2 - Introduction to pandas, matplotlib and regression.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy\n",
    "\n",
    "# things we already know\n",
    "from sklearn.cross_validation import train_test_split\n",
    "from sklearn.metrics import mean_squared_error\n",
    "from sklearn.linear_model import Ridge\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "\n",
    "\n",
    "# things we learn today\n",
    "import pandas\n",
    "\n",
    "from sklearn.tree import DecisionTreeRegressor, DecisionTreeClassifier\n",
    "from sklearn.svm import SVC, SVR"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Plotting in IPython\n",
    "\n",
    "below we use a **magic function**. It is a term!\n",
    "\n",
    "It says: activate matplotlib, show plots inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[-3 -2 -1  0  1  2  3  4]\n",
      "[ 9  4  1  0  1  4  9 16]\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x1099a5290>]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAW4AAAEACAYAAACTXJylAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxChxi4hEzP8HBl1Qr+vRUYoAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x1098f3290>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "x = numpy.array([-3, -2, -1, 0, 1, 2, 3, 4])\n",
    "print x\n",
    "print x ** 2\n",
    "\n",
    "plt.plot(x, x ** 2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX4AAAEACAYAAAC08h1NAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nGPyS1BiDX5IaY/BLUmP+PyLCmyva0LzgAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x109a09950>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "distribution = numpy.random.normal(loc=1., scale=2, size=10000)\n",
    "plt.hist(distribution)\n",
    "pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXsAAAEACAYAAABS29YJAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x109a09110>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(numpy.random.normal(loc=5., scale=2, size=10000), bins=30, alpha=0.4, normed=True, label='first')\n",
    "plt.hist(numpy.random.normal(loc=7., scale=3, size=10000), bins=30, alpha=0.4, normed=True, label='second')\n",
    "plt.hist(numpy.random.normal(loc=0., scale=1, size=10000), bins=30, alpha=0.4, normed=True, label='third')\n",
    "plt.legend()\n",
    "pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.collections.PathCollection at 0x10a1b6550>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/axelr/.conda/envs/rep/lib/python2.7/site-packages/matplotlib/collections.py:590: FutureWarning: elementwise comparison failed; returning scalar instead, but in the future will perform elementwise comparison\n",
      "  if self._edgecolors == str('face'):\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAr8AAAJPCAYAAAB1i7z3AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nNwi/AAAA8AbhFwAAAN74/wzgwDU2xxoeAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x109c4d7d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Large scatter plot\n",
    "plt.figure(figsize=[12, 10])\n",
    "plt.scatter(numpy.random.normal(size=300), numpy.random.normal(size=300))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Magics\n",
    "\n",
    "magics are not needed so far, those are just for the information"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 4.4 ms, sys: 3.45 ms, total: 7.84 ms\n",
      "Wall time: 8.11 ms\n"
     ]
    }
   ],
   "source": [
    "# sample two arrays of random numbers sampled from unifrom [0, 1]\n",
    "a = numpy.random.random(size=1000000)\n",
    "b = numpy.random.random(size=1000000)\n",
    "# measure time needed for operation\n",
    "%time result = a + b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 48.9 ms, sys: 9.22 ms, total: 58.2 ms\n",
      "Wall time: 78.6 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "# measure the time needed to run whole cell (%%, not %)\n",
    "a = numpy.random.random(size=1000000)\n",
    "b = numpy.random.random(size=1000000)\n",
    "result = a + b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " "
     ]
    }
   ],
   "source": [
    "# profiling of complex code\n",
    "%prun numpy.histogram(x)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# general info about magics in IPython\n",
    "%magic"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "following code works on my computer, since I have ruby installed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Hello from Ruby!\n"
     ]
    }
   ],
   "source": [
    "%%ruby\n",
    "def greet\n",
    "   puts 'Hello from Ruby!'\n",
    "end\n",
    "greet()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Pandas\n",
    "\n",
    "Downloading dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "head: data/winequality-white.csv: No such file or directory\r\n"
     ]
    }
   ],
   "source": [
    "!head data/winequality-white.csv"
   ]
  },
  {
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>quality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.9</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.9</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.2</td>\n",
       "      <td>0.32</td>\n",
       "      <td>0.16</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.045</td>\n",
       "      <td>30</td>\n",
       "      <td>136</td>\n",
       "      <td>0.9949</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.47</td>\n",
       "      <td>9.6</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.43</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.044</td>\n",
       "      <td>28</td>\n",
       "      <td>129</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>3.22</td>\n",
       "      <td>0.45</td>\n",
       "      <td>11.0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "0            7.0              0.27         0.36            20.7      0.045   \n",
       "1            6.3              0.30         0.34             1.6      0.049   \n",
       "2            8.1              0.28         0.40             6.9      0.050   \n",
       "3            7.2              0.23         0.32             8.5      0.058   \n",
       "4            7.2              0.23         0.32             8.5      0.058   \n",
       "5            8.1              0.28         0.40             6.9      0.050   \n",
       "6            6.2              0.32         0.16             7.0      0.045   \n",
       "7            7.0              0.27         0.36            20.7      0.045   \n",
       "8            6.3              0.30         0.34             1.6      0.049   \n",
       "9            8.1              0.22         0.43             1.5      0.044   \n",
       "\n",
       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "0                   45                   170   1.0010  3.00       0.45   \n",
       "1                   14                   132   0.9940  3.30       0.49   \n",
       "2                   30                    97   0.9951  3.26       0.44   \n",
       "3                   47                   186   0.9956  3.19       0.40   \n",
       "4                   47                   186   0.9956  3.19       0.40   \n",
       "5                   30                    97   0.9951  3.26       0.44   \n",
       "6                   30                   136   0.9949  3.18       0.47   \n",
       "7                   45                   170   1.0010  3.00       0.45   \n",
       "8                   14                   132   0.9940  3.30       0.49   \n",
       "9                   28                   129   0.9938  3.22       0.45   \n",
       "\n",
       "   alcohol  quality  \n",
       "0      8.8        6  \n",
       "1      9.5        6  \n",
       "2     10.1        6  \n",
       "3      9.9        6  \n",
       "4      9.9        6  \n",
       "5     10.1        6  \n",
       "6      9.6        6  \n",
       "7      8.8        6  \n",
       "8      9.5        6  \n",
       "9     11.0        6  "
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data = pandas.read_csv('data/2-winequality-white.csv', sep=';')\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y = data['quality']\n",
    "X = data.drop('quality', axis=1)"
   ]
  },
  {
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.9</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.9</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.2</td>\n",
       "      <td>0.32</td>\n",
       "      <td>0.16</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.045</td>\n",
       "      <td>30</td>\n",
       "      <td>136</td>\n",
       "      <td>0.9949</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.47</td>\n",
       "      <td>9.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.43</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.044</td>\n",
       "      <td>28</td>\n",
       "      <td>129</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>3.22</td>\n",
       "      <td>0.45</td>\n",
       "      <td>11.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "0            7.0              0.27         0.36            20.7      0.045   \n",
       "1            6.3              0.30         0.34             1.6      0.049   \n",
       "2            8.1              0.28         0.40             6.9      0.050   \n",
       "3            7.2              0.23         0.32             8.5      0.058   \n",
       "4            7.2              0.23         0.32             8.5      0.058   \n",
       "5            8.1              0.28         0.40             6.9      0.050   \n",
       "6            6.2              0.32         0.16             7.0      0.045   \n",
       "7            7.0              0.27         0.36            20.7      0.045   \n",
       "8            6.3              0.30         0.34             1.6      0.049   \n",
       "9            8.1              0.22         0.43             1.5      0.044   \n",
       "\n",
       "   free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "0                   45                   170   1.0010  3.00       0.45   \n",
       "1                   14                   132   0.9940  3.30       0.49   \n",
       "2                   30                    97   0.9951  3.26       0.44   \n",
       "3                   47                   186   0.9956  3.19       0.40   \n",
       "4                   47                   186   0.9956  3.19       0.40   \n",
       "5                   30                    97   0.9951  3.26       0.44   \n",
       "6                   30                   136   0.9949  3.18       0.47   \n",
       "7                   45                   170   1.0010  3.00       0.45   \n",
       "8                   14                   132   0.9940  3.30       0.49   \n",
       "9                   28                   129   0.9938  3.22       0.45   \n",
       "\n",
       "   alcohol  \n",
       "0      8.8  \n",
       "1      9.5  \n",
       "2     10.1  \n",
       "3      9.9  \n",
       "4      9.9  \n",
       "5     10.1  \n",
       "6      9.6  \n",
       "7      8.8  \n",
       "8      9.5  \n",
       "9     11.0  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Operations with pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "#leaving only 14 rows for testing\n",
    "test_frame = data[:14].copy()"
   ]
  },
  {
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>quality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.70</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.60</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.90</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.50</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.50</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.90</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.2</td>\n",
       "      <td>0.32</td>\n",
       "      <td>0.16</td>\n",
       "      <td>7.00</td>\n",
