Created
January 8, 2015 00:01
-
-
Save jakevdp/0b3e332015ec2de7b973 to your computer and use it in GitHub Desktop.
Simple KDE example with scikit-learn
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"metadata": { | |
"name": "", | |
"signature": "sha256:77165790a6d969fe3d3f19f41d04ec38176b032bba531bfe8176e09c63113f6f" | |
}, | |
"nbformat": 3, | |
"nbformat_minor": 0, | |
"worksheets": [ | |
{ | |
"cells": [ | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": [ | |
"%matplotlib inline\n", | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"from sklearn.neighbors import KernelDensity" | |
], | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 1 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": [ | |
"# create some data\n", | |
"x = np.random.randn(1000)\n", | |
"plt.hist(x, 50);" | |
], | |
"language": "python", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"metadata": {}, | |
"output_type": "display_data", | |
"png": "iVBORw0KGgoAAAANSUhEUgAAAW8AAAEACAYAAAB8nvebAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAADz5JREFUeJzt3V+sHPdZxvHncdIobdPUMkHHpjWEi7opKJDwJ6pEEJtS\ng1uBYy4I9KIypXAR/jRUUHHSCHIQgib0ogVxg0RbHUJbiNrGJCoiPhiv2gqUErBpGid1QViUUh9D\n6qS1rMpO/HKxY+f4ZP/vzM68s9+PtPLs78zOvnvW+2jO+5uZdUQIAJDLlroLAABMjvAGgIQIbwBI\niPAGgIQIbwBIiPAGgISuHGcl2yckfUPSC5LOR8QttrdJ+mtJ3yXphKQ7IuLZiuoEAGww7p53SOpE\nxM0RcUsxtixpLSJ2STpU3AcAzMEkbRNvur9X0mqxvCppXykVAQBGmmTP++9tP277l4uxpYhYL5bX\nJS2VXh0AoK+xet6SfiQivmb72yWt2X564w8jImxznj0AzMlY4R0RXyv+/V/bD0m6RdK67e0RcdL2\nDkmnNj+OQAeA6UTE5lb1ZUa2TWy/wvariuVXSvoJSU9IeljS/mK1/ZIODCigtbd777239hp4bbw+\nXl/7buMYZ897SdJDti+u/9GIOGj7cUkP2n6nikMFx3pGAMDMRoZ3RPynpJv6jH9d0purKAoAMBxn\nWM6g0+nUXUJl2vzaJF5fdm1/fePwuP2VqTZuR5XbB4A2sq2YdcISANA8hDcAJER4A0BChDcAJER4\nA0BChDcAJER4A0BChDcAJER4A0BChDcAJER4A0BC436TDlC64jLDfZVxTZxB2+d6O2gDwhs16xek\nQ6/HM+P2y9w2UB/aJgCQEOENAAkR3gCQEOENAAkR3gCQEOENAAkR3gCQEOENAAkR3gCQEOENAAkR\n3gCQEOENAAlxYSoMVPVV/8oyrM4qt93vdzBNLU36XSIPwhsjVH3Vv7JUWeek2x60fpbfJTKgbQIA\nCRHeAJAQbRNA1fbNgSoQ3sAl9KSRB20TAEiI8AaAhAhvAEhorPC2fYXtI7YfKe5vs71m+7jtg7a3\nVlsmAGCjcfe875J0TC/O6CxLWouIXZIOFfcBAHMyMrxtv1bSWyX9uV6cet8rabVYXpW0r5LqAAB9\njbPn/QFJ75F0YcPYUkSsF8vrkpbKLgwAMNjQ47xt/5SkUxFxxHan3zoREbYHXllnZWXl0nKn01Gn\n03czALCwut2uut3uRI/xsCua2f5DSW+X9LykqyVdK+lTkn5YUiciTtreIelwRNzQ5/HBFdPy6p11\n2P/ElTLe17K2P2w7Lx3vv+3JtlH9drDYbCsihp4hNrRtEhHvjYidEfHdkn5e0j9ExNslPSxpf7Ha\nfkkHyigYADCeSY/zvriLcJ+k3baPS3pTcR8AMCdD2yYzb5y2SWq0TQZto/rtYLHN3DYBADQT4Q0A\nCRHeAJAQ4Q0ACRHeAJAQ4Q0ACRHeAJAQ4Q0ACRHeAJAQ3x6P4qxAAJkQ3igMOqUbQBPRNgGAhAhv\nAEiItgkaaVAfnivwAT2ENxqKHjwwDG0TAEiI8AaAhAhvAEiInjcWDicloQ0IbywgJkORH20TAEiI\n8AaAhGiboHL0mIHyEd6YE/rMQJlomwBAQoQ3ACRE2wSYUh29/GHPyUW7FgvhDUytrj4+8wegbQIA\nKRHeAJAQ4Q0ACdHzBlqMCc72IryB1mOCs41omwBAQoQ3ACQ0NLxtX237MdtHbR+z/b5ifJvtNdvH\nbR+0vXU+5WLR2X7JDVhEQ8M7Ir4l6baIuEnS90m6zfatkpYlrUXELkmHivvAHESfG7B4RrZNIuJs\nsXiVpCsknZa0V9JqMb4qaV8l1QEA+hoZ3ra32D4qaV3S4Yh4UtJSRKwXq6xLWqqwRgDAJiMPFYyI\nC5Jusv1qSY/avm3Tz8M2f7sCwByNfZx3RDxn+9OSflDSuu3tEXHS9g5JpwY9bmVl5dJyp9NRp9OZ\nvloAaKFut6tutzvRYzzsLCvb10l6PiKetf1ySY9K+j1JPynpmYi43/aypK0R8ZJJS9vBWVzN1zti\nY9CJHP3HJ3lfp9l+deNNqqU3Xtbvst92Jl0fzWBbETH0UKpRe947JK3a3qJef/yBiDhk+4ikB22/\nU9IJSXeUUTAAYDxD97xn3jh73imw513vOHve2GycPW/OsASAhAhvAEiI8AaAhAhvAEiI8AaAhAhv\nAEiI8AaAhAhvAEiI8AaAhPgCYqBmg74NiDMgMQzhDdSOb3fH5GibAEBChDcAJER4A0BChDcAJER4\nA0BChDcAJER4A0BCHOeN0gw62QRA+QhvlIwTToB5oG0CAAkR3gCQEOENAAnR814gTCgC7UF4Lxwm\nFIE2oG0CAAkR3gCQEOENAAkR3gCQEOENAAkR3gCQEOENAAlxnHcLcTJOO/A+YhjCu7U4GSc/3kMM\nRtsEABIivAEgoZHhbXun7cO2n7T9RdvvKsa32V6zfdz2Qdtbqy8XQFls970hh3H2vM9LendEfK+k\nN0r6VdtvkLQsaS0idkk6VNwHkEb0uSGLkeEdEScj4mixfEbSU5JeI2mvpNVitVVJ+6oqEgBwuYl6\n3ravl3SzpMckLUXEevGjdUlLpVYGABho7PC2fY2kT0q6KyK+ufFnEcHfXAAwR2Md5237ZeoF9wMR\ncaAYXre9PSJO2t4h6VS/x66srFxa7nQ66nQ6MxWMZmBiCyhPt9tVt9ud6DHu7TQPWaH3KV2V9ExE\nvHvD+B8VY/fbXpa0NSKWNz02Rm0f5eu9ZYNO8Fj08SbVUu54v8/aNP8X+MzWz7YiYuge0jjhfauk\nz0j6gl58t++W9HlJD0r6TkknJN0REc9ueizhXQPCe9h4k2opd5zwbo9SwnvGAgjvGhDew8abVEu5\n44R3e4wT3lzbBMBl+s1nEOjNQ3gD2KTfXytoGq5tAgAJEd4AkBBtE6AlOPZ+sRDeQGvw5Q2LhLYJ\nACREeANAQoQ3ACREz7smwyaXBp8pN966ANqP8K7VpBNMnDwBoIe2CQAkRHgDQEK0TQCMxJxL8xDe\nAMbACUBNQ9sEABIivAEgIcIbABKi5w2gVJOegIbpEN4AKsAEZ9VomwBAQoQ3ACREeANAQoQ3ACRE\neANAQoQ3ACREeANAQoQ3ACREeANAQoQ3ACREeANAQlzbJLlhFwEC0F6Ed3pcAAhYRLRNACAhwhsA\nEiK8ASChkeFt+8O2120/sWFsm+0128dtH7S9tdoyATSR7ZfcMB/j7Hl/RNKeTWPLktYiYpekQ8V9\nAAsn+twwDyPDOyI+K+n0puG9klaL5VVJ+0quCwAwxLQ976WIWC+W1yUtlVQPAGAMMx/nHRFhe+Df\nSisrK5eWO52OOp3OrE8JoEX4tnmp2+2q2+1O9BiP88uxfb2kRyLixuL+05I6EXHS9g5JhyPihj6P\ni0X55U+q9x+2/wk2/X5n/dcfvA3GB403qZYs4+Vte/z/24PXXwS2FRFDZ3+nbZs8LGl/sbxf0oEp\ntwMAmMI4hwp+XNI/Snq97a/Yfoek+yTttn1c0puK+wCAORmrbTL1xmmbDETbpK7xJtWSZZy2ybyN\n0zbhwlQNxIkOAEYhvBuJKwUCGI5rmwBAQoQ3ACRE26Qk9KmB8g36XC3qROZGhHepJp2RBzAcn51B\naJsAQEKENwAkRHgDQEL0vAHMDRP75SG8AcwRE5BloW0CAAkR3gCQ0MK3TSb9Fg96dgCaYOHDu2fS\nPhx9OwD1om0CAAkR3gCQEG0TAK1Q5vxVhgtfEd4AWmRx5q9omwBAQoQ3ACREeANAQvS8h+CEHKCZ\n+GwS3iPkncwA2o3PJm0TAEiI8AaAhNK2TbIfYA+guTJ8a33a8O6h7wWgCs3PFtomAJAQ4Q0ACTW6\nbXL69Gndeedv6Pz5uisBgGZpdHifPXtWDz30Nzp37o83/eQrQx/HAfwAqtCkicxGh7ckXXnlK3Xu\n3P5No1+Q9DtDHjVosqH5kxAAmqw5GULPGwASIrwBIKGZwtv2HttP2/6y7d8uqygAwHBTh7ftKyT9\nqaQ9kr5H0ttsv6GswnLo1l1Ahbp1F1Cxbt0FVKxbdwEV69ZdQO1m2fO+RdK/R8SJiDgv6a8k3V5O\nWVl06y6gQt26C6hYt+4CKtatu4CKdesuoHazhPdrdPkxe/9djAEAKjbLoYJzObDx3LlndO21P33Z\n2IUL39CZM/N4dgBoJk97cLntN0paiYg9xf27JV2IiPs3rNOcS3ABQCIRMfQA8lnC+0pJX5L045L+\nR9LnJb0tIp6aaoMAgLFN3TaJiOdt/5qkRyVdIelDBDcAzMfUe94AgPpUeoal7d+3/W+2j9o+ZHtn\nlc83b7bfb/up4jV+yvar666pTLZ/1vaTtl+w/QN111OWNp9cZvvDttdtP1F3LWWzvdP24eL/5Bdt\nv6vumspk+2rbjxV5ecz2+4auX+Wet+1XRcQ3i+Vfl/T9EfFLlT3hnNneLelQRFywfZ8kRcRyzWWV\nxvYNki5I+jNJvxkR/1pzSTMrTi77kqQ3S/qqpH9Wi+ZqbP+opDOS/iIibqy7njLZ3i5pe0QctX2N\npH+RtK8t750k2X5FRJwt5hQ/J+m3IuJz/datdM/7YnAXrpH0f1U+37xFxFpEXCjuPibptXXWU7aI\neDoijtddR8lafXJZRHxW0um666hCRJyMiKPF8hlJT0n6jnqrKldEnC0Wr1JvLvHrg9at/MJUtv/A\n9n9J2i/pvqqfr0a/KOlv6y4CI3FyWQvYvl7SzertNLWG7S22j0pal3Q4Io4NWnfm63nbXpO0vc+P\n3hsRj0TEPZLusb0s6QOS3jHrc87TqNdXrHOPpHMR8bG5FleCcV5fyzBDn1zRMvmEpLuKPfDWKP6S\nv6mYP3vUdiciuv3WnTm8I2L3mKt+TAn3TEe9Ptu/IOmt6h3vns4E719bfFXSxonznertfSMB2y+T\n9ElJfxkRB+qupyoR8ZztT0v6IQ24kEvVR5u8bsPd2yUdqfL55s32HknvkXR7RHyr7noq1pavHHpc\n0utsX2/7Kkk/J+nhmmvCGNz7DrIPSToWER+su56y2b7O9tZi+eWSdmtIZlZ9tMknJL1e0guS/kPS\nnRFxqrInnDPbX1ZvYuHipMI/RcSv1FhSqWz/jKQ/kXSdpOckHYmIt9Rb1exsv0XSB/XiyWVDD8nK\nxPbHJf2YpG+TdErS70bER+qtqhy2b5X0GfW+B/FicN0dEX9XX1XlsX2jpFX1dqq3SHogIt4/cH1O\n0gGAfPgaNABIiPAGgIQIbwBIiPAGgIQIbwBIiPAGgIQIbwBIiPAGgIT+H4bDw+mLTBu+AAAAAElF\nTkSuQmCC\n", | |
"text": [ | |
"<matplotlib.figure.Figure at 0x1070b9ad0>" | |
] | |
} | |
], | |
"prompt_number": 2 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": [ | |
"# perform kernel density\n", | |
"xfit = np.linspace(-5, 5, 1000)\n", | |
"\n", | |
"# make data of shape [n_samples, n_features]\n", | |
"# this is required by scikit-learn, as it usually uses multi-dimensional data\n", | |
"X = x[:, np.newaxis]\n", | |
"Xfit = xfit[:, np.newaxis]" | |
], | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 3 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": [ | |
"kde = KernelDensity(bandwidth=0.2)\n", | |
"kde.fit(X)\n", | |
"\n", | |
"# really unfortunate notation... but this is how you get the density\n", | |
"density = np.exp(kde.score_samples(Xfit))\n", | |
"plt.hist(x, 50, normed=True, alpha=0.5)\n", | |
"plt.plot(xfit, density, '-k', lw=2);" | |
], | |
"language": "python", | |
"metadata": {}, | |
"outputs": [ | |
{ | |
"metadata": {}, | |
"output_type": "display_data", | |
"png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEACAYAAAC57G0KAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n", | |
"text": [ | |
"<matplotlib.figure.Figure at 0x10851af90>" | |
] | |
} | |
], | |
"prompt_number": 4 | |
}, | |
{ | |
"cell_type": "code", | |
"collapsed": false, | |
"input": [], | |
"language": "python", | |
"metadata": {}, | |
"outputs": [], | |
"prompt_number": 4 | |
} | |
], | |
"metadata": {} | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment