DBremen/SEC002 VID002 Build and Implement Random Forests Algorithm.ipynb

## SEC002 VID002 Build and Implement Random Forests Algorithm.ipynb
{
  "cells": [
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "# Build and implement random forests algo"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd\nimport numpy as np\nfrom matplotlib import pyplot as plt\n%matplotlib inline",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from zipline.data.data_portal import DataPortal\nfrom zipline.data import bundles\nfrom zipline.utils.calendars import get_calendar",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "bundle_data = bundles.load(\"quandl\")",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "end_date = pd.Timestamp(\"2019-01-01\", tz=\"utc\")",
      "execution_count": 4,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "bundle_data.equity_daily_bar_reader.first_trading_day",
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 5,
          "data": {
            "text/plain": "Timestamp('1990-01-02 00:00:00+0000', tz='UTC')"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Retrieve the data"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "data_por = DataPortal(\n    asset_finder=bundle_data.asset_finder, \n    trading_calendar=get_calendar(\"NYSE\"),\n    first_trading_day=bundle_data.equity_daily_bar_reader.first_trading_day,\n    equity_daily_reader=bundle_data.equity_daily_bar_reader\n)",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "TSLA = data_por.asset_finder.lookup_symbol(\n    \"TSLA\",\n    as_of_date=None\n)",
      "execution_count": 7,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = data_por.get_history_window(\n    assets=[TSLA],\n    end_dt=end_date,\n    bar_count=5000,\n    frequency='1d',\n    data_frequency='daily',\n    field=\"close\"\n)",
      "execution_count": 8,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Clean-up the data"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = df.dropna()\ndf.index = pd.DatetimeIndex(df.index)\ndf['close'] = df[list(df.columns)[0]]\ndf = df.drop(columns=[list(df.columns)[0]])",
      "execution_count": 9,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df.describe()",
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 10,
          "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>close</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>count</th>\n      <td>1949.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>158.641122</td>\n    </tr>\n    <tr>\n      <th>std</th>\n      <td>111.041317</td>\n    </tr>\n    <tr>\n      <th>min</th>\n      <td>15.800000</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n      <td>31.600000</td>\n    </tr>\n    <tr>\n      <th>50%</th>\n      <td>192.690000</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n      <td>240.240000</td>\n    </tr>\n    <tr>\n      <th>max</th>\n      <td>385.000000</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "             close\ncount  1949.000000\nmean    158.641122\nstd     111.041317\nmin      15.800000\n25%      31.600000\n50%     192.690000\n75%     240.240000\nmax     385.000000"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Plot the data"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from matplotlib.dates import MonthLocator, date2num, DateFormatter\n\nfig, ax = plt.subplots()\n\nfig.subplots_adjust(bottom=0.3)\n\nfig.set_figwidth(16)\nfig.set_figheight(8)\n\nax.plot(df.index, df.close)\n\nlctr = MonthLocator()  # every month\nfrmt = DateFormatter('%b')  # %b gives us Jan, Feb...\n\nax.xaxis.set_major_locator(lctr)\nax.xaxis.set_major_formatter(frmt)\n\nax.legend()\n\nplt.xticks(rotation=70)\nplt.tight_layout()\nplt.show();",
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 1152x576 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Adding column for future day's closing prices"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "for d in range(1, 41):\n    col = \"%dd\" % d\n    df[col] = df['close'].shift(-1 * d)\ndf.head()",
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 12,
