logistic and ridge regression'

Author: rishiraj824

.idea/workspace.xml

@@ -0,0 +1,106 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "### This is an example of a basic 10-fold cross validation on the boston housing dataset of sklearn using Ridge-Regression."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "from sklearn.datasets import load_boston\n",
+    "import matplotlib.pyplot as plt\n",
+    "from sklearn.linear_model import Ridge\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.metrics import r2_score\n",
+    "from sklearn.preprocessing import Normalizer\n",
+    "\n",
+    "\n",
+    "boston_dataset = load_boston()\n",
+    "\n",
+    "X = boston_dataset.data \n",
+    "\n",
+    "transformer = Normalizer().fit(X)\n",
+    "\n",
+    "transformer.transform(X)\n",
+    "\n",
+    "y = boston_dataset.target.reshape(-1, 1) # Converting to Column vector "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Cost after iteration 1 - 0.7126916135010682\n",
+      "Cost after iteration 2 - 0.6580161986180606\n",
+      "Cost after iteration 3 - 0.6593572420098802\n",
+      "Cost after iteration 4 - 0.6827689513882875\n",
+      "Cost after iteration 5 - 0.7427883698752009\n",
+      "Cost after iteration 6 - 0.7037718042199794\n",
+      "Cost after iteration 7 - 0.6266438909778318\n",
+      "Cost after iteration 8 - 0.7455364640710955\n",
+      "Cost after iteration 9 - 0.7291283475880821\n",
+      "Cost after iteration 10 - 0.7353142325508967\n",
+      "Aggregate R2 Coeff 0.69960\n"
+     ]
+    }
+   ],
+   "source": [
+    "r2_coeff = []\n",
+    "clf = Ridge(alpha=10)\n",
+    "for i in range(10):\n",
+    "    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20)\n",
+    "    clf.fit(X_train, y_train)\n",
+    "    y_predict=clf.predict(X_test)\n",
+    "    \n",
+    "    RSS = (np.mean((y_test-y_predict)**2)/np.std(y_test)**2)\n",
+    "    r2_coeff.append(1-RSS)\n",
+    "    print(\"Cost after iteration {} - {}\".format(i+1, 1-RSS))\n",
+    "    \n",
+    "average_r2 = np.mean(r2_coeff)\n",
+    "print(\"Aggregate R2 Coeff {0:.5f}\".format(average_r2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.7.4-final"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}