01-DNN-Regression.ipynb

      "354/354 [==============================] - 0s 165us/sample - loss: 4.9512 - mae: 1.6168 - mse: 4.9512 - val_loss: 9.3491 - val_mae: 2.2524 - val_mse: 9.3491\n",
      "Epoch 80/100\n",
      "354/354 [==============================] - 0s 161us/sample - loss: 4.8233 - mae: 1.5951 - mse: 4.8233 - val_loss: 10.4702 - val_mae: 2.3727 - val_mse: 10.4702\n",
      "Epoch 81/100\n",
      "354/354 [==============================] - 0s 163us/sample - loss: 4.8356 - mae: 1.6313 - mse: 4.8356 - val_loss: 10.8360 - val_mae: 2.5334 - val_mse: 10.8360\n",
      "Epoch 82/100\n",
      "354/354 [==============================] - 0s 165us/sample - loss: 4.7664 - mae: 1.5728 - mse: 4.7664 - val_loss: 9.0297 - val_mae: 2.1707 - val_mse: 9.0297\n",
      "Epoch 83/100\n",
      "354/354 [==============================] - 0s 160us/sample - loss: 4.8996 - mae: 1.5917 - mse: 4.8996 - val_loss: 9.0345 - val_mae: 2.1374 - val_mse: 9.0345\n",
      "Epoch 84/100\n",
      "354/354 [==============================] - 0s 160us/sample - loss: 4.7986 - mae: 1.6048 - mse: 4.7986 - val_loss: 9.4659 - val_mae: 2.2548 - val_mse: 9.4659\n",
      "Epoch 85/100\n",
      "354/354 [==============================] - 0s 171us/sample - loss: 4.5527 - mae: 1.5404 - mse: 4.5527 - val_loss: 9.5788 - val_mae: 2.1823 - val_mse: 9.5788\n",
      "Epoch 86/100\n",
      "354/354 [==============================] - 0s 162us/sample - loss: 4.6033 - mae: 1.5829 - mse: 4.6033 - val_loss: 9.7029 - val_mae: 2.2306 - val_mse: 9.7029\n",
      "Epoch 87/100\n",
      "354/354 [==============================] - 0s 158us/sample - loss: 4.5717 - mae: 1.5727 - mse: 4.5717 - val_loss: 9.1632 - val_mae: 2.1194 - val_mse: 9.1632\n",
      "Epoch 88/100\n",
      "354/354 [==============================] - 0s 158us/sample - loss: 4.4614 - mae: 1.5356 - mse: 4.4614 - val_loss: 8.9921 - val_mae: 2.1007 - val_mse: 8.9921\n",
      "Epoch 89/100\n",
      "354/354 [==============================] - 0s 164us/sample - loss: 4.6582 - mae: 1.5248 - mse: 4.6582 - val_loss: 9.0494 - val_mae: 2.1288 - val_mse: 9.0494\n",
      "Epoch 90/100\n",
      "354/354 [==============================] - 0s 158us/sample - loss: 4.3272 - mae: 1.5289 - mse: 4.3272 - val_loss: 9.8204 - val_mae: 2.3003 - val_mse: 9.8204\n",
      "Epoch 91/100\n",
      "354/354 [==============================] - 0s 157us/sample - loss: 4.4199 - mae: 1.5274 - mse: 4.4199 - val_loss: 10.0219 - val_mae: 2.2723 - val_mse: 10.0219\n",
      "Epoch 92/100\n",
      "354/354 [==============================] - 0s 163us/sample - loss: 4.3447 - mae: 1.5423 - mse: 4.3447 - val_loss: 11.5811 - val_mae: 2.5490 - val_mse: 11.5811\n",
      "Epoch 93/100\n",
      "354/354 [==============================] - 0s 163us/sample - loss: 4.3355 - mae: 1.5369 - mse: 4.3355 - val_loss: 8.8431 - val_mae: 2.1337 - val_mse: 8.8431\n",
      "Epoch 94/100\n",
      "354/354 [==============================] - 0s 156us/sample - loss: 4.3791 - mae: 1.5442 - mse: 4.3791 - val_loss: 9.4194 - val_mae: 2.1541 - val_mse: 9.4194\n",
      "Epoch 95/100\n",
      "354/354 [==============================] - 0s 157us/sample - loss: 4.3247 - mae: 1.5456 - mse: 4.3247 - val_loss: 8.9440 - val_mae: 2.0844 - val_mse: 8.9440\n",
      "Epoch 96/100\n",
      "354/354 [==============================] - 0s 164us/sample - loss: 4.2525 - mae: 1.4911 - mse: 4.2525 - val_loss: 9.1399 - val_mae: 2.1911 - val_mse: 9.1399\n",
      "Epoch 97/100\n",
      "354/354 [==============================] - 0s 161us/sample - loss: 4.2203 - mae: 1.4947 - mse: 4.2203 - val_loss: 9.4216 - val_mae: 2.2468 - val_mse: 9.4216\n",
      "Epoch 98/100\n",
      "354/354 [==============================] - 0s 158us/sample - loss: 4.0427 - mae: 1.5021 - mse: 4.0427 - val_loss: 9.8772 - val_mae: 2.2684 - val_mse: 9.8772\n",
      "Epoch 99/100\n",
      "354/354 [==============================] - 0s 156us/sample - loss: 4.1551 - mae: 1.4745 - mse: 4.1551 - val_loss: 9.2742 - val_mae: 2.1680 - val_mse: 9.2742\n",
      "Epoch 100/100\n",
      "354/354 [==============================] - 0s 166us/sample - loss: 4.1385 - mae: 1.4979 - mse: 4.1385 - val_loss: 9.1496 - val_mae: 2.1970 - val_mse: 9.1496\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(x_train,\n",
