{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "42267bba-a891-4f21-8c84-a549fb3de59d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd \n",
    "import torch \n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "48ab380a-2721-4646-9511-69d1513163eb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Index</th>\n",
       "      <th>Height(Inches)</th>\n",
       "      <th>Weight(Pounds)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>65.78331</td>\n",
       "      <td>112.9925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>71.51521</td>\n",
       "      <td>136.4873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>69.39874</td>\n",
       "      <td>153.0269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>68.21660</td>\n",
       "      <td>142.3354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>67.78781</td>\n",
       "      <td>144.2971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>96</td>\n",
       "      <td>70.55703</td>\n",
       "      <td>131.8001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>97</td>\n",
       "      <td>66.28644</td>\n",
       "      <td>120.0285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>98</td>\n",
       "      <td>63.42577</td>\n",
       "      <td>123.0972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>99</td>\n",
       "      <td>66.76711</td>\n",
       "      <td>128.1432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>100</td>\n",
       "      <td>68.88741</td>\n",
       "      <td>115.4759</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 3 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Index  Height(Inches)  Weight(Pounds)\n",
       "0          1        65.78331        112.9925\n",
       "1          2        71.51521        136.4873\n",
       "2          3        69.39874        153.0269\n",
       "3          4        68.21660        142.3354\n",
       "4          5        67.78781        144.2971\n",
       "..       ...             ...             ...\n",
       "95        96        70.55703        131.8001\n",
       "96        97        66.28644        120.0285\n",
       "97        98        63.42577        123.0972\n",
       "98        99        66.76711        128.1432\n",
       "99       100        68.88741        115.4759\n",
       "\n",
       "[100 rows x 3 columns]"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Input(Wieght)\n",
    "data = pd.read_csv(\"/Users/deepeshjha/Desktop/DSnML/weight.csv\",encoding='windows-1254', nrows=100)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8c8aef4d-25b3-41ae-8788-20f433fcdb49",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height(Inches)</th>\n",
       "      <th>Weight(Pounds)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65.78331</td>\n",
       "      <td>112.9925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>71.51521</td>\n",
       "      <td>136.4873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>69.39874</td>\n",
       "      <td>153.0269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>68.21660</td>\n",
       "      <td>142.3354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>67.78781</td>\n",
       "      <td>144.2971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>70.55703</td>\n",
       "      <td>131.8001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>66.28644</td>\n",
       "      <td>120.0285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>63.42577</td>\n",
       "      <td>123.0972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>66.76711</td>\n",
       "      <td>128.1432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>68.88741</td>\n",
       "      <td>115.4759</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Height(Inches)  Weight(Pounds)\n",
       "0         65.78331        112.9925\n",
       "1         71.51521        136.4873\n",
       "2         69.39874        153.0269\n",
       "3         68.21660        142.3354\n",
       "4         67.78781        144.2971\n",
       "..             ...             ...\n",
       "95        70.55703        131.8001\n",
       "96        66.28644        120.0285\n",
       "97        63.42577        123.0972\n",
       "98        66.76711        128.1432\n",
       "99        68.88741        115.4759\n",
       "\n",
       "[100 rows x 2 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.drop(columns='Index',axis=1,inplace=True)\n",
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "e36e2d2d-47f1-4670-a5da-07e45c1a8a5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x1473ecaa0>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAigAAAGdCAYAAAA44ojeAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/H5lhTAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA4OUlEQVR4nO3df3SU5Z3//9eEQKJIJgYbJqlEKVYlYqmCYLac3aJBA26sytriB6m1LBypsV1xlS/usZR1Wz7sutXqWqkej+w5oN11j6LoaVw0WtQNv5vdD8JaYFNBSGRLZELQhJC5v3/QmTLJTDL3/Ljv677n+Tgn55iZO5MruTHXe97X+3pfAcuyLAEAABikwO0BAAAA9EeAAgAAjEOAAgAAjEOAAgAAjEOAAgAAjEOAAgAAjEOAAgAAjEOAAgAAjFPo9gDSEYlEdPjwYY0aNUqBQMDt4QAAgBRYlqXjx4+rsrJSBQWD50g8GaAcPnxYY8eOdXsYAAAgDQcPHtT5558/6DWeDFBGjRol6fQPWFJS4vJoAABAKjo7OzV27NjYPD4YTwYo0WWdkpISAhQAADwmlfIMimQBAIBxCFAAAIBxCFAAAIBxCFAAAIBxCFAAAIBxCFAAAIBxCFAAAIBxCFAAAIBxPNmoDQCAVPVFLG1t7dCR490qH1WsqePKNKyAc9xMR4ACAPCtxl1tWrFht9rC3bHHKoLFWl5frbqJFS6ODENhiQcA4EuNu9q0eO3OuOBEktrD3Vq8dqcad7W5NDKkggAFAOA7fRFLKzbslpXguehjKzbsVl8k0RUwAQEKAMA4fRFLzfuP6pWWQ2ref9R2ILG1tWNA5uRMlqS2cLe2tnZkOFLkCjUoAACjZKNu5Mjx5MFJOtfBeWRQAADGyFbdSPmo4qxeB+cRoAAAjJDNupGp48pUESxWss3EAZ3OykwdV5bmaJFrBCgAACNks25kWEFAy+urJWlAkBL9fHl9Nf1QDEaAAgAwQrbrRuomVuip269UKBi/jBMKFuup26+kD4rhKJIFABghF3UjdRMrNLM6RCdZDyJAAQAYIVo30h7uTliHEtDp7IfdupFhBQHVjB+dlTHCOSzxAACMQN0IzkSAAgAwBnUjiGKJBwBgFOpGIBGgAAAMRN0IWOIBAADGIYMCAJB0upMryyowBQEKACArB/QB2cQSDwDkuWwd0AdkEwEKAOSxbB7QB2QTAQoA5LFsHtAHZBMBCgDksWwf0AdkCwEKAOSxXBzQB2QDAQoA5LHoAX3JNhMHdHo3j90D+oBMEaAAQB7jgD6YigAFAPIcB/TBRDRqAwBwQB+MQ4ACAJDEAX0wC0s8AADAOAQoAADAOAQoAADAOAQoAADAOAQoAADAOAQoAADAOLYDlE2bNqm+vl6VlZUKBAJav3593PPf+c53FAgE4j7q6uriruno6NC8efNUUlKi0tJSLViwQF1dXRn9IAAAwD9sBygnTpzQpEmT9OSTTya9pq6uTm1tbbGPF154Ie75efPm6YMPPtDGjRv12muvadOmTVq0aJH90QMAAF+y3aht1qxZmjVr1qDXFBUVKRQKJXxuz549amxs1LZt2zRlyhRJ0hNPPKHZs2frkUceUWVlpd0hAQAAn8lJDco777yj8vJyXXLJJVq8eLGOHj0ae665uVmlpaWx4ESSamtrVVBQoC1btuRiOAAAwGOy3uq+rq5Ot9xyi8aNG6f9+/frwQcf1KxZs9Tc3Kxhw4apvb1d5eXl8YMoLFRZWZna29sTvmZPT496enpin3d2dmZ72AAAwCBZD1Dmzp0b++/LL79cX/nKVzR+/Hi98847uvbaa9N6zZUrV2rFihXZGiIAADBczrcZf+lLX9J5552nffv2SZJCoZCOHDkSd82pU6fU0dGRtG5l2bJlCofDsY+DBw/metgAAMBFOQ9QPv74Yx09elQVFRWSpJqaGh07dkw7duyIXdPU1KRIJKJp06YlfI2ioiKVlJTEfQAAAP+yvcTT1dUVy4ZIUmtrq1paWlRWVqaysjKtWLFCc+bMUSgU0v79+/XAAw/ooosu0vXXXy9JmjBhgurq6rRw4UKtXr1avb29amho0Ny5c9nBAwAAJEkBy7IsO1/wzjvvaMaMGQMev+OOO/TUU0/ppptu0m9+8xsdO3ZMlZWVuu666/Twww9rzJgxsWs7OjrU0NCgDRs2qKCgQHPmzNHjjz+uc845J6UxdHZ2KhgMKhwOk00BAMAj7MzftgMUExCgAADgPXbmb87iAQAAxsn6NmMAAHKpL2Jpa2uHjhzvVvmoYk0dV6ZhBQG3h4UsI0ABAHhG4642rdiwW23h7thjFcFiLa+vVt3EChdHhmxjiQcA4AmNu9q0eO3OuOBEktrD3Vq8dqcad7W5NDLkAgEKAMB4fRFLKzbsVqJdHdHHVmzYrb6I5/Z9IAkCFACA8ba2dgzInJzJktQW7tbW1g7nBoWcogYFAOAKO8WuR44nD07SuQ7mI0ABADjObrFr+ajilF431etgPpZ4AACOSqfYdeq4MlUEi5VsM3FApwOcqePKsj9guIIABQDgmHSLXYcVBLS8vlqSBgQp0c+X11fTD8VHCFAAAI7JpNi1bmKFnrr9SoWC8cs4oWCxnrr9Svqg+Aw1KAAAx2Ra7Fo3sUIzq0N0ks0DBCgAAMdko9h1WEFANeNHZ2tIMBRLPAAAx1DsilQRoAB5pi9iqXn/Ub3SckjN+4/SeROOotgVqWKJB8gjHLQGE0SLXfv/WwzxbxFnCFiW5bm3T52dnQoGgwqHwyopKXF7OIAnRHtP9P8fPvo+lV0QcJqdTrLwBzvzNxkUIA8M1XsioNO9J2ZWh5gg4BiKXTEYalCAPMBBawC8hgAFyAMctAbAawhQgDzAQWsAvIYABcgD9J4A4DUEKEAe8FvvCXq5AP7HLh4gT/il9wS9XID8QB8UIM94ufcEvVwAb6MPCoCkvNp7gl4uQH4hQAHgCXZ6uXgxAEvEy9mu/vz0s8AZBCgAPCHfern4qdbGTz8LnMMuHgCekE+9XKK1Nv0zRu3hbi1eu1ONu9pcGpl9fvpZ4CwCFACe4IdeLqlsjx6q1kY6XWvjha3VfvpZ4DyWeAB4QrSXy+K1OxWQ4iY9L/RySXWZw0+1Nn76WeA8MigAPCPayyUUjF/GCQWLjd5ibGeZw0+1Nn76WeA8MigAPKVuYoVmVoc8syPE7vbodGptTN0hk091Q8g+AhQAnpPLXi7ZnuztLnNEa23aw90Jg5qATmeMorU2Ju+QsfuzeJWpAaLXEaAAwB/kYrK3u8xhp9YmWWfd6NKR28teXq8bSoXJAaLXUYMCAMrddth0ljlSqbXxyg4Zr9YNpYIt1LlFBgXwOa+ln90Yby7b6Ke7zDFUrY2Xdsh4rW4oFRy9kHsEKICPeS397NZ4cznZZ7LMMVitjdd2yHj1DKhkvBQgehVLPIBPeS397OZ4cz3Z52KZw0s7ZFJpUGfy6yfitQDRi8igAD7ktfRzuuPN1nKQE5N9tpc5vLJDJtdZMbeybl4KEL2KDArgQ3bSzyZIZ7yNu9o