       "      <td>0.045</td>\n",
       "      <td>30</td>\n",
       "      <td>136</td>\n",
       "      <td>0.9949</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.47</td>\n",
       "      <td>9.6</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.70</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.60</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.43</td>\n",
       "      <td>1.50</td>\n",
       "      <td>0.044</td>\n",
       "      <td>28</td>\n",
       "      <td>129</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>3.22</td>\n",
       "      <td>0.45</td>\n",
       "      <td>11.0</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.41</td>\n",
       "      <td>1.45</td>\n",
       "      <td>0.033</td>\n",
       "      <td>11</td>\n",
       "      <td>63</td>\n",
       "      <td>0.9908</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0.56</td>\n",
       "      <td>12.0</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>8.6</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.40</td>\n",
       "      <td>4.20</td>\n",
       "      <td>0.035</td>\n",
       "      <td>17</td>\n",
       "      <td>109</td>\n",
       "      <td>0.9947</td>\n",
       "      <td>3.14</td>\n",
       "      <td>0.53</td>\n",
       "      <td>9.7</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>7.9</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.37</td>\n",
       "      <td>1.20</td>\n",
       "      <td>0.040</td>\n",
       "      <td>16</td>\n",
       "      <td>75</td>\n",
       "      <td>0.9920</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.63</td>\n",
       "      <td>10.8</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>6.6</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.40</td>\n",
       "      <td>1.50</td>\n",
       "      <td>0.044</td>\n",
       "      <td>48</td>\n",
       "      <td>143</td>\n",
       "      <td>0.9912</td>\n",
       "      <td>3.54</td>\n",
       "      <td>0.52</td>\n",
       "      <td>12.4</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "0             7.0              0.27         0.36           20.70      0.045   \n",
       "1             6.3              0.30         0.34            1.60      0.049   \n",
       "2             8.1              0.28         0.40            6.90      0.050   \n",
       "3             7.2              0.23         0.32            8.50      0.058   \n",
       "4             7.2              0.23         0.32            8.50      0.058   \n",
       "5             8.1              0.28         0.40            6.90      0.050   \n",
       "6             6.2              0.32         0.16            7.00      0.045   \n",
       "7             7.0              0.27         0.36           20.70      0.045   \n",
       "8             6.3              0.30         0.34            1.60      0.049   \n",
       "9             8.1              0.22         0.43            1.50      0.044   \n",
       "10            8.1              0.27         0.41            1.45      0.033   \n",
       "11            8.6              0.23         0.40            4.20      0.035   \n",
       "12            7.9              0.18         0.37            1.20      0.040   \n",
       "13            6.6              0.16         0.40            1.50      0.044   \n",
       "\n",
       "    free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "0                    45                   170   1.0010  3.00       0.45   \n",
       "1                    14                   132   0.9940  3.30       0.49   \n",
       "2                    30                    97   0.9951  3.26       0.44   \n",
       "3                    47                   186   0.9956  3.19       0.40   \n",
       "4                    47                   186   0.9956  3.19       0.40   \n",
       "5                    30                    97   0.9951  3.26       0.44   \n",
       "6                    30                   136   0.9949  3.18       0.47   \n",
       "7                    45                   170   1.0010  3.00       0.45   \n",
       "8                    14                   132   0.9940  3.30       0.49   \n",
       "9                    28                   129   0.9938  3.22       0.45   \n",
       "10                   11                    63   0.9908  2.99       0.56   \n",
       "11                   17                   109   0.9947  3.14       0.53   \n",
       "12                   16                    75   0.9920  3.18       0.63   \n",
       "13                   48                   143   0.9912  3.54       0.52   \n",
       "\n",
       "    alcohol  quality  \n",
       "0       8.8        6  \n",
       "1       9.5        6  \n",
       "2      10.1        6  \n",
       "3       9.9        6  \n",
       "4       9.9        6  \n",
       "5      10.1        6  \n",
       "6       9.6        6  \n",
       "7       8.8        6  \n",
       "8       9.5        6  \n",
       "9      11.0        6  \n",
       "10     12.0        5  \n",
       "11      9.7        5  \n",
       "12     10.8        5  \n",
       "13     12.4        7  "
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     1.0010\n",
       "1     0.9940\n",
       "2     0.9951\n",
       "3     0.9956\n",
       "4     0.9956\n",
       "5     0.9951\n",
       "6     0.9949\n",
       "7     1.0010\n",
       "8     0.9940\n",
       "9     0.9938\n",
       "10    0.9908\n",
       "11    0.9947\n",
       "12    0.9920\n",
       "13    0.9912\n",
       "Name: density, dtype: float64"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_frame['density']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.001 ,  0.994 ,  0.9951,  0.9956,  0.9956,  0.9951,  0.9949,\n",
       "        1.001 ,  0.994 ,  0.9938,  0.9908,  0.9947,  0.992 ,  0.9912])"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# converting to numpy.array\n",