    "                    y_train,\n",
    "                    epochs          = 100,\n",
    "                    batch_size      = 10,\n",
    "                    verbose         = 1,\n",
    "                    validation_data = (x_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 6 - Evaluate\n",
    "### 6.1 - Model evaluation\n",
    "MAE =  Mean Absolute Error (between the labels and predictions)  \n",
    "A mae equal to 3 represents an average error in prediction of $3k."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "x_test / loss      : 9.1496\n",
      "x_test / mae       : 2.1970\n",
      "x_test / mse       : 9.1496\n"
     ]
    }
   ],
   "source": [
    "score = model.evaluate(x_test, y_test, verbose=0)\n",
    "\n",
    "print('x_test / loss      : {:5.4f}'.format(score[0]))\n",
    "print('x_test / mae       : {:5.4f}'.format(score[1]))\n",
    "print('x_test / mse       : {:5.4f}'.format(score[2]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 6.2 - Training history\n",
    "What was the best result during our training ?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "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>loss</th>\n",
       "      <th>mae</th>\n",
       "      <th>mse</th>\n",
       "      <th>val_loss</th>\n",
       "      <th>val_mae</th>\n",
       "      <th>val_mse</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "      <td>100.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>17.575156</td>\n",
       "      <td>2.393877</td>\n",
       "      <td>17.575157</td>\n",
       "      <td>17.672065</td>\n",
       "      <td>2.668328</td>\n",
       "      <td>17.672065</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>57.558606</td>\n",
       "      <td>2.374958</td>\n",
       "      <td>57.558606</td>\n",
       "      <td>44.606822</td>\n",
       "      <td>1.899542</td>\n",
       "      <td>44.606823</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.042664</td>\n",
       "      <td>1.474455</td>\n",
       "      <td>4.042665</td>\n",
       "      <td>8.843062</td>\n",
       "      <td>2.084356</td>\n",
       "      <td>8.843062</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>5.245075</td>\n",
       "      <td>1.661062</td>\n",
       "      <td>5.245075</td>\n",
       "      <td>9.571723</td>\n",
       "      <td>2.199997</td>\n",
       "      <td>9.571724</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>7.007228</td>\n",
       "      <td>1.878118</td>\n",
       "      <td>7.007228</td>\n",
       "      <td>10.348436</td>\n",
       "      <td>2.288131</td>\n",
       "      <td>10.348436</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>10.428114</td>\n",
       "      <td>2.234086</td>\n",
       "      <td>10.428113</td>\n",
       "      <td>11.670978</td>\n",
       "      <td>2.460876</td>\n",
       "      <td>11.670978</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>496.922868</td>\n",
       "      <td>20.339752</td>\n",
       "      <td>496.922882</td>\n",
       "      <td>419.540121</td>\n",
       "      <td>18.498610</td>\n",
       "      <td>419.540131</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             loss         mae         mse    val_loss     val_mae     val_mse\n",
       "count  100.000000  100.000000  100.000000  100.000000  100.000000  100.000000\n",
       "mean    17.575156    2.393877   17.575157   17.672065    2.668328   17.672065\n",
       "std     57.558606    2.374958   57.558606   44.606822    1.899542   44.606823\n",
       "min      4.042664    1.474455    4.042665    8.843062    2.084356    8.843062\n",
       "25%      5.245075    1.661062    5.245075    9.571723    2.199997    9.571724\n",
       "50%      7.007228    1.878118    7.007228   10.348436    2.288131   10.348436\n",
       "75%     10.428114    2.234086   10.428113   11.670978    2.460876   11.670978\n",
       "max    496.922868   20.339752  496.922882  419.540121   18.498610  419.540131"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "df=pd.DataFrame(data=history.history)\n",
