ML16/src/Sem05_trees.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Семинар 5. Практика. Решающие деревья"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Разделяющие поверхности"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_iris\n",
    "from sklearn.tree import DecisionTreeClassifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "iris = load_iris()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Iris Plants Database\n",
      "\n",
      "Notes\n",
      "-----\n",
      "Data Set Characteristics:\n",
      "    :Number of Instances: 150 (50 in each of three classes)\n",
      "    :Number of Attributes: 4 numeric, predictive attributes and the class\n",
      "    :Attribute Information:\n",
      "        - sepal length in cm\n",
      "        - sepal width in cm\n",
      "        - petal length in cm\n",
      "        - petal width in cm\n",
      "        - class:\n",
      "                - Iris-Setosa\n",
      "                - Iris-Versicolour\n",
      "                - Iris-Virginica\n",
      "    :Summary Statistics:\n",
      "\n",
      "    ============== ==== ==== ======= ===== ====================\n",
      "                    Min  Max   Mean    SD   Class Correlation\n",
      "    ============== ==== ==== ======= ===== ====================\n",
      "    sepal length:   4.3  7.9   5.84   0.83    0.7826\n",
      "    sepal width:    2.0  4.4   3.05   0.43   -0.4194\n",
      "    petal length:   1.0  6.9   3.76   1.76    0.9490  (high!)\n",
      "    petal width:    0.1  2.5   1.20  0.76     0.9565  (high!)\n",
      "    ============== ==== ==== ======= ===== ====================\n",
      "\n",
      "    :Missing Attribute Values: None\n",
      "    :Class Distribution: 33.3% for each of 3 classes.\n",
      "    :Creator: R.A. Fisher\n",
      "    :Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)\n",
      "    :Date: July, 1988\n",
      "\n",
      "This is a copy of UCI ML iris datasets.\n",
      "http://archive.ics.uci.edu/ml/datasets/Iris\n",
      "\n",
      "The famous Iris database, first used by Sir R.A Fisher\n",
      "\n",
      "This is perhaps the best known database to be found in the\n",
      "pattern recognition literature.  Fisher's paper is a classic in the field and\n",
      "is referenced frequently to this day.  (See Duda & Hart, for example.)  The\n",
      "data set contains 3 classes of 50 instances each, where each class refers to a\n",
      "type of iris plant.  One class is linearly separable from the other 2; the\n",
      "latter are NOT linearly separable from each other.\n",
      "\n",
      "References\n",
      "----------\n",
      "   - Fisher,R.A. \"The use of multiple measurements in taxonomic problems\"\n",
      "     Annual Eugenics, 7, Part II, 179-188 (1936); also in \"Contributions to\n",
      "     Mathematical Statistics\" (John Wiley, NY, 1950).\n",
      "   - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.\n",
      "     (Q327.D83) John Wiley & Sons.  ISBN 0-471-22361-1.  See page 218.\n",
      "   - Dasarathy, B.V. (1980) \"Nosing Around the Neighborhood: A New System\n",
      "     Structure and Classification Rule for Recognition in Partially Exposed\n",
      "     Environments\".  IEEE Transactions on Pattern Analysis and Machine\n",
      "     Intelligence, Vol. PAMI-2, No. 1, 67-71.\n",
      "   - Gates, G.W. (1972) \"The Reduced Nearest Neighbor Rule\".  IEEE Transactions\n",
      "     on Information Theory, May 1972, 431-433.\n",
      "   - See also: 1988 MLC Proceedings, 54-64.  Cheeseman et al\"s AUTOCLASS II\n",
      "     conceptual clustering system finds 3 classes in the data.\n",
      "   - Many, many more ...\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print iris.DESCR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "pair = (0, 1)\n",
    "X = iris.data[:, pair]\n",
    "y = iris.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "n_classes = 3\n",
    "plot_colors = \"bry\"\n",
    "plot_step = 0.02\n",
    "\n",
    "\n",
    "def plot_surface(clf):\n",
    "    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1\n",
    "    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1\n",
    "    xx, yy = np.meshgrid(np.arange(x_min, x_max, plot_step),\n",