0fVWTbntms37wyxbd9sxmTV/VlFamxak2+tFljm989YuqGT86o+AwunQUHd+ZTNkhk+usmJtZNz8cvWA6AhTAh0xIP9tJu9sdb7YnJi9M9omYvEMm17uM3N7F5NV/M17CEg/gQ26nn+2m3e2MN1fLV9HJvv+4QwYXFUvm7pDJdRGpCUWqXv034xUEKIAPuVmfkE7zMDvjzeXEZOpkPxQTd8jkOotnQpZQMu/fjNfaCgyGAAXwIbc6eKab3bAz3lxPTCZO9l6Ualbs98d79ErLIduTqdtZwjOZ8m/Ga20FhkINCuBTbtQnZFKcm+p4TZqYkNxQRaSSVBCQHn59T1pFzhSpxvNaW4FUkEEBfMzp9HOm2Y1UxuuV7bX5brCsWFT/+lU7Zwjlwzk/qcp2XZYpy0S2MyibNm1SfX29KisrFQgEtH79+qTX3nXXXQoEAnrsscfiHu/o6NC8efNUUlKi0tJSLViwQF1dXXaHAiAF2dzaOpRsZDeGGi+7J7wjWVYs2a2xu/vG5F1MQ8lmc7lsthXI5vb9TNnOoJw4cUKTJk3Sd7/7Xd1yyy1Jr3v55Ze1efNmVVZWDnhu3rx5amtr08aNG9Xb26s777xTixYt0vPPP293OAAM4lR2g90TZhnsHXf/rNjvj/fo4df3JH0tu0XOphWppiLbtSLZqssy7XRs2wHKrFmzNGvWrEGvOXTokO655x698cYbuuGGG+Ke27NnjxobG7Vt2zZNmTJFkvTEE09o9uzZeuSRRxIGNAC8wcm0uxcnJj9KZbI9s4j0lZZDKb2unSJnU4pUU5GLICAbmUsTu09nvUg2Eolo/vz5uv/++3XZZZcNeL65uVmlpaWx4ESSamtrVVBQoC1btmR7OAAc5mTa3cnlKy9x6myadAoz87nIOVfN5bJRMGxi9+msF8muWrVKhYWF+v73v5/w+fb2dpWXl8cPorBQZWVlam9vT/g1PT096unpiX3e2dmZvQEDyDqyG+5xaqtpuu+487nIOVc9fLKRuTSlr8yZsppB2bFjh372s59pzZo1CgSy94do5cqVCgaDsY+xY8dm7bUB5AbZDec5udU03Xfc+VzknMsgINPMpYmZraxmUN59910dOXJEVVVVscf6+vp033336bHHHtPvfvc7hUIhHTlyJO7rTp06pY6ODoVCoYSvu2zZMi1ZsiT2eWdnJ0EKAJzB6RqCTCbbfC1yznUQkEnm0sTMVlYDlPnz56u2tjbuseuvv17z58/XnXfeKUmqqanRsWPHtGPHDk2ePFmS1NTUpEgkomnTpiV83aKiIhUVFWVzqADgK06fTZPpZJuPy4BOBAHpFgyb2FfGdoDS1dWlffv2xT5vbW1VS0uLysrKVFVVpdGj438xw4cPVygU0iWXXCJJmjBhgurq6rRw4UKtXr1avb29amho0Ny5c9nBA8BopjSwSsTpGoJsTLZe2n2TDSYGAWcyLbNlO0DZvn27ZsyYEfs8uvRyxx13aM2aNSm9xrp169TQ0KBrr71WBQUFmjNnjh5//HG7QwEAx5h+zonTNQSmT7amMi0I6M+kzFbAsqzc7D/Loc7OTgWDQYXDYZWUlLg9HAA+l6x3RfRPtgldS/silqavahoyo/He0muyOtmYHriZyuRsXC7Zmb8JUABgENGJP1l9R64m/nREAykpcUYjV4FUvk62sM/O/M1pxgAwCBMbWCXj1tk0bCnPPqea7ZmM04wBYBAmNrAajEk1BEgPy2anEaAAwCBMbGAlDb6skm+7Y/zEtAP73ESAAsCXslUXYWIDK95h+5OJB/a5iQAFgO9kcwI3bTst77D9y+lme6ajSBaAr+TiPBq3ik/7y9VpuDCD1+qdco0MCgDfyGWK3ITiU95h+5up9U5uIUAB4Bu5nsDdLj7lHba/mVjv5CaWeAD4ht0J3Gu9JvLhHbbX7kk2ReudpD/WN0XZqXfyy++QDAoA37AzgXtxJ4zf32GbcE/c7oqb6Vk9JvwOs4VW9wB8I9XzaB66oVp3P2/22TrJuNXOPtdMOO/IpMk9nUDJhN/hUGh1DyAvpZIif+iGCXr4de/uhDFlR1E2mbA7KRe7vzJh9/gAE36H2cYSDwBfGSpFHjxrhOd3wpiwoyib3N6d5IcGaW7/DnOBAAWA7ww2gb/Sciil1zB9J4zbO4qyye3dSX6Y3N3+HeYCAQoAX0o2gefDThivcfue+GFyd/t3mAvUoADIK9GdMMkS9QGdLoz06k4YL3L7nqQ7uZu0ndft32EuEKAAyCvZ6jWB7HH7nqQzuTfuatP0VU267ZnN+sEvW3TbM5s1fVWT48W0UW7/DnOBAAVA3vHrThhT3s2nw817YndyN23HT5Tf/l3TBwVA3nK7KVe2mNS/I1Nu3pNUfo/RXjvJimqjvXbeW3qNa/+WTP53bWf+JkABAAfkatLwQnMuLxnqPjXvP6rbntk85Ou8sPBqY3f8uMnO/M0uHgDIsVxlOPzQv8M0Q23f9sOOH6+gBgUAciiX9Qp2+ncgO/y4nddUBCgAkCO5bj/Ou3nnDbXjR5JCJUWe2s5rKgIUAK7x+s6ToeQ6w8G7eecNtuMnqvtURBt3tzs3KJ+iBgWAK/y08ySZXGc4ou/mhzq9mXfz2RXdzvv/vfT/dOyz3gHPhz/r1eK1OylQzhAZFACOM7WPRLblOsPhx+ZcZzI5wzazOqTiwmEJn/Pq6cGmIYMCwFH5tPPEiQzHUKc3e/UdvOkZtq2tHWrv9PYBg6YjQAHgKD+cHJuqaIZj8dqdCkhxQUo2MxyDnd7sRcl6u0QzbCYsnVCgnHss8cDzTE4DY6B8+8PuVPvxaP+Ob3z1i6oZP9qzwUmudz5lCwXKuUcGBZ5mehoYA+XjH3a/ZThyySsZNgqUc48MCjwrXwot/Sadk2P9kCXzS4Yj17ySYfN7gbIJyKDAk/Kp0NJv7NZlkCXLL17KsPm1QNkUBCjwJK+kgZFYqn/YvVAsiezy2tIJy3e5Q4ACT/JKGhjJDfWHnSxZfnJq51M2DXXAINJDDQo8yUtpYCQ3WF0GB+HlL6d2PsFsZFDgSV5LA8M+smT5zemlk76IxTKNYQhQ4EleTAPDHrJkiGbYosHDa/91OCfBA4XYZiJAgWdRQe9dqbxbdStLxjtps+Q6eKAQ21wBy7I811Cgs7NTwWBQ4XBYJSUlbg8HLmNC8RY7E0508pASZ8n+qvZiXXje2Vm777yTNkuy4CF6lzMNHvoilqavakpa6xQNgt9beg1/U7LEzvxNgALAMelMOImChnPPHi5LijvqPtNAIteTIexxInho3n9Utz2zecjrXlh4Nbt0ssTO/M0uHgCOSPeMlbqJFXpv6TV6YeHV+tncr+re2i/r089644ITKbMOwl45/yWfOLGLi0JssxGgAHBEJhNOtFjyz79SqV9uO5j066X0Agm2NJvHieCBQmyzEaAAcEQ2JpxcBRK8kzaPE8FDOudCwTkEKAAckY0JJ1eBBO+kzeNE8MCBf2YjQAHgiGxMOLkKJHgnbR6ngge61pqLPigAHJGN5nq56o1C4z8zOdXriAP/zGQ7g7Jp0ybV19ersrJSgUBA69evj3v+Rz/6kS699FKNHDlS5557rmpra7Vly5a4azo6OjRv3jyVlJSotLRUCxYsUFdXV0Y/CADzZfpuNZfvqnknbab+u7heWHi13lt6Tdbvx2DnQsEdtvug/OpXv9L777+vyZMn65ZbbtHLL7+sm266Kfb8888/r/Lycn3pS1/S559/rkcffVQvvvii9u3bpy984QuSpFmzZqmtrU2/+MUv1NvbqzvvvFNXXXWVnn/++ZTGQB8UwF2ZNsfL9Otz2VCt/9gmX3Cudnz0Ke+sgSxwrFFbIBAYEKAkG8ybb76pa6+9Vnv27FF1dbW2bdumKVOmSJIaGxs1e/Zsffzxx6qsrBzy+xKgwO9M7o5rSrdVJ35HQ/2sJt8nwER25u+c1qCcPHlSTz/9tILBoCZNmiRJam5uVmlpaSw4kaTa2loVFBRoy5Ytuvnmm3M5JHhEPv/hNyUASMSkc0uiKflcGepnXfSn4/Tqf7YZeZ8AP8hJgPLaa69p7ty5+uyzz1RRUaGNGzfqvPPOkyS1t7ervLw8fhCFhSorK1N7e3vC1+vp6VFPT0/s887OzlwMG4YweYLONZMCgP6G6rYa0OkmaTOrQ54PJlPpLPuLTa0DnjPhPgF+kZNtxjNmzFBLS4v+4z/+Q3V1dfrmN7+pI0eOpP16K1euVDAYjH2MHTs2i6OFSaITdP9mXJm0MfcK09ut51O31aF+1mRMuE+J9EUsNe8/qldaDql5/1GjxgYkk5MAZeTIkbrooot09dVX69lnn1VhYaGeffZZSVIoFBoQrJw6dUodHR0KhUIJX2/ZsmUKh8Oxj4MHE7e6hreZPkFnw2AThQkBwGDjy6duq5n8DKYFao272jR9VZNue2azfvDLFt32zGZNX9Xk62Af/uBIH5RIJBJboqmpqdGxY8e0Y8cOTZ48WZLU1NSkSCSiadOmJfz6oqIiFRUVOTFUuMjOBO3Fk0WHWrpyOwAYanz51G01Gz9DsvvkZH2VyUuGwFBsByhdXV3at29f7PPW1la1tLSorKxMo0eP1o9//GPdeOONqqio0O9//3s9+eSTOnTokG699VZJ0oQJE1RXV6eFCxdq9erV6u3tVUNDg+bOnZvSDh74l9sTdC6lMlGkOin+7vefuTK+mdWhnDRJM9HkC85V2cjh6jjRO/TFSSS6n07WV6WakfRDzRD8yfYSz/bt23XFFVfoiiuukCQtWbJEV1xxhX74wx9q2LBh+u///m/NmTNHF198serr63X06FG9++67uuyyy2KvsW7dOl166aW69tprNXv2bE2fPl1PP/109n4qeJJf36GnOlFMvuDcQdutRz325m+zmp5PdXyS8uLcksZdbfqzf3g7aXAy1E+XrC2+0/VVqdTRmLQUBfRnO4Py9a9/XYO1TnnppZeGfI2ysrKUm7Ihf+SqjbnbUl262vHRp1peX6271u4c8jVTeeeb6lKCnaU1p1qPuyVZJulMoWCxbpxUoaf/sIsnlbb4buyAau9MLdOY6nWA0ziLB8bw63kodpauvvHVL+re2i/r0Tf3Jr0uGjBs/p+j+tpF5yW8xs5Sgt2lNb+eWzJYEBE1euQI/fr+GRpRWKArqs5NOVBzo76qo6tn6ItsXAc4jQAFRvHjO3S7S1cXnjcypevvXrdT/3fO5QN+J3YLI9NZWst1kzQ3pLIkcvTESe346FPVjB9tK1Bzo76qbOSIrF4HOI0ABcbx2zt0u0tXqQYMxz7vHRBwpLOU4NelNbvSCSJSDdTcqK8KBc/K6nWA03LSBwXIlJ9OFrV7Am80YEj1Jz6zN0w6vVRyeUKwl+QyiBjqniYrrM1E9HsOJtvfE8gmAhTAAdGlq1C/CSMULB6w5BINGFJpR9c/4Eh3KcHO+Pwql0GEG0Fg9HsO9vPkQ+AJ72KJB3BILpeuogFHJlkAvy2t2ZXrIm036quSfc98OdsK3hawBtszbCg7xzUDXtMXsTR9VZOts2BeWHi1asaPjn3tUPUk7y29Jm8CD7ty3UzNjZO68/l0cJjFzvxNBgUwjJ2D6voXsPp1q7aTcp1JcmMHlB93XcH/CFAAw9jdato/4PDjVm2nMaED7iNAAQyTah3J6JEj9OObJyYMOPK9ngSA9xGgAIYZqi+JJJWNHK7mZddqRGHyjXhuZQGodwCQDQQogGFSqSP5yc2XDxqcuMXJ03oB+Jt5f+EAeLIvidOn9QLwNzIogKG8VEfixmm9LCUB/kaAAhjMK7tJnD6t18mlJAIhwB0EKAAy5uRpvXZPa870e1FT4w0Ekv5DgAIgY06d1uvkUpKTgRAyQyDpTxTJAsiYU6f1pnNaczqGCoSk+FOk4R6Ks/2LAAWu64tYat5/VK+0HFLz/qP80fcgp07rdWopyalACJkhkPQ3lnjgKlKz/pGsxX7wrOG682sXamZ1KOPv4dRSkpM1NUif08XZcBYZFLiG1Kz/1E2s0HtLr9G9tRer9KzhkqRjn/fq0Tf3avqqpozvqVNLSU4FQsgMgaS/EaDAFaRm/Wvj7nY99uZvdezz3rjHsxF4OrWUlK1AiOXL3CKQ9DcCFLiCNX5/ciLwdKLLbjYCocZdbZq+qkm3PbNZP/hli257ZnNWskj4I6cyanAHNShwBalZb0m1x4RTNQFOdNlNVlMTSqFGii3Kzkjl3KpsZNTgDgIUuILUrHfYKWR2MvB0ostuOoGQG23/81kmgSTMRoACV0RTs+3h7oR/yAM6/QeG1Ky77GYC/Bh42g2E2FniPC+dW4XUUYMCV6S7xk/RoXPSqSehJoDlS7dEA8lvfPWLqhk/muDEBwhQ4Bq7xY4UHTornUJmp3bZmCzV7NDvj/cQaAODYIkHrko1NUvRofPSzQTke03AUMuXklQQkB5+fU/sc5oTAgMRoJyB0zDdMdQaP0WH7sikniSfawIG21kS1T9hQqANDESA8ge0XDcXRYfuyLSQ2YldNqZKlkUqCAwMTiQCbSARalBEy3XTUXToDupJMhNt+//Cwqv1s7lf1UM3TEgYnETRnBCIl/cBCi3XzefHrateUTexQk/+nyt17sgRcY9ns2trKry6e+vMnSXnjSpK6WsItIHT8n6Jh+UD89EzxT2Nu9r08Ou71XHiZOyxspHD9dANExwLTvyy/EqgDdiT9xkUlg/Mx1KDO5ItfX56old3P/8bR5Y+/bT8So8YwJ68D1B4V+MNThwQ5zeZLIuYsPRpwhiyiUAbsCfvl3hYPvCOfN66alemyyImLH2aMIZsy/ceMYAdeR+gcBqmt+Tz1tVUZaOpnQlLnyaMIRcItIHU5P0Sj8TyAfwjW8siJix9mjCGXOHcGGBoeZ9BieJdDfwgW8siJix9Tr7gXJWNHBG3g8jpMQBwDwHKGVg+gNdla1nE7aXPaA3NYMFJrscAc3EsSX4gQAF8JJvLIm4VdCaroTkTRaX5yy99cTA0AhTgD/zwrizbSzNOL30OVkMTVTZyuH59/wyNKKSELt9wqnl+IUAB5J93ZblYmnFy6XOoGhpJ6jjRqx0ffcpybJ7hVPP8w1sQ5D0/dSuVTmc9Fv3pOAX6/Y0OBKRFfzrO6IDLr1uLkTk7BeDwBwIU5DUTupVm+yC8xl1tenpT64CTcyOW9PSmVqMDLj9vLUZmCF7zD0s8yGtudCs9s9bld78/oRe2HlB7Z0/s+UyWllKp4TA5DW7C9maYieA1/9jOoGzatEn19fWqrKxUIBDQ+vXrY8/19vZq6dKluvzyyzVy5EhVVlbq29/+tg4fPhz3Gh0dHZo3b55KSkpUWlqqBQsWqKurK+MfBrDL6XdljbvaNH1Vk257ZrN+8MsWPfrm3rjgRMpsacnraXDOq0EyHLaYf2wHKCdOnNCkSZP05JNPDnjus88+086dO/XQQw9p586deumll/Thhx/qxhtvjLtu3rx5+uCDD7Rx40a99tpr2rRpkxYtWpT+TwGkycl3ZclqXfrLZGnJD2lwOjsjEYLX/GN7iWfWrFmaNWtWwueCwaA2btwY99g//dM/aerUqTpw4ICqqqq0Z88eNTY2atu2bZoyZYok6YknntDs2bP1yCOPqLKyMo0fA0iPU0sKqSy9nCndpSW/pMHp7IxEOGwxv+S8BiUcDisQCKi0tFSS1NzcrNLS0lhwIkm1tbUqKCjQli1bdPPNNw94jZ6eHvX0/DEN3tnZmethI0841TE1le2zidjNdPiphoPOzkiE4DV/5HQXT3d3t5YuXarbbrtNJSUlkqT29naVl5fHXVdYWKiysjK1t7cnfJ2VK1cqGAzGPsaOHZvLYSPPOLGkkO6Sit1MB2lw5AMOW8wPOcug9Pb26pvf/KYsy9JTTz2V0WstW7ZMS5YsiX3e2dlJkIKsyvW7snSWVM49e3hamQ7S4AD8ICcBSjQ4+eijj9TU1BTLnkhSKBTSkSNH4q4/deqUOjo6FAqFEr5eUVGRioqKcjFUICaXSwpDLb0kkkk3FNLgALwu60s80eBk7969evPNNzV6dPwf/JqaGh07dkw7duyIPdbU1KRIJKJp06ZleziAEQZbeknm2Ge9GW0HJg0OwMtsByhdXV1qaWlRS0uLJKm1tVUtLS06cOCAent79Rd/8Rfavn271