    "df.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "min( val_mae ) : 2.0844\n"
     ]
    }
   ],
   "source": [
    "print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAg4AAAGdCAYAAAB6oftJAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/d3fzzAAAACXBIWXMAAAsTAAALEwEAmpwYAABFmUlEQVR4nO3deXxkVZ3//9entlTS6YVutl6QVRZZVVpBHDYZRPmJozgKCoIjMFIiwszXUVwAl4coDMtPpETRUVHwCyg6MiAoI6sgi9jYIAgIDfRK70uSSi33fP84t5Kb6pt0pTupJf1+Ph7lrdw6t3LqNna9+6zmnENERESkHolmV0BERETah4KDiIiI1E3BQUREROqm4CAiIiJ1U3AQERGRuik4iIiISN0UHERERKRuCg4isklm9iMzc2Z272Zc+49m9kMze97M1pvZBjN7IXzPY+t8j73M7FtmNj98j34ze9XMHjWz75jZh8xs+jDXdpnZuWZ2j5ktN7Oima0ws6fM7FYz+7SZ7TvazyWytTItACUim2JmPwJOA+5zzh1Z5zXTgRuA4yKnewEHTIqcuwv4sHNu1TDvcxZwNZAJTzlgDdAFdESKnu+cu6rm2j2AO4HdI6d7gACYHDn3pHPuoDo+lshWTy0OIjLmzGwa8CA+NPQDXwN2dc5Ncs51AzsDXwYKwDuBB8Nrat/nMOBafGi4GzgCyDrnpgOdwJ7AOcDD+EARvTYF/AofGpYCZwMznHPdzrkpwAzgBOB6oG/sPr3IxKYWBxHZpNG2OJjZLcAH8F/I73LO3TdMucPxLQKdwC3OuQ/WvP5/gQ8BfwHe5JyrjPA7O51zfZGfjwN+E/441zn3eL3Xisjw1OIgImPKzA7GhwaAC4cLDQDOufuBi8If/9nM3lxTZP/w+JuRQkP4XrVf/NVrl40UGoa5VkSGoeAgImPtX8PjGuCaOsp/G1hbc22t2VtQn+lmlt2C60UkQsFBRMbakeHxt/X8Sz4s89uaa6uqLQUfMrP3j7Ie1WvTwLVmNnmkwiJSHwUHERkzZpYG9gh/fHIUl/4lPL4+HNRYdSl+JkYa+IWZLQindp5tZm82s+Rwb+icuweodpOcBiwxs/8xsy+Z2XFxgzFFZNMUHERkLEXXUlg5iutWxL2Hc+5p4Bjg6fDUzsDpQB7forDSzK41s52Ged/qrIkAPwX0eOAr+EGTK8O1Hd49inqKbPUUHERkLNlYX+ecexg/0PFI4JvA/cC68OWp+HER883sH2KuXeecOw3YFTgfuBV4OXw5Eb7n7WZ2+WbWW2Sro+AgImMp2sowYxTXRctutBCU8+5zzn3OOXcEvlXi7cCP8es3TAVuMrPOuDd3zr3inLvKOXeic24XfMvFv0V+17+Z2XtHUV+RrZaCg4iMGedcCfh7+OOBo7j0gPD4vHOuXMfvqTjn/uCcOx24MDw9k6GrVI50/SvOuSuBQ/FjKAD+ZRT1FdlqKTiIyFi7JzweO1wLQFRYprpnxbBrPozgB5Hne47mQufcc/gVLkd9rcjWSsFBRMba98LjNOCTdZQ/B9/VAPDdzfh9PZHnxS24fnOuFdnqKDiIyJhyzj2GH4QI8JVwWelY4YDGL4c//qJ2hUczO3KkKZehD0eez4tcu5+Z7TjShWa2A3B07bUiMjwFBxEZjbSZbbuJRxo4A/gbfg+K35rZV8zsddU3MbOdzOwi/MJPnWHZM2N+338CL5jZxWY2N3xvzCxhZrua2SXAt8Ky8/AzLqqOBF4ys5+Y2Xui226b2RQz+wi+m2Iqfrrmt8fg/ohMeNrkSkQ2KbLJVT2Ocs7da2YzgJ8B/xh5rQc/C6I7cu5u4CTn3EbrPpjZw8AhkVMBfnnqbvyiUFXPAO92zi2IXPuv+J01ozaEvz+6imQB+IRz7sd1fTqRrVxq00VEREYvDALHmtk78d0Jbwd2xK/Z8CLwB+BG59ydI7zNUfhtt98BzMWvSjkNKOO3yn4S+CXwU+fckDEKzrnvmtmjwLvC3/2G8Pcn8dNGnwd+D1wXDRwiMjK1OIiIiEjdNMZBRERE6qbgICIiInVTcBAREZG6KTiIiIhI3RQcRpDL5Vwul9PoURERkZCmY9ZH4UFERLYWw25zD2pxEBERkVFQcBAREZG6KTiIiIhI3RQcREREpG4aHLkZSqUSCxcupFAoNLsqLS2bzTJnzhzS6fSmC4uISFtQcNgMCxcuZPLkyeyyyy6YjTj4dKvlnGPlypUsXLiQXXfdtdnVERGRMdISXRVm5oZ5bIgpu5eZ/crMVptZj5k9YGZHD/O+CTM738yeNbOCmb1qZpeb2aQtqW+hUGDGjBkKDSMwM2bMmKFWGRGRCaaVWhweAL5Xc64U/cHMdgcewm+peymwFjgTuMvM3uWcu7vm+iuBc/Hb7l4O7BP+/EYzO8Y5F2xuZRUaNk33SERk4mml4PCic+6nmyhzCTANeLNzbh6AmV0PPA1cY2Z7u3CfcDPbF/gUcKtz7sTqG5jZS8C3gJOAG8f6QzRKd3c3GzZs1CAjIiIyrlqiq6LKzDJm1j3Ma5OAE4B7q6EBwDm3Afg+sCcwN3LJyfjVr66qeavrgF7glDGruIiIyFailYLDB/Bf6OvN7DUzu9rMpkZePwDoAB6OufaP4TEaHOYCAfBotKBzrgDMqynbtpxzfOYzn2G//fZj//3356abbgJgyZIlHH744Rx00EHst99+PPDAA1QqFU4//fSBsldeeWWTay8iIu2mVboqHgVuAV4ApgDvBs4BjjCzt4WtCrPCsotirq+emx05NwtY4ZzrH6b828ws45wrbknF3/nV27fk8hHd9aXjN1nm1ltvZd68eTz55JOsWLGCuXPncvjhh3PjjTfyzne+ky984QtUKhV6e3uZN28eixYt4qmnngJgzZo141Z3ERGZmFqixcE591bn3H86537lnLveOXcS8AVgf+DTYbGu8BgXBAo1ZarP48oOV36AmZ1lZo/X/QGa6MEHH+Tkk08mmUyyww47cMQRR/DYY48xd+5cfvjDH3LxxRczf/58Jk+ezG677caLL77Ipz71Ke68806mTJnS7OqLiEibaYngMIzLgCJQ/Wd3b3jsiCmbrSlTfR5XdrjyA5xz33POHVx/VZsnHAu6kcMPP5z777+f2bNnc+qpp3L99dezzTbb8OSTT3LkkUdyzTXXcMYZZzS4tiIi0u5apatiI865kpktBrYNTy0Oj7NjilfPRbsxFgNvMLOOmO6K2fhujC3qpoD6uhMAVq4vsHK9b+iY3t3BtlM6t/RXAz4gfPe73+W0005j1apV3H///Vx22WW8/PLLzJ49mzPPPJOenh6eeOIJ3v3ud5PJZDjxxBPZfffdOf3008ekDiIisvVo2eBgZllgDoMDH+fjux4OjSl+SHiMdi88BhwLvAW/RkT0fQ8C7h/bGo8sEVnTIIhvJNgs73vf+3j44Yc58MADMTMuvfRSdtxxR3784x9z2WWXkU6n6e7u5vrrr2fRokV87GMfIwj88hWXXHLJ2FVERES2Ck0PDmY2wzm3Mualr+Lrdxv4aZdmdhvwfjM70Dn3ZHh9N3AG8DxDZ1DcBHweOI9IcMAvGNUF3DDGH2VE0bWQhuteGI3qGg5mxmWXXcZll1025PXTTjuN0047baPrnnjiiS3+3SIisvVqenAAvmhmhwD3AK8A3fhZFUcBjwBXR8peALwD+K2ZXQmswweB2cDxLvKN7Jybb2bXAOeY2a3AHQyuHHkfDV78KbqK4hg2OIiIiDRUKwSHe4E3AKcBM4AKvvXgC8AV4boLADjnXjCzw4BvAJ8DMsATwHExy02Db21YAJyFH2S5Ah9ELtyS5aY3R2KMWxxERESaoenBwTn338B/j6L8M8B76yxbwe9Rcfnm1W7s2DiNcRAREWmkVp6OOaFEt3tSi4OIiLQrBYcGGTLGQblBRETalIJDg2iMg4iITAQKDg2iMQ4iIjIRKDg0yJB1HBo8IbO7O3ancgAWLFjAfvvt18DaiIhIO1NwaBCNcRARkYmg6dMx294Zx9VVLA3sOdr3/v6dsac/+9nPsvPOO5PL5QC4+OKLMTPuv/9+Vq9eTalU4mtf+xrvfW9ds1YHFAoFzj77bB5//HFSqRRXXHEFRx11FE8//TQf+9jHKBaLBEHAL37xC2bNmsUHP/hBFi5cSKVS4Utf+hIf+tCHRvsJRUSkzSg4tKGTTjqJ8847byA43Hzzzdx5552cf/75TJkyhRUrVnDIIYdwwgknDGnp2JRrrrkGgPnz5/Pss89y7LHH8txzz3Httdfy6U9/mo985CMUi0UqlQp33HEHs2bN4vbbbwdg7dq1Y/9BRUSk5airog298Y1v5LXXXmPx4sU8+eSTbLPNNsycOZPPf/7zHHDAARxzzDEsWrSIZcuWjep9H3zwQU499VQA9t57b3beeWeee+45Dj30UL7+9a/zzW9+k5dffpnOzk72339/7r77bj772c/ywAMPMHXq1PH4qCIi0mLU4rClhulOiPP8krUDUzH3mDl1yI6Zo/WBD3yAn//85yxdupSTTjqJG264geXLl/OnP/2JdDrNLrvsQqFQ2PQbRQw3TfTDH/4wb33rW7n99tt55zvfyfe//32OPvpo/vSnP3HHHXdwwQUXcOyxx3LhhRdu9ucREZH2oODQQGaDAyOdc0OnWozSSSedxJlnnsmKFSu47777uPnmm9l+++1Jp9Pcc889vPzyy6N+z8MPP5wbbriBo48+mueee45XXnmFvfbaixdffJHddtuNc889lxdffJG//OUv7L333kyfPp1TTjmF7u5ufvSjH232ZxERkfah4NBACTOCcCrmls6s2HfffVm/fj2zZ89m5syZfOQjH+E973kPBx98MAcddBB77733qN8zl8vxiU98gv33359UKsWPfvQjOjo6uOmmm/jpT39KOp1mxx135MILL+Sxxx7jM5/5DIlEgnQ6zXe+850t+0AiItIWTKsYDi+XyzmAfD4/5PwzzzzDPvvsM+r3e2nZOkoVvynnLttPJpNKjkEtW9vm3isREWmaEZvDNTiygbSWg4iItDt1VTSQNXG/ivnz5w/MmKjq6OjgkUceaWg9RESkvSk4NFCiiS0O+++/P/PmzWvsLxURkQlHXRWbaXNaDKItDkGD96toBo2fERGZeBQcNkM2m2XlypWj/mLcmsY4OOdYuXIl2Wy22VUREZExpK6KzTBnzhwWLlzI8uXLR3Xd2t4ihWIFgJ4VGbLpiT2rIpvNMmfOnGZXQ0RExpCCw2ZIp9Psuuuuo77u0l/N43/nLwHg/5xwIP+4j75URUSkvairooE6Ii0M/eVKE2siIiKyeRQcGiiTGrzdxXLQxJqIiIhsHgWHBoquFFksqcVBRETaj4JDA3VEWhzUVSEiIu1IwaGB0pEWh5K6KkREpA0pODRQR1otDiIi0t4UHBpo6BgHtTiIiEj7UXBooKGzKtTiICIi7UfBoYE6UtF1HNTiICIi7UfBoYEyabU4iIhIe1NwaKAhYxzU4iAiIm1IwaGBhoxx0AJQIiLShhQcGkhjHEREpN0pODSQZlWIiEi7U3BooExaYxxERKS9KTg00JCuCo1xEBGRNqTg0EDRrgrtVSEiIu1IwaGBol0V2qtCRETaUarZFdhq/O0vpF74K6eu+St/zs7hqexsKkFAMqHsJiIi7UPBoVGeehz7zc2cAhQtyVPZ2RTLAZ0ZBQcREWkf+tZqlHRm4GnGlQENkBQRkfaj4NAoqfTA07TzgUFTMkVEpN0oODTKkBaHanBQi4OIiLQXBYdGiWlx6C+pxUFERNqLgkOjqMVBREQmAAWHRklrjIOIiLS/lgsOZtZlZi+ZmTOzb8e8vpeZ/crMVptZj5k9YGZHD/NeCTM738yeNbOCmb1qZpeb2aTx/yQ1hnRV+FkVanEQEZF203LBAfgKsG3cC2a2O/AQcChwKfAZoBu4y8yOibnkSuAK4K/Ap4BbgHOB28yssZ892uJAdYyDgoOIiLSXlloAyszeBJwH/AdweUyRS4BpwJudc/PCa64HngauMbO9nXMuPL8vPizc6pw7MfI7XgK+BZwE3Dhen2UjsWMc1FUhIiLtpWVaHMwsCVwH3AncGvP6JOAE4N5qaABwzm0Avg/sCcyNXHIyYMBVNW91HdALnDJ2ta9D7DoOanEQEZH20jLBATgf2Bs4Z5jXDwA6gIdjXvtjeIwGh7lAADwaLeicKwDzasqOv5gWh361OIiISJtpieBgZrsCXwa+4pxbMEyxWeFxUcxr1XOza8qvcM71D1N+WzPLxLw2PtTiICIiE0BLBAfgO8BL+IGMw+kKj3FBoFBTpvo8ruxw5QeY2Vlm9vgIdRm9mL0qiloASkRE2kzTg4OZnQIcC3zCOVcaoWhveOyIeS1bU6b6PK7scOUHOOe+55w7eIS6jF7cypFqcRARkTbT1FkVZtaBb2W4A1hqZnuEL1W7HKaG51YAi2tei6qei3ZjLAbeYGYdMd0Vs/HdGMUt/Qx1ixnjUNIYBxERaTPNbnHoBLYDjgeejzzuDV8/Jfz5DGA+vuvh0Jj3OSQ8RrsXHsN/vrdEC5pZFjiopuz4U4uDiIhMAM1ex6EH+OeY89sBefzUzB8Af3HObTCz24D3m9mBzrknAcysGx8snmfoDIqbgM/j14V4IHL+TPzYhhvG9qNsQjpm5UiNcRARkTbT1OAQjmn4ee15M9slfPp351z09QuAdwC/NbMrgXX4IDAbOL66+FP43vPN7BrgHDO7Fd8dsg9+5cj7aOTiTzCkxSFDAM5pVoWIiLSdZrc4jIpz7gUzOwz4BvA5IAM8ARznnLs75pLzgAXAWfjukBXA1cCFzrnG/nPfzIeHsh//maaidRxERKTttGRwCNdysGFeewZ4b53vU8EvXR23fHXjpSPBwVXU4iAiIm2n2YMjty7R7gpX0V4VIiLSdhQcGikyJTPtKhS1O6aIiLQZBYdGGtLiUNZ0TBERaTsKDo1U2+KgrgoREWkzCg6NtNEYB7U4iIhIe1FwaKT00NUj+7UAlIiItBkFh0ZKDd0hs6QWBxERaTMKDo1U2+JQDogsdikiItLyFBwaqWaMA0Cpou4KERFpHwoOjRSdVYEPDppZISIi7UTBoZHittbWIlAiItJGFBwaKR0dHKkWBxERaT8KDo00ZHBkGUBrOYiISFtRcGik1NCVI0EtDiIi0l4UHBopvfGsCo1xEBGRdqLg0EjpjQdHqsVBRETaiYJDI8Ws46AxDiIi0k4UHBopvfEYB3VViIhIO1FwaKQhLQ7VWRXqqhARkfah4NBIMS0O6qoQEZF2ouDQSNEWh3DJ6X61OIiISBtRcGikmBYHba0tIiLtRMGhkWLGOPSX1OIgIiLtQ8GhkTTGQURE2pyCQyPF7I6pWRUiItJOFBwaKWblyH61OIiISBtRcGikmL0qiloASkRE2oiCQyOpq0JERNqcgkMjRQZHDq4cqRYHERFpHwoOjRTT4qAFoEREpJ0oODTSkBYHTccUEZH2o+DQSLVLTjtHUQtAiYhIG1FwaKREApKpgR/TBJqOKSIibUXBodFqxjmUNMZBRETaiIJDow1ZdrqsFgcREWkrCg6NVrMIlMY4iIhIO1FwaLSargrNqhARkXai4NBoNftVlANHJXBNrJCIiEj9FBwaLaXVI0VEpH0pODRazA6Z2q9CRETahYJDo8WsHtmvHTJFRKRNKDg0WnRwJFp2WkRE2ouCQ6PF7pCprgoREWkPCg6NNmQ6pg8ManEQEZF2oeDQaEMWgPItDv1aBEpERNqEgkOjpeJmVajFQURE2kPTg4OZ7WVmN5jZM2a21sx6zexZM7vCzGYOU/5XZrbazHrM7AEzO3qY906Y2fnh+xXM7FUzu9zMJo3/JxvGkL0qNB1TRETaS2rTRcbdHGAm8EtgIVAG9gfOAk4ys4Occ68BmNnuwENhmUuBtcCZwF1m9i7n3N01730lcG743pcD+4Q/v9HMjnHONf4bOzV0rwrQdEwREWkfTQ8Ozrn/Bf639ryZ3Q/cDJyODwkAlwDTgDc75+aF5a4HngauMbO9nXMuPL8v8CngVufciZH3fQn4FnAScOO4fKiRxLQ4lCpqcRARkfbQ9K6KEbwcHrcBCLsXTgDurYYGAOfcBuD7wJ7A3Mj1JwMGXFXzvtcBvcAp41HpTUrFDY5Ui4OIiLSHlgkOZpY1s23NbI6ZHQt8N3zpjvB4ANABPBxz+R/DYzQ4zAUC4NFoQedcAZhXU7ZxYloc+jU4UkRE2kTLBAfgDGA58CpwF75L4hTn3APh