diff --git a/.~lock.Schrick-Noah_QM-7063_Final.odt# b/.~lock.Schrick-Noah_QM-7063_Final.odt#
new file mode 100644
index 0000000..fedfc25
--- /dev/null
+++ b/.~lock.Schrick-Noah_QM-7063_Final.odt#
@@ -0,0 +1 @@
+,noah,NovaArchSys,26.04.2023 15:50,file:///home/noah/.config/libreoffice/4;
\ No newline at end of file
diff --git a/Schrick-Noah_QM-7063_Final.odt b/Schrick-Noah_QM-7063_Final.odt
index 4cbb1e0..e57fee4 100644
Binary files a/Schrick-Noah_QM-7063_Final.odt and b/Schrick-Noah_QM-7063_Final.odt differ
diff --git a/timing-analysis.ipynb b/timing-analysis.ipynb
index caa4a92..ffdc5d3 100644
--- a/timing-analysis.ipynb
+++ b/timing-analysis.ipynb
@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -38,7 +38,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -9183,34 +9183,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "intercept  303728.87235091545\n",
-      "  Predictor   coefficient\n",
-      "0     nodes -32534.157117\n",
+      "intercept  0.00014215703009013694\n",
+      "  Predictor  coefficient\n",
+      "0     nodes    -0.255466\n",
       "\n",
       "Regression statistics\n",
       "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 442361.0172\n",
-      "            Mean Absolute Error (MAE) : 198916.6752\n",
-      "          Mean Percentage Error (MPE) : -3076.0279\n",
-      "Mean Absolute Percentage Error (MAPE) : 3664.0029\n"
+      "                      Mean Error (ME) : 0.0000\n",
+      "       Root Mean Squared Error (RMSE) : 0.9457\n",
+      "            Mean Absolute Error (MAE) : 0.4004\n",
+      "          Mean Percentage Error (MPE) : -153.9195\n",
+      "Mean Absolute Percentage Error (MAPE) : 469.3563\n"
      ]
     }
    ],
    "source": [
     "predictors = ['nodes']\n",
     "overall_outcome = 'runtime'\n",
-    "\n",
+    "norm_df = (timing_df-timing_df.mean())/timing_df.std()\n",
     "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[overall_outcome]\n",
+    "X = norm_df[predictors]\n",
+    "overall_y = norm_df[overall_outcome]\n",
     "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
     "runtime_lm = LinearRegression()\n",
     "runtime_lm.fit(train_X, train_y)\n",
@@ -9221,50 +9221,6 @@
     "regressionSummary(train_y, runtime_lm.predict(train_X))"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  0.06488133316235689\n",
-      "  Predictor  coefficient\n",
-      "0     nodes    -0.085788\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "                      Mean Error (ME) : 0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 0.1060\n",
-      "            Mean Absolute Error (MAE) : 0.0477\n",
-      "          Mean Percentage Error (MPE) : -32832.1198\n",
-      "Mean Absolute Percentage Error (MAPE) : 33548.5134\n"
-     ]
-    }
-   ],
-   "source": [
-    "scaler = preprocessing.MinMaxScaler()\n",
-    "d = scaler.fit_transform(timing_df)\n",
-    "normalized_df = pd.DataFrame(d, columns=timing_df.columns)\n",
-    "\n",
-    "predictors = ['nodes']\n",
-    "overall_outcome = 'runtime'\n",
-    "\n",
-    "# partition data\n",
-    "X = normalized_df[predictors]\n",
-    "overall_y = normalized_df[overall_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "runtime_lm = LinearRegression()\n",
-    "runtime_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', runtime_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': runtime_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, runtime_lm.predict(train_X))\n"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -9275,24 +9231,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "intercept  -8788.042556187662\n",
+      "intercept  -0.006679327812999215\n",
       "  Predictor  coefficient\n",
-      "0   exploit    50.283347\n",
+      "0   exploit     0.876264\n",
       "\n",
       "Regression statistics\n",
       "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 197437.6040\n",
-      "            Mean Absolute Error (MAE) : 62749.3897\n",
-      "          Mean Percentage Error (MPE) : 180.5994\n",
-      "Mean Absolute Percentage Error (MAPE) : 275.3917\n"
+      "                      Mean Error (ME) : 0.0000\n",
+      "       Root Mean Squared Error (RMSE) : 0.4366\n",
+      "            Mean Absolute Error (MAE) : 0.1452\n",
+      "          Mean Percentage Error (MPE) : -56.0992\n",
+      "Mean Absolute Percentage Error (MAPE) : 193.5384\n"
      ]
     }
    ],
@@ -9301,8 +9257,8 @@
     "overall_outcome = 'runtime'\n",
     "\n",
     "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[overall_outcome]\n",
+    "X = norm_df[predictors]\n",
+    "overall_y = norm_df[overall_outcome]\n",
     "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
     "runtime_lm = LinearRegression()\n",
     "runtime_lm.fit(train_X, train_y)\n",
@@ -9323,98 +9279,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "intercept  42450.91771345622\n",
+      "intercept  0.00013241619854788668\n",
       "  Predictor  coefficient\n",
-      "0      appl  1748.317923\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 454831.8590\n",
-      "            Mean Absolute Error (MAE) : 186480.9214\n",
-      "          Mean Percentage Error (MPE) : -2691.9685\n",
-      "Mean Absolute Percentage Error (MAPE) : 2705.9283\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "[<matplotlib.lines.Line2D at 0x6fd6c0c1dc30>]"
-      ]
-     },
-     "execution_count": 60,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "predictors = ['appl']\n",