q1bp76+PrW3t6u9vV0nT54+Nn3ChAmqq6vTwoULtXXrVr3//vtqaGjQ3Llz2cEDX0tW6zIYk7cDA0AuBSzLspVJfueddzRjxowBj99xxx360Y9+pHHjxiX8urfffltf//rXJZ1u1NbQ0KANGzaooKBAc+bM0eOPP65zzjknpTF0dnYqGAwqHA7HLR8BXtAXsbTm/VY9/PqeIa99YeHV7GQB4Bt25m/bAYoJCFDgdX0RS9NXNQ25Hfi9pdewNAPAN+zM3xwWCLiA7cAAMDgCFMAltHQHgOQ4zRhwEduBASAxAhTAZbR0B4CBWOIBAADGIUABAADGIUABAADGoQYFgNH6IhZFxEAeIkABYKzGXW0DTmWu4FRmIC+wxAPASI272rR47c644ESS2sPdWrx2pxp3tbk0MgBOIEABYJy+iKUVG3YnPAYg+tiKDbvVF/HcSR0AUkSAAsA4W1s7BmROzmRJagt3a2trR07H0Rex1Lz/qF5pOaTm/UcJiAAHUYMCwDhHjicPTtK5Lh3UvwDuIoMCwDjlo4qHvsjGdXZ5tf6FjA/8hAwKAONMHVemimCx2sPdCetQAjp9qOLUcWVZ/95D1b8EdLr+ZWZ1yKjtzqZkfNgWjmwhQAFgnGEFAS2vr9bitTsVkOKChehUt7y+OicTn536FyfOUEplwo9mfPoHVdGMj1OnY5sSJMEfCFAAGKluYoWeuv3KARNeKMcTngn1L1GpTPimZHxMCZLgHwQoAIxVN7FCM6tDji4ZuF3/EpXqhG9CxseUIAn+QpEsAKMNKwioZvxofeOrX1TN+NE5n+Ci9S/JvktAp7MYuah/ibLTB8aEjI8p28LhLwQoAHCGaP2LpAFBSq7rX6LsTPgmZHxMCJLgPwQoANBPtP4lFIyf1EPBYkdqKexM+CZkfEwIkuA/1KAAQAJu1L9E2Znw3dzxFOXmtnD4FxkUAEYxqdmY0/UvUXazIm5nfExYFoP/BCzL8lyrwc7OTgWDQYXDYZWUlLg9HABZQh+NP4ru4pESZ0USBR5uN0nj/mEoduZvAhR4ltt/jJFdybbVDjYh+50XJ3z+v8RgCFDge178w43k+iKWpq9qSrpzJVrD8N7Sa/JusmPCh5/Ymb+pQYHnePUgNyRHH43k3KqDAdxGgAJPsdPACt5BHw0A/RGgwFN4p+1P9NEA0B99UOApuXqnzTq/u+ijAaA/AhR4Si7eaVNw6z4Tmo0BMAtLPPCUbLf1puDWHG43GwNgFjIo8JRsvtPmiHjzuNleHoBZyKDAc7L1TpuCWzNlsq3WpDb5ADJDBgWelI132mxt9RdqiZKjCBxeRIACz4q+004XW1v9I1mb/GgtUT7XsBC4watY4kHeynbBLdxB877kKAKHlxGgIG9xRLw/UEuUGIEbvI4ABXmNra3eRy1RYgRu8DpqUJD32NrqbdQSJUbgBq8jQAGUecEt3EOb/MQI3OB1LPEA8DRqiRKjCBxeR4ACwPOoJRqIwA1eF7Asy3Ml3J2dnQoGgwqHwyopKXF7OAAMQUOygeiDApPYmb8JUADA5wjcYAo78zdFsgDgcxSBw4uoQQEAAMaxHaBs2rRJ9fX1qqysVCAQ0Pr16+Oef+mll3Tddddp9OjRCgQCamlpGfAa3d3duvvuuzV69Gidc845mjNnjj755JN0fwYAAOAztgOUEydOaNKkSXryySeTPj99+nStWrUq6Wvce++92rBhg1588UX9+te/1uHDh3XLLbfYHQoAAPAp2zUos2bN0qxZs5I+P3/+fEnS7373u4TPh8NhPfvss3r++ed1zTXXSJKee+45TZgwQZs3b9bVV19td0gAkDUUlAJmcLxIdseOHert7VVtbW3ssUsvvVRVVVVqbm5OGKD09PSop6cn9nlnZ6cjYwWQX9iSC5jD8SLZ9vZ2jRgxQqWlpXGPjxkzRu3t7Qm/ZuXKlQoGg7GPsWPHOjBSAPmkcVebFq/dOeCAvfZwtxav3anGXW0ujQzIT57YxbNs2TKFw+HYx8GDB90eEgAf6YtYWrFhd8KzfKKPrdiwW30Rz7WNAjzL8QAlFArp5MmTOnbsWNzjn3zyiUKhUMKvKSoqUklJSdwHAGTL1taOAZmTM1mS2sLd2tra4dyggDzneIAyefJkDR8+XG+99VbssQ8//FAHDhxQTU2N08MBAB05njw4Sec6AJmzXSTb1dWlffv2xT5vbW1VS0uLysrKVFVVpY6ODh04cECHDx+WdDr4kE5nTkKhkILBoBYsWKAlS5aorKxMJSUluueee1RTU8MOHgCuKB9VPPRFNq4DkDnbAcr27ds1Y8aM2OdLliyRJN1xxx1as2aNXn31Vd15552x5+fOnStJWr58uX70ox9Jkh599FEVFBRozpw56unp0fXXX6+f//znmfwcgK+x9TW3po4rU0WwWO3h7oR1KAGdPhl56rgyp4cG5C0OCwQMx9ZXZ0R38UiKC1KiYeBTt1/J7xvIkJ352xO7eIB8xdZX59RNrNBTt1+pUDB+GScULCY4AVzAacaAoYba+hrQ6a2vM6tDLPdkSd3ECs2sDrGcBhiAAAUwlJ2trzXjRzs3MJ8bVhDg9wkYgCUewFBsfQWQzwhQAEOx9RVAPiNAAQwV3fqarPohoNO7edj6CsCPCFAAQw0rCGh5fbUkDQhSop8vr6+mgBOALxGgGKYvYql5/1G90nJIzfuPcjhZnmPrK4B8xS4eg9CQC4mw9RVAPqKTrCGiDbn63wy6WJqFlvMAkD478zcZFAPQkMsbyHABgHOoQTGAnYZccAct5wHAWQQoBqAhl9mGynBJpzNcFDQDQPYQoBiAhlxmI8MFAM4jQDEADbnMRoYLAJxHgGIAGnKZjQwXADiPAMUQNOQyFxkuAHAe24wNQkMuM0UzXIvX7lRAiiuWJcMFALlBozYgRfRBAYDM0KgNyAEyXADgHAIUwIZhBQHVjB/t9jAAwPcokgUAAMYhQAEAAMYhQAEAAMYhQAEAAMYhQAEAAMZhFw+AtPRFLLZcA8gZAhQAttG0Lv8QkMJpBCgAbGnc1abFa3eqfwvq9nC3Fq/dydlRPkRACjdQgwIgZX0RSys27B4QnEh/PKNoxYbd6ot47gQNJBENSM8MTqQ/BqSNu9pcGhn8jgDFB/oilpr3H9UrLYfUvP8okwNyZmtrx4CJ6kyWpLZwt7a2djg3KOQMASncxBKPx5F6hZOOHE8enKRzHcxmJyDlCAhkGxkUDyP1CqeVjyrO6nUwGwEp3ESA4lGkXuGGqePKVBEsVrK9GwGdzuBNHVfm5LCQIwSkcBMBikdRCwA3DCsIaHl9tSQNCFKiny+vr2b7qU8QkMJNBCgeReoVbqmbWKGnbr9SoWD8u+ZQsJgtxj5DQAo3USTrUaRe4aa6iRWaWR2icVceiAak/YvxQxTjI8cIUDwqmnptD3cnrEMJ6PQfEFKvyJVhBQF2buQJAlK4gQDFo6Kp18VrdyogxQUppF4BZBsBKZxGDYqHUQsAAPArMigeR+oVAOBHBCg+QOoVAOA3LPEAAADjEKAAAADjEKAAAADjEKAAAADjEKAAAADj2A5QNm3apPr6elVWVioQCGj9+vVxz1uWpR/+8IeqqKjQWWedpdraWu3duzfumo6ODs2bN08lJSUqLS3VggUL1NXVldEPAgAA/MN2gHLixAlNmjRJTz75ZMLn//7v/16PP/64Vq9erS1btmjkyJG6/vrr1d39xzMc5s2bpw8++EAbN27Ua6+9pk2bNmnRokXp/xQAAMBXApZlJTrKJbUvDgT08ssv66abbpJ0OntSWVmp++67T3/9138tSQqHwxozZozWrFmjuXPnas+ePaqurta2bds0ZcoUSVJjY6Nmz56tjz/+WJWVlUN+387OTgWDQYXDYZWUlKQ7fAAA4CA783dWa1BaW1vV3t6u2tra2GPBYFDTpk1Tc3OzJKm5uVmlpaWx4ESSamtrVVBQoC1btiR83Z6eHnV2dsZ9AAAA/8pqgNLe3i5JGjNmTNzjY8aMiT3X3t6u8vLyuOcLCwtVVlYWu6a/lStXKhgMxj7Gjh2bzWEDAADDeGIXz7JlyxQOh2MfBw8edHtIAAAgh7IaoIRCIUnSJ598Evf4J598EnsuFArpyJEjcc+fOnVKHR0dsWv6KyoqUklJSdwHAADwr6wGKOPGjVMoFNJbb70Ve6yzs1NbtmxRTU2NJKmmpkbHjh3Tjh07Ytc0NTUpEolo2rRp2RwOAADwKNunGXd1dWnfvn2xz1tbW9XS0qKysjJVVVXpr/7qr/R3f/d3+vKXv6xx48bpoYceUmVlZWynz4QJE1RXV6eFCxdq9erV6u3tVUNDg+bOnZvSDh4AAOB/tgOU7du3a8aMGbHPlyxZIkm64447tGbNGj3wwAM6ceKEFi1apGPHjmn69OlqbGxUcXFx7GvWrVunhoYGXXvttSooKNCcOXP0+OOPZ+HHAQAAfpBRHxS30AcFAADvsTN/286g5Iu+iKWtrR06crxb5aOKNXVcmYYVBNweFgAAeYEAJYHGXW1asWG32sJ/bM9fESzW8vpq1U2scHFkAADkB0/0QXFS4642LV67My44kaT2cLcWr92pxl1tLo0MAID8QYByhr6IpRUbditRUU70sRUbdqsv4rmyHQAAPIUA5QxbWzsGZE7OZElqC3dra2uHc4MCACAPEaCc4cjx5MFJOtcBAID0EKCcoXxU8dAX2bgOAACkhwDlDFPHlakiWKxkm4kDOr2bZ+q4MieHBQBA3iFAOcOwgoCW11dL0oAgJfr58vpq+qEAAJBjBCj91E2s0FO3X6lQMH4ZJxQs1lO3X0kfFAAAHECjtgTqJlZoZnWITrIAALiEACWJYQUB1Ywf7fYwAADISyzxAAAA4xCgAAAA4xCgAAAA4xCgAAAA4xCgAAAA4xCgAAAA4xCgAAAA4xCgAAAA4xCgAAAA43iyk6xlWZKkzs5Ol0cCAABSFZ23o/P4YDwZoBw/flySNHbsWJdHAgAA7Dp+/LiCweCg1wSsVMIYw0QiER0+fFijRo1SIOCfA/w6Ozs1duxYHTx4UCUlJW4PB4PgXnkL98tbuF/eYfdeWZal48ePq7KyUgUFg1eZeDKDUlBQoPPPP9/tYeRMSUkJ/1N6BPfKW7hf3sL98g4792qozEkURbIAAMA4BCgAAMA4BCgGKSoq0vLly1VUVOT2UDAE7pW3cL+8hfvlHbm8V54skgUAAP5GBgUAABiHAAUAABiHAAUAABiHAAUAABiHAMUFhw4d0u23367Ro0frrLPO0uWXX67t27cnvPauu+5SIBDQY4895uwgISm1e7Vnzx7deOONCgaDGjlypK666iodOHDApRHnt6HuV1dXlxoaGnT++efrrLPOUnV1tVavXu3iiPPXhRdeqEAgMODj7rvvliR1d3fr7rvv1ujRo3XOOedozpw5+uSTT1wedf4a7H51dHTonnvu0SWXXKKzzjpLVVVV+v73v69wOJzR9/RkJ1kv+/TTT/W1r31NM2bM0K9+9St94Qtf0N69e3XuuecOuPbll1/W5s2bVVlZ6cJIkcq92r9/v6ZPn64FCxZoxYoVKikp0QcffKDi4mIXR56fUrlfS5YsUVNTk9auXasLL7xQ//7v/67vfe97qqys1I033uji6PPPtm3b1NfXF/t8165dmjlzpm699VZJ0r333qvXX39dL774ooLBoBoaGnTLLbfo/fffd2vIeW2w+3X48GEdPnxYjzzyiKqrq/XRRx/prrvu0uHDh/Vv//Zv6X9TC45aunSpNX369CGv+/jjj60vfvGL1q5du6wLLrjAevTRR3M/OMRJ5V5961vfsm6//XaHRoTBpHK/LrvsMutv//Zv4x678sorrb/5m7/J5dCQgh/84AfW+PHjrUgkYh07dswaPny49eKLL8ae37NnjyXJam5udnGUiDrzfiXyr//6r9aIESOs3t7etL8HSzwOe/XVVzVlyhTdeuutKi8v1xVXXKFnnnkm7ppIJKL58+fr/vvv12WXXebSSDHUvYpEInr99dd18cUX6/rrr1d5ebmmTZum9evXuzfoPJbK/1t/8id/oldffVWHDh2SZVl6++239dvf/lbXXXedS6OGJJ08eVJr167Vd7/7XQUCAe3YsUO9vb2qra2NXXPppZeqqqpKzc3NLo4U0sD7lUg4HFZJSYkKCzNYqEk7tEFaioqKrKKiImvZsmXWzp07rV/84hdWcXGxtWbNmtg1P/nJT6yZM2fGIlMyKO4Y6l61tbVZkqyzzz7b+ulPf2r95je/sVauXGkFAgHrnXfecXn0+SeV/7e6u7utb3/725Ykq7Cw0BoxYoT1z//8zy6OGpZlWf/yL/9iDRs2zDp06JBlWZa1bt06a8SIEQOuu+qqq6wHHnjA6eGhn/73q7///d//taqqqqwHH3wwo+9DgOKw4cOHWzU1NXGP3XPPPdbVV19tWZZlbd++3RozZkzcjSdAccdQ9+rQoUOWJOu2226Lu6a+vt6aO3euY+PEaUPdL8uyrH/4h3+wLr74YuvVV1+1/vM//9N64oknrHPOOcfauHGj08PFGa677jrrz//8z2OfE6CYrf/9OlM4HLamTp1q1dXVWSdPnszo+7DE47CKigpVV1fHPTZhwoTYro93331XR44cUVVVlQoLC1VYWKiPPvpI9913ny688EIXRpy/hrpX5513ngoLCwe9Bs4Z6n59/vnnevDBB/XTn/5U9fX1+spXvqKGhgZ961vf0iOPPOLGkCHpo48+0ptvvqm//Mu/jD0WCoV08uRJHTt2LO7aTz75RKFQyOER4kyJ7lfU8ePHVVdXp1GjRunll1/W8OHDM/peBCgO+9rXvqYPP/ww7rHf/va3uuCCCyRJ8+fP13/913+ppaUl9lFZWan7779fb7zxhhtDzltD3asRI0boqquuGvQaOGeo+9Xb26ve3l4VFMT/2Rs2bJgikYhj40S85557TuXl5brhhhtij02ePFnDhw/XW2+9FXvsww8/1IEDB1RTU+PGMPEHie6XJHV2duq6667TiBEj9Oqrr2ZnJ2NG+RfYtnXrVquwsND68Y9/bO3du9dat26ddfbZZ1tr165N+jUs8bgjlXv10ksvWcOHD7eefvppa+/evdYTTzxhDRs2zHr33XddHHl+SuV+/dmf/Zl12WWXWW+//bb1P//zP9Zzzz1nFRcXWz//+c9dHHn+6uvrs6qqqqylS5cOeO6uu+6yqqqqrKamJmv79u1WTU3NgCU8OCvZ/QqHw9a0adOsyy+/3Nq3b5/V1tYW+zh16lTa348AxQUbNmywJk6caBUVFVmXXnqp9fTTTw96PQGKe1K5V88++6x10UUXWcXFxdakSZOs9evXuzBSWNbQ96utrc36zne+Y1VWVlrFxcXWJZdcYv3jP/5j0q2SyK033njDkmR9+OGHA577/PPPre9973vWueeea5199tnWzTffbLW1tbkwSkQlu19vv/22JSnhR2tra9rfL2BZlpV5HgYAACB7qEEBAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADGIUABAADG+f8BgJ8m05boYPQAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(data[\"Height(Inches)\"],data[\"Weight(Pounds)\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a9e26124-41f7-4e28-82db-2e05f45f4318",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Height(Inches)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>65.78331</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>71.51521</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>69.39874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>68.21660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>67.78781</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>70.55703</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>66.28644</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>63.42577</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>66.76711</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>68.88741</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Height(Inches)\n",
