diff --git a/stackoverflow-survey.ipynb b/stackoverflow-survey.ipynb
index 41a9311..a5acebe 100644
--- a/stackoverflow-survey.ipynb
+++ b/stackoverflow-survey.ipynb
@@ -263,24 +263,36 @@
     "\n",
     "    def run_log_regression(self, color='pink', nodraw=True):\n",
     "        df = self.devs\n",
-    "        X = df[[self.key_x]].sort_values(by=self.key_x)\n",
-    "        y = df[[self.key_y]].sort_values(by=self.key_y)\n",
+    "        X = df[[self.key_x]] #.sort_values(by=self.key_x)\n",
+    "        y = df[[self.key_y]] #.sort_values(by=self.key_y)\n",
     "\n",
-    "        X_log = np.log(X)\n",
-    "        x_fit = np.linspace(1, 40, len(y)).reshape(-1, 1)\n",
+    "        X_train, X_test, y_train, y_test = train_test_split(\n",
+    "                                                X, y, \n",
+    "                                                test_size=0.2, \n",
+    "                                                random_state=777)\n",
+    "    \n",
+    "        X_train_log = np.log(X_train)\n",
+    "        X_test_log = np.log(X_test)\n",
+    "    \n",
+    " #       X_train_log = X_train_log.sort_values(by=self.key_x)\n",
+    " #       y_train = y_train.sort_values(by=self.key_y)\n",
+    "        X_test_log = X_test_log.sort_values(by=self.key_x)\n",
+    "        X_test = X_test.sort_values(by=self.key_x)\n",
+    "        y_test = y_test.sort_values(by=self.key_y)\n",
     "        \n",
     "        model = LinearRegression()\n",
-    "        model.fit(X_log, y)\n",
-    "        y_pred = model.predict(X_log)\n",
+    "        model.fit(X_train_log, y_train)\n",
+    "        y_pred = model.predict(X_test_log)\n",
+    "        y_pred.sort()\n",
     "\n",
     "        m = model.coef_[0][0]\n",
     "        b = model.intercept_[0]\n",
     "        label = '%s log regression line for %s' % (color, self.language)\n",
-    "        show_model_stats(m, b, y, y_pred, label)\n",
+    "        show_model_stats(m, b, y_test, y_pred, label)\n",
     "\n",
     "        if nodraw:\n",
     "            return\n",
-    "        plt.plot(X, y_pred, color=color, label=\"Log regression\")\n",
+    "        plt.plot(X_test, y_pred, color=color, label=\"Log regression\")\n",
     "        plt.legend(loc='lower center', bbox_to_anchor=(1.5,0)) \n",
     "\n",
     "    def export_image(self, base_filename = 'images/programmers-%s-%s.png'):\n",