAU6JiZatYLZoDbNpMBWzzKq720KNUcaryf63nDYIstTdsKOeUJyxnY74rLjNBLSbC6Nn1ViG9ublawRnw2VygCtsYocAqiqipns+u3iMRSU3erbLdb0TwTGDRSNI+zu+cVV5jkaBYH5EmMQ+M5VN4q51BhcmO8zQIf6Da750gR81zc84Uay5HiyeWk/bvi5a+t3Bz7sT1y081yXydFu5XNtHQUV9SbwJW3+V3W0HQtzTmx8e/a+4f/Rlx1beVwtgzy/TIB1K5twLEnAUuWAJ07A7NnA/37I3NjPtqbuddKTY6Sey0ovhZ2rTJZ3lvrH1veRu7VHp8s2mTyoBgs1T62ZhqYI/q199pCF0iA26utw0rW5xQ53nKc2AKWGG/W84atfgx2uH1ZqYmm5cnuSmbdMbbWcX96ax0MJDcrHMSHIGBriAKnIJn1+xa88s0arNlRXDs8lTNNnzeiJ0YP6BispxGJiqZuf7e7qb+OAyma90e+VeiPJzXiHG8JcfHm5MRzK0/qptBffqnXUUuB7Gs7R6qsMt6MhPRM0u7ZLr3BKu924c6M1CQc1re9eW3cFwWNFO50JCeiXU0XpGdxww41xQ0ZTnC9YJ7YMlOSTED2W0GBSYpmEMXuMXaT5Zcy7ynO1DTK3rEN2LAB6NbNCpr69LEen5pkgkkrX6nKtBjZXXUMgxITEsz93gInzxY6q6r97ha6fp2yfLbQBTIIgPfzveTzsRWSgY690XyuFFNfjUGs9yDGbh1MSkhA+4wkU3bCPkY4KnFbUWWDrYMSPAqcghQ03T9tSW2tHPuX1LKthWY5KXiSUAnHpm6/8SxgD6M2I69cLVY0j8O42bLC2kQcys5pVna3giQhPSXBLPc13DuQfc312PIxf12eCSQ8k7SZvM3t5XoNtYJwGhP3E28nl6vBVhD3LsahPXK8Bpr+dOc2dSQgW+14wmeQmsFcpgqr5YetJzlpiSirsn58tj1iBDB9OtClC9CzZ73HM9DJSk2p7Vrle8Vq5WVV1mTH3loH3butPvl1E75esd3k/LBl79A+7XDs4M4+g9xABgHw2OrahgM1rHIM7t3I3A9sleSx56t1zz0Hb9UOTiHEpVbkxfkU+XhfOXiBFpWVuhQ4BaF7ji1NDJpYDp9f1pSZyl8BCViXV4pX567ByL7t1W0nIRNuTd2Ncc8j4cmG07Qwj2TxpgJTINBXHkmgo9tY66a2T293CsnuCK6F9jVP8BzVxhYt9+8RtlglpceZ75GOVU6vgUAgrSDuXYwMkrguJ3TlDz/e9qdbtDknY76HKTVTonDov1UJ2ypL0G7TOnSIq4Sr+xCrGOTw4T4f3z4z2XTV5aRbowkZWLNFJyPVqmHlq5gkrd1Rgh9W7zTzGDJY3FUSb27v0zXb53Y7AhgE4N66t3FXmUnUrnQ6kWSmLkmp6ab13brH5XxNbGXaPYqw5n1xsVSBy2cOXigLtEYjBU4BYk4Tu+fY0mR/2dl4m8v5C9VXBVwRCV4eiSOAExtr2KQmJ+CPXWWm2yg5aXedHLY0sRuPc3N5q3UTKDsQYFI0gyfPXCNOH+IrEAg0WAyki7G5J2NuC1tOrDIEcUgwgVMcem1bh+de/StSqirxwF+fQXFFP6/PaxffHNK9DdZsLzFdm9XV1WaEGN+jnm3TTUVyX6/ZVy/B8m1FDfYSBDIIwP2xnPetqa17dnDNFqXe7dJN97Gd48RU2vW7ysw+9RZch7JAazRS4BQgNrnyy40fPG+4nAer1wq4IhLUFpRATmxdstNM4LJxV2ltnlPtY8GJZ11m1BLXCzY7EDigR675oeWZa8QcJV9VuB1BKIXQnMmJAzkZ22UQWNCxT/sMc8Lf448VuOfVm5BTmIdVnXphbYLDZ6Kz/ZpZ0mBozzZei2+W+Si+GUgvQSCDADwfy+00tayq+NhSU+6iodY9O7jmMbir1Erc5z7g+Ye3eez6Cq6DWaBVFDgFjF8w/GXIDw4/eJ643PTVO3zXBBGR4LSgBHJi4wmHs9NzQt/8skrz6353DkmcWc6Wn4a6f5pb+du9CjdbI5pShTsYZSfYcvTpQisRv7iyCo6kRPzQdSeObmAy5kBOxp5lEPptWoG/PXkNsorzsarbXrjm/AdRldnWZ+doIMU3A+0laO7ABfuxo/p3MIHb4o0FuwcStXPg1P4dGh1A4NnKxpbQhJrguqFWtnCe9y0SqcUpQPxVxtFzTATnrxX3D6KTlWuLK9CvY6ZZT0Qa5wiwBaW5XU/2iWnYnu2wensRthbszkHpkJViTm6+Wn0CTb4NJBAItBQCt/mxmcuxbEthnYTl1TuKsWRLoUmiDnY+mXsZhPa//4LbX7gJGaVFWNZjAG668EFUZ+eYCYB9JToH8pqD1kvQxIEL7qMfOfnwsN5t/R79SI4AWtkitRhuuNJeCnQHJsabkgPsF2cTr3t/OT94WalJOHd4TyWGi/gpGC0ozRndVrfVp2lzrwWafBto8NPcYJEn7SnfrcMv63eZoJEnVdZAYsI1u7K4/M3v1+Fv4/cOaj6ZnSg9ePtqXP78DUgvK8Ginvvg75c8hPS2bfwqg9Dc1xxoL0FzBy4EMvox0OA6UovhhisFTkFgJxHadZz4weAHjy1NDJpUikCk9QtgNnV0WyAnpmAk3wZac6s5weL6vBJ8t3qnmeCWgcLuKVfikOxIxpaCcny7aqdZz7MEQzASpZcWdcP2vQaa1vl3b3kK+2ZkNKkMQnNecyC9BO7vc5/2DpPgzXw0Bte83WCdsADzjIKZXxUpxXDDlQKnIGFwxGRCVQ4XCVykTSoarOTbQGtuNTVYZC7PrtIKtM9I8brd2elJZlJYb7WrgnUif+Sqh9EhJw3pmRlNKoPQ3NccSC+B/T5zUt2f1u6qV6i0U3aKz/c5GHlGgXwuIrUYbjhS4BTMnZkYr5IDIkESSZOKBjP5trVrbsXZeTpeuYK/vz75BJg3D33uuKPOY8u3F7faiby5vQR8/zgakAVJ2W3rWag0v4wjElNabPRjoJ+LiC6GG0YUOIlI2IqUSUUjNfmWNanYqlRQUonUrIR63W35JZVmmHtDtauatL8++AA47TSgshIYMAB9TjutyWUQQtlLYJdRKCmvMiPZdndtJiDZEW8CR8aa3sooBDPPKJDPRaQVww1H4fUpFhEJA4HkR0VS8u0ebdJxSO+2mPHbFtMll5mWVFt4s7C00szhdnDvtma9gPfX228DZ50FVFdbwdNJJ3kdhThvdV6rTQHS1F4CzzIK9Vn3eWunU55R9FDgJCISoEg9KZoJbw/ubqb/WLa50IwktGtXsT7Qvl0yzf0Bb/cbbwDnnsvsauDPfwZeegkrdpZG3BQg7mUUuN2eFd55u20DZRSUZxQdFDiJiARBpJ4U7Qlvm1PQ0S8vvQRcdBGb3oALLgCefx7OuPiInALE4Tbf3Kb88noV3v0to6A8o8imwElEJEiCcVJsTuXxYGz35S2RNLx0KXDxxVbQdNllwFNPsZkLf+wsCYspQJq6r927ZIf2yGnyfHM25RlFNgVOIiJBFMhJsbmVx4OhRU7m/fpZwdKyZcAjjzAqCpspQMw0M7WtbFWmkCWDnqMH+p5mxr1LlkESA7yc9KRmlVGQyNXyQxf89MADD5hfGtdcc02D602dOhX9+/dHamoqBg0ahE84tFVEJMLZFanZmsGTMbupeM3bXM77I0Zp6e5/s6Xp0UdrgyZyuI1C9PrwJoxCZKvR+p0lWLK5wFzzdmPsaWY++nmjadnixM685m0ub2hf212yA7tkY1dJJdawFlZJpQm6wjEvS6K0xWnevHl47rnnMHjw4AbXmzt3Ls4880zcf//9OO644zBlyhRMmDAB8+fPx8CBA1tte0VEgikYlcfDxt138xcu8PnnQNu2jXZ5sXq3Z5eXv6MQm9NCZ6aZ+b5mmpmEuHojCbmc99/mZZoZm/KUYlvIW5yKiopw9tln44UXXkCbNg1PhPv444/j6KOPxo033ogBAwbg7rvvxpAhQ/AUm4JFRCJUUyqPhy3mMd12G/D3vwMLFwIffuhzVbvLKyE+DtN/24Ivl2/Dd6t2mGve5vLGurya20K3gdPMrNqBhDigbUaKadnilDO85m0+5ferdpj1/Ona7N8py1yHfUAr0RM4XXHFFRg/fjzGjBnT6LrffvttvfXGjRtnlvtSXl6OgoKCOhcRkXCyO+cn0WfOT3lVdYvm/AQcNN10E3Dvvdbthx+2RtD59Vjrqrb6kavpLXRsmWOwxWve5nK20Hnrtlu1vdgU9sxKT/I5zcyu0kqznkjYddW99dZbppuNXXX+2Lx5Mzp2rFsKn7e53Bd26915550Bb6uItL5QjDALBUeEVh6vDZqYm/rEE9btJ58ErrzSr8Cn2unCuH06eh2d1lDXZKBzA7riGKj5LmIp0pCQfQrXr1+PSZMmYcaMGSbRu6XccsstuO6662pvs8WpW7duLfZ8IhIcoRxh1toitfK4KWh5+eXAc89Zyd/PPgv85S+NPsw98ImPj0dWWt3Oj8YCn0BG5fVq50BOWrJJ6O6YFe91mpnstGSznkhYddX99NNP2Lp1q8lRSkxMNJc5c+bgiSeeMP+uZll+D506dcKWLVvqLONtLvclJSUFWVlZdS4iEt6iaoSZH+ycHw5nZyJ4YVklqpxOc83bYTvMfft2YNo0K2hioUs/gqZgdE06AhiV143TzPTKhdPlMnPU8Xn4b17zNv89rHeuWU8krAKn0aNHY+HChfj5559rL0OHDjWJ4vx3QkL9SRKHDRuGWbNm1VnGFisuF5HoEEj+SiSLyGHuHToAs2db89Cdd57fD3MEWI7AbqFjSxxbidzZLXR9OmR4baEz08wc0h37dssxxxWnmeExxWve5vIz/ZhmpjllECQ6hKyrLjMzs14JAYfDgbZt29YunzhxIrp27WrylIhdeyNHjsTkyZNNQjlzpH788Uc8//zzIXkNIhJ8geavRLKIGOZeWQn8+CN/yVq399wTzl69TTXw5lTgbk7XpHshymVbCpGZmmiCHuZMMQDi6LiGWuhqp5lZWFMAs7IK6UmJGLxHNsY1UAAzFruRpb4wzDTcbd26dab/2zZ8+HBTu+m2227Drbfeir59++KDDz5QDSeRKBIOVaVDKayn4ygvB04/HWDh4ffeA447rllBRDAmRebfHtW/A175Zg0WbywwdZhYj6lnOwdO7d+h0QDGTDNzZNODVLsbOZImJ5YoDpy++OKLBm/Tqaeeai4iEp0ckTzCLJqxGvjJJ1s5TRzQk5gYUBAR6KTIfO7ZS7bCkZKIYb3bmoCH3WUFZVVmeY+26Y3+jaYGqeFSqDRWRpuGK33ziEhYidgRZtGspAQ48URg5kwgLQ3473/hPHIUpn+xMqAgorldk+4BzF4ddz83dXK5WiyACYduZHUThp4CJxEJK8HoxpEgKiw0XXL48ksgIwP43/+Aww83OU3BCCKa0zUZqgAm1N3I6iYMDyGvHC4iEhUjzKJRcTGnZ7CCJpZy+ewzEzSFutp5qJ7bEcTJiZsqVkebhiO1OIlIWIqIEWbRjt1y/fsDv/9uBU0HHlh7lyOEuWiheu5QdiOHQzehWNTiJCJhSxOphvwNAF54wSo/4BY0BVpLKVCheu5QFiqN+PkMo4gCJxER2Y2zM9x8M1BVcwJmMeI99wyrICKUzx2qbmRHCLsJpS7tYRERsfzxB6d1AJYutWo2Pfpog3sm0JICgQytD8ZzR1I3skabhg8FTiIiworDwKhRwMqVACdCv+KKFg8iAh1aH2gAE0g9pNYuVKrRpuEjzuXZQRzlCgoKkJ2djfz8fE34KyJCq1dbQdOaNUCvXtb8cz17tui+qT+0PtF0Q9klJ1p69GSk1kNy327mNLGVjflcLd3KFu0KmhAbqMVJRCSWLV9uBU0bNgB9+wKcSJ0tTi0o1BW4I7kekkabhp4CJxGRWMUJe48+2gqaBgywgqbOnVv8aUM5tD7UQVvUz2cYAzSqTkQkViUlAU8/bZUa4NygrRA0hXpofVOCNhFvFDiJiMSa6urd/2Zl8O++Azp0aLWnd4RwaL3qIUmgFDiJiHjpzlm/swRLNheY66iaxuKHH4CBA4Fly+oWumxFoSye6VA9JAmQcpxERKJgtJVfvvkGOOYYa+Le224D3n47JJsRyqH1qockgVLgJCISBaOtGsUcpuOOsybuPeII4KWXQro5oSpgqXpIEigFTiIiUTLayqcZM4ATTwRKS4GxY4EPPgDS02N2aH0oq45L5FPgJCISzbPPf/IJ8Kc/WVOojB8PvPMOkJqKWB9ar3pI0lwKnERE6oy28p6QzBwctkxE1OzzTLx+4AEraDrpJOCtt4Dk5FBvVdhQPSRplcDpiSee8Lqcv8hSU1PRp08fHH744UjgjNoiIhHC4Tbait1zUTH7PFvOPvwQeOQR4O9/t+o2iUhAmvwN8Oijj2Lbtm0oKSlBmzZtzLK8vDykp6cjIyMDW7duRe/evfH555+jWwuX7RcRCZaoGm31++9WJXDi9/Tdd4d6i0SiRpOLd9x333048MADsXz5cuzYscNcli1bhoMPPhiPP/441q1bh06dOuHaa69tmS0WEWnB0VYcCs9E8MKySlQ5neaat1tyiHxQcbTcPvsAjz8e6i0RiUpxLs/qY43Yc8898e6772K//fars3zBggU4+eSTsWrVKsydO9f8e9OmTYjkGZBFJPZE9OzzzzwDXH659W9eP/WU1V0nIkGLDZrcVcdgqKqqfnIkl23evNn8u0uXLihkgTURkQgTsaOtHnsMsFv6r7nGymtS0CQS+q66I488EpdccolpYbLx35dddhlGjRplbi9cuBC9evUK7paKiLTyaKv+nbLMddgHTQ8+uDtouvlmBU0i4RQ4/fvf/0Zubi4OOOAApKSkmMvQoUPNMt5HTBKfPHlyS2yviIi4Y+I3gyW64w4moqqlSaQFNbmrjonfM2bMwJIlS0xSOPXr189c3FulRESkFaSkWNcMmG65JSYrvkdct6rEVnJ4pFNyuIhEne++Aw45BLEmqidkluhJDq+ursYrr7yCWbNmmZpNTqezzv2zZ89u+haLiIh/+J3LUgMXXgjYX/AxGjRF7YTMEtaaHDhNmjTJBE7jx4/HwIED683pJCIiLRg0XXop8MILwPvvA59/DsTgLA1RPSGzRF/g9NZbb+Htt9/Gscce