Update P2-example.ipynb

Author: dasimagin

P2-example.ipynb

@@ -248,24 +248,13 @@
     "    ids = list(ids.flatten())\n",
     "  \n",
     "    regression = LinearRegression()\n",
-    "#     regression = ElasticNet(alpha=1e-3)\n",
     "\n",
     "    X_subtrain = X_train[ids]\n",
     "    y_subtrain = y_train[ids]\n",
     "    \n",
     "    def transform(X):\n",
     "        grade = np.array([avg_price_by_grade[g - 3] for g in X['grade']])\n",
     "        \n",
-    "#         return np.vstack([\n",
-    "#             np.log(X['sqft_basement'] + 1),\n",
-    "#             np.log(X['sqft_above'] + 1),\n",
-    "#             np.log(grade + 1),\n",
-    "#             np.log(grade * X['sqft_lot'] + 1),\n",
-    "#             np.log(X['waterfront'] + 1),\n",
-    "#             np.log(X['condition'] * X['sqft_living'] + 1),\n",
-    "#             (X['yr_built'] >= 2012)\n",
-    "#         ]).T    \n",
-    "\n",
     "        return np.vstack([\n",
     "            X['sqft_basement'],\n",
     "            X['sqft_above'],\n",
@@ -283,8 +272,6 @@
     "    \n",
     "    y_predict.append(y[0])\n",
     "    \n",
-    "print((np.abs(y_test - y_predict)/y_test).mean())\n",
-    "    \n",
     "with open('y_solution.csv', 'w') as out:\n",
     "    print('Id,Price', file=out)\n",
     "    for pair in enumerate(y_predict, 1):\n",