    "                         np.arange(y_min, y_max, plot_step))\n",
    "\n",
    "    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])\n",
    "    Z = Z.reshape(xx.shape)\n",
    "    cs = plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)\n",
    "\n",
    "    plt.xlabel(iris.feature_names[pair[0]])\n",
    "    plt.ylabel(iris.feature_names[pair[1]])\n",
    "    plt.axis(\"tight\")\n",
    "\n",
    "    for i, color in zip(range(n_classes), plot_colors):\n",
    "        idx = np.where(y == i)\n",
    "        plt.scatter(X[idx, 0], X[idx, 1], c=color, label=iris.target_names[i],\n",
    "                    cmap=plt.cm.Paired)\n",
    "\n",
    "    plt.axis(\"tight\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/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": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEKCAYAAADticXcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkRT5P7J85oY33dr6AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x105939790>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "clf = DecisionTreeClassifier().fit(X, y)\n",
    "plot_surface(clf)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXUAAAEKCAYAAADticXcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxPAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10588e850>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "clf = DecisionTreeClassifier().fit(X[:120, :], y[:120])\n",
    "plot_surface(clf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Регрессия с помощью деревьев"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.datasets import load_boston"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Boston House Prices dataset\n",
      "\n",
      "Notes\n",
      "------\n",
      "Data Set Characteristics:  \n",
      "\n",
      "    :Number of Instances: 506 \n",
      "\n",
      "    :Number of Attributes: 13 numeric/categorical predictive\n",
      "    \n",
      "    :Median Value (attribute 14) is usually the target\n",
      "\n",
      "    :Attribute Information (in order):\n",
      "        - CRIM     per capita crime rate by town\n",
      "        - ZN       proportion of residential land zoned for lots over 25,000 sq.ft.\n",
      "        - INDUS    proportion of non-retail business acres per town\n",
      "        - CHAS     Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n",
      "        - NOX      nitric oxides concentration (parts per 10 million)\n",
      "        - RM       average number of rooms per dwelling\n",
      "        - AGE      proportion of owner-occupied units built prior to 1940\n",
      "        - DIS      weighted distances to five Boston employment centres\n",
      "        - RAD      index of accessibility to radial highways\n",
      "        - TAX      full-value property-tax rate per $10,000\n",
      "        - PTRATIO  pupil-teacher ratio by town\n",
      "        - B        1000(Bk - 0.63)^2 where Bk is the proportion of blacks by town\n",
      "        - LSTAT    % lower status of the population\n",
      "        - MEDV     Median value of owner-occupied homes in $1000's\n",
      "\n",
      "    :Missing Attribute Values: None\n",
      "\n",
      "    :Creator: Harrison, D. and Rubinfeld, D.L.\n",
      "\n",
      "This is a copy of UCI ML housing dataset.\n",
      "http://archive.ics.uci.edu/ml/datasets/Housing\n",
      "\n",
      "\n",
      "This dataset was taken from the StatLib library which is maintained at Carnegie Mellon University.\n",
      "\n",
      "The Boston house-price data of Harrison, D. and Rubinfeld, D.L. 'Hedonic\n",
      "prices and the demand for clean air', J. Environ. Economics & Management,\n",
      "vol.5, 81-102, 1978.   Used in Belsley, Kuh & Welsch, 'Regression diagnostics\n",
      "...', Wiley, 1980.   N.B. Various transformations are used in the table on\n",
      "pages 244-261 of the latter.\n",
      "\n",
      "The Boston house-price data has been used in many machine learning papers that address regression\n",
      "problems.   \n",
      "     \n",
      "**References**\n",
      "\n",
      "   - Belsley, Kuh & Welsch, 'Regression diagnostics: Identifying Influential Data and Sources of Collinearity', Wiley, 1980. 244-261.\n",