2zJbJCIi9VVXW61Mr77KYX/Wv2MwaIrqCZklOkfVJScnm/noRESklbB23sSJVtDEYOmNN4Bzz43Z3b97QuZEnxMys3hpRE3ILNEbOF1//fVmapUYyykXEQmNigrgjDOAKVOAxETgP/8Bzjwzpt8Nh9uEzN5E5ITMEjGafFR9/fXXZgLfadOmYZ999kGSx2zb7733XjC3T0Qktl1xBfDuu2zuB955Bzj+eMS6qJqQWaI/cMrJycFJJ53UMlsjIiJ1cfqU6dOB558Hjj5ae8dtQmaOnmMiOHOa2D3HliYGTREzIbNEJNVxEhEJN0yFcE96Li/fXehSomNCZomdOk4iItKCOEH6qada06gccYS1TEFTdE3ILBHNr8BpyJAhpuBlmzZtsP/++zdYu2n+/PnB3D4RkdiRnw8ccwzw7becLR1YuRJITQ31VkXEhMwiYRU4nXjiiWYyX/vfKnopIhJkO3cC48YBP/4ItGkDfPihgiaRMKQcJxGRUNu2DTjqKODnn4F27YAZM4D99gv1VonEjIIm5Dg1uY5T7969sWPHjnrLd+3aZe4TEZEm2LwZOPJIK2jq2BH44gsFTSJhrMnJ4WvWrDET/XoqLy/Hhg0bgrVdIiKxYfJkYPFioEsXzpIO9OsX6i0SkWAETh999FHtv6dPn26atGwMpJg83qtXL3//nIiI0H33AcXFwHXXAZrOSiR6cpziOalkzQSKng9h9fCePXti8uTJOO644xAt/ZgiIi3WPdehgzVZr4hEZx0np9NprtmqNG/ePLRjAqOIiDTNsmXAqFHW1ClPP1230KWIRF+O0+rVq1tmS0REot1vvwGjR1stTnPmcFSNVXpARCJGsyqHFxcXY86cOVi3bh0qOHO3m6uvvjpY2yYiEj1+/RUYM8YqPTBoEDBzpoImkVgInBYsWIBjjz0WJSUlJoDKzc3F9u3bkZ6ejg4dOihwEhHxxBkVxo61ilwOGQJ89hnQtq32k0gEanJm4rXXXovjjz8eeXl5SEtLw3fffYe1a9figAMOwMMPP9wyWykiEqm+/97KaWLQdPDBwKxZCppEYilw+vnnn3H99debUXYJCQmmflO3bt3wz3/+E7feemvLbKWISKTatAkoKgIOPdRqacrJCfUWiUhrBk4sPWCXJmDXHPOciMP41q9fH8i2iIhEnwkTgE8/BaZNA1QCRST2cpz2339/U46gb9++GDlyJP7+97+bHKfXX38dAwcObJmtFBGJJKwAvueeQI8e1m0mhYtIbLY43XfffejcubP597333os2bdrgsssuw7Zt2/Dcc8+1xDaKiESOjz8GjjnGymti2QERie0Wp6FDh9b+m111n7IJWkREgPffB04/HaisBPbdF8jN1V4RiTJBq/c/f/78sJ9uRUSkxfznP8Cpp1pB0xlnWLeTk7XDRWI5cOLkvjfccIMZPbdq1SqzbMmSJZgwYQIOPPDA2mlZRERiyuuvA2edxRnPgT//GXjjDY6kCfVWiUgou+r+/e9/4+KLLzYFL1nD6cUXX8QjjzyCq666CqeffjoWLVqEAQMGtMQ2ioiEr3feAc49F+Dk5xdeCDDXMyEh1FslIqFucXr88cfx4IMPmhF0b7/9trl++umnsXDhQjz77LMKmkQkNh1+ONCvH3D55cDzzytoEolycS4XfyY1zuFwYPHixejZsyf4kJSUFHz++ecYMWIEIklBQYGpOZWfn48s1VQRkWDgZL3Z2UBcnPanSARqSmzgd4tTaWmpmY+O4uLiTOBklyUQEYkpDz4IvPTS7tusBq6gSSQmNKkcAfOaMjIyzL+rqqrwyiuvoF27dnXWufrqq4O7hSIi4YIN9HffDdxxhxUosTzL4MGh3ioRCceuOnbRsaWpwT8WF1c72i5cqatOpHU5nS78sasUxRVVcCQnomtOGuLjI7BLi1+Vt93GKsDWbV7fckuot0pEWjk28LvFac2aNcHYNhGJISu2FmL6oi1Yua0IZVXVSE1MwJ7tMzBuYEf06ZCJiAqabrgBeOQR6/bkycB114V6q0QkkgtgNsczzzyDwYMHm+iOl2HDhmEaJ8L0gV2DbNVyv6SmprbqNouI/0HTy9+swaKN+chJT0Lvdhnmmre5nPdHBNanYwqCHTQ99ZSCJpEY1uQpV4Jpjz32wAMPPGAmDGaP4auvvooTTzwRCxYswD777OP1MQywli5dWnu7se5DEQlN9xxbmnYWV6Bvh4zaz2lmahIyUhKxfGsRPlu8xQRTYd9t99//WsESXwNrNF18cai3SERiNXA6/vjj69zmpMFshfruu+98Bk78Au7UqVMrbaGINAdzmtg91zk7td6PG97m8hVbi8x63XKt0bph64QTgJtuAvbe2yp0KSIxLaSBk7vq6mpMnToVxcXFpsvOl6KiIvTo0cNM7zJkyBDcd999PoMsKi8vNxf3BDARaVlMBGdOU3pymtf705ITsKWgzKwXlqqqrDnn0tKsliaWHxARCXWOE7HyOEscsC7UpZdeivfffx9785edF/369cNLL72EDz/8EG+88YYJnoYPH44NGzb4/Pv333+/yZS3L926dWvBVyMi5EhONIngJT4Co9KKaqQkJpj1wk5FhTVJ74knAmVlod4aEYnEcgRNaaVpajXuiooKrFu3zgwBfOedd0ytqDlz5vgMntxVVlaaqV7OPPNM3M3aKn62ODF4UuVwkZbNcXrmi5UmEdw9x4n4lcMcp0Fds3HpyD3DK8eJ3xWnnmrlNSUnA59/DgwfHuqtEpFIK0eQk5PjdxI2u9yaIjk5GX369DH/PuCAAzBv3jwzL95zTMJsRFJSEvbff3+sWLHC5zpsyeJFRFoPgyGWHNiYX2qCJOY0sXuOLU2b8suQ60jGUft0DK+gqbQUOOkkYPp0gKN1P/hAQZOINC9w4px07vWcbr75Zpx33nm1uUjffvutGRHHbrFAsfvNvYWosSCNXX3HHntswM8rIsHFOk3nj+hZW8eJOU3snmNLE4OmsKrjVFxsJYHPng1waim2OI0aFeqtEpFIDZxGjhxZ+++77roLjzzyiOkes51wwgkYNGgQnn/+eZzbhFEnt9xyC4455hh0794dhYWFmDJlCr744gtM5y8+ABMnTkTXrl1rAzI+9yGHHGJaqHbt2oWHHnoIa9euxUUXXdSU1ywirYTBUe8jMsK7cnhhITB+PPDVVwCnlPrkE+Cww0K9VSISppqcmcnWpWeffbbe8qFDhzY5gNm6dasJjjZt2mT6FlkMk0HT2LFjzf3MfYqP352/npeXh4svvhibN29GmzZtTNfe3Llz/cqHEpHQYJAU1iUHOCvCL78A2dnAp58ChxwS6i0SkWiYq859ZBuLVP7zn/+ss/ymm24yo93ci1OGI81VJyL1fPcdkyaZaKmdIxKDClpirjrbo48+ipNPPtlMjXLwwQebZT/88AOWL1+Od999t/lbLSLSWrZtY5P27kBJrUwi0lJ1nJiIvWzZMlP1e+fOnebCf3OZkrRFJOxt3gwceSQwejQwf36ot0ZEIkyzqs+xDhIrdouIRJQ//rBGyy1bBnTtaiWDi4i0dOXwr776Cuecc46p2v0Hv4gAvP766/j666+b8+dERFre2rXA4YdbQVP37sCcOcBee2nPi0jLBk7MYxo3bhzS0tIwf/782ppLTKhSK5SIhKVVq6ygide9ewNffgnsuWeot0pEYiFwuueee0w5ghdeeMFU7raNGDHCBFIiImFXboBBE5PB2cLElqYePUK9VSISKzlOLDdwOL+EPHAYH4tSioiElU6dgAEDrDpNM2cCnTuHeotEJJYCp06dOpm54Xr27FlnOfOberMJXEQknHDeuQ8/tKZVad8+1FsjIrHWVcfK3ZMmTcL3339vJv7duHEj/u///g833HADLrvsspbZShGRpvjpJ+DOOwG7vi/nn1PQJCKhaHHiBL+ciHf06NEoKSkx3XYpKSkmcLrqqquCsU0iIoFVAT/6aI5Ysbrl/vIX7U0RCd2UK7aKigrTZVdUVGTmisuIkHoomnJFJIqxJMoxxwBFRcChh1oT9mZmhnqrRCSKYoMmd9VdcMEFKCwsRHJysgmYDjroIBM0FRcXm/tERELi88+BceOsoImVwTlhr4ImEQmyJgdOr776KkpLS+st57LXXnstWNslIuK/6dM5HxRQUmIFT//7H+BwaA+KSOhynNiMxV49XtjilMqRKjWqq6vxySefoEOHDsHfQhGRhmzaBJx0ElBWBhx3HDB1qjWSTkQklIFTTk6OGUXHy15eping8js5ikVEpDUxAfyJJ6yuuSlTgORk7X8RCX1y+Jw5c0xr06hRo8y0K7m5ubX3Md+pR48e6NKlC8KdksNFokRlJeA2e4EpPRAXF8otEpEI1ZTYwO8Wp5EjR5rr1atXo3v37qaFSUQkJJhP+fDDViVwO0VA30kiEo7J4bNnz8Y777xTb/nUqVNN4riISIt68UXgvPOAhQuBF17QzhaR8A6c7r//frRr167eciaG33fffcHaLhGR+v71L05fYHXLXXEFcMst2ksiEt6B07p169CrV696y5njxPtERFrEo48CV15p/fu664AnnwTim/wVJiISkCZ/67Bl6ddff623/JdffkHbtm0D2xoREW8eeMAKloitTMxvUk6TiERC4HTmmWfi6quvxueff27qN/HCvCdO/HvGGWe0zFaKSOwqKACef976N0ue3HuvgiYRiZxJfu+++26sWbPGTPKbmGg9nJP+Tpw4UTlOIhJ8HBo8e7ZVDZx5TSIikTjJ77Jly0z3XFpaGgYNGmRynCKB6jiJRAB+Lf3yC7DffqHeEhGJAQUtUcfJE6uHe6sgLiISEKcTuPpq4NlnAZY+mTBBO1REwoZfgdN1111nuugcDof5d0MeeeSRYG2biMRi0HTJJVatJiZ/79gR6i0SEWl64LRgwQJUcnqDmn/7omriItJs1dXABRdYVcFZZuDll4GJE7VDRSQ6cpwilXKcRMIQf5gxSHrrLSAhAfi//wNOPz3UWyUiMaKgNXKcRESCFjQxSHr/fWvSXgZPf/qTdq6IhCW/Aqc/NeFL7L333gtke0Qk1rCsSfv2QHIy8O67wHHHhXqLREQCK4DJ5iv7wiasWbNm4ccff6y9/6effjLLeL+ISJMwCfyZZ4AfflDQJCLR0eL0MpM0a/z1r3/FaaedhmeffRYJzEUwOZ3VuPzyyxvtFxQRMYqLOQQXuPlmq3uOyeD77qudIyLRlxzevn17fP311+jXr1+d5UuXLsXw4cOxI8yHDys5XCTECguB8eOBr76yRtH9+9+h3iIRiXEFTUgOb/JcdVVVVViyZEm95VzGqVdERHzatQs46igraGLX/l/+op0lIhGlyaPqzj//fFx44YVYuXIlDjroILPs+++/xwMPPGDuExHxaudOK2j66ScgNxeYMQMYMkQ7S0SiO3B6+OGH0alTJ0yePBmbNm0yyzp37owbb7wR119/fUtso4hEum3bgDFjgF9/tUbQzZwJDB4c6q0SEWndApjsE6RISgpXjpNIK+NXzCGHWKPmOnUCZs0C9t5bb4OIxEaOk53nNHPmTLz55pu106xs3LgRRUVFzdtiEYle/I64/36gTx9gzhwFTSISW111a9euxdFHH41169ahvLwcY8eORWZmJh588EFzm2UKRERMS1PNDyuMGgX89ptVekBEJII1ucVp0qRJGDp0KPLy8pCWlla7/KSTTjJFMEVEsHIlwMEjDJZsCppEJBZbnL766ivMnTsXyZwewU3Pnj3xxx9/BHPbRCQSLV0KjB4N8Pvg8suBzz/f3fIkIhJrLU6s1cRK4Z42bNhguuxEJIYtXgyMHGkFTUwA54S9CppEJJYDp6OOOgqPPfZY7W0mhzMp/I477sCxxx4b7O0TkUjxyy/AEUcAW7ZYpQa++MIaRSciEsvlCNavX2+Sw/mw5cuXm3wnXrdr1w5ffvklOnTogHCmcgQiLYBFLceOBfLygAMOAKZPB9q21a4WkYjQlNigyTlO3bp1wy+//IL//Oc/5pqtTawkfvbZZ9dJFheRGPL3v1tBE+s1TZsG5OSEeotERELf4lRZWYn+/fvj448/xoABAxCJ1OIk0gLy84HbbgPuuw9QrqOIRJgWK4CZlJSEsrKyQLdPRKLB2rW7/80Je598UkGTiES9JieHX3HFFabYJauHi0iMYg5T//6cvDLUWyIi0qqanOM0b948U+jys88+w6BBg+BwOOrc/9577wVz+0Qk3Pz3v8AppwAVFcCXXwLXXQfEN2v2JhGRiNPkwCknJwcnn3xyy2yNiIQ3/jA6/XROWAnwe2DKFAVNIhJTmhw4vfzyyy2zJSIS3ljM8pxzABbAPeMM4PXXgcQmf4WIiES0+KZUDGdu04gRI3DggQfi5ptvRmlpactunYiEh1dfBc4+2wqaJk4E3nhDQZOIxCS/A6d7770Xt956KzIyMtC1a1c8/vjjJlFcRGIAazQ5ncBFF7HZGUhICPUWiYiEdx2nvn374oYbbsAll1xibs+cORPjx483rU7xEZQYqjpOIs00Y4Y1eW8Efd5FREJWx2ndunV15qIbM2aMmadu48aN/v4JEYkkzGHatWv3bU6poqBJRGKc34ET6zalpqbWK4jJauIiEmXuv9/KZTr6aEBFb0VEavk9JIY9eueddx5SUlJql7GK+KWXXlqnlpPqOIlEMPbc33mndaHx4wGPH0wiIrHM78Dp3HPPrbfsHA5NFpHoCZpuvRV44AHrNq//+tdQb5WISGQGTqrfJBLlQRMrgD/2mHX7kUeAa68N9VaJiIQdVa8TEeCOO3YHTf/6F3D55dorIiJeaFyxiABnnQV07gy8+KKCJhGRBqjFSUSA/v2BpUuBzEztDRGRBqjFSSQWsYzIeedZRS1tCppERMI7cHrmmWcwePBgU6WTl2HDhmHatGkNPmbq1Kno37+/qSk1aNAgfPLJJ622vSJRoaICOP10a/65U0+tW+RSRETCN3DaY4898MADD+Cnn37Cjz/+iFGjRuHEE0/E4sWLva4/d+5cnHnmmbjwwguxYMECTJgwwVwWLVrU6tsuEpFYzPJPfwLefx9ITrYm683JCfVWiYhE31x1rSU3NxcPPfSQCY48nX766SguLsbHH39cu+yQQw7Bfvvth2effdavv6+56iRmlZQAJ50EfPaZVdTyww+Bo44K