Last active
August 29, 2015 14:17
-
-
Save PatWie/035d4c45eb9eef06ebe5 to your computer and use it in GitHub Desktop.
logistic Regression
This file contains hidden or 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
{"nbformat_minor": 0, "cells": [{"execution_count": 25, "cell_type": "code", "source": "# read data from csv file\ndata = readdlm(\"breast-cancer.csv\", ',');\n# get shape of data \n(m,d) = size(data)\n", "outputs": [{"execution_count": 25, "output_type": "execute_result", "data": {"text/plain": "(263,10)"}, "metadata": {}}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 29, "cell_type": "code", "source": "# first half is training set\ny = data[1:int(m/2),1]; \ny[y .== -1] = 0 \nx = data[1:int(m/2),2:end];\nno = sum(x,1)\n# normalize\nx = x./no;\n# augment by one dimension\nx = [ones(int(m/2),1) x]\n\n\n(_,d) = size(x)\n\n# second half is test set\ny_test = data[int(m/2):end,1];\ny_test[y_test .== -1] = 0\nx_test = data[int(m/2):end,2:end];\n# normalize\nx_test = x_test./no;\n# augment by one dimension\nx_test = [ones(size(x_test,1),1) x_test];\n\nprint(size(x))\nprint(size(y))\nprint(size(x_test))\nprint(size(y_test))", "outputs": [{"output_type": "stream", "name": "stdout", "text": "(132,10)(132,)(132,10)(132,)"}], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 32, "cell_type": "code", "source": "\u03b2 = zeros(d,1) # initial guess\n\u03b7 = 0.03 # learning rate\nmaxIter = 10000;\n\nfor k=1:maxIter\n \u03b2 = \u03b2 + \u03b7*sum((y-1.0./(1.0+exp(-x*\u03b2))) .* x,1)';\nend", "outputs": [], "metadata": {"collapsed": false, "trusted": true}}, {"execution_count": 33, "cell_type": "code", "source": "# in sample error\nprediction = 1.0./(1.0+exp(-x*\u03b2))\nprint(\"in sample accuracy \",100/132.0*sum(int(int(prediction .> 0.5).==y)),\"\\n\")\n\n# out of sample error\nprediction = 1.0./(1.0+exp(-x_test*\u03b2))\nprint(\"in sample accuracy \",100/132.0*sum(int(int(prediction .> 0.5).==y_test)),\"\\n\")", "outputs": [{"output_type": "stream", "name": "stdout", "text": "in sample accuracy 75.0\nout of sample accuracy 70.45454545454545\n"}], "metadata": {"collapsed": false, "trusted": true}}], "nbformat": 4, "metadata": {"kernelspec": {"display_name": "Julia 0.3.6", "name": "julia 0.3", "language": "julia"}, "language_info": {"version": "0.3.6", "name": "julia"}, "language": "Julia"}} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment