multivariate linear regression in python

multivariate linear regression in python

{
 "metadata": {
  "name": "multivariate linear regression in python"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "#From http://stackoverflow.com/questions/11479064/multivariate-linear-regression-in-python\n",
      "import numpy as np\n",
      "import statsmodels.api as sm\n",
      "\n",
      "y = [1,2,3,4,3,4,5,4,5,5,4,5,4,5,4,5,6,5,4,5,4,3,4]\n",
      "\n",
      "x = [\n",
      "     [4,2,3,4,5,4,5,6,7,4,8,9,8,8,6,6,5,5,5,5,5,5,5],\n",
      "     [4,1,2,3,4,5,6,7,5,8,7,8,7,8,7,8,7,7,7,7,7,6,5],\n",
      "     [4,1,2,5,6,7,8,9,7,8,7,8,7,7,7,7,7,7,6,6,4,4,4]\n",
      "     ]\n",
      "\n",
      "def reg_m(y, x):\n",
      "    ones = np.ones(len(x[0]))\n",
      "    X = sm.add_constant(np.column_stack((x[0], ones)))\n",
      "    for ele in x[1:]:\n",
      "        X = sm.add_constant(np.column_stack((ele, X)))\n",
      "    results = sm.OLS(y, X).fit()\n",
      "    return results\n",
      "print reg_m(y, x).summary()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "                            OLS Regression Results                            \n",
        "==============================================================================\n",
        "Dep. Variable:                      y   R-squared:                       0.535\n",
        "Model:                            OLS   Adj. R-squared:                  0.461\n",
        "Method:                 Least Squares   F-statistic:                     7.281\n",
        "Date:                Wed, 09 Oct 2013   Prob (F-statistic):            0.00191\n",
        "Time:                        18:29:48   Log-Likelihood:                -26.025\n",
        "No. Observations:                  23   AIC:                             60.05\n",
        "Df Residuals:                      19   BIC:                             64.59\n",
        "Df Model:                           3                                         \n",
        "==============================================================================\n",
        "                 coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
        "------------------------------------------------------------------------------\n",
        "x1             0.2424      0.139      1.739      0.098        -0.049     0.534\n",
        "x2             0.2360      0.149      1.587      0.129        -0.075     0.547\n",
        "x3            -0.0618      0.145     -0.427      0.674        -0.365     0.241\n",
        "const          1.5704      0.633      2.481      0.023         0.245     2.895\n",
        "==============================================================================\n",
        "Omnibus:                        6.904   Durbin-Watson:                   1.905\n",
        "Prob(Omnibus):                  0.032   Jarque-Bera (JB):                4.708\n",
        "Skew:                          -0.849   Prob(JB):                       0.0950\n",
        "Kurtosis:                       4.426   Cond. No.                         38.6\n",
        "==============================================================================\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}