          "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>close</th>\n      <th>1d</th>\n      <th>2d</th>\n      <th>3d</th>\n      <th>4d</th>\n      <th>5d</th>\n      <th>6d</th>\n      <th>7d</th>\n      <th>8d</th>\n      <th>9d</th>\n      <th>...</th>\n      <th>31d</th>\n      <th>32d</th>\n      <th>33d</th>\n      <th>34d</th>\n      <th>35d</th>\n      <th>36d</th>\n      <th>37d</th>\n      <th>38d</th>\n      <th>39d</th>\n      <th>40d</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2010-06-29 00:00:00+00:00</th>\n      <td>23.89</td>\n      <td>23.83</td>\n      <td>21.96</td>\n      <td>19.20</td>\n      <td>16.11</td>\n      <td>15.80</td>\n      <td>17.46</td>\n      <td>17.40</td>\n      <td>17.05</td>\n      <td>18.14</td>\n      <td>...</td>\n      <td>17.60</td>\n      <td>18.32</td>\n      <td>18.78</td>\n      <td>19.15</td>\n      <td>18.77</td>\n      <td>18.79</td>\n      <td>19.10</td>\n      <td>20.13</td>\n      <td>19.20</td>\n      <td>19.90</td>\n    </tr>\n    <tr>\n      <th>2010-06-30 00:00:00+00:00</th>\n      <td>23.83</td>\n      <td>21.96</td>\n      <td>19.20</td>\n      <td>16.11</td>\n      <td>15.80</td>\n      <td>17.46</td>\n      <td>17.40</td>\n      <td>17.05</td>\n      <td>18.14</td>\n      <td>19.84</td>\n      <td>...</td>\n      <td>18.32</td>\n      <td>18.78</td>\n      <td>19.15</td>\n      <td>18.77</td>\n      <td>18.79</td>\n      <td>19.10</td>\n      <td>20.13</td>\n      <td>19.20</td>\n      <td>19.90</td>\n      <td>19.75</td>\n    </tr>\n    <tr>\n      <th>2010-07-01 00:00:00+00:00</th>\n      <td>21.96</td>\n      <td>19.20</td>\n      <td>16.11</td>\n      <td>15.80</td>\n      <td>17.46</td>\n      <td>17.40</td>\n      <td>17.05</td>\n      <td>18.14</td>\n      <td>19.84</td>\n      <td>19.89</td>\n      <td>...</td>\n      <td>18.78</td>\n      <td>19.15</td>\n      <td>18.77</td>\n      <td>18.79</td>\n      <td>19.10</td>\n      <td>20.13</td>\n      <td>19.20</td>\n      <td>19.90</td>\n      <td>19.75</td>\n      <td>19.70</td>\n    </tr>\n    <tr>\n      <th>2010-07-02 00:00:00+00:00</th>\n      <td>19.20</td>\n      <td>16.11</td>\n      <td>15.80</td>\n      <td>17.46</td>\n      <td>17.40</td>\n      <td>17.05</td>\n      <td>18.14</td>\n      <td>19.84</td>\n      <td>19.89</td>\n      <td>20.64</td>\n      <td>...</td>\n      <td>19.15</td>\n      <td>18.77</td>\n      <td>18.79</td>\n      <td>19.10</td>\n      <td>20.13</td>\n      <td>19.20</td>\n      <td>19.90</td>\n      <td>19.75</td>\n      <td>19.70</td>\n      <td>19.87</td>\n    </tr>\n    <tr>\n      <th>2010-07-06 00:00:00+00:00</th>\n      <td>16.11</td>\n      <td>15.80</td>\n      <td>17.46</td>\n      <td>17.40</td>\n      <td>17.05</td>\n      <td>18.14</td>\n      <td>19.84</td>\n      <td>19.89</td>\n      <td>20.64</td>\n      <td>21.91</td>\n      <td>...</td>\n      <td>18.77</td>\n      <td>18.79</td>\n      <td>19.10</td>\n      <td>20.13</td>\n      <td>19.20</td>\n      <td>19.90</td>\n      <td>19.75</td>\n      <td>19.70</td>\n      <td>19.87</td>\n      <td>19.48</td>\n    </tr>\n  </tbody>\n</table>\n<p>5 rows × 41 columns</p>\n</div>",
            "text/plain": "                           close     1d     2d     3d     4d     5d     6d  \\\n2010-06-29 00:00:00+00:00  23.89  23.83  21.96  19.20  16.11  15.80  17.46   \n2010-06-30 00:00:00+00:00  23.83  21.96  19.20  16.11  15.80  17.46  17.40   \n2010-07-01 00:00:00+00:00  21.96  19.20  16.11  15.80  17.46  17.40  17.05   \n2010-07-02 00:00:00+00:00  19.20  16.11  15.80  17.46  17.40  17.05  18.14   \n2010-07-06 00:00:00+00:00  16.11  15.80  17.46  17.40  17.05  18.14  19.84   \n\n                              7d     8d     9d  ...      31d    32d    33d  \\\n2010-06-29 00:00:00+00:00  17.40  17.05  18.14  ...    17.60  18.32  18.78   \n2010-06-30 00:00:00+00:00  17.05  18.14  19.84  ...    18.32  18.78  19.15   \n2010-07-01 00:00:00+00:00  18.14  19.84  19.89  ...    18.78  19.15  18.77   \n2010-07-02 00:00:00+00:00  19.84  19.89  20.64  ...    19.15  18.77  18.79   \n2010-07-06 00:00:00+00:00  19.89  20.64  21.91  ...    18.77  18.79  19.10   \n\n                             34d    35d    36d    37d    38d    39d    40d  \n2010-06-29 00:00:00+00:00  19.15  18.77  18.79  19.10  20.13  19.20  19.90  \n2010-06-30 00:00:00+00:00  18.77  18.79  19.10  20.13  19.20  19.90  19.75  \n2010-07-01 00:00:00+00:00  18.79  19.10  20.13  19.20  19.90  19.75  19.70  \n2010-07-02 00:00:00+00:00  19.10  20.13  19.20  19.90  19.75  19.70  19.87  \n2010-07-06 00:00:00+00:00  20.13  19.20  19.90  19.75  19.70  19.87  19.48  \n\n[5 rows x 41 columns]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = df.dropna()",
      "execution_count": 13,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Slice first 33 columns and cols 33 onwards as a training set"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "X = df.iloc[:, :33]\ny = df.iloc[:, 33:]\nprint('X: {}'.format(X.shape))\nprint('y: {}'.format(y.shape))",
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "text": "X: (1909, 33)\ny: (1909, 8)\n",
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Sci-Kit Learn Train Test Split [ <a href=\"https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html\">Link</a> ]"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4)",