       "0         65.78331\n",
       "1         71.51521\n",
       "2         69.39874\n",
       "3         68.21660\n",
       "4         67.78781\n",
       "..             ...\n",
       "95        70.55703\n",
       "96        66.28644\n",
       "97        63.42577\n",
       "98        66.76711\n",
       "99        68.88741\n",
       "\n",
       "[100 rows x 1 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inputs = pd.read_csv(\"/Users/deepeshjha/Desktop/DSnML/weight.csv\",encoding='windows-1254', nrows=100,usecols=(0,1))\n",
    "inputs.drop(columns='Index',axis=1,inplace=True)\n",
    "\n",
    "inputs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4bc99879-111f-4da6-b4da-c0e2ec449bbe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Weight(Pounds)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>112.9925</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>136.4873</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>153.0269</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>142.3354</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>144.2971</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>95</th>\n",
       "      <td>131.8001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>96</th>\n",
       "      <td>120.0285</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97</th>\n",
       "      <td>123.0972</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>98</th>\n",
       "      <td>128.1432</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>99</th>\n",
       "      <td>115.4759</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>100 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Weight(Pounds)\n",
       "0         112.9925\n",
       "1         136.4873\n",
       "2         153.0269\n",
       "3         142.3354\n",
       "4         144.2971\n",
       "..             ...\n",
       "95        131.8001\n",
       "96        120.0285\n",
       "97        123.0972\n",
       "98        128.1432\n",
       "99        115.4759\n",
       "\n",
       "[100 rows x 1 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "targets = pd.read_csv(\"/Users/deepeshjha/Desktop/DSnML/weight.csv\",encoding='windows-1254', nrows=100,usecols=(2,2))\n",
    "targets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e16b3b6b-5d5e-4f3d-ad35-92e45ea0656a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[65.78331],\n",
       "       [71.51521],\n",
       "       [69.39874],\n",
       "       [68.2166 ],\n",
       "       [67.78781],\n",
       "       [68.69784],\n",
       "       [69.80204],\n",
       "       [70.01472],\n",
       "       [67.90265],\n",
       "       [66.78236],\n",
       "       [66.48769],\n",
       "       [67.62333],\n",
       "       [68.30248],\n",
       "       [67.11656],\n",
       "       [68.27967],\n",
       "       [71.0916 ],\n",
       "       [66.461  ],\n",
       "       [68.64927],\n",
       "       [71.23033],\n",
       "       [67.13118],\n",
       "       [67.83379],\n",
       "       [68.87881],\n",
       "       [63.48115],\n",
       "       [68.42187],\n",
       "       [67.62804],\n",
       "       [67.20864],\n",
       "       [70.84235],\n",
       "       [67.49434],\n",
       "       [66.53401],\n",
       "       [65.44098],\n",
       "       [69.5233 ],\n",
       "       [65.8132 ],\n",
       "       [67.8163 ],\n",
       "       [70.59505],\n",
       "       [71.80484],\n",
       "       [69.20613],\n",
       "       [66.80368],\n",
       "       [67.65893],\n",
       "       [67.80701],\n",
       "       [64.04535],\n",
       "       [68.57463],\n",
       "       [65.18357],\n",
       "       [69.65814],\n",
       "       [67.96731],\n",
       "       [65.98088],\n",
       "       [68.67249],\n",
       "       [66.88088],\n",
       "       [67.69868],\n",
       "       [69.82117],\n",
       "       [69.08817],\n",
       "       [69.91479],\n",
       "       [67.33182],\n",
       "       [70.26939],\n",
       "       [69.10344],\n",
       "       [65.38356],\n",
       "       [70.18447],\n",
       "       [70.40617],\n",
       "       [66.54376],\n",
       "       [66.36418],\n",
       "       [67.537  ],\n",
       "       [66.50418],\n",
       "       [68.99958],\n",
       "       [68.30355],\n",
       "       [67.01255],\n",
       "       [70.80592],\n",
       "       [68.21951],\n",
       "       [69.05914],\n",
       "       [67.73103],\n",
       "       [67.21568],\n",
       "       [67.36763],\n",
       "       [65.27033],\n",
       "       [70.84278],\n",
       "       [69.92442],\n",
       "       [64.28508],\n",
       "       [68.2452 ],\n",
       "       [66.35708],\n",
       "       [68.36275],\n",
       "       [65.4769 ],\n",
       "       [69.71947],\n",
       "       [67.72554],\n",
       "       [68.63941],\n",
       "       [66.78405],\n",
       "       [70.05147],\n",
       "       [66.27848],\n",
       "       [69.20198],\n",
       "       [69.13481],\n",
       "       [67.36436],\n",
       "       [70.09297],\n",
       "       [70.1766 ],\n",
       "       [68.22556],\n",
       "       [68.12932],\n",
       "       [70.24256],\n",
       "       [71.48752],\n",
       "       [69.20477],\n",
       "       [70.06306],\n",
       "       [70.55703],\n",
       "       [66.28644],\n",
       "       [63.42577],\n",
       "       [66.76711],\n",
       "       [68.88741]], dtype=float32)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr = inputs.values\n",
    "arr = arr.astype('float32')\n",
    "arr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "beb315ca-950b-48d1-8b8e-68456c97913e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[112.9925 ],\n",
       "       [136.4873 ],\n",
       "       [153.0269 ],\n",
       "       [142.3354 ],\n",
       "       [144.2971 ],\n",
       "       [123.3024 ],\n",
       "       [141.4947 ],\n",
       "       [136.4623 ],\n",
       "       [112.3723 ],\n",
       "       [120.6672 ],\n",
       "       [127.4516 ],\n",
       "       [114.143  ],\n",
       "       [125.6107 ],\n",
       "       [122.4618 ],\n",
       "       [116.0866 ],\n",
       "       [139.9975 ],\n",
       "       [129.5023 ],\n",
       "       [142.9733 ],\n",
       "       [137.9025 ],\n",
       "       [124.0449 ],\n",
       "       [141.2807 ],\n",
       "       [143.5392 ],\n",
       "       [ 97.90191],\n",
       "       [129.5027 ],\n",
       "       [141.8501 ],\n",
       "       [129.7244 ],\n",
       "       [142.4235 ],\n",
       "       [131.5502 ],\n",
       "       [108.3324 ],\n",
       "       [113.8922 ],\n",
       "       [103.3016 ],\n",
       "       [120.7536 ],\n",
       "       [125.7886 ],\n",
       "       [136.2225 ],\n",
       "       [140.1015 ],\n",
       "       [128.7487 ],\n",
       "       [141.7994 ],\n",
       "       [121.2319 ],\n",
       "       [131.3478 ],\n",
       "       [106.7115 ],\n",
       "       [124.3598 ],\n",
       "       [124.8591 ],\n",
       "       [139.6711 ],\n",
       "       [137.3696 ],\n",
       "       [106.4499 ],\n",
       "       [128.7639 ],\n",
       "       [145.6837 ],\n",
       "       [116.819  ],\n",
       "       [143.6215 ],\n",
       "       [134.9325 ],\n",
       "       [147.0219 ],\n",
       "       [126.3285 ],\n",
       "       [125.4839 ],\n",
       "       [115.7084 ],\n",
       "       [123.4892 ],\n",
       "       [147.8926 ],\n",
       "       [155.8987 ],\n",
       "       [128.0742 ],\n",
       "       [119.3701 ],\n",
       "       [133.8148 ],\n",
       "       [128.7325 ],\n",
       "       [137.5453 ],\n",
       "       [129.7604 ],\n",
       "       [128.824  ],\n",
