From 67d144130324b76ea0122928d6fee04f811a820f Mon Sep 17 00:00:00 2001
From: scuti <scuti@tutamail.com>
Date: Sun, 27 Apr 2025 10:49:37 -0700
Subject: [PATCH] Added logarithmic regression

Not part of the course but fits better.
---
 stackoverflow-survey.ipynb | 40 ++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/stackoverflow-survey.ipynb b/stackoverflow-survey.ipynb
index f3f2bd8..dadb6fc 100644
--- a/stackoverflow-survey.ipynb
+++ b/stackoverflow-survey.ipynb
@@ -268,6 +268,35 @@
     "        plt.legend(loc='lower center', bbox_to_anchor=(1.5,0)) \n",
     "        del y_pred, model, X, y\n",
     "\n",
+    "    def run_log_regression(self, color='pink', nodraw=True):\n",
+    "        df = self.devs\n",
+    "        X = df[self.key_x].to_frame().sort_values(by=self.key_x)\n",
+    "        y = df[self.key_y].to_frame().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",
+    "        \n",
+    "        model = LinearRegression()\n",
+    "        model.fit(X_log, y)\n",
+    "        y_pred = model.predict(X_log)\n",
+    "\n",
+    "        m = model.coef_[0][0]\n",
+    "        b = model.intercept_[0]\n",
+    "        print('+----------------------+')\n",
+    "        print('%s log regression line for %s' % (color, self.language))\n",
+    "        print('coefficient = %0.2f' % m)\n",
+    "        print('intercept = %0.2f' % b)\n",
+    "        rmse = root_mean_squared_error(y, y_pred)\n",
+    "        print('rmse = %0.2f' % rmse)\n",
+    "        r2   = r2_score(y, y_pred)\n",
+    "        print('r2 score = %0.2f' % r2)\n",
+    "        print('sample predictions:')\n",
+    "        print(y_pred[3:6])\n",
+    "        print('+----------------------+')\n",
+    "        if nodraw:\n",
+    "            return\n",
+    "        plt.plot(X, 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",
     "        plt.figure(self.canvas)\n",
@@ -313,8 +342,9 @@
     "                       x_shift=0, y_shift=-1.5e4, random=888,\n",
     "                       color='cyan', name='Tuned regression line')\n",
     "\n",
-    "python.run_regression(x_transform=log_base_a, change_base=1.20, risky=2, random=555, \n",
-    "                      color='pink', name='Risky regression line')\n",
+    "#python.run_regression(x_transform=log_base_a, change_base=1.20, risky=2, random=555, \n",
+    "#                      color='pink', name='Risky regression line')\n",
+    "python.run_log_regression(nodraw=False)\n",
     "python.export_image()"
    ]
   },
@@ -370,14 +400,16 @@
     "c.run_regression()\n",
     "c.run_regression(x_transform=log_base_a, change_base=1.3, \n",
     "                 x_shift=2, y_shift=-5000, color='magenta', random=555)\n",
-    "c.run_regression(x_transform=log_base_a, change_base=1.3, risky=2, color='pink')\n",
+    "c.run_log_regression(nodraw=False)\n",
     "c.export_image()"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "b7026c56-3049-4e60-bbc6-ee548ff58297",
-   "metadata": {},
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
    "source": [
     "## Evaluation for C\n",
     "\n",