Anscombe's quartet

anscombe's_quartet.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Anscombe's quartet\n",
    "-----\n",
    "\n",
    "Anscombe's quartet is one of the most famous datasets in the field of Statistics. Francis Anscombe is seminal statistician and the quartet are  four separate groups of data that teaches fundamental lessons in statistical analysis.\n",
    "\n",
    "This is a [Jupyter Notebook](http://jupyter.org/) with Python code."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "# Import the required Python packages\n",
    "from scipy import stats\n",
    "import seaborn as sns\n",
    "\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "outputs": [],
   "source": [
    "# Load Anscombe's quartet from Seaborn\n",
    "anscombe = sns.load_dataset(\"anscombe\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>dataset</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>I</td>\n",
       "      <td>10.0</td>\n",
       "      <td>8.04</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>I</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>II</td>\n",
       "      <td>10.0</td>\n",
       "      <td>9.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>II</td>\n",
       "      <td>8.0</td>\n",
       "      <td>8.14</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>III</td>\n",
       "      <td>10.0</td>\n",
       "      <td>7.46</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>III</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.77</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>IV</td>\n",
       "      <td>8.0</td>\n",
       "      <td>6.58</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>IV</td>\n",
       "      <td>8.0</td>\n",
       "      <td>5.76</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   dataset     x     y\n",
       "0        I  10.0  8.04\n",
       "1        I   8.0  6.95\n",
       "11      II  10.0  9.14\n",
       "12      II   8.0  8.14\n",
       "22     III  10.0  7.46\n",
       "23     III   8.0  6.77\n",
       "33      IV   8.0  6.58\n",
       "34      IV   8.0  5.76"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Take a peek at the data\n",
    "anscombe.groupby('dataset').head(n=2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "There are 4 groups. Each group has two variables (x and y) both of which are continuous."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>dataset</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">I</th>\n",
       "      <th>count</th>\n",
       "      <td>11.000000</td>\n",
       "      <td>11.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.500909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.316625</td>\n",
       "      <td>2.031568</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>4.260000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>6.500000</td>\n",
       "      <td>6.315000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.580000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>11.500000</td>\n",
       "      <td>8.570000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>14.000000</td>\n",
       "      <td>10.840000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">II</th>\n",
       "      <th>count</th>\n",
       "      <td>11.000000</td>\n",
       "      <td>11.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.500909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.316625</td>\n",
       "      <td>2.031657</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>3.100000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>6.500000</td>\n",
       "      <td>6.695000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>8.140000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>11.500000</td>\n",
       "      <td>8.950000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>14.000000</td>\n",
       "      <td>9.260000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">III</th>\n",
       "      <th>count</th>\n",
       "      <td>11.000000</td>\n",
       "      <td>11.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.500000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.316625</td>\n",
       "      <td>2.030424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>4.000000</td>\n",
       "      <td>5.390000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>6.500000</td>\n",
       "      <td>6.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.110000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>11.500000</td>\n",
       "      <td>7.980000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>14.000000</td>\n",
       "      <td>12.740000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"8\" valign=\"top\">IV</th>\n",
       "      <th>count</th>\n",
       "      <td>11.000000</td>\n",
       "      <td>11.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>9.000000</td>\n",
       "      <td>7.500909</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>3.316625</td>\n",