67PC46KYa6vnZkfOzQJWOOf6hym/rZllYl4bXzF7VZQ0OFJERNpEKwWHXwH/CLwP+AqwBtgu8npXeIwLAoWaMtXncWWHKz/AzM4ys8c3WePNEbPktLoqRESkXbRMcHDOLXTO3e2c+5Vz7iLgNOCbZnZBWKQ3PHbEXJ6tKVN9Hld2uPLRunzPOXdw/bUfhfTGsyo0HVNERNpFywSHWs65vwB/BnLhqcXhcXZM8eq5aDfGYnx3RFx4mI3vxiiORV1HRWMcRESkjbVscAh1AtPD5/PxXQ+HxpQ7JDxGuxcew3++t0QLmlkWOKimbOPEzKooaslpERFpE00PDma24zDnjwL2I5wxEU67vA040swOjJTrxg+sfJ6hMyhuAhxwXs1bn4kf23DD2HyCUVKLg4iItLGmLwAFfCdcWvr3+LUbssCb8Qs0rQf+PVL2AuAdwG/N7EpgHT4IzAaOry7+BOCcm29m1wDnmNmt+Gmd1ZUj76MZiz+BVo4UEZG21grB4Wf4gZCn4mdROHyA+C5wmXPulWpB59wLZnYY8A3gc0AGeAI4Lma5afCtDQvwy1cfD6wArgYubMpy0xDf4qDgICIibaLpwcE5dzN+ael6yz8DvLfOshX8HhWXb17txkHcypHqqhARkTYxJsEhl8sdCByFX+L5gXw+35yBh+0gZlvtfg2OFBGRNlHX4MhcLnd4Lpe7PpfLHRLz2sX47oLLgf8EHsnlcleMaS0nEnVViIhIG6t3VsU/Ax8EnomezOVy/wBciN8T4gbgWmAl8OlcLvfuMaznxJGOWTlSXRUiItIm6g0OhwKP5PP5tTXn/xU/mPHcfD7/0Xw+/0ngcKAMfGzsqjmBpAZbHDSrQkRE2k29wWEWfp2EWkcDPfitqgHI5/PP4jepas7uk60uZpMrBQcREWkX9QaHGcCy6IlcLrcjsCPwUD6fL9eUfx7YYcurNwHVzqpwjmI5IBhcgkJERKRl1Rsc+tg4CLwpPP45pnw/vrtCaiWTkPC3PQEk8TMqtNGViIi0g3qDw7PAu3K5XHT65vH48Q0PxZTfCViyhXWbuNIa5yAiIu2p3nUcfg5cCvw6l8tdC+wJfBxYC/wupvxh1MzAkIhUGvoLgB/n0IeCg4iItId6g8PVwMnAccA7w3MG/J98Pl+IFszlcm8FdgmvkThqcRARkTZVV1dFPp/vx0+zvBC4E79mw3vy+fy3Y4ofBPw3fidLiRO7eqSCg4iItL66l5zO5/M9wNfqKPdd/AZVMpwhLQ7ar0JERNpHvYMjZSxpvwoREWlTW7zJVS6XSwNn4xeDMuA+4Jqwe0PipKNrOairQkRE2ke9m1x9NJfLvZLL5d5Rcz4B/A9wJXAC8B7gMuD3NVM3JSql/SpERKQ91dtV8Y/AZODemvMnh68tA84APgQ8AhyCn64pcYbskBmOcVCLg4iItIF6g8Ob8EtL1367nYJfBOqj+Xz+v/L5/C3Asfj1HT44dtWcYLRfhYiItKl6g8MOwIsx598GLMvn83dXT+Tz+Q3A7cB+W169CSpuh0x1VYiISBuoNzhMwe+COSCXy+2B7774Q0z5hcC0LarZRBbb4qBZFSIi0vrqDQ6rgV1rzlW3zY7b5CoFbNjcSk14WjlSRETaVL3B4c/A8blcbmbk3En48Q33xZR/Pdrkangx6zgU1VUhIiJtoN4pkz/AD3p8OJfL3Yrf5OrdwAv5fH5IV0U4DfMf8EtTS5wh6zj4WRUFtTiIiEgbqHeviluA7wOvA87Dh4a1wJkxxd8DbEP8rpkC8S0OCg4iItIG6l5yOp/PnwW8Hfgsfs2GffP5fFw3RS9wPvDrManhRKQxDiIi0qZGtbpjPp9/CHhoE2XuAu7akkpNeDErRxbKmlUhIiKtT5tcNUPM7pjqqhARkXYw6v0kcrncocBZwGHALPzMiiXAg8B1+Xz+4TGt4UQUuzumgoOIiLS+uoNDuAtmHvgX/C6YUXuEj9Nyudx/Abl8Pl8as1pONEP2qgi7KhQcRESkDYymxeEH+L0pVuNnWPwOeBUfIubgN7v6OD5YZIDTxrSmE0lq4221tY6DiIi0g7qCQy6XOwYfGv4EvCefzy+tKfIscHcul7sCv832Kblc7vp8Pv+/Y1rbiSKmxUFLTouISDuod3Dkmfi9Kv4pJjQMyOfzy4B/AvqIX+NBQLtjiohI26o3OBwK/Cafzy/aVMGwzO34nTMlTmrjlSO1O6aIiLSDeoPD9sDzo3jfF4DtRl+drUR64zEOlcBRrqi7QkREWlu9waEXv4V2vSYDhdFXZysRaXHoYLClQd0VIiLS6uoNDs8DR4/ifY9idC0UW5foAlAMtjKou0JERFpdvcHhdmCfXC6X21TBXC73CeAN+NkVEic6xmFIi4O6KkREpLXVu47Dt4BPAf9/LpebBVyWz+fXRgvkcrkpwGfwm2CtAq4ey4pOKDHTMUFdFSIi0vrqCg75fH5NLpc7Ed/ycAHwb7lc7k/4BaAcfrvtNwMd+KmYH8jn86vHp8oTQHTJ6aA88FxdFSIi0upGs632/cBbgXuALH6vipOAk8PnWeBe4JBhttuWqkiLQ0otDiIi0kZGu632X4FjcrncLsDbgZn4JaeXAA/m8/mXAHK5XBbI5PP5dWNb3QliuBYHBQcREWlxo94dEyCfzy8AFoxQ5DvAqZv7/hNeMgmWABeQwJFwAYElFBxERKTl1d1VsRlqd9CUKrOaRaDC1SMVHEREpMWNZ3CQkaRi9qsoazqmiIi0NgWHZolZdlotDiIi0uoUHJoldmttBQcREWltCg7NklKLg4iItB8Fh2aJtjhQHeOg4CAiIq2trumSuVxu3L7RzGxP4BTgWGB3/EJSfwduAa5yzvXUlN8L+CZwBJABngAucs79Pua9E8CngX8FdgGWAzcDF9a+b8OlNKtCRETaT70tDrYZj3r9C3A+Pix8Bb/fxd+ArwEPmVnnQCXMdgceAg4FLg3LdgN3mdkxMe99JXAF8Ff8Xhu3AOcCt4WhonlixzhoVoWIiLS2eveqGM8v2Z8DlzjnoptmXWtmzwNfAD4OfDs8fwkwDXizc24egJldDzwNXGNmezvnXHh+X3xYuNU5d2L1jc3sJfymXScBN47j5xpZ3BgHdVWIiEiLa/oYB+fc4zWhoeqm8LgfgJlNAk4A7q2GhvD6DcD3gT2BuZHrT8a3fFxV877XAb347pHmSces46CuChERaXFNDw4jmBMel4XHA/C7bz4cU/aP4TEaHOYCAfBotKBzrgDMqynbeBrjICIibaglg4OZJYELgTKD3QmzwuOimEuq52ZHzs0CVjjn+ocpv62ZZWJew8zOMrPHR13x0Ygb46CuChERaXEtGRzw3QuH4Gc//C081xUe44JAoaZM9Xlc2eHKD3DOfc85d3Ddtd0ccUtOa3CkiIi0uJYLDmb2VeAc4HvOuUsiL/WGx46Yy7I1ZarP48oOV76xtHKkiIi0oZYKDmZ2MfBF4IfAJ2peXhweZ7Ox6rloN8ZifHdEXHiYje/GKG5+bbeQZlWIiEgbapngYGYXARcB1wNnVKdVRszHdz0cGnP5IeExOi7hMfzne0vN78kCB9WUbTy1OIiISBtqieBgZhcCFwM/AT7mnNuosz+cdnkbcKSZHRi5ths4A3ieoTMobgIccF7NW52JH9tww9h9gs0QnY6JgoOIiLSHuhaAGk9m9kngy8ArwN3Ah82GLDy5zDn3u/D5BcA7gN+a2ZXAOnwQmA0cH22lcM7NN7NrgHPM7FbgDmAf/MqR99HMxZ8AUoMtDtXpmMVyQOAcCRvNwpsiIiKN0/TgwOB6Cq8Dfhzz+n3A7wCccy+Y2WHAN4DPMbhXxXHOubtjrj0PWACcBRwPrACuxs/WaO4UhkiLQ9YGq1IsB2TTyWbUSEREZJOaHhycc6cDp4+i/DPAe+ssWwEuDx+tJTM4ZrOL8sDz/lJFwUFERFpWS4xx2CplB/buYpIbGhxERERalYJDs2QH156aFJkVquAgIiKtTMGhWToHg0NXoOAgIiLtQcGhWbLDBActAiUiIi1MwaFZIsEhO6TFQftViIhI61JwaJZIV0W2MrgXl7oqRESklSk4NEtkVkVHuR/CtavUVSEiIq1MwaFZUumB/SoSODrCKZlqcRARkVam4NBM0QGS4ZRMBQcREWllCg7NFOmuqM6sUFeFiIi0MgWHZopZy0GzKkREpJUpODRTzFoO6qoQEZFWpuDQTJ0bj3EoqqtCRERamIJDMw1pcSgBUFCLg4iItDAFh2bSrAoREWkzCg7NFDM4sqjgICIiLUzBoZliBkcWyppVISIirUvBoZliBkeqq0JERFqZgkMzxSwApa4KERFpZQoOzRTXVaHgICIiLUzBoZk6N56OqSWnRUSklSk4NFN20sDTzuoCUFpyWkREWpiCQzPFbXKlrgoREWlhCg7NFDOrQmMcRESklSk4NFMkOEwKWxwC5yhX1F0hIiKtScGhmTJZMAMg68oknA8M6q4QEZFWpeDQTIkEdAyOc+h02uhKRERam4JDs8XtV6Flp0VEpEUpODRbzCJQ6qoQEZFWpeDQbDEDJNVVISIirUrBodkiLQ4Di0Bp9UgREWlRCg7NpkWgRESkjSg4NJs2uhIRkTai4NBsMatHamttERFpVQoOzRYzHbNf0zFFRKRFKTg0W0e0xUELQImISGtTcGi2uAWgFBxERKRFKTg0W1xXhYKDiIi0KAWHZotbOVLrOIiISItScGi2mFkVanEQEZFWpeDQbLELQGlWhYiItCYFh2Yb0lXhZ1Woq0JERFqVgkOzxXRVbCiUmlUbERGRESk4NFt0k6ugCM6xYl2hiRUSEREZnoJDs6UzkEz5pwSkqbByvYKDiIi0JgWHVlCzlkNPf5m+YrmJFRIREYnX9OBgZheY2S1m9qKZOTNbsInye5nZr8xstZn1mNkDZnb0MGUTZna+mT1rZgUze9XMLjezSePyYTZXpLtiUjizQt0VIiLSipoeHICvA0cDfwdWj1TQzHYHHgIOBS4FPgN0A3eZ2TExl1wJXAH8FfgUcAtwLnCbmbXCZ/diVo9coe4KERFpQalmVwDY3Tn3IoCZPYUPAsO5BJgGvNk5Ny+85nrgaeAaM9vbOefC8/viw8KtzrkTq29gZi8B3wJOAm4c80+zOaIDJMONrtTiICIirajp/+quhoZNCbsXTgDurYaG8PoNwPeBPYG5kUtOBgy4quatrgN6gVM2u9JjLWYRKA2QFBGRVtT04DAKBwAdwMMxr/0xPEaDw1wgAB6NFnTOFYB5NWWbS10VIiLSJtopOMwKj4tiXquem11TfoVzrn+Y8tuaWSbuF5nZWWb2+GbXdLSigyOdBkeKiEjraqfgUP12jQsChZoy1edxZYcrP8A59z3n3MGjruHm6qxZBAq1OIiISGtqp+DQGx47Yl7L1pSpPo8rO1z55onZWltjHEREpBW1U3BYHB5nx7xWPRftxliM746ICw+z8d0YxTGs3+aL6apYvaGfckW7ZIqISGtpp+AwH9/1cGjMa4eEx+i4hMfwn+8t0YJmlgUOqinbXJGuimkJvzOmA1ZtGK6nRUREpDnaJjiE0y5vA440swOr582sGzgDeJ6hMyhuwn//nlfzVmfixzbcMJ71HZVIi8PU5OCW2hrnICIirabpC0CZ2anAzuGP2wEZM/ti+PPLzrmfRIpfALwD+K2ZXQmswweB2cDx1cWfAJxz883sGuAcM7sVuAPYB79y5H20yuJPMGQdh8kMbqmtmRUiItJqmh4cgI8DR9Sc+2p4vA8YCA7OuRfM7DDgG8DngAzwBHCcc+7umPc+D1gAnAUcD6wArgYudM61zgCCzo3HOIBaHEREpPU0PTg4544cZflngPfWWbYCXB4+Wld24+mYoJkVIiLSetpmjMOE1jm4WWdHeXBApLoqRESk1Sg4tIJIi0O6NBgW1FUhIiKtRsGhFWSzA0+TxQIWjvFUV4WIiLQaBYdWkEhCx2B4iG6tHZkoIiIi0nQKDq0i0l0xI+XXcihVAtb1lYa7QkREpOEUHFpFZErmzE4beL5iXV8zaiMiIhJLwaFVRBaBmjnYa6EBkiIi0lIUHFpFdnBK5naZwbWpVq7XfhUiItI6FBxaRaSrYtv0YHBYrq4KERFpIQoOrSIyOHKbVLTFQV0VIiLSOhQcWsWQrbXLA8+1eqSIiLQSBYdWMdwOmWpxEBGRFqLg0Cqy0R0yB4ODuipERKSVKDi0ikhXRUe5n3TS/9FsKJQpFMvDXSUiItJQCg6tItLiYP19TJ/cMfCzuitERKRVKDi0iu4pg8+XLWTbyYOrQGmApIiItAoFh1ax295g4R/Hyy+wU0dl4CW1OIiISKtQcGgVkybDrnv6586xf+8rAy9pgKSIiLQKBYdWsu+bB56+fsXzA8+Xq6tCRERahIJDK9lvMDjsuPhZcA5Qi4OIiLQOBYdWsste0NUNQEfPGnYprQTgxWXrcGGIEBERaSYFh1aSTMI+Bw38eGhpIQBL1/Tx7KI1zamTiIhIhIJDq4mMczjSlg48/9/5i5pRGxERkSEUHFrNfgcPPH3dqgV0BH756fv/uoRyJRjuKhERkYZQcGg107eDma8DIFEpcVhyBQBre4v86cXlzayZiIiIgkNLinRXvDvz2sDz389f3IzaiIiIDFBwaEWRaZl7rf77wPOH/7aU3n5teCUiIs2j4NCKXr8fpNIAZJYv4k1T/VTM/nLAH55dOtKVIiIi40rBoRV1ZGHP/Qd+fP/kVQPPf/+UZleIiEjzKDi0qsg4hwNWPIOFC0DNe2mFVpIUEZGmUXBoVQe8ZeBpx9/+zKldfmBk4ODepzVIUkREmkPBoVXN3An+4biBHz/40p3MKG8A4JePvMTydX3NqpmIiGzFFBxa2YfOgm13ACDd38v/Wf17cI7l6wpc8NNHWNPT3+QKiojI1kbBoZVlu+Bj/w5mALyp92Xe0/M0AK+u7OELNz5KT6HUzBqKiMhWRsGh1e11ABzzvoEfz177B2aV1gDwwtJ1XHjT4xRKlSZVTkREtjYKDu3g/acPLEOdLBf5ztrbOLT3RQCeemUV5/3XH/jjc8u09baIiIw7BYd2kM7Axz/jt90Gsj1ruHj57Xxx+R1ML2/gpdfWc9FNj3PuD/7AI88rQIiIyPgxfckML5fLOYB8Pt/sqnjz/gg/vgrWrxk41ZPI8OvuA7hv0ut5KT0DzJgzYxJHvGEWh79hJrtsP7lp1RURkbZkI76o4DC8lgsOABvWw8+vgwd/u9FLr6am8UDXHvy5cyeez2xPXyLD67bt5q2v3579d57OfjtNZ1I23YRKi4hIG1Fw2FwtGRyqnn0SfvItWBa/BHUAvJKeznOZ7SlZis6gSJcrMj3lcJOnUNxuDjbrdXTushvb7b4bU6apZUJERIBNBIdUo2ohY2zvA+HL18JfHoXHH4AnH4H+wUWhEsAupVXsUlq18bXrgcXz4cnBUz2JDno6p1CavA1u+g6UZ76OxJxdyOy8O1OmT6NrwypYuQxWLPXLV+6+D8zZFRIaJiMisjVRcGhnqTS86TD/KPbDU4/7IPHS32DxK+CCut9qUtDPpJ7l0LMclj4Hf930NYVMF8t22IN1O+xGVyZBV8LRlaiQTSVJbLcjqZmzsR3mwIztIJHcgg8qIiKtQsFhosh0DIYIgP4CvPwCLHwRLAHZTgrJDK+sL9OzZAmJpa/SuXIx26xbxrT+daSpP2RUZYu97PzqX+DVv4xYrkyCvmSGYiJDKZWmnMxgySSphJEMH4mEkTTDEgmSCcNlOwk6J1OZNJmgawquaxKJbCfJzk6SXZPIJBMkgxIUi1Dq959x8jSYPNU/OieBc4PhKQj880olfO4glfLhK5X2z50LX6/455ksZDuHtqoEAfT1QG+Pf617ysACXSPqDzcm68iO+j6LbJEggMUv+//2tpvZ7NpMLEGwVba6KjhMVB1Z2HM//whlgT1jilYqFV59dSlLXnqV1QsXk1q+mKmrF7PduqXs2LuclCuzPNnNstQUlqWm0OFKHFBYxDZBfftlpAiYXClApQBtttClM8N1dOI6slipiPX1DOxUCvjQMW0GbDPDh5VE0k+bTSahtxdWL4fVK6DX7zPCpMkwY3uYsQNMne4DXyYDqQwkU1AuQrnkH5XAv0814CRT4SPpj4kEFHqhZwP0bYC+XujoHAxPk6f6ckHgw1BQgWTa/7fRkfXBqNADq5bDytf8sVzy13VPge6p0NXt69jR4Y/pDl+XdAbSaR+w1q6GNSv9Y8M6/1q20z86soANhjjn/HtPm+Ef0SAVBL7lbNVyWLEEXlsCK5ZBMgE7zIHtZ8GOc/x9i4a1oOKvWb4Uli/xdciE9e3I+mP1niVTG7d+Gf6zTp0OnV2bDoLlkg+qyZr3KfT57ryVy/ybztzJ/zlv7hdLpeJnUK1bAz3r/efonARdk/wxnRn+vZ3z/3B47F547H5/fwBevy8cdYL/B0aqSX/99xdg6auw5FX/Z9XX4+9dodeH/70P9F2h6Uxz6hfl3OD/H0sl/4+UhQvghafhhb/Cgud8Pd9yJBzxbthpt7GvQ7nk/7ut5x8oDaLBkSNo6cGRjRIEOBewoehYtaHAyvX9rO3tp6+/TOq1V5n2yrNk1yxjQ9lYXzHWlaBYLLF9/xpmllYzq7SW6UFvsz+FtKrOSf7Lr9gPpWL91w0EqKRvdaqUx6Y+mQ6Yso3/MjAb/Mu62O+/2Pp6/V/kEAlIXf78hrXx77fjHP+ePev9F2XPev9+HdnB69OZyBdUEfr7oWed/+Ia8T6EgSiV9oEokfB1DiqwPqY+VVOnw0GH+vCHDQ6FC4LIo+LrWS75Y1DxwbEaxjId4e8Lf6dzPuisWQlrV8G6tf79Ozp9IMt0+IC6ctmmP1emA16/n/8ijn5hlko+hPf1+PvYX/D1qrYUVqqPsj/ifFjvnuIfk6b49662MlbDUxAG26Dig/Cq5f6xZuXgn3c9dtvb72zc1+vv//o1/s+zq9s/Jk32f+aVchhEwn8o9Bf8PS4W/PPeDf4fBD3r/evpjA9VU8JHpqPmHxFJOOJd8Lo96q/ryDSrYnMpOGyZwDlK5YD+nl76e3ro39BDsbeH/p4+egpFegplNhRK9BRK9JUq9BfL9BX9MVMu0F3upbvcx6RyH9lyP+lyP5lKkUy5SOAC+i1Fv6UoWoqUC5ga9DG10sfUoI/OoIQDHIYzf6yQIDB/dEDaBaQpk3EVUi6gghFYIjwanUGJLrfxXxo9lqY30UFX0M+kmNfjlKu/czO6hES2WFe3Hzxd0fL0E1buS4Nd1Vtu651VYWYJ4NPAvwK7AMuBm4ELnXM9TazaViFhRkc6Sce0yTDG0z2dc/SXA3r7S/T1V+gtlikUy6wrVlhWLNNfrlCuOMqVgHLgA0yxXKG/VKG/XKFYDnDOETgIAkclcPQVy/T0l+ntL9NXLBM4h7mAzkqRbKXIhsBYWUnTV3ZU43ZnUGRGpYcZ5Q1kXZkEASkXkCKgYGmWJ7tZkepmbaITgG0qvWxfWc8O5XVMrfSRcRU6XJmMK5MioESSoiUpWZKKJfx7uQopAtKuQjJ875QLSBDQaxl6Eh2sT3TQl8jQGRTDAFVgatBHwgWRMJQg7Sp0uBLZoEynK9FvKV5LTWZ5spvXUpMpWoopQR9TKgWmBAW6g346XJmOoEyHK9HhyqRdxT+okHCO1ckuViS7WZmaxNpEJxlXodMV6QxKZMNg5TACDMMxLehjRrmHGZUeUjVBqmAp1iQ6WZKeypLUVJamppByAbPKa5hTWsPs8homBxvvCrsq0RVeM4XVyS5/X4My2bDO1fuWdAHJmt+ZcL5O0ys9ZN2mWy4q4eeo7SQoW4I12Wms69qGpAuYseE1uoub/9eMwyhkuujLTqY/O4lUpUSm2Ee6VCBTKpCqjBxaS+ksy3Z7Iyv2fiuF3fcnXdjAdvPuYYcn76GjZ4TWiHHmEgnYbhbM3Ambvh2u2urSkYXFL2PPzIPXFjetfhuptuhUu+e22dZ3peyxrz8uXQj33QFP/GHsWr6iLFHfQPdk477OJ3RwAK4EzgV+CVwO7BP+/EYzO8a5UUw7kJZiZmTTSbLpJHQ39ndXQ0t/qUKhWPbHUoX+MJyUwtcA0qkE6aR/OPDBJSxfiASV1f3+fRI2OFgUfKtNpeIoBwHlSkBfsUJf2DLTVywPBKJiOaBUCcikEnRmUmQzSTpSSQLnwt8ZUCiVKZYDKkFrtDKac0wJCgRAv6UpWrKuflxzLgwBvqWoZEn6E2OwsJlzdLkS0yq9pFyA+fYqEjgKlqY3kaHXMr6eQIcr0xUGpH5LsSo5CRet/2SYUunjdaVVTAqKrE9kWZfMsi6Rpd9SZF2JrqBEpyuScZWBwFgkSTGRYm2ik8BGGB/hHMkwUKadb0dLusE6r052US4kYV4F5s0LL9qJ1IyPMLfrZXYsr8PHE7AwCgcMtrhVSFC0FEVLUrQUFUuQcWWygQ9jWVf2v8u5sD3NsTbRycrUJFYlJ7E62UXKBXQFRTpdia6gyMrkJBanp1GyJKzGP4bYHevcnR3nrOeg/oVsU+6lEmkVr5BgfaJjICyXUhkslSaZTpFMpUgkU5QtQZkEpfAfzd2VPiZX+phS7qO7XCBNhYwFZFyFtAuo4CgHRtlBOXD0ZiaxoWsafZO2ob97G8rpDiqBo+IcQfj/nUTRSDxrJP72d9+jNeUdTHrbW9l/6XymFdbQk+5iQ6abDekuSok0nZUCk0p9dJX7yFRKVJIpgmSKSsIfy6kM5WSGUjLtn2cnUe7oIujqhnQHyXKRjr51ZHrX0dG3nmRQJhH4f0gkXUDCVdg1M4OdN/M//dGasMHBzPYFPgXc6pw7MXL+JeBbwEnAjU2qnrSxaGiZ2tUCA7hGqRI4ShUfOILA+XGL+GMQ/uVYCRyBc5Qrvmyp4oNLsRxQDFtt+ksVShVHOmk+HKX8TJnq+/uw46gEPqxUnwfOh68g/Mu4VA588AoDVSVwYb18HSoOf121XoHDzAYyhnP4OobhqRIEmIWzdMIy1c9QLPvPYWb4bOYLFIplygH0WobeRH1/pv2Wpp80q0eYabwu2clTydnx15Nm7ZbMUjajQpKKJSmM4rKyJXm4axwG8Y0RByxJTmZJ1z71X1QOH7G6wgdDd2eKZtTaP4dC+Fi5rv46APewh/8dFaAvfAAwdRT1rRZYFz6iDJgSe8VFiW4FhzFwMv4uX1Vz/jrgG8ApKDjIVshPgQ1ba2RAsVzxLTn9ZRIJI5NKDLQYBY6B1qRSORj412e1u6tYrrYi+ZagSuBImG85SpgPm875Li4Xdo9Vw0ypXKEchqFkWNZssAut+qj+u7s6Li36WjkIfMuB2cCxVAnoK5YpFH1XnnOOZCJBKmGkkonwPcJQNxDIwu/TcLBjJaxr4PzvKUa6+krlgHQqQSaVIJNKkk4mBkJjqVyhVPEhMRoc/Wfy3YejafkyGKhztS4ylI08LGFMTeTgMBe/8vKj0ZPOuYKZzQtfFxEBIJNKkkkN34qkoDW2nPNhqfZcELZ8VQNSMlzbpZZvEQvoLw2OXypFWpOqIcrh/6f6ntEwUwkcqbArsRoSS+Ug7A70XYIOH7h8EAx/dxB9v6Ehxjk/vsvCOlQ/10CLXvV5GMiqP1c/00ALWtjKVyoHJBI2sO5NImFhEPUfrHrtrg3c0HAiB4dZwArn3MYjqWAR8DYzyzjnNpoDZmZnAWedffbZ411HEZGtUm1oqJ5LGiTr+Ndzwmwg7IE272ukibzkVRcQFxqAgS7BrrgXnXPfc84dPC61EhERaWMTOTj0Ah3DvJaNlBEREZE6TeTgsBjY1sziwsNsfDfGKJaqExERkYkcHB7Df763RE+aWRY4CHi8CXUSERFpaxM5ONyEH1B7Xs35M/FjG25odIVERETa3YSdVeGcm29m1wDnmNmtwB0Mrhx5H1rDQUREZNQmbHAInQcsAM4CjgdWAFfj96rQctMiIiKjNKGDg3Ougt+j4vJm10VERGQimMhjHERERGSMKTiIiIhI3RQcREREpG4TeozDWMnlcs2ugoiISKO4fD4/7IYhanEQERGRuplz2te8kczscW2gteV0H8eG7uPY0H0cG7qPY2O876NaHERERKRuCg4iIiJSNwWHxvtesyswQeg+jg3dx7Gh+zg2dB/HxrjeR41xEBERkbqpxUFERETqpuAgIiIidVNwGGdmljCz883sWTMrmNmrZna5mU1qdt1akZntaWZfMbM/mtlyM1tvZvPM7Atx98zM9jKzX5nZajPrMbMHzOzoZtS9lZlZl5m9ZGbOzL4d87ru4wjMbLqZ/aeZvRD+/3i5md1jZv9QU073cRhm1m1mnzez+eH/r1eY2UNmdrqZWU3Zrf4+mtkFZnaLmb0Y/v92wSbK133PtvR7SStHjr8rgXOBX+J36dwn/PmNZnaMtvfeyL8AnwR+DdwAlICjgK8BHzSzQ5xzfQBmtjvwEFAGLgXWAmcCd5nZu5xzdzeh/q3qK8C2cS/oPo7MzHYG7gW6gR8AzwFTgQOA2ZFyuo/DMLME8BvgbcCPgauBLuBk4If4vxc/G5bVffS+DqwCngCmjVRwM+7Zln0vOef0