9VaJiETnXHUtrbq6Gm+99ZYJjNhl5823335r5shzN27cOLPcl/LycrND3C8iMae4GDjuOCtoSk8H2MWtoElEpMlCHjgtXLgQGRkZZioXTt/y/vvvY++99/a67ubNm9GxY8c6y3iby325//77TRRpX7p16xb01yAS9h5/HPj8cysBfPp04MgjQ71FIiIRKeSBU79+/fDzzz/j+++/x2WXXWamdvntt9+C9vdvueUW0/RmX9avXx+0vy0SMW66CWD3N0fRHXpoqLdGRCRihbyOU3JyMvr06WP+fcABB2DevHl4/PHH8dxzz9Vbt1OnTtiyZUudZbzN5b6wJct9YmKRmJGfD2RkAAkJQGKiVdxSREQiu8XJk9PpNHlJ3jD3adasWXWWzZgxw2dOlEjM2rYNOPxw4JJL+KEK9daIiESNkLY4sRvtmGOOQffu3VFYWIgpU6bgiy++wHTmYACYOHEiunbtavKUaNKkSRg5ciQmT56M8ePHm2RyljF4/vnnQ/kyRMLLpk0AB1Gwy3vrVut2166h3ioRkagQ0sBp69atJjjatGmTSdxmMUwGTWPHjjX3r1u3DvHxuxvFhg8fboKr2267Dbfeeiv69u2LDz74AAMHDgzhqxAJIxs2AKNHA8uWWcHS7NkKmkREormOU0tTHSeJWmvXAqNGAatWAT16WEFT796h3ioRkbAXkXWcRCQAK1daOU0MmvbcE/jySwVNIiItQIGTSDRg19zGjazvAcyZA3TvHuotEhGJSiEvRyAiQXDMMcBHHwH778+6HdqlIiItRIGTSKT65RerThO75uzgSUREWpS66kQi0Y8/WtOmMBl83bpQb42ISMxQ4CQSaTipNUsO5OUBXboA2dmh3iIRkZihwEkkknC03FFHcewscNhhwGefKXASEWlFCpxEIgWnG2IeU1GR1UU3bRqQmRnqrRIRiSkKnEQiAUsMHHccUFICHH008PHHgMMR6q0SEYk5GlUnEgn22Qfo2xfo2ROYOhVISQn1FomIxCQFTiKRoF074PPPra655ORQb42ISMxSV51IuHrzTeC553bfbttWQZOISIipxUkkHL36KnD++QDn4O7fHxg5MtRbJCIianESCUMvvLA7aLr4YqvsgIiIhAV11YmEk6eeAv7yFytouvJKq6suXh9TEZFwoW9kkXAxeTJw1VXWv6+/HnjiCSAuLtRbJSIibhQ4iYSDr78GbrjB+vff/gY89JCCJhGRMKTkcJFwMGIEcOutQGoqcPvtod4aERHxQYGTSKgwj6miwipmyS65e+5RK5OISJhTV51IqIKm666z5p7jNCqkfCYRkbCnwEmktTmdwBVXAI89ZlUDnzlT74GISIRQV51Ia6quBi65BPj3v60WphdfBE44Qe+BiEiEUOAk0lqqqoALLgBef92qzcTq4Oeco/0vIhJBFDiJtIbKSitIevttICEBmDIFOO007XsRkQijwEmkNaxZA8yYASQlWcHThAna7yIiEUiBk0hr6NsX+OwzYOtW4Nhjtc9FRCKUAieRlsIyA8uWAfvtZ90eOlT7WkQkwqkcgUhLKCoCxo8HDj8c+OEH7WMRkSihwEkk2AoKgKOPBr74YndiuIiIRAV11YkEU16eFTSxlSknB5g+HTjoIO1jEZEoocBJJFh27ADGjgUWLAByc61RdEOGaP+KiEQRBU4iwbB9OzBqFLBwIdC+PTBrFjBokPatiEiUUeAkEgyZmUDXrlYAxaBpwADtVxGRKKTASSQYUlKA994DNm8GevXSPhURiVIaVScSSDXw++4DXC7rdlqagiYRkSinFieR5li50sppWrcOSE4GbrhB+1FEJAaoxUmkqZYutQpbMmjq1w846yztQxGRGKHASaQpFi0CRo4ENm4E9tkHmDMH6NJF+1BEJEYocBLx1y+/AEceCWzZYs0/x8rgHTtq/4mIxBAFTiL+TqMyZoxVboCT9bLkQLt22nciIjFGgZOIP7KygMmTgREjgJkzrcrgIiIScxQ4iTTE6dz974kTrZym7GztMxGRGKXAScQXdsexW45FLW0JCdpfIiIxTIGTiDeffgocd5w1Ye+992ofiYiIocBJxNN//wuceCJQVgaccALw8MPaRyIiYihwEnH37rvAn/4EVFQAp5wCTJ1qzUMnIiKiwEnEzZQpwOmnA1VVVjXwN9+0plMRERGpoRYnEWIL0113AdXVwHnnAa+9BiRqKkcREalLgZMIsWVpxgzg9tuBf/9bo+dERMQrBU4S25Yv3/3vbt2sVqd4fSxERMQ7nSEkdrES+IABVgK4iIiIHxQ4SWxibaYbbrBymhYtCvXWiIhIhFDgJLHF5QL+/nfgttus2+yau/POUG+ViIhECA0bktgKmm6+GfjnP63bDz4I3HRTqLdKREQiiAIniZ2g6dprgccft24/9hgwaVKot0pERCKMAieJHcxnomeeAS69NNRbIyIiEUiBk8SGuDirtYmVwQ89NNRbIyIiEUrJ4RK9OHUKgyVWBSfWZ1LQJCIiAVDgJNGpshI4+2zgmmuAiRNDvTUiIhIl1FUn0ae8HDjjDOCDD4CkJOvfIiIiQaDASaJLWRlw8snAJ58AKSnAu+8C48eHeqtERCRKKHCS6FFSAkyYYE3Wm5YGfPghMHZsqLdKRESiiAIniR7skmPQ5HAAH38MHHFEqLdIRESiTEiTw++//34ceOCByMzMRIcOHTBhwgQsXbq0wce88soriIuLq3NJTU1ttW2WMMa55zp1AqZPV9AkIiLR1+I0Z84cXHHFFSZ4qqqqwq233oqjjjoKv/32GxxsNfAhKyurToDF4EkEhx8OrFplddOJiIhEW+D06aef1mtNYsvTTz/9hMN5EvSBgVIntixIbNu+HTjrLGDyZGDQIGuZgiYREYmVOk75+fnmOjc3t8H1ioqK0KNHD3Tr1g0nnngiFi9e7HPd8vJyFBQU1LlIFNiyBTjySCunicGT0xnqLRIRkRgQNoGT0+nENddcgxEjRmDgwIE+1+vXrx9eeuklfPjhh3jjjTfM44YPH44NGzb4zKPKzs6uvTDYkgi3caOVw7RoEdC5M/D221ZVcBERkRYW53Jx2vjQu+yyyzBt2jR8/fXX2GOPPfx+XGVlJQYMGIAzzzwTd999t9cWJ15sbHFi8MTWLeZKSYRZvx4YNQpYsQLgcTJ7NtC3b6i3SkREIhhjAzau+BMbhEU5giuvvBIff/wxvvzyyyYFTZSUlIT9998fK3gi9SIlJcVcJAqsXm0FTWvWAD17WkFTr16h3ioREYkhIe3fYGMXg6b3338fs2fPRq9mnASrq6uxcOFCdGaXjUS3226zgqY+fYAvv1TQJCIirS6kLU4sRTBlyhSTr8RaTps3bzbL2VyWVjM6auLEiejatavJVaK77roLhxxyCPr06YNdu3bhoYcewtq1a3HRRReF8qVIa3j2WWvuufvuA7p00T4XEZHYCpyeeeYZc32ER4Xnl19+Geedd57597p16xDvlvibl5eHiy++2ARZbdq0wQEHHIC5c+di7733buWtl1axdSvQoYP178xM1qzQjhcRkZAJm+TwcEwAkxD7+WdgzBjguuuAW28N9daIiEiUakpsoDHcEp7mzbMSwXfsAD74gMMjQ71FIiIiCpwkDM2da7U05eUBw4dbRS41MlJERMKAWpwkvHC03FFHsd0UGDnSmrA3OzvUWyUiImIocJLwMXMmcPTRQHGx1eL0ySdARkaot0pERKSWAicJH8uXA6WlwDHHAP/9L5CeHuotEhERCb/K4SLGZZdZc88xcFJOk4iIhCG1OEloTZtmjZyzTZigoElERMKWAicJnSlTgOOO250MLiIiEuYUOElosAL4OecATicweDDgcOidEBGRsKfASVrf888D55/PWZ6BSy4B/v1vICFB74SIiIQ9BU7Sup580gqW6OqrOWEh4DYXoYiISDjTGUtaz3PPWcES3Xgj8NhjQFyc3gEREYkYKkcgrWf0aKvcwIUXAnfdpaBJREQijgInaT19+gC//gq0a6e9LiIiEUldddJymPz9t79ZU6fYFDSJiEgEU4uTtFzQdO21wOOPA6mp1nQqe+yhvS0iIhFNgZMEH2szXXEF8Oyz1u1HH1XQJCIiUUGBkwRXdTVw8cXAyy9byd+s0cSaTSIiIlFAgZMET1UVcN55wP/9n1Wb6bXXgLPP1h4WEZGoocBJgufFF62gKTHRmofu1FO1d0VEJKoocJLgYRfd998DEyYAJ56oPSsiIlFHgZMEpqwMSEqy5prjhblNIiIiUUp1nKT5SkqA448HLrjAGkknIiIS5RQ4SfMUFQHHHgvMnAm8+y6wdKn2pIiIRD0FTtJ0+fnAuHHAnDlAVhbw2WfAgAHakyIiEvWU4yRNk5dnBU3z5gE5OVbQdOCB2osiIhITFDiJ/7ZvB8aOBX7+GWjbFpgxA9h/f+1BERGJGQqcxH+LFgG//QZ06GDlNg0apL0nIiIxRYGT+O+II4D33gP23BPo3197TkREYo4CJ2nY+vVWraa+fa3b48drj4mISMzSqDrxbfVq4PDDgVGjgFWrtKdERCTmKXAS75YvB0aOBNasAdLSrOrgIiIiMU5ddVLf778Do0cDmzZZuUyzZwOdO2tPiYhIzFOLk9QfOcckcAZNAwcCX3yhoElERKSGWpykftC0Y4dVn4nFLdu10x4SERGpocBJduvSBejWzSo38OmnQJs22jsiIiJuFDjJbrm5VjVwJoJnZ2vPiIiIeFCOU6zjRL3PPLP7NrvmFDSJiIh4pRanWMZpU044ASgtBfbYAzj++FBvkYiISFhTi1Os+uQT4LjjrKDp2GOtyXtFRESkQQqcYtGHHwITJgDl5dY1559LTQ31VomIiIQ9BU6xZupU4JRTgMpK4LTTgLffBlJSQr1VIiIiEUE5TrHkt9+AM84AnE7gnHOAl18GEnUIiIhEEqfThT92laK4ogqO5ER0zUlDfHxcqDcrZuisGUv23hu4/XZg/Xrg+eeBhIRQb5GIiDTBiq2FmL5oC1ZuK0JZVTVSExOwZ/sMjBvYEX06ZGpftgIFTrGgqmp3y9Idd1jXcfp1IiISaUHTy9+swc7iCnTOTkV6chpKKqqwaGM+NuaX4vwRPRU8tQLlOEW7J54ARo0Ciot3B0wKmkREIq57ji1NDJr6dshAZmoSEuLjzDVvc/lni7eY9aRlKXCKZg89BEyaBHz1FTBlSqi3RkREmok5TeyeY0tTnMePX97m8hVbi8x60rIUOEWre+4BbrrJ+jfzmi66KNRbJCIizcREcOY0pSd7z7BJS05AeVW1WU9algKnaONyWYESL3T33cBdd6l7TkQkgjmSE00iOHOavCmtqEZKYoJZT1qWAqdoC5r++lertYn++U/gtttCvVUiIhIglhzg6LlN+WVw8bveDW9zeZ8OGWY9aVkKnKLJxo3ASy9Z/378ceDGG0O9RSIiEgSs08SSA7mOZCzfWoTCskpUOZ3mmre5/Kh9OqqeUytQm1406doVmDEDmD8fuPDCUG+NiIgEEes0seSAXcdpS0GZ6Z4b1DXbBE2q49Q64lyebX5RrqCgANnZ2cjPz0dWVhYiXnU1sHSpVdxSRESiniqHhzY2UFddpBe2nDgROOgg4JtvQr01IiLSSt123XLT0b9TlrnWdCutS111kYqT9J59tjVpL6uCb94c6i0SERGJegqcIlF5OXD66cCHHwJJSVbwdOKJod4qERGRqKfAKdKUlgInnwxMmwakpADvvw8cc0yot0pERCQmKHCKJCUlVsvSzJlAWhrw3/8Co0eHeqtERERihgKnSMJcJgZMDgfwv/8BI0eGeotERERiigKnSJKcbOUzsfzA4MGh3hoREZGYo3IE4W7nTmDyZGs6FWJek4ImERGRkFCLUzjbvh0YOxb4+WcgP9+arFdERERCRoFTuNqyxUr8XrwY6NABOO20UG+RiIhIzAtpV93999+PAw88EJmZmejQoQMmTJiApczfacTUqVPRv39/pKamYtCgQfjkk08QdZP1HnGEFTR17gzMmQMMHBjqrRIREYl5IQ2c5syZgyuuuALfffcdZsyYgcrKShx11FEoLi72+Zi5c+fizDPPxIUXXogFCxaYYIuXRYsWISqsWwccfjiwZAnQrRvw5ZdA//6h3ioREREJt0l+t23bZlqeGFAdzuDBi9NPP90EVh9//HHtskMOOQT77bcfnn322cie5JcVwdmytGIF0KsXMHs20LNnqLdKREQkqhVE6iS/3GDKzc31uc63336LMWPG1Fk2btw4s9yb8vJys0PcL2GLI+buvBPo18/qnlPQJCIiElbCJnByOp245pprMGLECAxsIJ9n8+bN6NixY51lvM3lvvKoGEXal27s/go37o1+Z50F/Pqr1U0nIiIiYSVsAifmOjFP6a233grq373llltMS5Z9Wb9+PcLKwoXAoYcCf/xRt9CliIiIhJ2wKEdw5ZVXmpylL7/8EnvssUeD63bq1AlbOFTfDW9zuTcpKSnmEpYWLLDqNO3YAVx/PRDkoFFERESiqMWJeekMmt5//33Mnj0bvZgQ3Yhhw4Zh1qxZdZZxRB6XR5QffgBGjbKCpoMOAp55JtRbJCIiIuHc4sTuuSlTpuDDDz80tZzsPCXmIqVxMlsAEydORNeuXU2uEk2aNAkjR47E5MmTMX78eNO19+OPP+L5559HxPjmG+CYY4DCQmDECIB1qMJthJ+IiIiEV4vTM888Y/KOjjjiCHTu3Ln28p///Kd2nXXr1mHTpk21t4cPH26CLQZK++67L9555x188MEHDSaUh5UvvuAwQCtoYpHLTz9V0CQiIhIhwqqOU2sIaR0npxM48EBg/nwrt+mDD4D09NbdBhEREYmOOk5RLz4e+Ogj4LLLrGsFTSIiIhFFgVNrcC810LUr8PTTQGpqqzy1iIiIBI8Cp5Y2dSrQuzcwZUqLP5WIiIi0LAVOLemNN4AzzgAqKoCZM1v0qURERKTlKXBqKS+9xFoKVkL4hRcCL7zQYk8lIiIirUOBU0t49lkrWOKARSaCs8ZUQkKLPJWIiIi0HgVOwfb441awRNdcA/zrX9ZoOhEREYl4OqMH27p11vVf/wo88ggQFxf0pxAREZEYnuQ3qjz8sDUH3bHHKmgSERGJMgqcgo0tTOPHB/3PioiISOipq05ERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPykwElERETETwqcRERERPyUiBjjcrnMdUFBQag3RURERMKAHRPYMUJDYi5wKiwsNNfdunUL9aaIiIhImMUI2dnZDa4T5/InvIoiTqcTGzduRGZmJuLi4hBuES8DuvXr1yMrKyvUmxP2tL+0v3R8hQ99HrW/Ivn4YijEoKlLly6Ij284iynmWpy4Q/bYYw+EMx4UCpy0v3R8hQd9HrW/dHzFxucxu5GWJpuSw0VERET8pMBJRERExE8KnMJISkoK7rjjDnMt2l86vkJLn0ftLx1f4SMljM6PMZccLiIiItJcanESERER8ZMCJxERERE/KXASERER8ZMCp1Zy//3348ADDzSFNzt06IAJEyZg6dKljT5u6tSp6N+/P1JTUzFo0CB88skniAXN2V+vvPKKKWrqfuF+iwXPPPMMBg8eXFvjZNiwYZg2bVqDj4nVY6s5+yuWjy1vHnjgAbMPrrnmmgbXi+VjrKn7K9aPsX/84x/1Xj+PnXA8vhQ4tZI5c+bgiiuuwHfffYcZM2agsrISRx11FIqLi30+Zu7cuTjzzDNx4YUXYsGCBSZ44GXRokWIds3ZX8ST4KZNm2ova9euRSxgUVd+Of/000/48ccfMWrUKJx44olYvHix1/Vj+dhqzv6K5WPL07x58/Dcc8+ZwLMhsX6MNXV/UawfY/vss0+d1//111+H5/HFUXXS+rZu3crRjK45c+b4XOe0005zjR8/vs6ygw8+2HXJJZe4Yo0/++vll192ZWdnt+p2hbM2bdq4XnzxRa/36dhq2v7SsWUpLCx09e3b1zVjxgzXyJEjXZMmTfJ5/OkYa9r+ivVj7I477nDtu+++fq8fyuNLLU4hkp+fb65zc3N9rvPtt99izJgxdZaNGzfOLI81/uwvKioqQo8ePcycRo21IESr6upqvPXWW6Z1jl1Q3ujYatr+Ih1bMK3A48ePr/e9pGMs8P2lYwxYvny5mSuud+/eOPvss7Fu3bqwPL5ibq66cJlomH3dI0aMwMCBA32ut3nzZnTs2LHOMt7m8lji7/7q168fXnrpJdMkzkDr4YcfxvDhw03wFO7zEwbDwoULzYm/rKwMGRkZeP/997H33nt7XVfHVtP2V6wfW8Tgcv78+abryR+xfow1dX/F+jF28MEHmzwv7gd2091555047LDDTNcbc13D6fhS4BSiXyE8GBrqv5Wm7y+eBN1bDPilM2DAAJNfcPfdd0f9LuUXzs8//2y+dN955x2ce+65JlfMVzAQ65qyv2L92OKM9JMmTTL5hrGUsNya+yvWj7Fjjjmm9t8MHhlIsffg7bffNnlM4USBUyu78sor8fHHH+PLL79s9FdEp06dsGXLljrLeJvLY0VT9penpKQk7L///lixYgViQXJyMvr06WP+fcABB5hfuo8//rj54vWkY6tp+yvWjy0m0W/duhVDhgyp08XJz+VTTz2F8vJyJCQk1HlMLB9jzdlfsX6MecrJycFee+3l8/WH8vhSjlMr4cw2DALYHTB79mz06tWr0cfw18esWbPqLOMvmIbyMGJ5f3niFxW7Yzp37oxYxC5OfkF7E8vHVnP2V6wfW6NHjzavly109mXo0KEmD4X/9hYExPIx1pz9FevHmLecwpUrV/p8/SE9vlo8/VyMyy67zIyY+OKLL1ybNm2qvZSUlNTuoT//+c+um2++ufb2N99840pMTHQ9/PDDrt9//92MOkhKSnItXLgw6vdqc/bXnXfe6Zo+fbpr5cqVrp9++sl1xhlnuFJTU12LFy92RTvuB444XL16tevXX381t+Pi4lyfffaZuV/HVmD7K5aPLV88R4npGAtsf8X6MXb99deb73t+JnnuGzNmjKtdu3ZmRHW4HV/qqmvFgnt0xBFH1Fn+8ssv47zzzjP/5giC+Pj4On3cU6ZMwW233YZbb70Vffv2xQcffNBggnQs76+8vDxcfPHFJjmwTZs2pvuFtT5iIceH3QITJ040SZXZ2dkmR2D69OkYO3asuV/HVmD7K5aPLX/pGAtsf8X6MbZhwwZTl2nHjh1o3749Dj30UFPHj/8Ot+MrjtFTiz+LiIiISBRQjpOIiIiInxQ4iYiIiPhJgZOIiIiInxQ4iYiIiPhJgZOIiIiInxQ4iYiIiPhJgZOIiIiInxQ4iYiIiPhJgZOISBC88sorZmJSEYluCpxEpEXFxcU1ePnHP/7Rau8Ap/Cxnzc1NdXMvn7//febSaWbomfPnnjsscfqLDv99NOxbNmyIG+xiIQbzVUnIi2K88HZ/vOf/+Dvf/87li5dWrssIyOj9t8MYDgrfGJiy301cT6wu+66C+Xl5Zg9ezb+8pe/mJaiyy67LKC/m5aWZi4iEt3U4iQiLapTp061F06oy9Ye+/aSJUuQmZmJadOmmUlNU1JS8PXXX5uJnCdMmFDn71xzzTV1Jn12Op2mtahXr14mYNl3333xzjvvNLo96enp5rl79OiB888/30zwO2PGjNr7V65ciRNPPBEdO3Y0Qd2BBx6ImTNn1t7PbVi7di2uvfba2tYrb111bEnbb7/98Prrr5sWKr72M844A4WFhbXr8N9nn302HA4HOnfujEcffdT8fb5WEQlPCpxEJORuvvlmPPDAA/j9999NIOMPBk2vvfYann32WSxevNgEMueccw7mzJnj1+PZuvXVV1+Z4C05Obl2eVFREY499ljMmjULCxYswNFHH43jjz/ezM5O7733HvbYYw/TasXWNPcWNU8Mwjhj+8cff2wu3Da+Ttt1112Hb775Bh999JEJ3rg98+fP92v7RSQ01FUnIiHHIGTs2LF+r89utvvuu8+0BA0bNsws6927t2mteu655zBy5Eifj3366afx4osvoqKiApWVlSbX6eqrr669ny1XvNjuvvtuvP/++ya4ufLKK5Gbm4uEhATTUsaWq4awVYwtUVyX/vznP5uA7N577zWtTa+++iqmTJmC0aNHm/tffvlldOnSxe/9ICKtT4GTiITc0KFDm7T+ihUrUFJSUi/YYjC0//77N/hYdo397W9/Q15eHu644w4MHz7cXNxbnNjN9r///c+0JlVVVaG0tLS2xakp2EVnB03E7ritW7eaf69atcoEbgcddFDt/ezO69evX5OfR0RajwInEQk55vi4i4+PrzfSjUGGe3BDDG66du1aZz3mSTWEwUmfPn3Mv99++23z70MOOQRjxowxy2644QbTbfbwww+b+5g/dcopp5igrKmSkpLq3GY+FFuhRCRyKXASkbDTvn17LFq0qM6yn3/+uTYQ2XvvvU2AxFaghrrlGsPk70mTJplgiflMDGyYc8Tk9JNOOqk2SFuzZk2dxzEniqP/AsGuRb6eefPmoXv37mZZfn6+KWlw+OGHB/S3RaTlKDlcRMLOqFGj8OOPP5rk7+XLl5suNfdAit1fDHaYEM48ISZhM6n6ySefNLeb4pJLLjHByrvvvmtu9+3b1ySAM1D75ZdfcNZZZ9VrJWIX3Jdffok//vgD27dvb9Zr5Gs499xzceONN+Lzzz83Ce4XXnihaW2zR+qJSPhR4CQiYWfcuHG4/fbbcdNNN5lyAEyknjhxYp11mLTNdTi6bsCAAWb0G7vuWJ6gKZjszb/NvCYGSI888gjatGlj8p44mo7bMmTIkHrJ7GyF2nPPPU3rWHPxuZjcftxxx5muwhEjRpjXwoR1EQlPca6mlswVEZEWUVxcbHK2Jk+ebFqfRCT8KMdJRCREmFfFOlIcWcf8JrZkEQtwikh4UuAkIhJCHL3HKWiYcM7q6SyC2a5dO70nImFKXXUiIiIiflJyuIiIiIifFDiJiIiI+EmBk4iIiIifFDiJiIiI+EmBk4iIiIifFDiJiIiI+EmBk4iIiIifFDiJiIiI+EmBk4iIiAj88//pqApYoXB5GgAAAABJRU5ErkJggg=="
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 99
-  },
-  {
-   "cell_type": "markdown",
-   "id": "46d1bd68d47ea764",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-25T16:34:36.630819600Z",
-     "start_time": "2026-04-25T16:34:36.611164400Z"
-    }
-   },
-   "source": [
-    "## Trying Ridge Regression\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "id": "f7b09be17154ad47",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.588296500Z",
-     "start_time": "2026-04-26T14:56:43.520726500Z"
-    }
-   },
-   "source": [
-    "best_ridge_alpha = None\n",
-    "best_ridge_rmse = float('inf')\n",
-    "best_ridge_model = None\n",
-    "best_y_pred_ridge = None\n",
-    "best_ridge_res = None\n",
-    "\n",
-    "for alpha in [0.1, 1.0, 10.0, 50.0]:\n",
-    "    ridge_model_tmp = Ridge(alpha=alpha, solver='lsqr', random_state=seed)\n",
-    "    ridge_res_tmp, y_pred_ridge_tmp = evaluate_model(ridge_model_tmp, X_train, X_test, y_train, y_test, f\"Ridge Regression (alpha={alpha})\")\n",
-    "\n",
-    "    if ridge_res_tmp['RMSE'] < best_ridge_rmse:\n",
-    "        best_ridge_rmse = ridge_res_tmp['RMSE']\n",
-    "        best_ridge_alpha = alpha\n",
-    "        best_ridge_model = ridge_model_tmp\n",
-    "        best_y_pred_ridge = y_pred_ridge_tmp\n",
-    "        best_ridge_res = ridge_res_tmp\n",
-    "\n",
-    "display(pd.DataFrame([{\n",
-    "    'Selection': 'Ridge best alpha by RMSE',\n",
-    "    'Best alpha': best_ridge_alpha,\n",
-    "    'RMSE': best_ridge_rmse\n",
-    "}]))\n",
-    "\n",
-    "ridge_model = best_ridge_model\n",
-    "ridge_res = best_ridge_res\n",
-    "y_pred_ridge = best_y_pred_ridge\n",
-    "results.append(ridge_res)"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "                  Selection  Best alpha      RMSE\n",
-       "0  Ridge best alpha by RMSE        50.0  0.416581"
-      ],
-      "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>Selection</th>\n",
-       "      <th>Best alpha</th>\n",
-       "      <th>RMSE</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Ridge best alpha by RMSE</td>\n",
-       "      <td>50.0</td>\n",
-       "      <td>0.416581</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 100
-  },
-  {
-   "cell_type": "code",
-   "id": "751e4cca3fc3b4bb",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.765152600Z",
-     "start_time": "2026-04-26T14:56:43.590296800Z"
-    }
-   },
-   "source": [
-    "plt.figure(figsize=(6, 6))\n",
-    "plt.scatter(y_test, y_pred_ridge, alpha=0.5)\n",
-    "plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')\n",
-    "plt.title(\"Part E - Ridge Regression: Actual vs Predicted\")\n",
-    "plt.xlabel(\"True Rating\")\n",
-    "plt.ylabel(\"Predicted Rating\")\n",
-    "plt.tight_layout()\n",
-    "plt.show()"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Figure size 600x600 with 1 Axes>"
-      ],
-      "image/png": "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"
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 101
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fd2c011a69ca364f",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-25T16:42:13.392229200Z",
-     "start_time": "2026-04-25T16:42:13.355459900Z"
