Simple linier regression with Python

Simple linier regression with Python

{
 "metadata": {
  "name": "Simple linier regression with Python"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#Example from http://www.answermysearches.com/how-to-do-a-simple-linear-regression-in-python/124/\n",
      "from math import sqrt\n",
      "def linreg(X, Y):\n",
      "    \"\"\"\n",
      "    Summary\n",
      "        Linear regression of y = ax + b\n",
      "    Usage\n",
      "        real, real, real = linreg(list, list)\n",
      "    Returns coefficients to the regression line \"y=ax+b\" from x[] and y[], and R^2 Value\n",
      "    \"\"\"\n",
      "    if len(X) != len(Y):  raise ValueError, 'unequal length'\n",
      "    N = len(X)\n",
      "    Sx = Sy = Sxx = Syy = Sxy = 0.0\n",
      "    for x, y in map(None, X, Y):\n",
      "        Sx = Sx + x\n",
      "        Sy = Sy + y\n",
      "        Sxx = Sxx + x*x\n",
      "        Syy = Syy + y*y\n",
      "        Sxy = Sxy + x*y\n",
      "    det = Sxx * N - Sx * Sx\n",
      "    a, b = (Sxy * N - Sy * Sx)/det, (Sxx * Sy - Sx * Sxy)/det\n",
      "    meanerror = residual = 0.0\n",
      "    for x, y in map(None, X, Y):\n",
      "        meanerror = meanerror + (y - Sy/N)**2\n",
      "        residual = residual + (y - a * x - b)**2\n",
      "    RR = 1 - residual/meanerror\n",
      "    ss = residual / (N-2)\n",
      "    Var_a, Var_b = ss * N / det, ss * Sxx / det\n",
      "    #print \"y=ax+b\"\n",
      "    #print \"N= %d\" % N\n",
      "    #print \"a= %g \\\\pm t_{%d;\\\\alpha/2} %g\" % (a, N-2, sqrt(Var_a))\n",
      "    #print \"b= %g \\\\pm t_{%d;\\\\alpha/2} %g\" % (b, N-2, sqrt(Var_b))\n",
      "    #print \"R^2= %g\" % RR\n",
      "    #print \"s^2= %g\" % ss\n",
      "    return a, b, RR\n",
      "\n",
      "if __name__=='__main__':\n",
      "    #testing\n",
      "    X=[1,2,3,4]\n",
      "    Y=[357.14,53.57,48.78,10.48]\n",
      "    print linreg(X,Y)\n",
      "    #should be:\n",
      "    #Slope\tY-Int\tR\n",
      "    #-104.477\t378.685\t0.702499064"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "(-104.47700000000005, 378.68500000000006, 0.7024990637134721)\n"
       ]
      }
     ],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}