-    "overall_outcome = 'runtime'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[overall_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "runtime_lm = LinearRegression()\n",
-    "runtime_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', runtime_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': runtime_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, runtime_lm.predict(train_X))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  0.010048066606673962\n",
-      "  Predictor  coefficient\n",
-      "0      appl      0.04191\n",
+      "0      appl     0.123285\n",
       "\n",
       "Regression statistics\n",
       "\n",
       "                      Mean Error (ME) : 0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 0.1090\n",
-      "            Mean Absolute Error (MAE) : 0.0447\n",
-      "          Mean Percentage Error (MPE) : -17606.2312\n",
-      "Mean Absolute Percentage Error (MAPE) : 17620.2063\n"
+      "       Root Mean Squared Error (RMSE) : 0.9715\n",
+      "            Mean Absolute Error (MAE) : 0.3759\n",
+      "          Mean Percentage Error (MPE) : 93.5442\n",
+      "Mean Absolute Percentage Error (MAPE) : 116.5608\n"
      ]
     }
    ],
    "source": [
-    "scaler = preprocessing.MinMaxScaler()\n",
-    "d = scaler.fit_transform(timing_df)\n",
-    "normalized_df = pd.DataFrame(d, columns=timing_df.columns)\n",
-    "\n",
     "predictors = ['appl']\n",
     "overall_outcome = 'runtime'\n",
     "\n",
     "# partition data\n",
-    "X = normalized_df[predictors]\n",
-    "overall_y = normalized_df[overall_outcome]\n",
+    "X = norm_df[predictors]\n",
+    "overall_y = norm_df[overall_outcome]\n",
     "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
     "runtime_lm = LinearRegression()\n",
     "runtime_lm.fit(train_X, train_y)\n",
@@ -9435,24 +9327,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "intercept  445536.13965568773\n",
+      "intercept  -0.007075826820466129\n",
       "  Predictor  coefficient\n",
-      "0      load -1015.396933\n",
+      "0      load    -0.183009\n",
       "\n",
       "Regression statistics\n",
       "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 442633.9662\n",
-      "            Mean Absolute Error (MAE) : 186136.1892\n",
-      "          Mean Percentage Error (MPE) : -3308.5538\n",
-      "Mean Absolute Percentage Error (MAPE) : 3331.5614\n"
+      "                      Mean Error (ME) : 0.0000\n",
+      "       Root Mean Squared Error (RMSE) : 0.9620\n",
+      "            Mean Absolute Error (MAE) : 0.3813\n",
+      "          Mean Percentage Error (MPE) : 233.9860\n",
+      "Mean Absolute Percentage Error (MAPE) : 370.4181\n"
      ]
     }
    ],
@@ -9461,8 +9353,8 @@
     "overall_outcome = 'runtime'\n",
     "\n",
     "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[overall_outcome]\n",
+    "X = norm_df[predictors]\n",
+    "overall_y = norm_df[overall_outcome]\n",
     "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
     "runtime_lm = LinearRegression()\n",
     "runtime_lm.fit(train_X, train_y)\n",
@@ -9491,27 +9383,27 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "intercept  -58054.89252320345\n",
+      "intercept  -0.001661686455377755\n",
       "  Predictor  coefficient\n",
-      "0     nodes  -872.584718\n",
-      "1   exploit    49.805953\n",
-      "2      appl  1575.244214\n",
-      "3      load   -68.075156\n",
+      "0     nodes    -0.024622\n",
+      "1   exploit     0.877093\n",
+      "2      appl     0.128728\n",
+      "3      load     0.031007\n",
       "\n",
       "Regression statistics\n",
       "\n",
       "                      Mean Error (ME) : 0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 189043.5348\n",
-      "            Mean Absolute Error (MAE) : 82436.8687\n",
-      "          Mean Percentage Error (MPE) : 334.3634\n",
-      "Mean Absolute Percentage Error (MAPE) : 1191.8060\n"
+      "       Root Mean Squared Error (RMSE) : 0.4165\n",
+      "            Mean Absolute Error (MAE) : 0.1847\n",
+      "          Mean Percentage Error (MPE) : -112.7836\n",
+      "Mean Absolute Percentage Error (MAPE) : 284.0935\n"
      ]
     }
    ],
@@ -9520,8 +9412,8 @@
     "overall_outcome = 'runtime'\n",
     "\n",
     "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[overall_outcome]\n",
+    "X = norm_df[predictors]\n",
+    "overall_y = norm_df[overall_outcome]\n",
     "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
     "runtime_lm = LinearRegression()\n",
     "runtime_lm.fit(train_X, train_y)\n",
@@ -9532,306 +9424,6 @@
     "regressionSummary(train_y, runtime_lm.predict(train_X))"
    ]
   },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 0"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  0.0\n",
-      "  Predictor  coefficient\n",
-      "0     nodes          0.0\n",
-      "1   exploit          0.0\n",
-      "2      appl          0.0\n",
-      "3      load          0.0\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "               Mean Error (ME) : 0.0000\n",
-      "Root Mean Squared Error (RMSE) : 0.0000\n",
-      "     Mean Absolute Error (MAE) : 0.0000\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 0\n",
-    "t0_outcome = 'task0'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t0_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t0_lm = LinearRegression()\n",
-    "t0_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t0_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t0_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t0_lm.predict(train_X))"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 1"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  -8930.11863104882\n",
-      "  Predictor  coefficient\n",
-      "0     nodes  -232.287083\n",
-      "1   exploit    18.859014\n",
-      "2      appl   151.902207\n",
-      "3      load    -7.775745\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 19547.1452\n",
-      "            Mean Absolute Error (MAE) : 11878.2487\n",
-      "          Mean Percentage Error (MPE) : 766.9344\n",
-      "Mean Absolute Percentage Error (MAPE) : 912.9252\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 1\n",
-    "t1_outcome = 'task1'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t1_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t1_lm = LinearRegression()\n",
-    "t1_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t1_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t1_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t1_lm.predict(train_X))"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  -33033.61791812297\n",
-      "  Predictor  coefficient\n",
-      "0     nodes    98.141525\n",
-      "1   exploit    28.211256\n",
-      "2      appl  1191.485769\n",
-      "3      load  -114.265223\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "                      Mean Error (ME) : 0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 164019.5175\n",
-      "            Mean Absolute Error (MAE) : 67768.4301\n",
-      "          Mean Percentage Error (MPE) : 14109.3156\n",
-      "Mean Absolute Percentage Error (MAPE) : 40718.5528\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 2\n",
-    "t2_outcome = 'task2'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t2_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t2_lm = LinearRegression()\n",
-    "t2_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t2_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t2_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t2_lm.predict(train_X))"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 3"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  64.74568294128446\n",
-      "  Predictor  coefficient\n",
-      "0     nodes    20.863592\n",
-      "1   exploit    -0.002906\n",
-      "2      appl    -0.027356\n",
-      "3      load     0.227492\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "                      Mean Error (ME) : -0.0000\n",
-      "       Root Mean Squared Error (RMSE) : 95.9494\n",
-      "            Mean Absolute Error (MAE) : 80.7147\n",
-      "          Mean Percentage Error (MPE) : -48.7684\n",
-      "Mean Absolute Percentage Error (MAPE) : 77.1556\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 3\n",
-    "t3_outcome = 'task3'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t3_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t3_lm = LinearRegression()\n",
-    "t3_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t3_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t3_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t3_lm.predict(train_X))"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 4"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  346.4317371043873\n",
-      "  Predictor  coefficient\n",
-      "0     nodes    -2.648924\n",
-      "1   exploit     0.000311\n",
-      "2      appl     0.000503\n",
-      "3      load    -0.696739\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "               Mean Error (ME) : 0.0000\n",
-      "Root Mean Squared Error (RMSE) : 150.2358\n",
-      "     Mean Absolute Error (MAE) : 111.7243\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 4\n",
-    "t4_outcome = 'task4'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t4_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t4_lm = LinearRegression()\n",
-    "t4_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t4_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t4_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t4_lm.predict(train_X))"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Linear Regression - Task 5"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "intercept  3.2276550472205336\n",
-      "  Predictor  coefficient\n",
-      "0     nodes    -0.344255\n",
-      "1   exploit     0.000049\n",
-      "2      appl     0.001636\n",
-      "3      load    -0.001017\n",
-      "\n",
-      "Regression statistics\n",
-      "\n",
-      "               Mean Error (ME) : 0.0000\n",
-      "Root Mean Squared Error (RMSE) : 1.8391\n",
-      "     Mean Absolute Error (MAE) : 1.4637\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Linear Regression - Task 5\n",
-    "t5_outcome = 'task5'\n",
-    "\n",
-    "# partition data\n",
-    "X = timing_df[predictors]\n",
-    "overall_y = timing_df[t5_outcome]\n",
-    "train_X, valid_X, train_y, valid_y = train_test_split(X, overall_y, test_size=0.4, random_state=1)\n",
-    "t5_lm = LinearRegression()\n",
-    "t5_lm.fit(train_X, train_y)\n",
-    "# print coefficients\n",
-    "print('intercept ', t5_lm.intercept_)\n",
-    "print(pd.DataFrame({'Predictor': X.columns, 'coefficient': t5_lm.coef_}))\n",
-    "# print performance measures\n",
-    "regressionSummary(train_y, t5_lm.predict(train_X))"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",