       "       [135.3165 ],\n",
       "       [109.6113 ],\n",
       "       [142.4684 ],\n",
       "       [132.749  ],\n",
       "       [103.5275 ],\n",
       "       [124.7299 ],\n",
       "       [129.3137 ],\n",
       "       [134.0175 ],\n",
       "       [140.3969 ],\n",
       "       [102.8351 ],\n",
       "       [128.5214 ],\n",
       "       [120.2991 ],\n",
       "       [138.6036 ],\n",
       "       [132.9574 ],\n",
       "       [115.6233 ],\n",
       "       [122.524  ],\n",
       "       [134.6254 ],\n",
       "       [121.8986 ],\n",
       "       [155.3767 ],\n",
       "       [128.9418 ],\n",
       "       [129.1013 ],\n",
       "       [139.4733 ],\n",
       "       [140.8901 ],\n",
       "       [131.5916 ],\n",
       "       [121.1232 ],\n",
       "       [131.5127 ],\n",
       "       [136.5479 ],\n",
       "       [141.4896 ],\n",
       "       [140.6104 ],\n",
       "       [112.1413 ],\n",
       "       [133.457  ],\n",
       "       [131.8001 ],\n",
       "       [120.0285 ],\n",
       "       [123.0972 ],\n",
       "       [128.1432 ],\n",
       "       [115.4759 ]], dtype=float32)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "arr1 = targets.values\n",
    "arr1 = arr1.astype('float32')\n",
    "arr1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "caacc6e7-9b91-4c0d-ae14-dfcdf6d8cbe2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[65.7833],\n",
       "        [71.5152],\n",
       "        [69.3987],\n",
       "        [68.2166],\n",
       "        [67.7878],\n",
       "        [68.6978],\n",
       "        [69.8020],\n",
       "        [70.0147],\n",
       "        [67.9026],\n",
       "        [66.7824],\n",
       "        [66.4877],\n",
       "        [67.6233],\n",
       "        [68.3025],\n",
       "        [67.1166],\n",
       "        [68.2797],\n",
       "        [71.0916],\n",
       "        [66.4610],\n",
       "        [68.6493],\n",
       "        [71.2303],\n",
       "        [67.1312],\n",
       "        [67.8338],\n",
       "        [68.8788],\n",
       "        [63.4812],\n",
       "        [68.4219],\n",
       "        [67.6280],\n",
       "        [67.2086],\n",
       "        [70.8423],\n",
       "        [67.4943],\n",
       "        [66.5340],\n",
       "        [65.4410],\n",
       "        [69.5233],\n",
       "        [65.8132],\n",
       "        [67.8163],\n",
       "        [70.5950],\n",
       "        [71.8048],\n",
       "        [69.2061],\n",
       "        [66.8037],\n",
       "        [67.6589],\n",
       "        [67.8070],\n",
       "        [64.0453],\n",
       "        [68.5746],\n",
       "        [65.1836],\n",
       "        [69.6581],\n",
       "        [67.9673],\n",
       "        [65.9809],\n",
       "        [68.6725],\n",
       "        [66.8809],\n",
       "        [67.6987],\n",
       "        [69.8212],\n",
       "        [69.0882],\n",
       "        [69.9148],\n",
       "        [67.3318],\n",
       "        [70.2694],\n",
       "        [69.1034],\n",
       "        [65.3836],\n",
       "        [70.1845],\n",
       "        [70.4062],\n",
       "        [66.5438],\n",
       "        [66.3642],\n",
       "        [67.5370],\n",
       "        [66.5042],\n",
       "        [68.9996],\n",
       "        [68.3036],\n",
       "        [67.0126],\n",
       "        [70.8059],\n",
       "        [68.2195],\n",
       "        [69.0591],\n",
       "        [67.7310],\n",
       "        [67.2157],\n",
       "        [67.3676],\n",
       "        [65.2703],\n",
       "        [70.8428],\n",
       "        [69.9244],\n",
       "        [64.2851],\n",
       "        [68.2452],\n",
       "        [66.3571],\n",
       "        [68.3627],\n",
       "        [65.4769],\n",
       "        [69.7195],\n",
       "        [67.7255],\n",
       "        [68.6394],\n",
       "        [66.7840],\n",
       "        [70.0515],\n",
       "        [66.2785],\n",
       "        [69.2020],\n",
       "        [69.1348],\n",
       "        [67.3644],\n",
       "        [70.0930],\n",
       "        [70.1766],\n",
       "        [68.2256],\n",
       "        [68.1293],\n",
       "        [70.2426],\n",
       "        [71.4875],\n",
       "        [69.2048],\n",
       "        [70.0631],\n",
       "        [70.5570],\n",
       "        [66.2864],\n",
       "        [63.4258],\n",
       "        [66.7671],\n",
       "        [68.8874]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "inputtens = torch.tensor(arr)\n",
    "inputtens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3d5e8506-3ebb-4ef1-9a0d-45002a991265",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[112.9925],\n",
       "        [136.4873],\n",
       "        [153.0269],\n",
       "        [142.3354],\n",
       "        [144.2971],\n",
       "        [123.3024],\n",
       "        [141.4947],\n",
       "        [136.4623],\n",
       "        [112.3723],\n",
       "        [120.6672],\n",
       "        [127.4516],\n",
       "        [114.1430],\n",
       "        [125.6107],\n",
       "        [122.4618],\n",
       "        [116.0866],\n",
       "        [139.9975],\n",
       "        [129.5023],\n",
       "        [142.9733],\n",
       "        [137.9025],\n",
       "        [124.0449],\n",
       "        [141.2807],\n",
       "        [143.5392],\n",
       "        [ 97.9019],\n",
       "        [129.5027],\n",
       "        [141.8501],\n",
       "        [129.7244],\n",
       "        [142.4235],\n",
       "        [131.5502],\n",
       "        [108.3324],\n",
       "        [113.8922],\n",
       "        [103.3016],\n",
       "        [120.7536],\n",
       "        [125.7886],\n",
       "        [136.2225],\n",
       "        [140.1015],\n",
       "        [128.7487],\n",
       "        [141.7994],\n",
       "        [121.2319],\n",
       "        [131.3478],\n",
       "        [106.7115],\n",
       "        [124.3598],\n",
       "        [124.8591],\n",
       "        [139.6711],\n",
       "        [137.3696],\n",
       "        [106.4499],\n",
       "        [128.7639],\n",
       "        [145.6837],\n",
       "        [116.8190],\n",
       "        [143.6215],\n",
       "        [134.9325],\n",
       "        [147.0219],\n",
       "        [126.3285],\n",
       "        [125.4839],\n",
       "        [115.7084],\n",
       "        [123.4892],\n",
       "        [147.8926],\n",
       "        [155.8987],\n",
       "        [128.0742],\n",
       "        [119.3701],\n",
       "        [133.8148],\n",
       "        [128.7325],\n",
       "        [137.5453],\n",
       "        [129.7604],\n",
       "        [128.8240],\n",
       "        [135.3165],\n",
       "        [109.6113],\n",
       "        [142.4684],\n",
       "        [132.7490],\n",
       "        [103.5275],\n",
       "        [124.7299],\n",
       "        [129.3137],\n",
       "        [134.0175],\n",
       "        [140.3969],\n",
       "        [102.8351],\n",
       "        [128.5214],\n",
       "        [120.2991],\n",
       "        [138.6036],\n",
       "        [132.9574],\n",
       "        [115.6233],\n",
       "        [122.5240],\n",
       "        [134.6254],\n",
       "        [121.8986],\n",
       "        [155.3767],\n",
       "        [128.9418],\n",
       "        [129.1013],\n",
       "        [139.4733],\n",
       "        [140.8901],\n",
       "        [131.5916],\n",
       "        [121.1232],\n",
       "        [131.5127],\n",
       "        [136.5479],\n",
       "        [141.4896],\n",
       "        [140.6104],\n",
       "        [112.1413],\n",
       "        [133.4570],\n",
       "        [131.8001],\n",
       "        [120.0285],\n",
       "        [123.0972],\n",
       "        [128.1432],\n",
       "        [115.4759]])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputtens = torch.tensor(arr1)\n",
    "outputtens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "f5b4f1fd-40fa-4be1-8f0e-67006692fec9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[-1.6313]], requires_grad=True)\n",
