tritemio/pybroom-example.ipynb

## pybroom-example.ipynb
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# PyBroom Example\n",
    "\n",
    "Example usage for `pybroom`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from numpy import sqrt, pi, exp, linspace\n",
    "from lmfit import Model\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format='retina'  # for hi-dpi displays"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "lmfit: 0.9.3\n"
     ]
    }
   ],
   "source": [
    "import lmfit\n",
    "print('lmfit: %s' % lmfit.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pybroom as br"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Create Noisy Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "x = np.linspace(-10, 10, 101)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "peak1 = lmfit.models.GaussianModel(prefix='p1_')\n",
    "peak2 = lmfit.models.GaussianModel(prefix='p2_')\n",
    "model = peak1 + peak2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "params = model.make_params(p1_amplitude=1, p2_amplitude=1, \n",
    "                           p1_sigma=1, p2_sigma=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(101,)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_data = model.eval(x=x, p1_center=-1, p2_center=2, p1_sigma=0.5, p2_sigma=1, p1_amplitude=1, p2_amplitude=2)\n",
    "y_data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "y_data += np.random.randn(*y_data.shape)/10"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1199d5ac8>]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAv8AAAH/CAYAAADAE7K/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQfAPAAAAZATBPwAAAJARBP8AAABARvw/8uqp8wyWyAsAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x119a5eb00>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 255,
       "width": 383
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(x, y_data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Model Fitting"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "params = model.make_params(p1_center=0, p2_center=3, \n",
    "                           p1_sigma=0.5, p2_sigma=1, \n",
    "                           p1_amplitude=1, p2_amplitude=2)\n",
    "result = model.fit(y_data, x=x, params=params)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Fit result from an lmfit `Model` can be inspected with\n",
    "with `fit_report` or `params.pretty_print()`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[Model]]\n",
      "    (Model(gaussian, prefix='p1_') + Model(gaussian, prefix='p2_'))\n",
      "[[Fit Statistics]]\n",
      "    # function evals   = 80\n",
      "    # data points      = 101\n",
      "    # variables        = 6\n",
      "    chi-square         = 0.869\n",
      "    reduced chi-square = 0.009\n",
      "    Akaike info crit   = -462.119\n",
      "    Bayesian info crit = -446.428\n",
      "[[Variables]]\n",
      "    p1_center:     -1.06506613 +/- 0.044504 (4.18%) (init= 0)\n",
      "    p1_amplitude:   0.92555631 +/- 0.077811 (8.41%) (init= 1)\n",
      "    p1_sigma:       0.48727592 +/- 0.045109 (9.26%) (init= 0.5)\n",
      "    p2_center:      1.88014965 +/- 0.067168 (3.57%) (init= 3)\n",
      "    p2_amplitude:   2.01978273 +/- 0.111363 (5.51%) (init= 2)\n",
      "    p2_sigma:       1.08615599 +/- 0.072809 (6.70%) (init= 1)\n",
      "    p1_fwhm:        1.14744709 +/- 0.106225 (9.26%)  == '2.3548200*p1_sigma'\n",
      "    p1_height:      0.75777099 +/- 0.056530 (7.46%)  == '0.3989423*p1_amplitude/p1_sigma'\n",
      "    p2_fwhm:        2.55770187 +/- 0.171454 (6.70%)  == '2.3548200*p2_sigma'\n",
      "    p2_height:      0.74186099 +/- 0.038648 (5.21%)  == '0.3989423*p2_amplitude/p2_sigma'\n",
      "[[Correlations]] (unreported correlations are <  0.100)\n",
      "    C(p2_amplitude, p2_sigma)    =  0.652 \n",
      "    C(p1_amplitude, p1_sigma)    =  0.647 \n",
      "    C(p1_amplitude, p2_sigma)    = -0.416 \n",
      "    C(p1_amplitude, p2_amplitude)  = -0.328 \n",
      "    C(p1_sigma, p2_sigma)        = -0.317 \n",
      "    C(p1_center, p2_sigma)       = -0.299 \n",
      "    C(p1_sigma, p2_amplitude)    = -0.266 \n",
      "    C(p1_amplitude, p2_center)   =  0.258 \n",
      "    C(p1_center, p2_amplitude)   = -0.240 \n",
      "    C(p1_sigma, p2_center)       =  0.228 \n",
      "    C(p1_center, p2_center)      =  0.196 \n",
      "    C(p1_center, p1_amplitude)   =  0.158 \n",