      "   - Quinlan,R. (1993). Combining Instance-Based and Model-Based Learning. In Proceedings on the Tenth International Conference of Machine Learning, 236-243, University of Massachusetts, Amherst. Morgan Kaufmann.\n",
      "   - many more! (see http://archive.ics.uci.edu/ml/datasets/Housing)\n",
      "\n"
     ]
    }
   ],
   "source": [
    "data = load_boston()\n",
    "print data.DESCR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_full = data.data\n",
    "y_full = data.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(506, 13)"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_full.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 24. ,  21.6,  34.7,  33.4,  36.2,  28.7,  22.9,  27.1,  16.5,  18.9])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_full[:10]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from sklearn.cross_validation import train_test_split\n",
    "X, X_test, y, y_test = train_test_split(X_full, y_full, test_size=100, \n",
    "                                        random_state=241)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.cross_validation import KFold, cross_val_score\n",
    "cv = KFold(X.shape[0], shuffle=True, random_state=241)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "24.4502234931\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "regr = DecisionTreeRegressor(random_state=241)\n",
    "print -cross_val_score(regr, X, y, cv=cv, \n",
    "                       scoring='mean_squared_error').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<sklearn.tree._tree.Tree at 0x106a55440>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "regr.fit(X, y)\n",
    "regr.tree_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.705238866424\n"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeRegressor\n",
    "regr = DecisionTreeRegressor(random_state=241)\n",
    "print cross_val_score(regr, X, y, cv=cv, \n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[mean: 0.60310, std: 0.07101, params: {'max_features': None, 'max_depth': 2},\n",
       " mean: 0.42140, std: 0.06060, params: {'max_features': 'log2', 'max_depth': 2},\n",
       " mean: 0.42140, std: 0.06060, params: {'max_features': 'sqrt', 'max_depth': 2},\n",
       " mean: 0.73879, std: 0.11251, params: {'max_features': None, 'max_depth': 4},\n",
       " mean: 0.38099, std: 0.12633, params: {'max_features': 'log2', 'max_depth': 4},\n",
       " mean: 0.38099, std: 0.12633, params: {'max_features': 'sqrt', 'max_depth': 4},\n",
       " mean: 0.76242, std: 0.03348, params: {'max_features': None, 'max_depth': 6},\n",
       " mean: 0.51970, std: 0.05065, params: {'max_features': 'log2', 'max_depth': 6},\n",
       " mean: 0.51970, std: 0.05065, params: {'max_features': 'sqrt', 'max_depth': 6},\n",
       " mean: 0.73660, std: 0.00573, params: {'max_features': None, 'max_depth': 8},\n",
       " mean: 0.59787, std: 0.05413, params: {'max_features': 'log2', 'max_depth': 8},\n",
       " mean: 0.59787, std: 0.05413, params: {'max_features': 'sqrt', 'max_depth': 8},\n",
       " mean: 0.72800, std: 0.00374, params: {'max_features': None, 'max_depth': 10},\n",
       " mean: 0.38682, std: 0.21010, params: {'max_features': 'log2', 'max_depth': 10},\n",
       " mean: 0.38682, std: 0.21010, params: {'max_features': 'sqrt', 'max_depth': 10},\n",
       " mean: 0.70527, std: 0.04412, params: {'max_features': None, 'max_depth': 20},\n",
       " mean: 0.58301, std: 0.05719, params: {'max_features': 'log2', 'max_depth': 20},\n",
       " mean: 0.58301, std: 0.05719, params: {'max_features': 'sqrt', 'max_depth': 20},\n",
       " mean: 0.70527, std: 0.04412, params: {'max_features': None, 'max_depth': 50},\n",
       " mean: 0.58301, std: 0.05719, params: {'max_features': 'log2', 'max_depth': 50},\n",
       " mean: 0.58301, std: 0.05719, params: {'max_features': 'sqrt', 'max_depth': 50}]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.grid_search import GridSearchCV\n",
    "gs = GridSearchCV(DecisionTreeRegressor(random_state=241),\n",
    "                  param_grid={'max_features': [None, 'log2', 'sqrt'], \n",
    "                              'max_depth': [2, 4, 6, 8, 10, 20, 50]},\n",
    "                  cv=cv,\n",
    "                  scoring='r2')\n",
    "gs.fit(X, y)\n",
