Chapter 11 section 08 completed.

11-SVM/07-What-is-RBF-Kernel/07-What-is-RBF-Kernel.ipynb

@@ -0,0 +1,179 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 直观理解高斯核函数"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "x = np.arange(-4, 5, 1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([-4, -3, -2, -1,  0,  1,  2,  3,  4])"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "y = np.array((x >= -2) & (x <= 2), dtype='int')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 0, 1, 1, 1, 1, 1, 0, 0])"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYwAAAD8CAYAAABkbJM/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nTkSuQmCC\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x10ee24438>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.scatter(x[y==0], [0]*len(x[y==0]))\n",
+    "plt.scatter(x[y==1], [0]*len(x[y==1]))\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def gaussian(x, l):\n",
+    "    gamma = 1.0\n",
+    "    return np.exp(-gamma * (x-l)**2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "l1, l2 = -1, 1\n",
+    "\n",
+    "X_new = np.empty((len(x), 2))\n",
+    "for i, data in enumerate(x):\n",
+    "    X_new[i, 0] = gaussian(data, l1)\n",
+    "    X_new[i, 1] = gaussian(data, l2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n6P8B0TWCEyVMrKwAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x10f150ac8>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.scatter(X_new[y==0,0], X_new[y==0,1])\n",
+    "plt.scatter(X_new[y==1,0], X_new[y==1,1])\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "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": "3.6.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}