      "    C(p2_center, p2_sigma)       = -0.148 \n",
      "    C(p1_center, p1_sigma)       =  0.127 \n",
      "    C(p2_center, p2_amplitude)   = -0.119 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(result.fit_report())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Name             Value      Min      Max   Stderr     Vary     Expr\n",
      "p1_amplitude    0.9256     -inf      inf  0.07781     True     None\n",
      "p1_center       -1.065     -inf      inf   0.0445     True     None\n",
      "p1_fwhm          1.147     -inf      inf   0.1062    False 2.3548200*p1_sigma\n",
      "p1_height       0.7578     -inf      inf  0.05653    False 0.3989423*p1_amplitude/p1_sigma\n",
      "p1_sigma        0.4873        0      inf  0.04511     True     None\n",
      "p2_amplitude      2.02     -inf      inf   0.1114     True     None\n",
      "p2_center         1.88     -inf      inf  0.06717     True     None\n",
      "p2_fwhm          2.558     -inf      inf   0.1715    False 2.3548200*p2_sigma\n",
      "p2_height       0.7419     -inf      inf  0.03865    False 0.3989423*p2_amplitude/p2_sigma\n",
      "p2_sigma         1.086        0      inf  0.07281     True     None\n"
     ]
    }
   ],
   "source": [
    "result.params.pretty_print()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These methods a re convenient but extracting the data\n",
    "from the lmfit object requires some work and the knowledge\n",
    "of lmfit object structure.\n",
    "\n",
    "pybroom comes to help, extracting data from fit results and\n",
    "returning  pandas DataFrame in tidy format that can be \n",
    "much more easily manipulated, filtered and plotted."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Glance\n",
    "\n",
    "Glancing at the fit results (dropping some verbose columns):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>method</th>\n",
       "      <th>num_params</th>\n",
       "      <th>num_data_points</th>\n",
       "      <th>chisqr</th>\n",
       "      <th>redchi</th>\n",
       "      <th>AIC</th>\n",
       "      <th>BIC</th>\n",
       "      <th>num_func_eval</th>\n",
       "      <th>success</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>leastsq</td>\n",
       "      <td>6</td>\n",
       "      <td>101</td>\n",
       "      <td>0.86904</td>\n",
       "      <td>0.00914778</td>\n",
       "      <td>-462.119</td>\n",
       "      <td>-446.428</td>\n",
       "      <td>80</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    method num_params num_data_points   chisqr      redchi      AIC      BIC  \\\n",
       "0  leastsq          6             101  0.86904  0.00914778 -462.119 -446.428   \n",
       "\n",
       "  num_func_eval success  \n",
       "0            80    True  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dg = br.glance(result)\n",
    "dg.drop('name', 1).drop('message', 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `glance` function always return a one-row DataFrame."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Application Idea\n",
    "\n",
    "If you fit *N* models to the same dataset\n",
    "you can compare statistics such as reduced-$\\chi^2$\n",
    "\n",
    "Or, fitting several with several methods (and datasets) you\n",
    "can study the convergence properties using reduced-$\\chi^2,\n",
    "number of function evaluation and success rate."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tidy\n",
    "\n",
    "Tidy fit results for all the parameters:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>value</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>vary</th>\n",
       "      <th>expr</th>\n",
       "      <th>stderr</th>\n",
       "      <th>init_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>p1_amplitude</td>\n",
       "      <td>0.925556</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0778111</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>p1_center</td>\n",
       "      <td>-1.06507</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0445048</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>p1_fwhm</td>\n",
       "      <td>1.14745</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>False</td>\n",
       "      <td>2.3548200*p1_sigma</td>\n",
       "      <td>0.106225</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>p1_height</td>\n",
       "      <td>0.757771</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>False</td>\n",