    "test_frame['density'].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0    7.0\n",
       "1    6.3\n",
       "2    8.1\n",
       "3    7.2\n",
       "4    7.2\n",
       "Name: fixed acidity, dtype: float64"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_frame['fixed acidity'][:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "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>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.32</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.36</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   citric acid  residual sugar  chlorides  free sulfur dioxide  \\\n",
       "0         0.36            20.7      0.045                   45   \n",
       "4         0.32             8.5      0.058                   47   \n",
       "7         0.36            20.7      0.045                   45   \n",
       "\n",
       "   total sulfur dioxide  \n",
       "0                   170  \n",
       "4                   186  \n",
       "7                   170  "
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# indexing with numbers - iloc\n",
    "test_frame.iloc[[0, 4, 7], 2:7]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "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>volatile acidity</th>\n",
       "      <th>fixed acidity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.27</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.30</td>\n",
       "      <td>6.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.28</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.23</td>\n",
       "      <td>7.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.23</td>\n",
       "      <td>7.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.28</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.32</td>\n",
       "      <td>6.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.27</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.30</td>\n",
       "      <td>6.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.22</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.27</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.23</td>\n",
       "      <td>8.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.18</td>\n",
       "      <td>7.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.16</td>\n",
       "      <td>6.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    volatile acidity  fixed acidity\n",
       "0               0.27            7.0\n",
       "1               0.30            6.3\n",
       "2               0.28            8.1\n",
       "3               0.23            7.2\n",
       "4               0.23            7.2\n",
       "5               0.28            8.1\n",
       "6               0.32            6.2\n",
       "7               0.27            7.0\n",
       "8               0.30            6.3\n",
       "9               0.22            8.1\n",
       "10              0.27            8.1\n",
       "11              0.23            8.6\n",
       "12              0.18            7.9\n",
       "13              0.16            6.6"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# indexing with named labels - loc\n",
    "test_frame.loc[:, ['volatile acidity', 'fixed acidity']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "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>volatile acidity</th>\n",
       "      <th>fixed acidity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.27</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.30</td>\n",
       "      <td>6.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.28</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.23</td>\n",
       "      <td>7.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.23</td>\n",
       "      <td>7.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.28</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.32</td>\n",
       "      <td>6.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.27</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.30</td>\n",
       "      <td>6.3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.22</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>0.27</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>0.23</td>\n",
       "      <td>8.6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>0.18</td>\n",
       "      <td>7.9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>0.16</td>\n",
       "      <td>6.6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    volatile acidity  fixed acidity\n",
       "0               0.27            7.0\n",
       "1               0.30            6.3\n",
       "2               0.28            8.1\n",
       "3               0.23            7.2\n",
       "4               0.23            7.2\n",
       "5               0.28            8.1\n",
       "6               0.32            6.2\n",
       "7               0.27            7.0\n",
       "8               0.30            6.3\n",
       "9               0.22            8.1\n",
       "10              0.27            8.1\n",
       "11              0.23            8.6\n",
       "12              0.18            7.9\n",
       "13              0.16            6.6"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# shortcut for previous\n",
    "test_frame[['volatile acidity', 'fixed acidity']]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "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>quality</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>pH</th>\n",
       "      <th>density</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>fixed acidity</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6</td>\n",
       "      <td>8.8</td>\n",
       "      <td>0.45</td>\n",
       "      <td>3.00</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>170</td>\n",
       "      <td>45</td>\n",
       "      <td>0.045</td>\n",
       "      <td>20.7</td>\n",
