Data Conversion and SVM Classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Data Analysis with Diamonds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "done\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import sklearn\n",
    "from sklearn.linear_model import SGDRegressor\n",
    "from sklearn import svm\n",
    "\n",
    "print('done')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Ideal</td>\n",
       "      <td>E</td>\n",
       "      <td>SI2</td>\n",
       "      <td>61.5</td>\n",
       "      <td>55.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.95</td>\n",
       "      <td>3.98</td>\n",
       "      <td>2.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.21</td>\n",
       "      <td>Premium</td>\n",
       "      <td>E</td>\n",
       "      <td>SI1</td>\n",
       "      <td>59.8</td>\n",
       "      <td>61.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.89</td>\n",
       "      <td>3.84</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.23</td>\n",
       "      <td>Good</td>\n",
       "      <td>E</td>\n",
       "      <td>VS1</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.29</td>\n",
       "      <td>Premium</td>\n",
       "      <td>I</td>\n",
       "      <td>VS2</td>\n",
       "      <td>62.4</td>\n",
       "      <td>58.0</td>\n",
       "      <td>334</td>\n",
       "      <td>4.20</td>\n",
       "      <td>4.23</td>\n",
       "      <td>2.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.31</td>\n",
       "      <td>Good</td>\n",
       "      <td>J</td>\n",
       "      <td>SI2</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   carat      cut color clarity  depth  table  price     x     y     z\n",
       "1   0.23    Ideal     E     SI2   61.5   55.0    326  3.95  3.98  2.43\n",
       "2   0.21  Premium     E     SI1   59.8   61.0    326  3.89  3.84  2.31\n",
       "3   0.23     Good     E     VS1   56.9   65.0    327  4.05  4.07  2.31\n",
       "4   0.29  Premium     I     VS2   62.4   58.0    334  4.20  4.23  2.63\n",
       "5   0.31     Good     J     SI2   63.3   58.0    335  4.34  4.35  2.75"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('diamonds.csv', index_col=0)\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Convert non numerical values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Ideal', 'Premium', 'Good', 'Very Good', 'Fair'], dtype=object)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['cut'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# one way to do this is with cat codes but we need to preserve a pre known higheracry so we will use somthing else\n",
    "# df['cut'].astype('category').cat.codes\n",
    "\n",
    "cut_class_dict = {'Fair':1, 'Good':2, 'Very Good':3, 'Premium':4, 'Ideal':5}\n",
    "clarity_dict = {\"I3\": 1, \"I2\": 2, \"I1\": 3, \"SI2\": 4, \"SI1\": 5, \"VS2\": 6, \"VS1\": 7, \"VVS2\": 8, \"VVS1\": 9, \"IF\": 10, \"FL\": 11}\n",
    "color_dict = {\"J\": 1,\"I\": 2,\"H\": 3,\"G\": 4,\"F\": 5,\"E\": 6,\"D\": 7}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Now we need to map these values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.23</td>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>4</td>\n",
       "      <td>61.5</td>\n",
       "      <td>55.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.95</td>\n",
       "      <td>3.98</td>\n",
       "      <td>2.43</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.21</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>5</td>\n",
       "      <td>59.8</td>\n",
       "      <td>61.0</td>\n",
       "      <td>326</td>\n",
       "      <td>3.89</td>\n",
       "      <td>3.84</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.23</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "      <td>56.9</td>\n",
       "      <td>65.0</td>\n",
       "      <td>327</td>\n",
       "      <td>4.05</td>\n",
       "      <td>4.07</td>\n",
       "      <td>2.31</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.29</td>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "      <td>6</td>\n",
       "      <td>62.4</td>\n",
       "      <td>58.0</td>\n",
       "      <td>334</td>\n",
       "      <td>4.20</td>\n",
       "      <td>4.23</td>\n",
       "      <td>2.63</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.31</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>63.3</td>\n",
       "      <td>58.0</td>\n",
       "      <td>335</td>\n",
       "      <td>4.34</td>\n",
       "      <td>4.35</td>\n",
       "      <td>2.75</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   carat  cut  color  clarity  depth  table  price     x     y     z\n",
       "1   0.23    5      6        4   61.5   55.0    326  3.95  3.98  2.43\n",
       "2   0.21    4      6        5   59.8   61.0    326  3.89  3.84  2.31\n",
       "3   0.23    2      6        7   56.9   65.0    327  4.05  4.07  2.31\n",
       "4   0.29    4      2        6   62.4   58.0    334  4.20  4.23  2.63\n",
       "5   0.31    2      1        4   63.3   58.0    335  4.34  4.35  2.75"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['cut'] = df['cut'].map(cut_class_dict)\n",
    "df['clarity'] = df['clarity'].map(clarity_dict)\n",
    "df['color'] = df['color'].map(color_dict)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Next we shuffle these values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>0.71</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>63.8</td>\n",
       "      <td>58.0</td>\n",
       "      <td>2804</td>\n",
       "      <td>5.62</td>\n",