      "tensor([[ 0.3640],\n",
      "        [ 0.4578],\n",
      "        [-0.2280],\n",
      "        [ 0.8230],\n",
      "        [ 0.3227],\n",
      "        [ 0.0840],\n",
      "        [-0.3212],\n",
      "        [ 0.1655],\n",
      "        [ 0.5730],\n",
      "        [-0.4883],\n",
      "        [ 1.0952],\n",
      "        [ 0.9407],\n",
      "        [ 2.2522],\n",
      "        [-0.0274],\n",
      "        [ 1.4389],\n",
      "        [-0.5267],\n",
      "        [ 1.4747],\n",
      "        [-0.7532],\n",
      "        [-0.6311],\n",
      "        [ 2.1627],\n",
      "        [ 0.4899],\n",
      "        [ 0.7637],\n",
      "        [ 0.6485],\n",
      "        [ 1.2025],\n",
      "        [ 0.2459],\n",
      "        [ 0.1473],\n",
      "        [-2.3008],\n",
      "        [-0.7537],\n",
      "        [-1.1512],\n",
      "        [-0.6872],\n",
      "        [-1.1901],\n",
      "        [-0.8182],\n",
      "        [ 0.1322],\n",
      "        [ 0.4698],\n",
      "        [-1.0642],\n",
      "        [ 0.7324],\n",
      "        [ 2.3941],\n",
      "        [ 0.2191],\n",
      "        [ 0.2571],\n",
      "        [ 0.3011],\n",
      "        [-1.6922],\n",
      "        [-1.3596],\n",
      "        [ 0.4794],\n",
      "        [-0.6092],\n",
      "        [ 0.0362],\n",
      "        [ 0.9389],\n",
      "        [-0.0921],\n",
      "        [ 0.7333],\n",
      "        [-0.3299],\n",
      "        [-1.9814],\n",
      "        [ 0.3726],\n",
      "        [-0.2153],\n",
      "        [ 1.6981],\n",
      "        [-0.3395],\n",
      "        [ 0.2804],\n",
      "        [-1.1851],\n",
      "        [ 0.0993],\n",
      "        [-0.5853],\n",
      "        [-0.5532],\n",
      "        [ 0.9530],\n",
      "        [ 0.0082],\n",
      "        [-0.7154],\n",
      "        [-0.4459],\n",
      "        [ 0.8444],\n",
      "        [-0.7292],\n",
      "        [-0.7376],\n",
      "        [ 0.6551],\n",
      "        [ 0.3394],\n",
      "        [-1.0288],\n",
      "        [ 0.0195],\n",
      "        [-0.4089],\n",
      "        [-1.3883],\n",
      "        [ 0.0122],\n",
      "        [ 1.7722],\n",
      "        [ 1.1468],\n",
      "        [ 0.0302],\n",
      "        [-0.4004],\n",
      "        [-0.1592],\n",
      "        [-0.0305],\n",
      "        [ 0.5156],\n",
      "        [ 0.6942],\n",
      "        [ 0.8665],\n",
      "        [ 1.6664],\n",
      "        [-0.7205],\n",
      "        [-2.0495],\n",
      "        [-1.9289],\n",
      "        [ 0.5188],\n",
      "        [-1.5122],\n",
      "        [-0.1012],\n",
      "        [-1.5340],\n",
      "        [-0.4765],\n",
      "        [-0.7763],\n",
      "        [ 0.9087],\n",
      "        [ 0.9382],\n",
      "        [-0.7229],\n",
      "        [-0.3025],\n",
      "        [ 0.9606],\n",
      "        [-2.4262],\n",
      "        [ 1.0602],\n",
      "        [-0.1201]], requires_grad=True)\n"
     ]
    }
   ],
   "source": [
    "w = torch.randn(1,1,requires_grad = True)\n",
    "b = torch.randn(100,1, requires_grad=True)\n",
    "print(w);print(b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ef6f463a-6341-47bb-8d4c-0e315b801cb3",
   "metadata": {},
   "outputs": [],
   "source": [
    "def model(x):\n",
    "    return x@w.t()+b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "c6b7b8ea-dec1-47c0-9fd2-508d4641e3f2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-106.9474],\n",
       "        [-116.2038],\n",
       "        [-113.4371],\n",
       "        [-110.4577],\n",
       "        [-110.2585],\n",
       "        [-111.9818],\n",
       "        [-114.1882],\n",
       "        [-114.0485],\n",
       "        [-110.1955],\n",
       "        [-109.4294],\n",
       "        [-107.3652],\n",
       "        [-109.3722],\n",
       "        [-109.1686],\n",
       "        [-109.5136],\n",
       "        [-109.9447],\n",
       "        [-116.4973],\n",
       "        [-106.9421],\n",
       "        [-112.7397],\n",
       "        [-116.8281],\n",
       "        [-107.3474],\n",
       "        [-110.1663],\n",
       "        [-111.5973],\n",
       "        [-102.9073],\n",
       "        [-110.4130],\n",
       "        [-110.0747],\n",
       "        [-109.4891],\n",
       "        [-117.8648],\n",
       "        [-110.8562],\n",
       "        [-109.6871],\n",
       "        [-107.4400],\n",
       "        [-114.6024],\n",
       "        [-108.1782],\n",
       "        [-110.4955],\n",
       "        [-114.6909],\n",
       "        [-118.1983],\n",
       "        [-112.1625],\n",
       "        [-106.5817],\n",
       "        [-110.1519],\n",
       "        [-110.3554],\n",
       "        [-104.1751],\n",
       "        [-113.5570],\n",
       "        [-107.6925],\n",
       "        [-113.1528],\n",
       "        [-111.4832],\n",
       "        [-107.5974],\n",
       "        [-111.0855],\n",
       "        [-109.1938],\n",
       "        [-109.7025],\n",
       "        [-114.2281],\n",
       "        [-114.6839],\n",
       "        [-113.6784],\n",
       "        [-110.0527],\n",
       "        [-112.9313],\n",
       "        [-113.0669],\n",
       "        [-106.3789],\n",
       "        [-115.6759],\n",
       "        [-114.7533],\n",
       "        [-109.1371],\n",
       "        [-108.8121],\n",
       "        [-109.2191],\n",
       "        [-108.4791],\n",
       "        [-113.2734],\n",
       "        [-111.8684],\n",
       "        [-108.4722],\n",
       "        [-116.2338],\n",
       "        [-112.0230],\n",
       "        [-112.0000],\n",
       "        [-110.1492],\n",
       "        [-110.6767],\n",
       "        [-109.8763],\n",
       "        [-106.8834],\n",
       "        [-116.9531],\n",
       "        [-114.0544],\n",
       "        [-103.0950],\n",
       "        [-110.1806],\n",
       "        [-108.2171],\n",
       "        [-111.9195],\n",
       "        [-106.9706],\n",
       "        [-113.7628],\n",
       "        [-109.9641],\n",
       "        [-111.2763],\n",
       "        [-108.0773],\n",
       "        [-112.6075],\n",
       "        [-108.8396],\n",
       "        [-114.9376],\n",
       "        [-114.7074],\n",
       "        [-109.3717],\n",
       "        [-115.8538],\n",
       "        [-114.5792],\n",
       "        [-112.8294],\n",
       "        [-111.6148],\n",
       "        [-115.3619],\n",
       "        [-115.7078],\n",
       "        [-111.9545],\n",
       "        [-115.0157],\n",
       "        [-115.4011],\n",
       "        [-107.1714],\n",
       "        [-105.8917],\n",
       "        [-107.8560],\n",
       "        [-112.4951]], grad_fn=<AddBackward0>)"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred = model(inputtens)\n",
    "pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "fc5b3c9a-dcb5-4bed-b13e-242814088108",
   "metadata": {},
   "outputs": [],
   "source": [
    "def mse(t1,t2):\n",
    "    diff = t1 - t2\n",
    "    return torch.sum(diff*diff) / torch.numel(t1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "23ed2b53-84cd-4a2e-9549-d73a598b0be6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor(57970.6367, grad_fn=<DivBackward0>)"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loss = mse(pred, outputtens)\n",
    "loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "ad1199f1-df9d-476e-acd1-f8ecbe89cce2",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(100):\n",
    "    pred = model(inputtens)\n",
    "    loss = mse(pred, outputtens)\n",
    "    loss.backward()\n",
    "    with torch.no_grad(): \n",
    "        w -= w.grad * 2e-4\n",
    "        b -= b.grad * 2e-4\n",
    "        w.grad.zero_()\n",
    "        b.grad.zero_()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "fa3f2fd0-cc3a-4931-8adf-56d19722d852",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor(114.4077, grad_fn=<DivBackward0>)\n"
     ]
    }
   ],
   "source": [
    "pred = model(inputtens)\n",
    "loss = mse(pred, outputtens)\n",
