Statsmodels Formula

Statsmodels Formula.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:968c8a914ea58c2d9f281bf1a4807e0855bcde20b39626d57618599147f74244"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "import pandas as pd\n",
      "import statsmodels.formula.api as smf"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "N = 10000"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "x = np.random.normal(size=N)\n",
      "y = x * 1.344 + 1344"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df = pd.DataFrame({'x': x, 'y': y})"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "model = smf.ols(formula=\"y ~ x\", data=df)\n",
      "fit = model.fit()\n",
      "fit.summary()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<table class=\"simpletable\">\n",
        "<caption>OLS Regression Results</caption>\n",
        "<tr>\n",
        "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th>  <td>   1.000</td> \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th>  <td>   1.000</td> \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th>  <td>5.434e+27</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Date:</th>             <td>Sat, 20 Dec 2014</td> <th>  Prob (F-statistic):</th>   <td>  0.00</td>  \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Time:</th>                 <td>18:50:53</td>     <th>  Log-Likelihood:    </th> <td>2.5612e+05</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>No. Observations:</th>      <td> 10000</td>      <th>  AIC:               </th> <td>-5.122e+05</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Df Residuals:</th>          <td>  9998</td>      <th>  BIC:               </th> <td>-5.122e+05</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>      <td> </td>    \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>      <td> </td>    \n",
        "</tr>\n",
        "</table>\n",
        "<table class=\"simpletable\">\n",
        "<tr>\n",
        "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th> <th>[95.0% Conf. Int.]</th> \n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Intercept</th> <td> 1344.0000</td> <td> 1.82e-14</td> <td> 7.37e+16</td> <td> 0.000</td> <td> 1344.000  1344.000</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>x</th>         <td>    1.3440</td> <td> 1.82e-14</td> <td> 7.37e+13</td> <td> 0.000</td> <td>    1.344     1.344</td>\n",
        "</tr>\n",
        "</table>\n",
        "<table class=\"simpletable\">\n",
        "<tr>\n",
        "  <th>Omnibus:</th>       <td> 0.108</td> <th>  Durbin-Watson:     </th> <td>   0.019</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Prob(Omnibus):</th> <td> 0.947</td> <th>  Jarque-Bera (JB):  </th> <td>   0.131</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Skew:</th>          <td>-0.002</td> <th>  Prob(JB):          </th> <td>   0.937</td>\n",
        "</tr>\n",
        "<tr>\n",
        "  <th>Kurtosis:</th>      <td> 2.983</td> <th>  Cond. No.          </th> <td>    1.02</td>\n",
        "</tr>\n",
        "</table>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "<class 'statsmodels.iolib.summary.Summary'>\n",
        "\"\"\"\n",
        "                            OLS Regression Results                            \n",
        "==============================================================================\n",
        "Dep. Variable:                      y   R-squared:                       1.000\n",
        "Model:                            OLS   Adj. R-squared:                  1.000\n",
        "Method:                 Least Squares   F-statistic:                 5.434e+27\n",
        "Date:                Sat, 20 Dec 2014   Prob (F-statistic):               0.00\n",
        "Time:                        18:50:53   Log-Likelihood:             2.5612e+05\n",
        "No. Observations:               10000   AIC:                        -5.122e+05\n",
        "Df Residuals:                    9998   BIC:                        -5.122e+05\n",
        "Df Model:                           1                                         \n",
        "Covariance Type:            nonrobust                                         \n",
        "==============================================================================\n",
        "                 coef    std err          t      P>|t|      [95.0% Conf. Int.]\n",
        "------------------------------------------------------------------------------\n",
        "Intercept   1344.0000   1.82e-14   7.37e+16      0.000      1344.000  1344.000\n",
        "x              1.3440   1.82e-14   7.37e+13      0.000         1.344     1.344\n",
        "==============================================================================\n",
        "Omnibus:                        0.108   Durbin-Watson:                   0.019\n",
        "Prob(Omnibus):                  0.947   Jarque-Bera (JB):                0.131\n",
        "Skew:                          -0.002   Prob(JB):                        0.937\n",
        "Kurtosis:                       2.983   Cond. No.                         1.02\n",
        "==============================================================================\n",
        "\n",
        "Warnings:\n",
        "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
        "\"\"\""
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}