       "      <td>0.3989423*p1_amplitude/p1_sigma</td>\n",
       "      <td>0.0565309</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>p1_sigma</td>\n",
       "      <td>0.487276</td>\n",
       "      <td>0</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0451097</td>\n",
       "      <td>0.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>p2_amplitude</td>\n",
       "      <td>2.01978</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.111363</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>p2_center</td>\n",
       "      <td>1.88015</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0671688</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>p2_fwhm</td>\n",
       "      <td>2.5577</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>False</td>\n",
       "      <td>2.3548200*p2_sigma</td>\n",
       "      <td>0.171454</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>p2_height</td>\n",
       "      <td>0.741861</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>False</td>\n",
       "      <td>0.3989423*p2_amplitude/p2_sigma</td>\n",
       "      <td>0.0386483</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>p2_sigma</td>\n",
       "      <td>1.08616</td>\n",
       "      <td>0</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0728099</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "           name     value  min  max   vary                             expr  \\\n",
       "0  p1_amplitude  0.925556 -inf  inf   True                             None   \n",
       "1     p1_center  -1.06507 -inf  inf   True                             None   \n",
       "2       p1_fwhm   1.14745 -inf  inf  False               2.3548200*p1_sigma   \n",
       "3     p1_height  0.757771 -inf  inf  False  0.3989423*p1_amplitude/p1_sigma   \n",
       "4      p1_sigma  0.487276    0  inf   True                             None   \n",
       "5  p2_amplitude   2.01978 -inf  inf   True                             None   \n",
       "6     p2_center   1.88015 -inf  inf   True                             None   \n",
       "7       p2_fwhm    2.5577 -inf  inf  False               2.3548200*p2_sigma   \n",
       "8     p2_height  0.741861 -inf  inf  False  0.3989423*p2_amplitude/p2_sigma   \n",
       "9      p2_sigma   1.08616    0  inf   True                             None   \n",
       "\n",
       "      stderr init_value  \n",
       "0  0.0778111          1  \n",
       "1  0.0445048          0  \n",
       "2   0.106225        NaN  \n",
       "3  0.0565309        NaN  \n",
       "4  0.0451097        0.5  \n",
       "5   0.111363          2  \n",
       "6  0.0671688          3  \n",
       "7   0.171454        NaN  \n",
       "8  0.0386483        NaN  \n",
       "9  0.0728099          1  "
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt = br.tidy(result)\n",
    "dt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `tidy` function returns one row for each parameter."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Application Idea\n",
    "\n",
    "If you fit *N* datasets with the same model \n",
    "(e.g. multiple measurement, bootstrap, etc.)\n",
    "you can build a single DataFrame and easily \n",
    "filter a single paramenter (e.g. to see the dispersion):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>value</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>vary</th>\n",
       "      <th>expr</th>\n",
       "      <th>stderr</th>\n",
       "      <th>init_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>p1_center</td>\n",
       "      <td>-1.06507</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0445048</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        name    value  min  max  vary  expr     stderr init_value\n",
       "1  p1_center -1.06507 -inf  inf  True  None  0.0445048          0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt.query('name==\"p1_center\"')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Or with a different syntax:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>name</th>\n",
       "      <th>value</th>\n",
       "      <th>min</th>\n",
       "      <th>max</th>\n",
       "      <th>vary</th>\n",
       "      <th>expr</th>\n",
       "      <th>stderr</th>\n",
       "      <th>init_value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>p1_center</td>\n",