-    }
-   },
-   "source": [
-    "## Trying Lasso Regression\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "id": "11024fb6674354a3",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.868079700Z",
-     "start_time": "2026-04-26T14:56:43.773660600Z"
-    }
-   },
-   "source": [
-    "best_lasso_alpha = None\n",
-    "best_lasso_rmse = float('inf')\n",
-    "best_lasso_model = None\n",
-    "best_y_pred_lasso = None\n",
-    "best_lasso_res = None\n",
-    "\n",
-    "for alpha in [1e-4, 5e-4, 1e-3, 5e-3, 1e-2]:\n",
-    "    lasso_model_tmp = Lasso(alpha=alpha, max_iter=20000, random_state=seed)\n",
-    "    lasso_res_tmp, y_pred_lasso_tmp = evaluate_model(lasso_model_tmp, X_train, X_test, y_train, y_test, f\"Lasso Regression (alpha={alpha})\")\n",
-    "\n",
-    "    if lasso_res_tmp['RMSE'] < best_lasso_rmse:\n",
-    "        best_lasso_rmse = lasso_res_tmp['RMSE']\n",
-    "        best_lasso_alpha = alpha\n",
-    "        best_lasso_model = lasso_model_tmp\n",
-    "        best_y_pred_lasso = y_pred_lasso_tmp\n",
-    "        best_lasso_res = lasso_res_tmp\n",
-    "\n",
-    "display(pd.DataFrame([{\n",
-    "    'Selection': 'Lasso best alpha by RMSE',\n",
-    "    'Best alpha': best_lasso_alpha,\n",
-    "    'RMSE': best_lasso_rmse\n",
-    "}]))\n",
-    "\n",
-    "lasso_model = best_lasso_model\n",
-    "lasso_res = best_lasso_res\n",
-    "y_pred_lasso = best_y_pred_lasso\n",
-    "results.append(lasso_res)"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "                  Selection  Best alpha      RMSE\n",
-       "0  Lasso best alpha by RMSE      0.0005  0.386607"
-      ],
-      "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>Selection</th>\n",
-       "      <th>Best alpha</th>\n",
-       "      <th>RMSE</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Lasso best alpha by RMSE</td>\n",
-       "      <td>0.0005</td>\n",
-       "      <td>0.386607</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 102
-  },
-  {
-   "cell_type": "code",
-   "id": "3f0658c719c2ecc6",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.964901Z",
-     "start_time": "2026-04-26T14:56:43.868079700Z"
-    }
-   },
-   "source": [
-    "plt.figure(figsize=(6, 6))\n",
-    "plt.scatter(y_test, y_pred_lasso, alpha=0.5)\n",
-    "plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'r--')\n",
-    "plt.title(\"Part E - Lasso Regression: Actual vs Predicted\")\n",
-    "plt.xlabel(\"True Rating\")\n",
-    "plt.ylabel(\"Predicted Rating\")\n",
-    "plt.tight_layout()\n",
-    "plt.show()"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Figure size 600x600 with 1 Axes>"
-      ],
-      "image/png": "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"
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 103
-  },
-  {
-   "cell_type": "code",
-   "id": "b6d9827d298e4fa6",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:43.989302200Z",
-     "start_time": "2026-04-26T14:56:43.965900700Z"
-    }
-   },
-   "source": [
-    "results_df = pd.DataFrame(results)\n",
-    "results_df"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "                             Model       MAE       MSE      RMSE        R2\n",
-       "0                Linear Regression  0.280613  0.149546  0.386712  0.146514\n",
-       "1            Polynomial Regression  0.295032  0.172895  0.415806  0.013258\n",
-       "2    Ridge Regression (alpha=50.0)  0.302947  0.173539  0.416581  0.009580\n",
-       "3  Lasso Regression (alpha=0.0005)  0.280977  0.149465  0.386607  0.146976"
-      ],
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>Model</th>\n",
-       "      <th>MAE</th>\n",
-       "      <th>MSE</th>\n",
-       "      <th>RMSE</th>\n",
-       "      <th>R2</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Linear Regression</td>\n",
-       "      <td>0.280613</td>\n",
-       "      <td>0.149546</td>\n",
-       "      <td>0.386712</td>\n",
-       "      <td>0.146514</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "      <td>0.295032</td>\n",
-       "      <td>0.172895</td>\n",
-       "      <td>0.415806</td>\n",
-       "      <td>0.013258</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "      <td>0.302947</td>\n",
-       "      <td>0.173539</td>\n",
-       "      <td>0.416581</td>\n",
-       "      <td>0.009580</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "      <td>0.280977</td>\n",
-       "      <td>0.149465</td>\n",
-       "      <td>0.386607</td>\n",
-       "      <td>0.146976</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "execution_count": 104,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 104
-  },
-  {
-   "cell_type": "code",
-   "id": "aa66d8d2df993766",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:44.022349500Z",
-     "start_time": "2026-04-26T14:56:43.990308500Z"
-    }
-   },
-   "source": [
-    "pred_sheet_part_e_linear = regression_prediction_sheet(y_test, y_pred_lin, 'Linear Regression')\n",
-    "pred_sheet_part_e_poly = regression_prediction_sheet(y_test, y_pred_poly, 'Polynomial Regression')\n",
-    "pred_sheet_part_e_ridge = regression_prediction_sheet(y_test, y_pred_ridge, f'Ridge Regression (alpha={best_ridge_alpha})')\n",
-    "pred_sheet_part_e_lasso = regression_prediction_sheet(y_test, y_pred_lasso, f'Lasso Regression (alpha={best_lasso_alpha})')\n",
-    "\n",
-    "best_model_part_e = results_df.sort_values('RMSE').iloc[0]['Model']\n",
-    "part_e_pred_sheet = {\n",
-    "    'Linear Regression': pred_sheet_part_e_linear,\n",
-    "    'Polynomial Regression': pred_sheet_part_e_poly,\n",
-    "}.get(best_model_part_e, pred_sheet_part_e_linear)\n",
-    "\n",
-    "if 'Ridge Regression' in best_model_part_e:\n",
-    "    part_e_pred_sheet = pred_sheet_part_e_ridge\n",
-    "if 'Lasso Regression' in best_model_part_e:\n",
-    "    part_e_pred_sheet = pred_sheet_part_e_lasso\n",
-    "\n",
-    "part_e_pred_sheet"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "    True  Predicted  Residual  Abs_Error                            Model\n",
-       "0    4.1   4.306335 -0.206335   0.206335  Lasso Regression (alpha=0.0005)\n",
-       "1    4.1   4.287329 -0.187329   0.187329  Lasso Regression (alpha=0.0005)\n",
-       "2    4.4   4.297757  0.102243   0.102243  Lasso Regression (alpha=0.0005)\n",
-       "3    4.6   4.197993  0.402007   0.402007  Lasso Regression (alpha=0.0005)\n",
-       "4    4.5   4.371379  0.128621   0.128621  Lasso Regression (alpha=0.0005)\n",
-       "5    3.2   4.304839 -1.104839   1.104839  Lasso Regression (alpha=0.0005)\n",
-       "6    4.2   4.324286 -0.124286   0.124286  Lasso Regression (alpha=0.0005)\n",
-       "7    3.9   4.005045 -0.105045   0.105045  Lasso Regression (alpha=0.0005)\n",
-       "8    3.7   4.138157 -0.438157   0.438157  Lasso Regression (alpha=0.0005)\n",
-       "9    4.6   4.312731  0.287269   0.287269  Lasso Regression (alpha=0.0005)\n",
-       "10   4.6   4.468202  0.131798   0.131798  Lasso Regression (alpha=0.0005)\n",
-       "11   4.5   4.364965  0.135035   0.135035  Lasso Regression (alpha=0.0005)\n",
-       "12   4.6   4.443139  0.156861   0.156861  Lasso Regression (alpha=0.0005)\n",
-       "13   4.4   4.289412  0.110588   0.110588  Lasso Regression (alpha=0.0005)\n",
-       "14   4.0   4.302132 -0.302132   0.302132  Lasso Regression (alpha=0.0005)\n",
-       "15   4.3   4.373179 -0.073179   0.073179  Lasso Regression (alpha=0.0005)\n",
-       "16   4.4   4.172033  0.227967   0.227967  Lasso Regression (alpha=0.0005)\n",
-       "17   3.8   4.161517 -0.361517   0.361517  Lasso Regression (alpha=0.0005)\n",
-       "18   4.5   4.134825  0.365175   0.365175  Lasso Regression (alpha=0.0005)\n",
-       "19   4.2   4.279803 -0.079803   0.079803  Lasso Regression (alpha=0.0005)"
-      ],
-      "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>True</th>\n",
-       "      <th>Predicted</th>\n",
-       "      <th>Residual</th>\n",
-       "      <th>Abs_Error</th>\n",
-       "      <th>Model</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.306335</td>\n",
-       "      <td>-0.206335</td>\n",
-       "      <td>0.206335</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.287329</td>\n",
-       "      <td>-0.187329</td>\n",
-       "      <td>0.187329</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.297757</td>\n",
-       "      <td>0.102243</td>\n",
-       "      <td>0.102243</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.197993</td>\n",
-       "      <td>0.402007</td>\n",
-       "      <td>0.402007</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.371379</td>\n",
-       "      <td>0.128621</td>\n",
-       "      <td>0.128621</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>3.2</td>\n",
-       "      <td>4.304839</td>\n",
-       "      <td>-1.104839</td>\n",
-       "      <td>1.104839</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.324286</td>\n",
-       "      <td>-0.124286</td>\n",
-       "      <td>0.124286</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>3.9</td>\n",
-       "      <td>4.005045</td>\n",
-       "      <td>-0.105045</td>\n",
-       "      <td>0.105045</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>3.7</td>\n",
-       "      <td>4.138157</td>\n",
-       "      <td>-0.438157</td>\n",
-       "      <td>0.438157</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.312731</td>\n",
-       "      <td>0.287269</td>\n",
-       "      <td>0.287269</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.468202</td>\n",
-       "      <td>0.131798</td>\n",
-       "      <td>0.131798</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.364965</td>\n",
-       "      <td>0.135035</td>\n",
-       "      <td>0.135035</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.443139</td>\n",
-       "      <td>0.156861</td>\n",
-       "      <td>0.156861</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.289412</td>\n",
-       "      <td>0.110588</td>\n",
-       "      <td>0.110588</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>4.0</td>\n",
-       "      <td>4.302132</td>\n",
-       "      <td>-0.302132</td>\n",
-       "      <td>0.302132</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15</th>\n",
-       "      <td>4.3</td>\n",
-       "      <td>4.373179</td>\n",
-       "      <td>-0.073179</td>\n",
-       "      <td>0.073179</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>16</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.172033</td>\n",
-       "      <td>0.227967</td>\n",
-       "      <td>0.227967</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>3.8</td>\n",
-       "      <td>4.161517</td>\n",
-       "      <td>-0.361517</td>\n",
-       "      <td>0.361517</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.134825</td>\n",
-       "      <td>0.365175</td>\n",
-       "      <td>0.365175</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.279803</td>\n",
-       "      <td>-0.079803</td>\n",
-       "      <td>0.079803</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "execution_count": 105,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 105
-  },
-  {
-   "cell_type": "code",
-   "id": "7e02905489f7769d",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:44.069476700Z",
-     "start_time": "2026-04-26T14:56:44.023349500Z"
-    }
-   },
-   "source": [
-    "part_e_prediction_compare = pd.concat([\n",
-    "    pred_sheet_part_e_linear.head(8),\n",
-    "    pred_sheet_part_e_poly.head(8),\n",
-    "    pred_sheet_part_e_ridge.head(8),\n",
-    "    pred_sheet_part_e_lasso.head(8),\n",
-    "], ignore_index=True)\n",
-    "\n",
-    "part_e_prediction_compare"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "    True  Predicted  Residual  Abs_Error                            Model\n",
-       "0    4.1   4.299298 -0.199298   0.199298                Linear Regression\n",
-       "1    4.1   4.277702 -0.177702   0.177702                Linear Regression\n",
-       "2    4.4   4.314717  0.085283   0.085283                Linear Regression\n",
-       "3    4.6   4.189314  0.410686   0.410686                Linear Regression\n",
-       "4    4.5   4.376513  0.123487   0.123487                Linear Regression\n",
-       "5    3.2   4.317265 -1.117265   1.117265                Linear Regression\n",
-       "6    4.2   4.345980 -0.145980   0.145980                Linear Regression\n",
-       "7    3.9   4.000260 -0.100260   0.100260                Linear Regression\n",
-       "8    4.1   4.279363 -0.179363   0.179363            Polynomial Regression\n",
-       "9    4.1   4.292264 -0.192264   0.192264            Polynomial Regression\n",
-       "10   4.4   4.275074  0.124926   0.124926            Polynomial Regression\n",
-       "11   4.6   4.230751  0.369249   0.369249            Polynomial Regression\n",
-       "12   4.5   4.287948  0.212052   0.212052            Polynomial Regression\n",
-       "13   3.2   4.233728 -1.033728   1.033728            Polynomial Regression\n",
-       "14   4.2   4.233425 -0.033425   0.033425            Polynomial Regression\n",
-       "15   3.9   4.081532 -0.181532   0.181532            Polynomial Regression\n",
-       "16   4.1   4.290152 -0.190152   0.190152    Ridge Regression (alpha=50.0)\n",
-       "17   4.1   4.261329 -0.161329   0.161329    Ridge Regression (alpha=50.0)\n",
-       "18   4.4   4.250952  0.149048   0.149048    Ridge Regression (alpha=50.0)\n",
-       "19   4.6   4.245164  0.354836   0.354836    Ridge Regression (alpha=50.0)\n",
-       "20   4.5   4.254136  0.245864   0.245864    Ridge Regression (alpha=50.0)\n",
-       "21   3.2   4.237515 -1.037515   1.037515    Ridge Regression (alpha=50.0)\n",
-       "22   4.2   4.237951 -0.037951   0.037951    Ridge Regression (alpha=50.0)\n",
-       "23   3.9   4.262971 -0.362971   0.362971    Ridge Regression (alpha=50.0)\n",
-       "24   4.1   4.306335 -0.206335   0.206335  Lasso Regression (alpha=0.0005)\n",
-       "25   4.1   4.287329 -0.187329   0.187329  Lasso Regression (alpha=0.0005)\n",
-       "26   4.4   4.297757  0.102243   0.102243  Lasso Regression (alpha=0.0005)\n",
-       "27   4.6   4.197993  0.402007   0.402007  Lasso Regression (alpha=0.0005)\n",
-       "28   4.5   4.371379  0.128621   0.128621  Lasso Regression (alpha=0.0005)\n",