       "      <td>0.36</td>\n",
       "      <td>0.27</td>\n",
       "      <td>7.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6</td>\n",
       "      <td>9.9</td>\n",
       "      <td>0.40</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>186</td>\n",
       "      <td>47</td>\n",
       "      <td>0.058</td>\n",
       "      <td>8.5</td>\n",
       "      <td>0.32</td>\n",
       "      <td>0.23</td>\n",
       "      <td>7.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6</td>\n",
       "      <td>9.6</td>\n",
       "      <td>0.47</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.9949</td>\n",
       "      <td>136</td>\n",
       "      <td>30</td>\n",
       "      <td>0.045</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.32</td>\n",
       "      <td>6.2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>6</td>\n",
       "      <td>11.0</td>\n",
       "      <td>0.45</td>\n",
       "      <td>3.22</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>129</td>\n",
       "      <td>28</td>\n",
       "      <td>0.044</td>\n",
       "      <td>1.5</td>\n",
       "      <td>0.43</td>\n",
       "      <td>0.22</td>\n",
       "      <td>8.1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>5</td>\n",
       "      <td>10.8</td>\n",
       "      <td>0.63</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.9920</td>\n",
       "      <td>75</td>\n",
       "      <td>16</td>\n",
       "      <td>0.040</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.37</td>\n",
       "      <td>0.18</td>\n",
       "      <td>7.9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    quality  alcohol  sulphates    pH  density  total sulfur dioxide  \\\n",
       "0         6      8.8       0.45  3.00   1.0010                   170   \n",
       "3         6      9.9       0.40  3.19   0.9956                   186   \n",
       "6         6      9.6       0.47  3.18   0.9949                   136   \n",
       "9         6     11.0       0.45  3.22   0.9938                   129   \n",
       "12        5     10.8       0.63  3.18   0.9920                    75   \n",
       "\n",
       "    free sulfur dioxide  chlorides  residual sugar  citric acid  \\\n",
       "0                    45      0.045            20.7         0.36   \n",
       "3                    47      0.058             8.5         0.32   \n",
       "6                    30      0.045             7.0         0.16   \n",
       "9                    28      0.044             1.5         0.43   \n",
       "12                   16      0.040             1.2         0.37   \n",
       "\n",
       "    volatile acidity  fixed acidity  \n",
       "0               0.27            7.0  \n",
       "3               0.23            7.2  \n",
       "6               0.32            6.2  \n",
       "9               0.22            8.1  \n",
       "12              0.18            7.9  "
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_frame.iloc[::3, ::-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>quality</th>\n",
       "      <th>dioxide sum</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.70</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "      <td>215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.60</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "      <td>146</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.90</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "      <td>127</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.50</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "      <td>233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7.2</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.32</td>\n",
       "      <td>8.50</td>\n",
       "      <td>0.058</td>\n",
       "      <td>47</td>\n",
       "      <td>186</td>\n",
       "      <td>0.9956</td>\n",
       "      <td>3.19</td>\n",
       "      <td>0.40</td>\n",
       "      <td>9.9</td>\n",
       "      <td>6</td>\n",
       "      <td>233</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.28</td>\n",
       "      <td>0.40</td>\n",
       "      <td>6.90</td>\n",
       "      <td>0.050</td>\n",
       "      <td>30</td>\n",
       "      <td>97</td>\n",
       "      <td>0.9951</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.44</td>\n",
       "      <td>10.1</td>\n",
       "      <td>6</td>\n",
       "      <td>127</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>6.2</td>\n",
       "      <td>0.32</td>\n",
       "      <td>0.16</td>\n",
       "      <td>7.00</td>\n",
       "      <td>0.045</td>\n",
       "      <td>30</td>\n",
       "      <td>136</td>\n",
       "      <td>0.9949</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.47</td>\n",
       "      <td>9.6</td>\n",
       "      <td>6</td>\n",
       "      <td>166</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>7.0</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.36</td>\n",
       "      <td>20.70</td>\n",
       "      <td>0.045</td>\n",
       "      <td>45</td>\n",
       "      <td>170</td>\n",
       "      <td>1.0010</td>\n",
       "      <td>3.00</td>\n",
       "      <td>0.45</td>\n",
       "      <td>8.8</td>\n",
       "      <td>6</td>\n",
       "      <td>215</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>6.3</td>\n",
       "      <td>0.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.60</td>\n",
       "      <td>0.049</td>\n",
       "      <td>14</td>\n",
       "      <td>132</td>\n",
       "      <td>0.9940</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.49</td>\n",
       "      <td>9.5</td>\n",
       "      <td>6</td>\n",
       "      <td>146</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.22</td>\n",
       "      <td>0.43</td>\n",
       "      <td>1.50</td>\n",
       "      <td>0.044</td>\n",
       "      <td>28</td>\n",
       "      <td>129</td>\n",