       "      <td>5.66</td>\n",
       "      <td>3.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40545</th>\n",
       "      <td>0.55</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>63.6</td>\n",
       "      <td>57.0</td>\n",
       "      <td>1149</td>\n",
       "      <td>5.15</td>\n",
       "      <td>5.19</td>\n",
       "      <td>3.29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50301</th>\n",
       "      <td>0.27</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>59.7</td>\n",
       "      <td>59.0</td>\n",
       "      <td>544</td>\n",
       "      <td>4.19</td>\n",
       "      <td>4.22</td>\n",
       "      <td>2.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43181</th>\n",
       "      <td>0.52</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>62.2</td>\n",
       "      <td>56.4</td>\n",
       "      <td>1391</td>\n",
       "      <td>5.09</td>\n",
       "      <td>5.16</td>\n",
       "      <td>3.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37801</th>\n",
       "      <td>0.51</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>61.9</td>\n",
       "      <td>54.0</td>\n",
       "      <td>1000</td>\n",
       "      <td>5.12</td>\n",
       "      <td>5.15</td>\n",
       "      <td>3.18</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat  cut  color  clarity  depth  table  price     x     y     z\n",
       "343     0.71    3      6        6   63.8   58.0   2804  5.62  5.66  3.60\n",
       "40545   0.55    3      2        5   63.6   57.0   1149  5.15  5.19  3.29\n",
       "50301   0.27    3      5        9   59.7   59.0    544  4.19  4.22  2.51\n",
       "43181   0.52    5      3        6   62.2   56.4   1391  5.09  5.16  3.19\n",
       "37801   0.51    5      2        5   61.9   54.0   1000  5.12  5.15  3.18"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# always shuffle your data to avoid any biases that may emerge b/c of some order.\n",
    "df = sklearn.utils.shuffle(df)\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### We will also drop the price to make sure that it dose not have that data\n",
    "\n",
    "Recall that many methods will return a dataframe. So for X we want all of the columns EXCEPT for the price one, so we can just drop it. Then we use .values to convert to a numpy array. Then, for our labels, y, we say this is just the price column's values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>carat</th>\n",
       "      <th>cut</th>\n",
       "      <th>color</th>\n",
       "      <th>clarity</th>\n",
       "      <th>depth</th>\n",
       "      <th>table</th>\n",
       "      <th>price</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>z</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>343</th>\n",
       "      <td>0.71</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>63.8</td>\n",
       "      <td>58.0</td>\n",
       "      <td>2804</td>\n",
       "      <td>5.62</td>\n",
       "      <td>5.66</td>\n",
       "      <td>3.60</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>40545</th>\n",
       "      <td>0.55</td>\n",
       "      <td>3</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>63.6</td>\n",
       "      <td>57.0</td>\n",
       "      <td>1149</td>\n",
       "      <td>5.15</td>\n",
       "      <td>5.19</td>\n",
       "      <td>3.29</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50301</th>\n",
       "      <td>0.27</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>9</td>\n",
       "      <td>59.7</td>\n",
       "      <td>59.0</td>\n",
       "      <td>544</td>\n",
       "      <td>4.19</td>\n",
       "      <td>4.22</td>\n",
       "      <td>2.51</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>43181</th>\n",
       "      <td>0.52</td>\n",
       "      <td>5</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>62.2</td>\n",
       "      <td>56.4</td>\n",
       "      <td>1391</td>\n",
       "      <td>5.09</td>\n",
       "      <td>5.16</td>\n",
       "      <td>3.19</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37801</th>\n",
       "      <td>0.51</td>\n",
       "      <td>5</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>61.9</td>\n",
       "      <td>54.0</td>\n",
       "      <td>1000</td>\n",
       "      <td>5.12</td>\n",
       "      <td>5.15</td>\n",
       "      <td>3.18</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       carat  cut  color  clarity  depth  table  price     x     y     z\n",
       "343     0.71    3      6        6   63.8   58.0   2804  5.62  5.66  3.60\n",
       "40545   0.55    3      2        5   63.6   57.0   1149  5.15  5.19  3.29\n",
       "50301   0.27    3      5        9   59.7   59.0    544  4.19  4.22  2.51\n",
       "43181   0.52    5      3        6   62.2   56.4   1391  5.09  5.16  3.19\n",
       "37801   0.51    5      2        5   61.9   54.0   1000  5.12  5.15  3.18"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = df.drop(\"price\", axis=1).values\n",
    "y = df[\"price\"].values\n",
    "\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Split values for testing\n",
    "\n",
    "We want to probably split and save some of these values for testing the model after it's been trained. So we'll do something like:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([  621,  2889,  1640,   772, 11190,  4320,  5382, 11206,   716,\n",
       "         886,  5265,  6908,  4078,   625,  6999,   972,  2822,   886,\n",
       "         625,  1752,  2947,  6281, 16941,   778, 17492,  1289,   625,\n",