    "print(loss)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "7e0e4ee8-511f-45fd-932d-3082a1172709",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[125.1754],\n",
       "        [136.1499],\n",
       "        [131.4568],\n",
       "        [130.2610],\n",
       "        [128.9485],\n",
       "        [130.4274],\n",
       "        [132.1239],\n",
       "        [133.0117],\n",
       "        [129.4037],\n",
       "        [126.2214],\n",
       "        [127.2480],\n",
       "        [129.2422],\n",
       "        [131.8459],\n",
       "        [127.3166],\n",
       "        [130.9858],\n",
       "        [134.3638],\n",
       "        [127.5776],\n",
       "        [129.5063],\n",
       "        [134.5216],\n",
       "        [129.5342],\n",
       "        [129.2016],\n",
       "        [131.4581],\n",
       "        [121.0875],\n",
       "        [131.0246],\n",
       "        [128.5677],\n",
       "        [127.6688],\n",
       "        [132.1186],\n",
       "        [127.3107],\n",
       "        [125.0828],\n",
       "        [123.4758],\n",
       "        [130.7115],\n",
       "        [124.0536],\n",
       "        [128.8047],\n",
       "        [134.4165],\n",
       "        [135.1792],\n",
       "        [132.0418],\n",
       "        [129.1515],\n",
       "        [128.5912],\n",
       "        [128.9141],\n",
       "        [121.8138],\n",
       "        [128.4187],\n",
       "        [122.3198],\n",
       "        [132.6506],\n",
       "        [128.3546],\n",
       "        [125.2199],\n",
       "        [131.2361],\n",
       "        [126.8143],\n",
       "        [129.1789],\n",
       "        [132.1524],\n",
       "        [129.1079],\n",
       "        [133.0335],\n",
       "        [127.5386],\n",
       "        [135.0224],\n",
       "        [130.7703],\n",
       "        [124.3378],\n",
       "        [131.9883],\n",
       "        [133.6958],\n",
       "        [125.6749],\n",
       "        [125.3628],\n",
       "        [129.0986],\n",
       "        [126.1933],\n",
       "        [130.2064],\n",
       "        [129.1526],\n",
       "        [127.9934],\n",
       "        [133.6176],\n",
       "        [128.6935],\n",
       "        [131.6912],\n",
       "        [128.8528],\n",
       "        [126.4961],\n",
       "        [127.8406],\n",
       "        [123.4364],\n",
       "        [133.0281],\n",
       "        [132.6889],\n",
       "        [123.7374],\n",
       "        [130.6334],\n",
       "        [125.9329],\n",
       "        [129.3138],\n",
       "        [124.0793],\n",
       "        [132.2475],\n",
       "        [129.0144],\n",
       "        [130.9311],\n",
       "        [127.5793],\n",
       "        [134.5893],\n",
       "        [125.0369],\n",
       "        [129.2533],\n",
       "        [129.2506],\n",
       "        [128.3400],\n",
       "        [131.4812],\n",
       "        [133.0461],\n",
       "        [127.9176],\n",
       "        [128.7942],\n",
       "        [132.5045],\n",
       "        [136.5497],\n",
       "        [132.2383],\n",
       "        [132.2143],\n",
       "        [133.5707],\n",
       "        [126.7289],\n",
       "        [117.9190],\n",
       "        [127.7433],\n",
       "        [130.5798]], grad_fn=<AddBackward0>)"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2bf9f77f-46ab-4840-94e7-30aa56a8fdfe",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[112.9925],\n",
       "        [136.4873],\n",
       "        [153.0269],\n",
       "        [142.3354],\n",
       "        [144.2971],\n",
       "        [123.3024],\n",
       "        [141.4947],\n",
       "        [136.4623],\n",
       "        [112.3723],\n",
       "        [120.6672],\n",
       "        [127.4516],\n",
       "        [114.1430],\n",
       "        [125.6107],\n",
       "        [122.4618],\n",
       "        [116.0866],\n",
       "        [139.9975],\n",
       "        [129.5023],\n",
       "        [142.9733],\n",
       "        [137.9025],\n",
       "        [124.0449],\n",
       "        [141.2807],\n",
       "        [143.5392],\n",
       "        [ 97.9019],\n",
       "        [129.5027],\n",
       "        [141.8501],\n",
       "        [129.7244],\n",
       "        [142.4235],\n",
       "        [131.5502],\n",
       "        [108.3324],\n",
       "        [113.8922],\n",
       "        [103.3016],\n",
       "        [120.7536],\n",
       "        [125.7886],\n",
       "        [136.2225],\n",
       "        [140.1015],\n",
       "        [128.7487],\n",
       "        [141.7994],\n",
       "        [121.2319],\n",
       "        [131.3478],\n",
       "        [106.7115],\n",
       "        [124.3598],\n",
       "        [124.8591],\n",
       "        [139.6711],\n",
       "        [137.3696],\n",
       "        [106.4499],\n",
       "        [128.7639],\n",
       "        [145.6837],\n",
       "        [116.8190],\n",
       "        [143.6215],\n",
       "        [134.9325],\n",
       "        [147.0219],\n",
       "        [126.3285],\n",
       "        [125.4839],\n",
       "        [115.7084],\n",
       "        [123.4892],\n",
       "        [147.8926],\n",
       "        [155.8987],\n",
       "        [128.0742],\n",
       "        [119.3701],\n",
       "        [133.8148],\n",
       "        [128.7325],\n",
       "        [137.5453],\n",
       "        [129.7604],\n",
       "        [128.8240],\n",
       "        [135.3165],\n",
       "        [109.6113],\n",
       "        [142.4684],\n",
       "        [132.7490],\n",
       "        [103.5275],\n",
       "        [124.7299],\n",
       "        [129.3137],\n",
       "        [134.0175],\n",
       "        [140.3969],\n",
       "        [102.8351],\n",
       "        [128.5214],\n",
       "        [120.2991],\n",
       "        [138.6036],\n",
       "        [132.9574],\n",
       "        [115.6233],\n",
       "        [122.5240],\n",
       "        [134.6254],\n",
       "        [121.8986],\n",
       "        [155.3767],\n",
       "        [128.9418],\n",
       "        [129.1013],\n",
       "        [139.4733],\n",
       "        [140.8901],\n",
       "        [131.5916],\n",
       "        [121.1232],\n",
       "        [131.5127],\n",
       "        [136.5479],\n",
       "        [141.4896],\n",
       "        [140.6104],\n",
       "        [112.1413],\n",
       "        [133.4570],\n",
       "        [131.8001],\n",
       "        [120.0285],\n",
       "        [123.0972],\n",
       "        [128.1432],\n",
       "        [115.4759]])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "outputtens"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "847109cf-7a80-42b8-86a4-fe739637d80c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch.nn as nn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "2409fab5-cbd7-4fa4-9c50-7cdb56c04442",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch.utils.data import TensorDataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "28bf033e-3755-48aa-b9e7-c98a69999468",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(tensor([[65.7833],\n",
       "         [71.5152],\n",
       "         [69.3987]]),\n",
       " tensor([[112.9925],\n",
       "         [136.4873],\n",
       "         [153.0269]]))"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Define dataset\n",
    "train_ds = TensorDataset(inputtens, outputtens)\n",
    "train_ds[0:3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "fe4d61cd-9774-42f1-873b-ee04d44cb2ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "from torch.utils.data import DataLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "e943b0a1-370d-4377-b05c-ff947d44e8b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "batch_size = 20\n",
    "train_dl = DataLoader(train_ds,batch_size,shuffle =True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "1d0c093b-65ff-46dc-931b-96c8db8104ec",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "tensor([[69.7195],\n",
      "        [68.1293],\n",
      "        [68.3627],\n",