    "gs.grid_scores_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "GridSearchCV(cv=sklearn.cross_validation.KFold(n=406, n_folds=3, shuffle=True, random_state=241),\n",
       "       error_score='raise',\n",
       "       estimator=DecisionTreeRegressor(criterion='mse', max_depth=None, max_features=None,\n",
       "           max_leaf_nodes=None, min_samples_leaf=1, min_samples_split=2,\n",
       "           min_weight_fraction_leaf=0.0, presort=False, random_state=241,\n",
       "           splitter='best'),\n",
       "       fit_params={}, iid=True, n_jobs=1,\n",
       "       param_grid={'max_features': [None, 'log2', 'sqrt'], 'max_depth': [2, 4, 6, 8, 10, 20, 50], 'min_samples_leaf': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]},\n",
       "       pre_dispatch='2*n_jobs', refit=True, scoring='r2', verbose=0)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.grid_search import GridSearchCV\n",
    "gs = GridSearchCV(DecisionTreeRegressor(random_state=241),\n",
    "                  param_grid={'max_features': [None, 'log2', 'sqrt'],\n",
    "                              'max_depth': [2, 4, 6, 8, 10, 20, 50], \n",
    "                              'min_samples_leaf': range(1, 20)},\n",
    "                  cv=cv,\n",
    "                  scoring='r2')\n",
    "gs.fit(X, y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.775856892150106"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gs.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mean: 0.77586, std: 0.03204, params: {'max_features': None, 'max_depth': 6, 'min_samples_leaf': 2}\n"
     ]
    }
   ],
   "source": [
    "for z in gs.grid_scores_:\n",
    "    if z.mean_validation_score == gs.best_score_:\n",
    "        print z"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Решающие леса"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.730458978863\n"
     ]
    }
   ],
   "source": [
    "regr = DecisionTreeRegressor()\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.734972717894\n"
     ]
    }
   ],
   "source": [
    "regr = DecisionTreeRegressor()\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.ensemble import BaggingRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.744495766448\n"
     ]
    }
   ],
   "source": [
    "regr = BaggingRegressor(DecisionTreeRegressor(), n_estimators=10,\n",
    "                        bootstrap=False, random_state=241)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.805541688419\n"
     ]
    }
   ],
   "source": [
    "regr = BaggingRegressor(DecisionTreeRegressor(), n_estimators=10,\n",
    "                        bootstrap=False, random_state=241, max_samples=0.5)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.83885573889\n"
     ]
    }
   ],
   "source": [
    "regr = BaggingRegressor(DecisionTreeRegressor(), n_estimators=100,\n",
    "                        bootstrap=False, random_state=241, max_samples=0.5)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.839208296696\n"
     ]
    }
   ],
   "source": [
    "regr = BaggingRegressor(DecisionTreeRegressor(), n_estimators=1000,\n",
    "                        bootstrap=False, random_state=241, max_samples=0.5)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.839403189711\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "regr = RandomForestRegressor(n_estimators=10)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.846289849392\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "regr = RandomForestRegressor(n_estimators=100)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.848259598419\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "regr = RandomForestRegressor(n_estimators=300)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.847760466833\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "regr = RandomForestRegressor(n_estimators=500)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.847839647812\n"
     ]
    }
   ],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor\n",
    "regr = RandomForestRegressor(n_estimators=1000)\n",
    "print cross_val_score(regr, X, y, cv=cv,\n",
    "                       scoring='r2').mean()"
   ]
  }
 ],
 "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": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}