-       "29   3.2   4.304839 -1.104839   1.104839  Lasso Regression (alpha=0.0005)\n",
-       "30   4.2   4.324286 -0.124286   0.124286  Lasso Regression (alpha=0.0005)\n",
-       "31   3.9   4.005045 -0.105045   0.105045  Lasso Regression (alpha=0.0005)"
-      ],
-      "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>True</th>\n",
-       "      <th>Predicted</th>\n",
-       "      <th>Residual</th>\n",
-       "      <th>Abs_Error</th>\n",
-       "      <th>Model</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.299298</td>\n",
-       "      <td>-0.199298</td>\n",
-       "      <td>0.199298</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.277702</td>\n",
-       "      <td>-0.177702</td>\n",
-       "      <td>0.177702</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.314717</td>\n",
-       "      <td>0.085283</td>\n",
-       "      <td>0.085283</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.189314</td>\n",
-       "      <td>0.410686</td>\n",
-       "      <td>0.410686</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.376513</td>\n",
-       "      <td>0.123487</td>\n",
-       "      <td>0.123487</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>5</th>\n",
-       "      <td>3.2</td>\n",
-       "      <td>4.317265</td>\n",
-       "      <td>-1.117265</td>\n",
-       "      <td>1.117265</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>6</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.345980</td>\n",
-       "      <td>-0.145980</td>\n",
-       "      <td>0.145980</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>7</th>\n",
-       "      <td>3.9</td>\n",
-       "      <td>4.000260</td>\n",
-       "      <td>-0.100260</td>\n",
-       "      <td>0.100260</td>\n",
-       "      <td>Linear Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>8</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.279363</td>\n",
-       "      <td>-0.179363</td>\n",
-       "      <td>0.179363</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>9</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.292264</td>\n",
-       "      <td>-0.192264</td>\n",
-       "      <td>0.192264</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>10</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.275074</td>\n",
-       "      <td>0.124926</td>\n",
-       "      <td>0.124926</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>11</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.230751</td>\n",
-       "      <td>0.369249</td>\n",
-       "      <td>0.369249</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>12</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.287948</td>\n",
-       "      <td>0.212052</td>\n",
-       "      <td>0.212052</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>13</th>\n",
-       "      <td>3.2</td>\n",
-       "      <td>4.233728</td>\n",
-       "      <td>-1.033728</td>\n",
-       "      <td>1.033728</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>14</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.233425</td>\n",
-       "      <td>-0.033425</td>\n",
-       "      <td>0.033425</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>15</th>\n",
-       "      <td>3.9</td>\n",
-       "      <td>4.081532</td>\n",
-       "      <td>-0.181532</td>\n",
-       "      <td>0.181532</td>\n",
-       "      <td>Polynomial Regression</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>16</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.290152</td>\n",
-       "      <td>-0.190152</td>\n",
-       "      <td>0.190152</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>17</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.261329</td>\n",
-       "      <td>-0.161329</td>\n",
-       "      <td>0.161329</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>18</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.250952</td>\n",
-       "      <td>0.149048</td>\n",
-       "      <td>0.149048</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>19</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.245164</td>\n",
-       "      <td>0.354836</td>\n",
-       "      <td>0.354836</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>20</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.254136</td>\n",
-       "      <td>0.245864</td>\n",
-       "      <td>0.245864</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>21</th>\n",
-       "      <td>3.2</td>\n",
-       "      <td>4.237515</td>\n",
-       "      <td>-1.037515</td>\n",
-       "      <td>1.037515</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>22</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.237951</td>\n",
-       "      <td>-0.037951</td>\n",
-       "      <td>0.037951</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>23</th>\n",
-       "      <td>3.9</td>\n",
-       "      <td>4.262971</td>\n",
-       "      <td>-0.362971</td>\n",
-       "      <td>0.362971</td>\n",
-       "      <td>Ridge Regression (alpha=50.0)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>24</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.306335</td>\n",
-       "      <td>-0.206335</td>\n",
-       "      <td>0.206335</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>25</th>\n",
-       "      <td>4.1</td>\n",
-       "      <td>4.287329</td>\n",
-       "      <td>-0.187329</td>\n",
-       "      <td>0.187329</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>26</th>\n",
-       "      <td>4.4</td>\n",
-       "      <td>4.297757</td>\n",
-       "      <td>0.102243</td>\n",
-       "      <td>0.102243</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>27</th>\n",
-       "      <td>4.6</td>\n",
-       "      <td>4.197993</td>\n",
-       "      <td>0.402007</td>\n",
-       "      <td>0.402007</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>28</th>\n",
-       "      <td>4.5</td>\n",
-       "      <td>4.371379</td>\n",
-       "      <td>0.128621</td>\n",
-       "      <td>0.128621</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>29</th>\n",
-       "      <td>3.2</td>\n",
-       "      <td>4.304839</td>\n",
-       "      <td>-1.104839</td>\n",
-       "      <td>1.104839</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>30</th>\n",
-       "      <td>4.2</td>\n",
-       "      <td>4.324286</td>\n",
-       "      <td>-0.124286</td>\n",
-       "      <td>0.124286</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>31</th>\n",
-       "      <td>3.9</td>\n",
-       "      <td>4.005045</td>\n",
-       "      <td>-0.105045</td>\n",
-       "      <td>0.105045</td>\n",
-       "      <td>Lasso Regression (alpha=0.0005)</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "execution_count": 106,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "execution_count": 106
-  },
-  {
-   "cell_type": "code",
-   "id": "24cd7fb5c2d8d4b2",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:44.232721200Z",
-     "start_time": "2026-04-26T14:56:44.070477300Z"
-    }
-   },
-   "source": [
-    "results_melted = results_df.melt(\n",
-    "    id_vars='Model',\n",
-    "    value_vars=['MAE', 'MSE', 'RMSE', 'R2'],\n",