       "      <td>0.9938</td>\n",
       "      <td>3.22</td>\n",
       "      <td>0.45</td>\n",
       "      <td>11.0</td>\n",
       "      <td>6</td>\n",
       "      <td>157</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>8.1</td>\n",
       "      <td>0.27</td>\n",
       "      <td>0.41</td>\n",
       "      <td>1.45</td>\n",
       "      <td>0.033</td>\n",
       "      <td>11</td>\n",
       "      <td>63</td>\n",
       "      <td>0.9908</td>\n",
       "      <td>2.99</td>\n",
       "      <td>0.56</td>\n",
       "      <td>12.0</td>\n",
       "      <td>5</td>\n",
       "      <td>74</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>8.6</td>\n",
       "      <td>0.23</td>\n",
       "      <td>0.40</td>\n",
       "      <td>4.20</td>\n",
       "      <td>0.035</td>\n",
       "      <td>17</td>\n",
       "      <td>109</td>\n",
       "      <td>0.9947</td>\n",
       "      <td>3.14</td>\n",
       "      <td>0.53</td>\n",
       "      <td>9.7</td>\n",
       "      <td>5</td>\n",
       "      <td>126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>7.9</td>\n",
       "      <td>0.18</td>\n",
       "      <td>0.37</td>\n",
       "      <td>1.20</td>\n",
       "      <td>0.040</td>\n",
       "      <td>16</td>\n",
       "      <td>75</td>\n",
       "      <td>0.9920</td>\n",
       "      <td>3.18</td>\n",
       "      <td>0.63</td>\n",
       "      <td>10.8</td>\n",
       "      <td>5</td>\n",
       "      <td>91</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>6.6</td>\n",
       "      <td>0.16</td>\n",
       "      <td>0.40</td>\n",
       "      <td>1.50</td>\n",
       "      <td>0.044</td>\n",
       "      <td>48</td>\n",
       "      <td>143</td>\n",
       "      <td>0.9912</td>\n",
       "      <td>3.54</td>\n",
       "      <td>0.52</td>\n",
       "      <td>12.4</td>\n",
       "      <td>7</td>\n",
       "      <td>191</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "0             7.0              0.27         0.36           20.70      0.045   \n",
       "1             6.3              0.30         0.34            1.60      0.049   \n",
       "2             8.1              0.28         0.40            6.90      0.050   \n",
       "3             7.2              0.23         0.32            8.50      0.058   \n",
       "4             7.2              0.23         0.32            8.50      0.058   \n",
       "5             8.1              0.28         0.40            6.90      0.050   \n",
       "6             6.2              0.32         0.16            7.00      0.045   \n",
       "7             7.0              0.27         0.36           20.70      0.045   \n",
       "8             6.3              0.30         0.34            1.60      0.049   \n",
       "9             8.1              0.22         0.43            1.50      0.044   \n",
       "10            8.1              0.27         0.41            1.45      0.033   \n",
       "11            8.6              0.23         0.40            4.20      0.035   \n",
       "12            7.9              0.18         0.37            1.20      0.040   \n",
       "13            6.6              0.16         0.40            1.50      0.044   \n",
       "\n",
       "    free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "0                    45                   170   1.0010  3.00       0.45   \n",
       "1                    14                   132   0.9940  3.30       0.49   \n",
       "2                    30                    97   0.9951  3.26       0.44   \n",
       "3                    47                   186   0.9956  3.19       0.40   \n",
       "4                    47                   186   0.9956  3.19       0.40   \n",
       "5                    30                    97   0.9951  3.26       0.44   \n",
       "6                    30                   136   0.9949  3.18       0.47   \n",
       "7                    45                   170   1.0010  3.00       0.45   \n",
       "8                    14                   132   0.9940  3.30       0.49   \n",
       "9                    28                   129   0.9938  3.22       0.45   \n",
       "10                   11                    63   0.9908  2.99       0.56   \n",
       "11                   17                   109   0.9947  3.14       0.53   \n",
       "12                   16                    75   0.9920  3.18       0.63   \n",
       "13                   48                   143   0.9912  3.54       0.52   \n",
       "\n",
       "    alcohol  quality  dioxide sum  \n",
       "0       8.8        6          215  \n",
       "1       9.5        6          146  \n",
       "2      10.1        6          127  \n",
       "3       9.9        6          233  \n",
       "4       9.9        6          233  \n",
       "5      10.1        6          127  \n",
       "6       9.6        6          166  \n",
       "7       8.8        6          215  \n",
       "8       9.5        6          146  \n",
       "9      11.0        6          157  \n",
       "10     12.0        5           74  \n",
       "11      9.7        5          126  \n",
       "12     10.8        5           91  \n",
       "13     12.4        7          191  "
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# adding new feature\n",
    "test_frame['dioxide sum'] = test_frame['total sulfur dioxide'] + test_frame['free sulfur dioxide']\n",
    "test_frame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "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>fixed acidity</th>\n",
       "      <th>volatile acidity</th>\n",
       "      <th>citric acid</th>\n",
       "      <th>residual sugar</th>\n",
       "      <th>chlorides</th>\n",
       "      <th>free sulfur dioxide</th>\n",
       "      <th>total sulfur dioxide</th>\n",
       "      <th>density</th>\n",
       "      <th>pH</th>\n",
       "      <th>sulphates</th>\n",