       "        3536,  4909,  9176, 13095,  1343,  6292,  2088,  9474,  1613,\n",
       "        5141,  1758,  2853,  1024,  9173,   921,  9530,  3830,  1092,\n",
       "       12654,  1080,  6098, 12308,  8736, 15575,  2327,  4347,  2078,\n",
       "       13477,  1712,   683,  9681,  4291, 15105,  1815,  1016,   844,\n",
       "        3215,  2163,   814,  1813, 14768,  1936,  1436,  6787,   792,\n",
       "        1132,  3838, 13629,  1675,  1621, 15308,   687,  8752,  2263,\n",
       "        1415,  9333,  4372,  3231,  3724, 10508,  1662, 10869,  4616,\n",
       "        5902,   767, 10071, 10161,   755,  4586,  2872,   442,  6353,\n",
       "       14680,  1089,   816,   561, 12170,  1154,  2142,   709,   475,\n",
       "        1849, 15802, 15930,   473,  6098,   645,   625,  3593,  2861,\n",
       "         942,  1960,   990,  3206,  4455,   835,  5055,   872,   855,\n",
       "        2599,  1015,  1184,  4136,   747,  2841,  4304,   794,  5666,\n",
       "        1446,  1056,  5509, 15651,  1129,  1387,   959,   596, 11262,\n",
       "        3898,  2830,  6019,  6066,   827,  1284, 12215,  2782,   537,\n",
       "        3457, 15312,  2716,   912,  9979,  1998,  1010,   568,  1013,\n",
       "        3976,  5018,  5181,  2314,   853, 12779,  7577,  2066,   876,\n",
       "        8602,  1815,  4136,   737,  3668,   622,   900,  1104,  1571,\n",
       "        4167,   702,   559, 14304,  4133,  1284,  8622,  1659, 10920,\n",
       "       10214,   465,   607,  1002,   523,   658,  2016,  5608,  3882,\n",
       "        5497,  2729])"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test_size = 200\n",
    "\n",
    "X_train = X[:-test_size]\n",
    "y_train = y[:-test_size]\n",
    "\n",
    "X_test = X[-test_size:]\n",
    "y_test = y[-test_size:]\n",
    "\n",
    "y_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Now we want to train the model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "SGDRegressor(alpha=0.0001, average=False, early_stopping=False, epsilon=0.1,\n",
       "             eta0=0.01, fit_intercept=True, l1_ratio=0.15,\n",
       "             learning_rate='invscaling', loss='squared_loss', max_iter=1000,\n",
       "             n_iter_no_change=5, penalty='l2', power_t=0.25, random_state=None,\n",
       "             shuffle=True, tol=0.001, validation_fraction=0.1, verbose=0,\n",
       "             warm_start=False)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# set up the model \n",
    "clf = SGDRegressor(max_iter=1000)\n",
    "clf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### now lets check out our current model score "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-122555925.37483901\n"
     ]
    }
   ],
   "source": [
    "print(clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### we then look at the actual prediction values "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "12538490.452625751 621\n",
      "14809061.717327118 2889\n",
      "-10328077.384397507 1640\n",
      "34390301.02269459 772\n",
      "9970008.495135307 11190\n",
      "33374377.18662119 4320\n",
      "23241604.113889694 5382\n",
      "-42134625.6554265 11206\n",
      "-13726324.440168858 716\n",
      "24794500.457984924 886\n"
     ]
    }
   ],
   "source": [
    "for X,y in list(zip(X_test, y_test))[:10]:\n",
    "    print(clf.predict([X])[0], y)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Results\n",
    "Well, that's not very good. The score for these regression models is r-squared/coefficient of determination, so I am actually not even sure how we got -70999348.67836547, but apparently we did. R-Squared is more often between 0 and 100%, where 100% is a perfect fit (1.0). Let's try support vector regression instead:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8214178865581102\n"
     ]
    }
   ],
   "source": [
    "clf = svm.SVR(kernel = 'linear')\n",
    "\n",
    "clf.fit(X_train, y_train)\n",
    "print(clf.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "model predicts -57.70413925314824, real value: 621\n",
      "model predicts 3440.349640774677, real value: 2889\n",
      "model predicts 1987.0987409995141, real value: 1640\n",
      "model predicts 670.2613760289405, real value: 772\n",
      "model predicts 10045.212686385816, real value: 11190\n",
      "model predicts 3971.869918691127, real value: 4320\n",
      "model predicts 5685.796701435216, real value: 5382\n",
      "model predicts 8078.358552975917, real value: 11206\n",
      "model predicts 658.7389351081783, real value: 716\n",
      "model predicts 1183.9861732721038, real value: 886\n",
      "model predicts 6117.2906105654165, real value: 5265\n",
      "model predicts 5592.126946772254, real value: 6908\n",
      "model predicts 4800.211617934468, real value: 4078\n",
      "model predicts 152.05984682459348, real value: 625\n",
      "model predicts 5705.3228395102, real value: 6999\n",
      "model predicts 353.89889734903227, real value: 972\n",
      "model predicts 3257.5260410553583, real value: 2822\n",
      "model predicts 1000.8761885445292, real value: 886\n",
      "model predicts -210.93714901554995, real value: 625\n",
      "model predicts 1911.2550299925988, real value: 1752\n"
     ]
    }
   ],
   "source": [
    "for X,y in list(zip(X_test, y_test))[:20]:\n",
    "    print(f\"model predicts {clf.predict([X])[0]}, real value: {y}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Final Results \n",
    "here we can see the SVM model dose a much better job"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}