DecisionTreeClassifier.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "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": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'DESCR': 'Iris Plants Database\\n====================\\n\\nNotes\\n-----\\nData 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\\nThis is a copy of UCI ML iris datasets.\\nhttp://archive.ics.uci.edu/ml/datasets/Iris\\n\\nThe famous Iris database, first used by Sir R.A Fisher\\n\\nThis is perhaps the best known database to be found in the\\npattern recognition literature.  Fisher\\'s paper is a classic in the field and\\nis referenced frequently to this day.  (See Duda & Hart, for example.)  The\\ndata set contains 3 classes of 50 instances each, where each class refers to a\\ntype of iris plant.  One class is linearly separable from the other 2; the\\nlatter are NOT linearly separable from each other.\\n\\nReferences\\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",
       " 'data': array([[ 5.1,  3.5,  1.4,  0.2],\n",
       "        [ 4.9,  3. ,  1.4,  0.2],\n",
       "        [ 4.7,  3.2,  1.3,  0.2],\n",
       "        [ 4.6,  3.1,  1.5,  0.2],\n",
       "        [ 5. ,  3.6,  1.4,  0.2],\n",
       "        [ 5.4,  3.9,  1.7,  0.4],\n",
       "        [ 4.6,  3.4,  1.4,  0.3],\n",
       "        [ 5. ,  3.4,  1.5,  0.2],\n",
       "        [ 4.4,  2.9,  1.4,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 5.4,  3.7,  1.5,  0.2],\n",
       "        [ 4.8,  3.4,  1.6,  0.2],\n",
       "        [ 4.8,  3. ,  1.4,  0.1],\n",
       "        [ 4.3,  3. ,  1.1,  0.1],\n",
       "        [ 5.8,  4. ,  1.2,  0.2],\n",
       "        [ 5.7,  4.4,  1.5,  0.4],\n",
       "        [ 5.4,  3.9,  1.3,  0.4],\n",
       "        [ 5.1,  3.5,  1.4,  0.3],\n",
       "        [ 5.7,  3.8,  1.7,  0.3],\n",
       "        [ 5.1,  3.8,  1.5,  0.3],\n",
       "        [ 5.4,  3.4,  1.7,  0.2],\n",
       "        [ 5.1,  3.7,  1.5,  0.4],\n",
       "        [ 4.6,  3.6,  1. ,  0.2],\n",
       "        [ 5.1,  3.3,  1.7,  0.5],\n",
       "        [ 4.8,  3.4,  1.9,  0.2],\n",
       "        [ 5. ,  3. ,  1.6,  0.2],\n",
       "        [ 5. ,  3.4,  1.6,  0.4],\n",
       "        [ 5.2,  3.5,  1.5,  0.2],\n",
       "        [ 5.2,  3.4,  1.4,  0.2],\n",
       "        [ 4.7,  3.2,  1.6,  0.2],\n",
       "        [ 4.8,  3.1,  1.6,  0.2],\n",
       "        [ 5.4,  3.4,  1.5,  0.4],\n",
       "        [ 5.2,  4.1,  1.5,  0.1],\n",
       "        [ 5.5,  4.2,  1.4,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 5. ,  3.2,  1.2,  0.2],\n",
       "        [ 5.5,  3.5,  1.3,  0.2],\n",
       "        [ 4.9,  3.1,  1.5,  0.1],\n",
       "        [ 4.4,  3. ,  1.3,  0.2],\n",
       "        [ 5.1,  3.4,  1.5,  0.2],\n",