-    "    var_name='Metric',\n",
-    "    value_name='Score'\n",
-    ")\n",
-    "\n",
-    "plt.figure(figsize=(9, 5))\n",
-    "sns.barplot(data=results_melted, x='Model', y='Score', hue='Metric')\n",
-    "plt.title(\"Part E: Regression Model Comparison (MAE, RMSE, R2)\")\n",
-    "plt.xticks(rotation=15)\n",
-    "plt.tight_layout()\n",
-    "plt.show()"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Figure size 900x500 with 1 Axes>"
-      ],
-      "image/png": "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"
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 107
-  },
   {
    "cell_type": "markdown",
    "id": "e12551afcc108484",
@@ -3497,7 +2426,7 @@
    "source": [
     "### Part F Analysis\n",
     "\n",
-    "To find out which single input is the best at predicting the app rating, I trained three separate simple linear regression models using just one input at a time:\n",
+    "To find out which single input is the best at predicting the app rating, I trained two separate simple linear regression models using just one input at a time:\n",
     "- `Reviews` (number of reviews)\n",
     "- `Size in bytes` (app size)\n",
     "- `Numeric Installs` (install count)\n",
@@ -3505,7 +2434,9 @@
     "The bar chart above compares each model using **MAE**, **RMSE**, and **R²**. The feature with the lowest RMSE is our most predictive single input. \n",
     "I printed out the best feature in the code cell above.\n",
     "\n",
-    "Looking at the \"Actual vs Predicted\" scatter plot for the best single feature, you can see the typical spread you get when trying to guess the rating from just one piece of info. This is why using multiple inputs together (like in the previous part) generally gives much better predictions than relying on just one.\n"
+    "Looking at the \"Actual vs Predicted\" scatter plot for the best single feature, you can see the typical spread you get when trying to guess the rating from just one piece of info.\n",
+    "\n",
+    "This is why using multiple inputs together (like in the previous part) generally gives much better predictions than relying on just one.\n"
    ]
   },
   {
@@ -3858,156 +2789,6 @@
    ],
    "execution_count": 131
   },
-  {
-   "cell_type": "markdown",
-   "id": "636e6b9a053c8f8d",
-   "metadata": {},
-   "source": [
-    "# Trying Ridge Regression for Part G\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "id": "a31ad4ed704f4541",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:46.167539400Z",
-     "start_time": "2026-04-26T14:56:46.058071300Z"
-    }
-   },
-   "source": [
-    "best_ridge_alpha_g = None\n",
-    "best_ridge_cv_r2_g = float('-inf')\n",
-    "best_ridge_rmse_g = float('inf')\n",
-    "best_ridge_model_g = None\n",
-    "best_ridge_res_g = None\n",
-    "best_y_pred_ridge_g = None\n",
-    "best_cv_ridge_g = None\n",
-    "\n",
-    "for alpha in [0.1, 1.0, 10.0, 50.0, 100.0]:\n",
-    "    ridge_model_tmp = Ridge(alpha=alpha, solver='lsqr', random_state=seed)\n",
-    "    ridge_res_tmp, y_pred_tmp, cv_tmp = evaluate_model_cv(\n",
-    "        ridge_model_tmp, X_train_g, X_test_g, y_train_g, y_test_g, f\"Ridge Regression (alpha={alpha})\"\n",
-    "    )\n",
-    "\n",
-    "    if (ridge_res_tmp['CV R2 (mean)'] > best_ridge_cv_r2_g) or (\n",
-    "        ridge_res_tmp['CV R2 (mean)'] == best_ridge_cv_r2_g and ridge_res_tmp['RMSE (test)'] < best_ridge_rmse_g\n",
-    "    ):\n",
-    "        best_ridge_cv_r2_g = ridge_res_tmp['CV R2 (mean)']\n",
-    "        best_ridge_rmse_g = ridge_res_tmp['RMSE (test)']\n",
-    "        best_ridge_alpha_g = alpha\n",
-    "        best_ridge_model_g = ridge_model_tmp\n",
-    "        best_ridge_res_g = ridge_res_tmp\n",
-    "        best_y_pred_ridge_g = y_pred_tmp\n",
-    "        best_cv_ridge_g = cv_tmp\n",
-    "\n",
-    "display(pd.DataFrame([{\n",
-    "    'Selection': 'Part G Ridge best alpha by CV R2 mean then RMSE',\n",
-    "    'Best alpha': best_ridge_alpha_g,\n",
-    "    'CV R2 mean': best_ridge_cv_r2_g,\n",
-    "    'RMSE (test)': best_ridge_rmse_g\n",
-    "}]))\n",
-    "\n",
-    "ridge_model_g = best_ridge_model_g\n",
-    "ridge_res_g = best_ridge_res_g\n",
-    "y_pred_ridge_g = best_y_pred_ridge_g\n",
-    "cv_ridge_g = best_cv_ridge_g\n",
-    "\n",
-    "results_g.append(ridge_res_g)"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "                                         Selection  Best alpha  CV R2 mean  \\\n",
-       "0  Part G Ridge best alpha by CV R2 mean then RMSE         1.0    0.090846   \n",
-       "\n",
-       "    RMSE (test)  \n",
-       "0  2.162718e+07  "
-      ],
-      "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>Selection</th>\n",
-       "      <th>Best alpha</th>\n",
-       "      <th>CV R2 mean</th>\n",
-       "      <th>RMSE (test)</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Part G Ridge best alpha by CV R2 mean then RMSE</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.090846</td>\n",
-       "      <td>2.162718e+07</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 132
-  },
-  {
-   "cell_type": "code",
-   "id": "121ba346ffaea0e5",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2026-04-26T14:56:46.335645900Z",
-     "start_time": "2026-04-26T14:56:46.198104800Z"
-    }
-   },
-   "source": [
-    "plt.figure(figsize=(6, 6))\n",
-    "plt.scatter(y_test_g, y_pred_ridge_g, alpha=0.5)\n",
-    "plt.plot([y_test_g.min(), y_test_g.max()], [y_test_g.min(), y_test_g.max()], 'r--')\n",
-    "plt.title(\"Part G - Ridge Regression: Actual vs Predicted\")\n",
-    "plt.xlabel(\"True Size in Bytes\")\n",
-    "plt.ylabel(\"Predicted Size in Bytes\")\n",
-    "plt.tight_layout()\n",
-    "plt.show()"
-   ],
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Figure size 600x600 with 1 Axes>"
-      ],
-      "image/png": "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"
-     },
-     "metadata": {},
-     "output_type": "display_data",
-     "jetTransient": {
-      "display_id": null
-     }
-    }
-   ],
-   "execution_count": 133
-  },
   {
    "cell_type": "markdown",
    "id": "f238f4198de0c527",
@@ -4877,9 +3658,8 @@
     "Then, I used the test RMSE as a secondary check (lower is better).\n",
     "\n",
     "**What the results show:**\n",
-    "- Linear Regression is the strongest overall here: it has the best mean CV R² and the best test R², along with a lower test RMSE than Ridge. It's also way more stable than the polynomial model.\n",
+    "- Linear Regression is the strongest overall here: it has the best mean CV R² and the best test R², along with a low test RMSE. It's also way more stable than the polynomial model.\n",
     "- Polynomial Regression actually performs really poorly for this dataset (it got a negative test R² and a super unstable CV R²), meaning it's overcomplicating things and not generalizing well.\n",
-    "- Ridge Regression is more stable than the polynomial model, but it still underperforms compared to standard Linear Regression on both metrics.\n",
     "\n",
     "So, based on the cross-validation and test metrics, **Linear Regression is the best model for predicting `Size in bytes`**.\n",
     "\n",