       "      <td>2.030579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>5.250000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>6.170000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>7.040000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>8.000000</td>\n",
       "      <td>8.190000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>19.000000</td>\n",
       "      <td>12.500000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       x          y\n",
       "dataset                            \n",
       "I       count  11.000000  11.000000\n",
       "        mean    9.000000   7.500909\n",
       "        std     3.316625   2.031568\n",
       "        min     4.000000   4.260000\n",
       "        25%     6.500000   6.315000\n",
       "        50%     9.000000   7.580000\n",
       "        75%    11.500000   8.570000\n",
       "        max    14.000000  10.840000\n",
       "II      count  11.000000  11.000000\n",
       "        mean    9.000000   7.500909\n",
       "        std     3.316625   2.031657\n",
       "        min     4.000000   3.100000\n",
       "        25%     6.500000   6.695000\n",
       "        50%     9.000000   8.140000\n",
       "        75%    11.500000   8.950000\n",
       "        max    14.000000   9.260000\n",
       "III     count  11.000000  11.000000\n",
       "        mean    9.000000   7.500000\n",
       "        std     3.316625   2.030424\n",
       "        min     4.000000   5.390000\n",
       "        25%     6.500000   6.250000\n",
       "        50%     9.000000   7.110000\n",
       "        75%    11.500000   7.980000\n",
       "        max    14.000000  12.740000\n",
       "IV      count  11.000000  11.000000\n",
       "        mean    9.000000   7.500909\n",
       "        std     3.316625   2.030579\n",
       "        min     8.000000   5.250000\n",
       "        25%     8.000000   6.170000\n",
       "        50%     8.000000   7.040000\n",
       "        75%     8.000000   8.190000\n",
       "        max    19.000000  12.500000"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calculate descriptive statistics for each group separately\n",
    "anscombe.groupby('dataset').describe()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "Each group looks very similar in size, central tendency, and spread."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "    Dataset I:\n",
      "    slope       = 0.5 \n",
      "    intercept   = 3.00 \n",
      "    correlation = 0.816 \n",
      "    p value     = 0.002\n",
      "    std error   = 0.118\n",
      "\n",
      "    Dataset II:\n",
      "    slope       = 0.5 \n",
      "    intercept   = 3.00 \n",
      "    correlation = 0.816 \n",
      "    p value     = 0.002\n",
      "    std error   = 0.118\n",
      "\n",
      "    Dataset III:\n",
      "    slope       = 0.5 \n",
      "    intercept   = 3.00 \n",
      "    correlation = 0.816 \n",
      "    p value     = 0.002\n",
      "    std error   = 0.118\n",
      "\n",
      "    Dataset IV:\n",
      "    slope       = 0.5 \n",
      "    intercept   = 3.00 \n",
      "    correlation = 0.817 \n",
      "    p value     = 0.002\n",
      "    std error   = 0.118\n"
     ]
    }
   ],
   "source": [
    "# Fit a linear regression, y ~ x, for each group\n",
    "for dataset in 'I II III IV'.split():\n",
    "    slope, intercept, r_value, p_value, std_err = stats.linregress(x=anscombe[anscombe.dataset==dataset].x,\n",
    "                                                               y=anscombe[anscombe.dataset==dataset].y)\n",
    "    print(\"\"\"\n",
    "    Dataset {}:\n",
    "    slope       = {:.1f} \n",
    "    intercept   = {:.2f} \n",
    "    correlation = {:.3f} \n",
    "    p value     = {:.3f}\n",
    "    std error   = {:.3f}\"\"\".format(dataset, slope, intercept, r_value, p_value , std_err))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "source": [
    "Each group looks exactly the same with respect to linear regression.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "\n",
    "-----"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjgAAAI4CAYAAABndZP2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/z/Fz3KG5amLVgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1159e4828>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot each dataset\n",
    "sns.lmplot(x=\"x\", y=\"y\", col=\"dataset\", hue=\"dataset\", data=anscombe,\n",
    "           col_wrap=2, ci=None, palette=\"muted\", size=4, scatter_kws={\"s\": 50, \"alpha\": 1});"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "![](https://media.giphy.com/media/dNKjTFq6AfH5m/giphy.gif)\n",
    "\n",
    "Each group is very different! We were mislead by the descriptive statistics and linear regression. \n",
    "\n",
    "__Lesson Learned__: Plot the data first to better understand what is going on before numerical analysis.\n",
    "\n",
    "This is Anscombe's quartet. Learn more [here](https://en.wikipedia.org/wiki/Anscombe's_quartet). "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true,
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "<br>\n",
    "<br> \n",
    "<br>"
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}