       "      <td>-1.06507</td>\n",
       "      <td>-inf</td>\n",
       "      <td>inf</td>\n",
       "      <td>True</td>\n",
       "      <td>None</td>\n",
       "      <td>0.0445048</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        name    value  min  max  vary  expr     stderr init_value\n",
       "1  p1_center -1.06507 -inf  inf  True  None  0.0445048          0"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt.loc[dt.name == 'p1_center']"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Augment\n",
    "\n",
    "Tidy dataframe with data function of the independent variable ('x'). Columns include\n",
    "the data being fitted, best fit, best fit components, residuals, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>data</th>\n",
       "      <th>best_fit</th>\n",
       "      <th>residual</th>\n",
       "      <th>Model(gaussian, prefix='p1_')</th>\n",
       "      <th>Model(gaussian, prefix='p2_')</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-10.0</td>\n",
       "      <td>-0.037329</td>\n",
       "      <td>7.795483e-27</td>\n",
       "      <td>0.037329</td>\n",
       "      <td>7.391636e-74</td>\n",
       "      <td>7.795483e-27</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-9.8</td>\n",
       "      <td>0.037410</td>\n",
       "      <td>5.743356e-26</td>\n",
       "      <td>-0.037410</td>\n",
       "      <td>1.260995e-70</td>\n",
       "      <td>5.743356e-26</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-9.6</td>\n",
       "      <td>0.065175</td>\n",
       "      <td>4.090376e-25</td>\n",
       "      <td>-0.065175</td>\n",
       "      <td>1.817702e-67</td>\n",
       "      <td>4.090376e-25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-9.4</td>\n",
       "      <td>-0.046542</td>\n",
       "      <td>2.816019e-24</td>\n",
       "      <td>0.046542</td>\n",
       "      <td>2.213954e-64</td>\n",
       "      <td>2.816019e-24</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-9.2</td>\n",
       "      <td>0.048188</td>\n",
       "      <td>1.874057e-23</td>\n",
       "      <td>-0.048188</td>\n",
       "      <td>2.278510e-61</td>\n",
       "      <td>1.874057e-23</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      x      data      best_fit  residual  Model(gaussian, prefix='p1_')  \\\n",
       "0 -10.0 -0.037329  7.795483e-27  0.037329                   7.391636e-74   \n",
       "1  -9.8  0.037410  5.743356e-26 -0.037410                   1.260995e-70   \n",
       "2  -9.6  0.065175  4.090376e-25 -0.065175                   1.817702e-67   \n",
       "3  -9.4 -0.046542  2.816019e-24  0.046542                   2.213954e-64   \n",
       "4  -9.2  0.048188  1.874057e-23 -0.048188                   2.278510e-61   \n",
       "\n",
       "   Model(gaussian, prefix='p2_')  \n",
       "0                   7.795483e-27  \n",
       "1                   5.743356e-26  \n",
       "2                   4.090376e-25  \n",
       "3                   2.816019e-24  \n",
       "4                   1.874057e-23  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "da = br.augment(result)\n",
    "da.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The `augment` function returns one row for each data point."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "d = br.augment(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA28AAAO+CAYAAACTrS12AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEQkABW8iIiIiIiIB8P8B2eMZmGYTW8sAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x119b602e8>"
      ]
     },
     "metadata": {
      "image/png": {
       "height": 479,
       "width": 439
      }
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = plt.subplots(2, 1, figsize=(7, 8))\n",
    "ax[1].plot('x', 'data', data=d, marker='o', ls='None')\n",
    "ax[1].plot('x', \"Model(gaussian, prefix='p1_')\", data=d, lw=2, ls='--')\n",
    "ax[1].plot('x', \"Model(gaussian, prefix='p2_')\", data=d, lw=2, ls='--')\n",
    "ax[1].plot('x', 'best_fit', data=d, lw=2)\n",
    "ax[0].plot('x', 'residual', data=d);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Application Idea\n",
    "\n",
    "Fitting *N* datasets with the same model \n",
    "(or N models with the same dataset)\n",
    "you can automatically build a panel plot \n",
    "with seaborn using the dataset (or the model)\n",
    "as categorical variable."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}