      "        [69.9148],\n",
      "        [65.7833],\n",
      "        [71.0916],\n",
      "        [67.2157],\n",
      "        [66.4877],\n",
      "        [69.2020],\n",
      "        [68.8788],\n",
      "        [67.3318],\n",
      "        [68.2195],\n",
      "        [67.6589],\n",
      "        [68.5746],\n",
      "        [70.0147],\n",
      "        [69.5233],\n",
      "        [66.7671],\n",
      "        [67.7878],\n",
      "        [67.6987],\n",
      "        [70.0515]])\n",
      "tensor([[115.6233],\n",
      "        [136.5479],\n",
      "        [138.6036],\n",
      "        [147.0219],\n",
      "        [112.9925],\n",
      "        [139.9975],\n",
      "        [103.5275],\n",
      "        [127.4516],\n",
      "        [129.1013],\n",
      "        [143.5392],\n",
      "        [126.3285],\n",
      "        [109.6113],\n",
      "        [121.2319],\n",
      "        [124.3598],\n",
      "        [136.4623],\n",
      "        [103.3016],\n",
      "        [128.1432],\n",
      "        [144.2971],\n",
      "        [116.8190],\n",
      "        [155.3767]])\n"
     ]
    }
   ],
   "source": [
    "for xb,yb in train_dl:\n",
    "    print(xb)\n",
    "    print(yb)\n",
    "    break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "5ead94c8-1cdd-469f-aaa8-f9ee06c84116",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Parameter containing:\n",
      "tensor([[-0.3148]], requires_grad=True)\n",
      "Parameter containing:\n",
      "tensor([0.9556], requires_grad=True)\n"
     ]
    }
   ],
   "source": [
    "#define model \n",
    "model = nn.Linear(1,1)\n",
    "print(model.weight)\n",
    "print(model.bias)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "4766750a-6ca9-4ebb-ae47-8f614b6dcc17",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Parameter containing:\n",
       " tensor([[-0.3148]], requires_grad=True),\n",
       " Parameter containing:\n",
       " tensor([0.9556], requires_grad=True)]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(model.parameters())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "14f6de56-463e-4b38-9364-0908781d5c04",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[-19.7557],\n",
       "        [-21.5603],\n",
       "        [-20.8940],\n",
       "        [-20.5218],\n",
       "        [-20.3868],\n",
       "        [-20.6733],\n",
       "        [-21.0210],\n",
       "        [-21.0879],\n",
       "        [-20.4230],\n",
       "        [-20.0702],\n",
       "        [-19.9775],\n",
       "        [-20.3350],\n",
       "        [-20.5488],\n",
       "        [-20.1755],\n",
       "        [-20.5417],\n",
       "        [-21.4270],\n",
       "        [-19.9691],\n",
       "        [-20.6580],\n",
       "        [-21.4707],\n",
       "        [-20.1801],\n",
       "        [-20.4013],\n",
       "        [-20.7303],\n",
       "        [-19.0309],\n",
       "        [-20.5864],\n",
       "        [-20.3365],\n",
       "        [-20.2045],\n",
       "        [-21.3485],\n",
       "        [-20.2944],\n",
       "        [-19.9921],\n",
       "        [-19.6479],\n",
       "        [-20.9332],\n",
       "        [-19.7651],\n",
       "        [-20.3958],\n",
       "        [-21.2706],\n",
       "        [-21.6515],\n",
       "        [-20.8334],\n",
       "        [-20.0770],\n",
       "        [-20.3462],\n",
       "        [-20.3928],\n",
       "        [-19.2085],\n",
       "        [-20.6345],\n",
       "        [-19.5669],\n",
       "        [-20.9757],\n",
       "        [-20.4433],\n",
       "        [-19.8179],\n",
       "        [-20.6653],\n",
       "        [-20.1013],\n",
       "        [-20.3587],\n",
       "        [-21.0270],\n",
       "        [-20.7962],\n",
       "        [-21.0565],\n",
       "        [-20.2432],\n",
       "        [-21.1681],\n",
       "        [-20.8010],\n",
       "        [-19.6298],\n",
       "        [-21.1414],\n",
       "        [-21.2112],\n",
       "        [-19.9951],\n",
       "        [-19.9386],\n",
       "        [-20.3078],\n",
       "        [-19.9827],\n",
       "        [-20.7683],\n",
       "        [-20.5492],\n",
       "        [-20.1427],\n",
       "        [-21.3370],\n",
       "        [-20.5227],\n",
       "        [-20.7871],\n",
       "        [-20.3689],\n",
       "        [-20.2067],\n",
       "        [-20.2545],\n",
       "        [-19.5942],\n",
       "        [-21.3486],\n",
       "        [-21.0595],\n",
       "        [-19.2840],\n",
       "        [-20.5308],\n",
       "        [-19.9364],\n",
       "        [-20.5678],\n",
       "        [-19.6592],\n",
       "        [-20.9950],\n",
       "        [-20.3672],\n",
       "        [-20.6549],\n",
       "        [-20.0708],\n",
       "        [-21.0995],\n",
       "        [-19.9116],\n",
       "        [-20.8320],\n",
       "        [-20.8109],\n",
       "        [-20.2535],\n",
       "        [-21.1126],\n",
       "        [-21.1389],\n",
       "        [-20.5246],\n",
       "        [-20.4943],\n",
       "        [-21.1597],\n",
       "        [-21.5516],\n",
       "        [-20.8329],\n",
       "        [-21.1031],\n",
       "        [-21.2587],\n",
       "        [-19.9141],\n",
       "        [-19.0135],\n",
       "        [-20.0654],\n",
       "        [-20.7330]], grad_fn=<AddmmBackward0>)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pred = model(inputtens)\n",
    "pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "634982b0-8960-4c80-badb-aa57c9c7ba1a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch.nn.functional as F"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "3bd3cc25-9b97-4432-b91d-222d40c4b8c6",
   "metadata": {},
   "outputs": [],
   "source": [
    "loss_fn = F.mse_loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "e54d013c-58cc-4355-aa49-864ea696dd01",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor(22565.3145, grad_fn=<MseLossBackward0>)"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "loss = loss_fn(model(inputtens),outputtens)\n",
    "loss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "37477f67-1d2f-45b9-993b-0f6494ca251a",
   "metadata": {},
   "outputs": [],
   "source": [
    "opt = torch.optim.SGD(model.parameters(),lr=1e-5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "bd1f13b3-7009-4daf-a569-e4650584a618",
   "metadata": {},
   "outputs": [],
   "source": [
    "def fit(num_epochs, model, loss_fn, opt, train_dl):\n",
    "    for epoch in range(num_epochs):\n",
    "        for xb,yb in train_dl:\n",
    "            pred = model(xb)\n",
    "            loss = loss_fn(pred,yb)\n",
    "            loss.backward()\n",
    "            opt.step()\n",
    "            opt.zero_grad()\n",
    "        if(epoch+1)%10 == 0:\n",
    "            print('Epoch [{}/{} Loss: {:.4f}'.format(epoch+1, num_epochs,loss.item()))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "8f2e0973-31c8-4879-9108-89d418d1b056",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch [10/100 Loss: 95.5826\n",
      "Epoch [20/100 Loss: 135.4428\n",
      "Epoch [30/100 Loss: 112.6919\n",
      "Epoch [40/100 Loss: 84.2813\n",
      "Epoch [50/100 Loss: 77.5900\n",
      "Epoch [60/100 Loss: 99.5134\n",
      "Epoch [70/100 Loss: 68.5490\n",
      "Epoch [80/100 Loss: 84.0584\n",
      "Epoch [90/100 Loss: 119.4308\n",
      "Epoch [100/100 Loss: 152.1199\n"
     ]
    }
   ],
   "source": [
    "fit(100,model,loss_fn,opt,train_dl)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "id": "404b257b-45fb-4f0b-a399-64b76a252c39",
   "metadata": {},
   "outputs": [],
   "source": [
    "height = 167\n",
    "height = height/2.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "id": "bf1b548a-8b84-4f8e-9c5e-bfe171bd6cb0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor([[57.5882]], grad_fn=<MulBackward0>)"
      ]
     },
     "execution_count": 70,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "ans = model(torch.tensor([[height]]))\n",
    "ans = ans*0.453592\n",
    "ans"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}