GKcHsC8QAL+oOf8pwAEfbnYdW+0BHAxMjTn/tfCenRM5dzNQAQ6KnOsGXgb+Rjj4d2t/AG8K/0L5t/Aefrvmdd3Hke/fA8CrwMxNlNN9HP7eHBr+t3dlzfkM8CKwRvdxo3u2W+T5U8CCEcrWfc/G4ntJXRXj62TAgKtqzl8H9AKnNLpCrc4597hzbm3MSzeFx/0Awia1E4B7nXPzItdvAL4P7AnMHd/atj4zS+L/e7sTuDXmdd3HEZjZ4cDbgUudc0vMLG1mXTHldB9HNiU8Lo6edM4VgRVAD+g+RjnnXqyn3Gbcsy3+XlJwGF9z8cnu0ehJ51wBmMdW8n+AMTInPC4LjwcAHcDDMWX/GB51f+F8YG/gnGFe130c2bvD4ytmdhvQB/SY2XNmFv0LVvdxZI8Ca4D/MLN/NrPXhX3ylwBvBi4Oy+k+jt5o79kWfy8pOIyvWcAK51x/zGuLgG3NLNPgOrWd8F/NF+Kb228MT88Kj4tiLqmemx3z2lbDzHYFvgx8xTm3YJhiuo8j2ys8XgdMB04DPg4UgZ+Y2cfC13UfR+CcW43/V/EqfLP6y8Cz+PFMJzrnrguL6j6O3mjv2RZ/L2lw5PjqAuL+cAAKkTLFxlSnbV0FHAJ83jn3t/Bctbk47v4Waspsrb4DvARcMUIZ3ceRTQ6P64GjwqZ1zOyX+L75r5vZj9F9rMcGfF/9r/ED+abjg8ONZvZe59zv0H3cHKO9Z1v8vaTgML56ge2HeS0bKSPDMLOv4pvZv+ecuyTyUvW+dcRcttXf27AZ/VjgcOdcaYSiuo8j6wuPP6uGBvD/gjazXwMfxbdK6D6OwMz2x4eF851z10bO/wwfJq4LZwboPo7eaO/ZFn8vqatifC3GN/vE/YHOxjcXqbVhGGZ2MfBF/HStT9S8XB1kFddsWT0X13Q34YX/vV0B3AEsNbM9zGwPYOewyNTw3DR0HzdlYXhcGvPakvC4DbqPm3I+/kvpluhJ51wvcDv+v81d0H3cHKO9Z1v8vaTgML4ew9/jt0RPmlkWOAh4vAl1agtmdhFwEXA9cIYL5wtFzMc3tx0ac/kh4XFrvb+dwHbA8cDzkce94eunhD+fge7jplQHkM2Jea167jV0Hzel+gWWjHktFTnqPo7eaO/Zln8vNXuu6kR+APsz8nzZU5pdx1Z84AdCOnxoSIxQ7hb83OUDI+eqc5efYyuZ7x1zX9LAB2IeZ4f39Tfhz3vqPm7yXm4DrMO3PHRHzs/E99k/Fzmn+zj8fbwy/G/vP2rOT8P/C3gVkNJ9HPb+bWodh7rv2Vh8L2l3zHFmZlfj++h/iW86rq7Q9QfgaKeVI4cws08C3wZeAb6E/w88apnzg6gIm98fxa8ueSX+L/gz8f/HON45d1ej6t0OzGwX/GDJa5xz50TO6z6OwMzOAr4LPA38F37RorPx4eH/c879Niyn+ziMcPXNJ/BB7Ab833/T8fdnF+CTzrl8WFb3ETCzUxnsXvwU/r+7y8OfX3bO/SRSdlT3bIu/l5qdpCb6A9809+/41bv68X1NVxD514seQ+7Xj/Cpd7jHvTXl9wH+Gz9HvBd4EDim2Z+jFR/4v6A3WjlS97Gue/d+/Jz4HvwMi98Ch+k+juoe7o5fbnph+AW3DrgfeL/uY+z9urfevwdHe8+29HtJLQ4iIiJSNw2OFBERkbopOIiIiEjdFBxERESkbgoOIiIiUjcFBxEREambgoOIiIjUTcFBRERE6qbdMUVkwsvlchfj9z45Kp/P39vc2oi0NwUHEdmkXC5Xz0px+lIW2QooOIjIaHx5hNcWNKoSItI8Cg4iUrd8Pn9xs+sgIs2l4CAiYy46pgC/w995wN74DaL+B/h8Pp9fGnPd6/G7or4D2A5YAdwNfDWfzz8fUz6J3wXwVGA//A6Ci/AbBH1zmGs+APxHWL6A37Dq3/P5/KIt+MgiWw3NqhCR8XQ+cC3wJHAVfje+jwEP5XK57aIFc7ncXOBx4BTgMeA/8TtSfgR4PJfLHVxTPgPcCXwH2Am4EfgW8CfgfcBhMfXJAT/Fd6tcAzwFfAi4O5fLdWzphxXZGqjFQUTqFrYkxCnk8/lvxJx/F/DWfD7/58h7XIlvgfgG8PHwnAHXA1OAU/L5/A2R8h8C/i/w01wu94Z8Ph+EL10MHAPcBvxzPp/vj1zTEb5XreOAufl8fn6k7I3AycB7gZuH++wi4qnFQURG46JhHp8bpvxPoqEhdDGwFvhw5F/5b8N3ZTwcDQ0A+Xz+JuBBYC/g7TDQRZED+oBPRENDeE1/Pp9fHlOfb0VDQ+i68PiWYT6DiESoxUFE6pbP522Ul9wX8x5rc7ncPOAIYB9gHvCm8OXfD/M+v8eHhjcC9+NDxlTgkXw+v3gU9Xk85tyr4XGbUbyPyFZLLQ4iMp6WDXO+OjByas1xyTDlq+en1RxHO6BxTcy5cnhMjvK9RLZKCg4iMp52GOb8juFxbc1xx5iyADNryq0Jj7M3u2YislkUHERkPB1ReyKXy00FDsJPhXwmPF0dB3HkMO9TPf9EeHwWHx4OyOVys7a8miJSLwUHERlPp+ZyuTfWnLsY3zXxs8igxj/gp2q+PVxnYUD48+HAc/hBkuTz+QqQBzqBa2unUuZyuUztdE8RGRsaHCkidRthOibAr/L5/Lyac78B/pDL5W7Gj1N4e/hYQGQmRj6fd7lc7jTgd8BNuVzuv/GtCnsB/4RfOOqjkamY4Je/fivwHuC5XC73P2G5nYBjgc8AP9qMjykiI1BwEJHRuGiE1xbgZ0hEXQn8Er9uw4eADfgv88/n8/nXogXz+fwj4SJQX8Svz/Ae/MqRP8OvHPm3mvLFXC53HPAJ4KPAaYABi8Pf+eBoP5yIbJo5V8+mdyIi9dM21iITl8Y4iIiISN0UHERERKRuCg4iIiJSN41xEBERkbqpxUFERETqpuAgIiIidVNwEBERkbopOIiIiEjdFBxERESkbgoOIiIiUrf/B+kLXBbANMbgAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 576x432 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ooo.plot_history(history, plot={'MSE' :['mse', 'val_mse'],\n",
    "                                'MAE' :['mae', 'val_mae'],\n",
    "                                'LOSS':['loss','val_loss']})"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 7 - Make a prediction\n",
    "The data must be normalized with the parameters (mean, std) previously used."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "my_data = [ 1.26425925, -0.48522739,  1.0436489 , -0.23112788,  1.37120745,\n",
    "       -2.14308942,  1.13489104, -1.06802005,  1.71189006,  1.57042287,\n",
    "        0.77859951,  0.14769795,  2.7585581 ]\n",
    "real_price = 10.4\n",
    "\n",
    "my_data=np.array(my_data).reshape(1,13)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Prediction : 10.66 K$\n",
      "Reality    : 10.40 K$\n"
     ]
    }
   ],
   "source": [
    "\n",
    "predictions = model.predict( my_data )\n",
    "print(\"Prediction : {:.2f} K$\".format(predictions[0][0]))\n",
    "print(\"Reality    : {:.2f} K$\".format(real_price))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}