       "      <th>alcohol</th>\n",
       "      <th>quality</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2945</th>\n",
       "      <td>4.9</td>\n",
       "      <td>0.330</td>\n",
       "      <td>0.31</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.016</td>\n",
       "      <td>39</td>\n",
       "      <td>150</td>\n",
       "      <td>0.98713</td>\n",
       "      <td>3.33</td>\n",
       "      <td>0.59</td>\n",
       "      <td>14.00</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3367</th>\n",
       "      <td>6.0</td>\n",
       "      <td>0.290</td>\n",
       "      <td>0.25</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.033</td>\n",
       "      <td>30</td>\n",
       "      <td>114</td>\n",
       "      <td>0.98794</td>\n",
       "      <td>3.08</td>\n",
       "      <td>0.43</td>\n",
       "      <td>13.20</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3370</th>\n",
       "      <td>6.0</td>\n",
       "      <td>0.290</td>\n",
       "      <td>0.25</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.033</td>\n",
       "      <td>30</td>\n",
       "      <td>114</td>\n",
       "      <td>0.98794</td>\n",
       "      <td>3.08</td>\n",
       "      <td>0.43</td>\n",
       "      <td>13.20</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3673</th>\n",
       "      <td>5.4</td>\n",
       "      <td>0.300</td>\n",
       "      <td>0.30</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.029</td>\n",
       "      <td>25</td>\n",
       "      <td>93</td>\n",
       "      <td>0.98742</td>\n",
       "      <td>3.31</td>\n",
       "      <td>0.40</td>\n",
       "      <td>13.60</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3676</th>\n",
       "      <td>5.3</td>\n",
       "      <td>0.300</td>\n",
       "      <td>0.30</td>\n",
       "      <td>1.2</td>\n",
       "      <td>0.029</td>\n",
       "      <td>25</td>\n",
       "      <td>93</td>\n",
       "      <td>0.98742</td>\n",
       "      <td>3.31</td>\n",
       "      <td>0.40</td>\n",
       "      <td>13.60</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3710</th>\n",
       "      <td>4.7</td>\n",
       "      <td>0.670</td>\n",
       "      <td>0.09</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.020</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>0.98722</td>\n",
       "      <td>3.30</td>\n",
       "      <td>0.34</td>\n",
       "      <td>13.60</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3773</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.610</td>\n",
       "      <td>0.12</td>\n",
       "      <td>1.3</td>\n",
       "      <td>0.009</td>\n",
       "      <td>65</td>\n",
       "      <td>100</td>\n",
       "      <td>0.98740</td>\n",
       "      <td>3.26</td>\n",
       "      <td>0.37</td>\n",
       "      <td>13.50</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3904</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.455</td>\n",
       "      <td>0.18</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.036</td>\n",
       "      <td>33</td>\n",
       "      <td>106</td>\n",
       "      <td>0.98746</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0.83</td>\n",
       "      <td>14.00</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3915</th>\n",
       "      <td>4.7</td>\n",
       "      <td>0.455</td>\n",
       "      <td>0.18</td>\n",
       "      <td>1.9</td>\n",
       "      <td>0.036</td>\n",
       "      <td>33</td>\n",
       "      <td>106</td>\n",
       "      <td>0.98746</td>\n",
       "      <td>3.21</td>\n",
       "      <td>0.83</td>\n",
       "      <td>14.00</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3918</th>\n",
       "      <td>6.4</td>\n",
       "      <td>0.350</td>\n",
       "      <td>0.28</td>\n",
       "      <td>1.6</td>\n",
       "      <td>0.037</td>\n",
       "      <td>31</td>\n",
       "      <td>113</td>\n",
       "      <td>0.98779</td>\n",
       "      <td>3.12</td>\n",
       "      <td>0.40</td>\n",
       "      <td>14.20</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4149</th>\n",
       "      <td>5.8</td>\n",
       "      <td>0.240</td>\n",
       "      <td>0.28</td>\n",
       "      <td>1.4</td>\n",
       "      <td>0.038</td>\n",
       "      <td>40</td>\n",
       "      <td>76</td>\n",
       "      <td>0.98711</td>\n",
       "      <td>3.10</td>\n",
       "      <td>0.29</td>\n",
       "      <td>13.90</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4645</th>\n",
       "      <td>5.0</td>\n",
       "      <td>0.240</td>\n",
       "      <td>0.34</td>\n",
       "      <td>1.1</td>\n",
       "      <td>0.034</td>\n",
       "      <td>49</td>\n",
       "      <td>158</td>\n",
       "      <td>0.98774</td>\n",
       "      <td>3.32</td>\n",
       "      <td>0.32</td>\n",
       "      <td>13.10</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4789</th>\n",
       "      <td>5.5</td>\n",
       "      <td>0.620</td>\n",
       "      <td>0.33</td>\n",
       "      <td>1.7</td>\n",
       "      <td>0.037</td>\n",
       "      <td>24</td>\n",
       "      <td>118</td>\n",
       "      <td>0.98758</td>\n",
       "      <td>3.15</td>\n",
       "      <td>0.39</td>\n",
       "      <td>13.55</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      fixed acidity  volatile acidity  citric acid  residual sugar  chlorides  \\\n",
       "2945            4.9             0.330         0.31             1.2      0.016   \n",
       "3367            6.0             0.290         0.25             1.4      0.033   \n",
       "3370            6.0             0.290         0.25             1.4      0.033   \n",
       "3673            5.4             0.300         0.30             1.2      0.029   \n",
       "3676            5.3             0.300         0.30             1.2      0.029   \n",
       "3710            4.7             0.670         0.09             1.0      0.020   \n",
       "3773            5.0             0.610         0.12             1.3      0.009   \n",
       "3904            5.0             0.455         0.18             1.9      0.036   \n",
       "3915            4.7             0.455         0.18             1.9      0.036   \n",
       "3918            6.4             0.350         0.28             1.6      0.037   \n",
       "4149            5.8             0.240         0.28             1.4      0.038   \n",
       "4645            5.0             0.240         0.34             1.1      0.034   \n",
       "4789            5.5             0.620         0.33             1.7      0.037   \n",
       "\n",
       "      free sulfur dioxide  total sulfur dioxide  density    pH  sulphates  \\\n",
       "2945                   39                   150  0.98713  3.33       0.59   \n",
       "3367                   30                   114  0.98794  3.08       0.43   \n",
       "3370                   30                   114  0.98794  3.08       0.43   \n",
       "3673                   25                    93  0.98742  3.31       0.40   \n",
       "3676                   25                    93  0.98742  3.31       0.40   \n",
       "3710                    5                     9  0.98722  3.30       0.34   \n",
       "3773                   65                   100  0.98740  3.26       0.37   \n",
       "3904                   33                   106  0.98746  3.21       0.83   \n",
       "3915                   33                   106  0.98746  3.21       0.83   \n",
       "3918                   31                   113  0.98779  3.12       0.40   \n",
       "4149                   40                    76  0.98711  3.10       0.29   \n",
       "4645                   49                   158  0.98774  3.32       0.32   \n",
       "4789                   24                   118  0.98758  3.15       0.39   \n",
       "\n",
       "      alcohol  quality  \n",
       "2945    14.00        8  \n",
       "3367    13.20        6  \n",
       "3370    13.20        6  \n",
       "3673    13.60        7  \n",
       "3676    13.60        7  \n",
       "3710    13.60        5  \n",
       "3773    13.50        5  \n",
       "3904    14.00        7  \n",
       "3915    14.00        7  \n",
       "3918    14.20        7  \n",
       "4149    13.90        7  \n",
       "4645    13.10        7  \n",
       "4789    13.55        6  "
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "filtered_data = data[data['density'] < 0.988]\n",
    "filtered_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "14 (14, 13)\n",
      "Index([u'fixed acidity', u'volatile acidity', u'citric acid',\n",
      "       u'residual sugar', u'chlorides', u'free sulfur dioxide',\n",
      "       u'total sulfur dioxide', u'density', u'pH', u'sulphates', u'alcohol',\n",
      "       u'quality', u'dioxide sum'],\n",
      "      dtype='object')\n"
     ]
    }
   ],
   "source": [
    "print len(test_frame), test_frame.shape \n",
    "print test_frame.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.colorbar.Colorbar instance at 0x10cf44518>"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAVsAAAEACAYAAAAdhtXZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10a4a0b10>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(X['total sulfur dioxide'], X['volatile acidity'], c=y, alpha=0.4)\n",
    "plt.colorbar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## Exercise\n",
    "1. plot histograms of all features in dataset\n",
    "2. Let's classify wines in:\n",
    "   * good means quality >= 7\n",
    "   * bad means quality <= 4\n",
    "   * mediocre means quality five or six\n",
    "   \n",
    "   Plot histograms of all features for good and bad wines. Which feature is most discriminative?\n",
    "   \n",
    "3. Plot some scatter plots:\n",
    "   - alcohol vs fixed acidity for good and bad wines, what can we say about good wines?\n",
    "   - alcohol vs fixed acidity for quality=5 and quality=6\n",
    "   - alcohol vs density for good and bad wines. What can we conclude?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Linear models"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "trainX, testX, trainY, testY = train_test_split(X, y, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0 \t0.564587791519\n",
      "0.001 \t0.568293991144\n",
      "0.01 \t0.573570550784\n",
      "0.1 \t0.574990791682\n",
      "1 \t0.575287625141\n",
      "10 \t0.576469007479\n",
      "100 \t0.593064358623\n"
     ]
    }
   ],
   "source": [
    "for alpha in [0., 0.001, 0.01, 0.1, 1, 10, 100]:\n",
    "    linear_reg = Ridge(alpha)\n",
    "    linear_reg.fit(trainX, trainY)\n",
    "    print alpha, '\\t', mean_squared_error(testY, linear_reg.predict(testX)) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Linear models with non linear features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "X_extend = StandardScaler().fit_transform(X)\n",
    "X_extend = pandas.DataFrame(X_extend, columns=X.columns)\n",
    "\n",
    "for f in X_extend.columns:\n",
    "    X_extend[f + '_abs']  = numpy.abs(X_extend[f])\n",
    "    X_extend[f + '_tanh'] = numpy.tanh(X_extend[f])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "trainX_ex, testX_ex = train_test_split(X_extend, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.0 \t0.516931032212\n",
      "0.001 \t0.516931019462\n",
      "0.01 \t0.516930904672\n",
      "0.1 \t0.516929753694\n",
      "1 \t0.516918023577\n",
      "10 \t0.516826197999\n",
      "100 \t0.518524350888\n"
     ]
    }
   ],
   "source": [
    "for alpha in [0., 0.001, 0.01, 0.1, 1, 10, 100]:\n",
    "    linear_reg = Ridge(alpha)\n",
    "    linear_reg.fit(trainX_ex, trainY)\n",
    "    print alpha, '\\t', mean_squared_error(testY, linear_reg.predict(testX_ex)) "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}