      "execution_count": 23,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "X_train.shape",
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 24,
          "data": {
            "text/plain": "(1145, 33)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "X_test.shape",
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 25,
          "data": {
            "text/plain": "(764, 33)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Sci-Kit Learn Random Forest Regressor [<a href=\"https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomForestRegressor.html\">Link</a>]"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from sklearn.ensemble import RandomForestRegressor\nregressor = RandomForestRegressor(\n    n_estimators=100,\n    criterion='mse',\n    max_depth=None,\n    min_samples_split=2,\n    min_samples_leaf=1,\n    min_weight_fraction_leaf=0.0,\n    max_features='auto',\n    max_leaf_nodes=None,\n    min_impurity_decrease=0.0,\n    min_impurity_split=None,\n    bootstrap=True,\n    oob_score=True,\n    n_jobs=16,\n    random_state=None,\n    verbose=1,\n    warm_start=False)\nregressor.fit(X_train, y_train)",
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "text": "[Parallel(n_jobs=16)]: Using backend ThreadingBackend with 16 concurrent workers.\n[Parallel(n_jobs=16)]: Done  18 tasks      | elapsed:    0.1s\n[Parallel(n_jobs=16)]: Done 100 out of 100 | elapsed:    0.7s finished\n",
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "execution_count": 26,
          "data": {
            "text/plain": "RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,\n           max_features='auto', max_leaf_nodes=None,\n           min_impurity_decrease=0.0, min_impurity_split=None,\n           min_samples_leaf=1, min_samples_split=2,\n           min_weight_fraction_leaf=0.0, n_estimators=100, n_jobs=16,\n           oob_score=True, random_state=None, verbose=1, warm_start=False)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "regressor.score(X_test, y_test)",
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "text": "[Parallel(n_jobs=16)]: Using backend ThreadingBackend with 16 concurrent workers.\n[Parallel(n_jobs=16)]: Done  18 tasks      | elapsed:    0.0s\n[Parallel(n_jobs=16)]: Done 100 out of 100 | elapsed:    0.0s finished\n",
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "execution_count": 27,
          "data": {
            "text/plain": "0.993275722565433"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "regressor.feature_importances_",
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 28,
          "data": {
            "text/plain": "array([4.74323865e-04, 5.71422402e-04, 5.34575062e-04, 1.03150345e-03,\n       1.16027913e-03, 2.04918974e-03, 2.59556623e-03, 1.51737814e-03,\n       4.58363189e-03, 8.60229563e-04, 4.69674856e-04, 2.91630323e-04,\n       8.33703655e-04, 2.27471517e-03, 9.53073315e-04, 1.11382020e-03,\n       9.44454942e-04, 8.18457576e-04, 2.10037877e-04, 3.86481566e-04,\n       5.50323817e-04, 4.27987080e-04, 2.18402667e-04, 2.28767534e-03,\n       6.35263718e-04, 1.31005561e-03, 2.89521651e-04, 2.85139310e-04,\n       1.55885187e-03, 2.24698725e-02, 1.41122012e-01, 1.80827795e-01,\n       6.24342951e-01])"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "y_test.head()",
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 29,
          "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>33d</th>\n      <th>34d</th>\n      <th>35d</th>\n      <th>36d</th>\n      <th>37d</th>\n      <th>38d</th>\n      <th>39d</th>\n      <th>40d</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>2012-10-24 00:00:00+00:00</th>\n      <td>33.610</td>\n      <td>33.81</td>\n      <td>34.400</td>\n      <td>34.59</td>\n      <td>34.61</td>\n      <td>34.430</td>\n      <td>34.000</td>\n      <td>34.28</td>\n    </tr>\n    <tr>\n      <th>2013-03-21 00:00:00+00:00</th>\n      <td>55.786</td>\n      <td>69.40</td>\n      <td>76.764</td>\n      <td>87.80</td>\n      <td>83.24</td>\n      <td>84.842</td>\n      <td>92.247</td>\n      <td>91.50</td>\n    </tr>\n    <tr>\n      <th>2016-12-06 00:00:00+00:00</th>\n      <td>254.470</td>\n      <td>252.51</td>\n      <td>252.950</td>\n      <td>250.63</td>\n      <td>251.93</td>\n      <td>249.240</td>\n      <td>251.550</td>\n      <td>251.33</td>\n    </tr>\n    <tr>\n      <th>2016-08-29 00:00:00+00:00</th>\n      <td>196.510</td>\n      <td>193.96</td>\n      <td>199.100</td>\n      <td>203.56</td>\n      <td>199.10</td>\n      <td>200.090</td>\n      <td>202.760</td>\n      <td>202.34</td>\n    </tr>\n    <tr>\n      <th>2015-12-08 00:00:00+00:00</th>\n      <td>188.070</td>\n      <td>189.70</td>\n      <td>191.200</td>\n      <td>196.94</td>\n      <td>182.78</td>\n      <td>173.480</td>\n      <td>175.330</td>\n      <td>162.60</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            "text/plain": "                               33d     34d      35d     36d     37d      38d  \\\n2012-10-24 00:00:00+00:00   33.610   33.81   34.400   34.59   34.61   34.430   \n2013-03-21 00:00:00+00:00   55.786   69.40   76.764   87.80   83.24   84.842   \n2016-12-06 00:00:00+00:00  254.470  252.51  252.950  250.63  251.93  249.240   \n2016-08-29 00:00:00+00:00  196.510  193.96  199.100  203.56  199.10  200.090   \n2015-12-08 00:00:00+00:00  188.070  189.70  191.200  196.94  182.78  173.480   \n\n                               39d     40d  \n2012-10-24 00:00:00+00:00   34.000   34.28  \n2013-03-21 00:00:00+00:00   92.247   91.50  \n2016-12-06 00:00:00+00:00  251.550  251.33  \n2016-08-29 00:00:00+00:00  202.760  202.34  \n2015-12-08 00:00:00+00:00  175.330  162.60  "
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "y_predicted = regressor.predict(X_test)",
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "stream",
          "text": "[Parallel(n_jobs=16)]: Using backend ThreadingBackend with 16 concurrent workers.\n[Parallel(n_jobs=16)]: Done  18 tasks      | elapsed:    0.0s\n[Parallel(n_jobs=16)]: Done 100 out of 100 | elapsed:    0.0s finished\n",
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "y_predicted",
      "execution_count": 31,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 31,
          "data": {
            "text/plain": "array([[ 35.2424 ,  34.9578 ,  34.6422 , ...,  33.9822 ,  34.2444 ,\n         34.64795],\n       [ 67.36401,  69.58159,  69.87076, ...,  84.63656,  85.33062,\n         87.0124 ],\n       [251.83459, 251.8109 , 251.34679, ..., 252.71581, 253.88626,\n        253.10956],\n       ...,\n       [ 20.7863 ,  20.8886 ,  21.0022 , ...,  20.97425,  20.9889 ,\n         21.0953 ],\n       [318.35699, 320.7976 , 319.1766 , ..., 325.01568, 325.86078,\n        329.51528],\n       [ 23.72605,  23.973  ,  24.5772 , ...,  25.1526 ,  25.3563 ,\n         25.94   ]])"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Plot the predictions against the actual"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "fig, ax = plt.subplots()\n\nfig.subplots_adjust(bottom=0.3)\n\nfig.set_figwidth(16)\nfig.set_figheight(8)\n\nax.plot(y_test.index, y_test['40d'], 'ro')\n#in predictions column with index 7 is the 40d one\nax.plot(y_test.index, y_predicted[:, 7], 'bo')\n\nax.legend()\n\nplt.xticks(rotation=70)\nplt.tight_layout()\nplt.show();",
      "execution_count": 32,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": "<Figure size 1152x576 with 1 Axes>"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Export the model to a file"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from joblib import dump\ndump(regressor, 'rf_regressor.joblib')",
      "execution_count": 34,
      "outputs": [
        {
          "output_type": "error",
          "ename": "ImportError",
          "evalue": "No module named 'joblib'",
          "traceback": [
            "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[1;31mImportError\u001b[0m                               Traceback (most recent call last)",
            "\u001b[1;32m<ipython-input-34-9778a1e7dae4>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mjoblib\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mdump\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[0mdump\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mregressor\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'rf_regressor.joblib'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
            "\u001b[1;31mImportError\u001b[0m: No module named 'joblib'"
          ]
        }
      ]
    },
    {
      "metadata": {
        "trusted": false
      },
      "cell_type": "code",
      "source": "",
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "base_numbering": 1,
      "title_cell": "Table of Contents",
      "title_sidebar": "Contents",
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": true,
      "toc_window_display": false
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3",
      "language": "python"
    },
    "language_info": {
      "file_extension": ".py",
      "nbconvert_exporter": "python",
      "codemirror_mode": {
        "version": 3,
        "name": "ipython"
      },
      "pygments_lexer": "ipython3",
      "mimetype": "text/x-python",
      "version": "3.5.6",
      "name": "python"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Build and implement random forests algo",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}