       "        [ 5. ,  3.5,  1.3,  0.3],\n",
       "        [ 4.5,  2.3,  1.3,  0.3],\n",
       "        [ 4.4,  3.2,  1.3,  0.2],\n",
       "        [ 5. ,  3.5,  1.6,  0.6],\n",
       "        [ 5.1,  3.8,  1.9,  0.4],\n",
       "        [ 4.8,  3. ,  1.4,  0.3],\n",
       "        [ 5.1,  3.8,  1.6,  0.2],\n",
       "        [ 4.6,  3.2,  1.4,  0.2],\n",
       "        [ 5.3,  3.7,  1.5,  0.2],\n",
       "        [ 5. ,  3.3,  1.4,  0.2],\n",
       "        [ 7. ,  3.2,  4.7,  1.4],\n",
       "        [ 6.4,  3.2,  4.5,  1.5],\n",
       "        [ 6.9,  3.1,  4.9,  1.5],\n",
       "        [ 5.5,  2.3,  4. ,  1.3],\n",
       "        [ 6.5,  2.8,  4.6,  1.5],\n",
       "        [ 5.7,  2.8,  4.5,  1.3],\n",
       "        [ 6.3,  3.3,  4.7,  1.6],\n",
       "        [ 4.9,  2.4,  3.3,  1. ],\n",
       "        [ 6.6,  2.9,  4.6,  1.3],\n",
       "        [ 5.2,  2.7,  3.9,  1.4],\n",
       "        [ 5. ,  2. ,  3.5,  1. ],\n",
       "        [ 5.9,  3. ,  4.2,  1.5],\n",
       "        [ 6. ,  2.2,  4. ,  1. ],\n",
       "        [ 6.1,  2.9,  4.7,  1.4],\n",
       "        [ 5.6,  2.9,  3.6,  1.3],\n",
       "        [ 6.7,  3.1,  4.4,  1.4],\n",
       "        [ 5.6,  3. ,  4.5,  1.5],\n",
       "        [ 5.8,  2.7,  4.1,  1. ],\n",
       "        [ 6.2,  2.2,  4.5,  1.5],\n",
       "        [ 5.6,  2.5,  3.9,  1.1],\n",
       "        [ 5.9,  3.2,  4.8,  1.8],\n",
       "        [ 6.1,  2.8,  4. ,  1.3],\n",
       "        [ 6.3,  2.5,  4.9,  1.5],\n",
       "        [ 6.1,  2.8,  4.7,  1.2],\n",
       "        [ 6.4,  2.9,  4.3,  1.3],\n",
       "        [ 6.6,  3. ,  4.4,  1.4],\n",
       "        [ 6.8,  2.8,  4.8,  1.4],\n",
       "        [ 6.7,  3. ,  5. ,  1.7],\n",
       "        [ 6. ,  2.9,  4.5,  1.5],\n",
       "        [ 5.7,  2.6,  3.5,  1. ],\n",
       "        [ 5.5,  2.4,  3.8,  1.1],\n",
       "        [ 5.5,  2.4,  3.7,  1. ],\n",
       "        [ 5.8,  2.7,  3.9,  1.2],\n",
       "        [ 6. ,  2.7,  5.1,  1.6],\n",
       "        [ 5.4,  3. ,  4.5,  1.5],\n",
       "        [ 6. ,  3.4,  4.5,  1.6],\n",
       "        [ 6.7,  3.1,  4.7,  1.5],\n",
       "        [ 6.3,  2.3,  4.4,  1.3],\n",
       "        [ 5.6,  3. ,  4.1,  1.3],\n",
       "        [ 5.5,  2.5,  4. ,  1.3],\n",
       "        [ 5.5,  2.6,  4.4,  1.2],\n",
       "        [ 6.1,  3. ,  4.6,  1.4],\n",
       "        [ 5.8,  2.6,  4. ,  1.2],\n",
       "        [ 5. ,  2.3,  3.3,  1. ],\n",
       "        [ 5.6,  2.7,  4.2,  1.3],\n",
       "        [ 5.7,  3. ,  4.2,  1.2],\n",
       "        [ 5.7,  2.9,  4.2,  1.3],\n",
       "        [ 6.2,  2.9,  4.3,  1.3],\n",
       "        [ 5.1,  2.5,  3. ,  1.1],\n",
       "        [ 5.7,  2.8,  4.1,  1.3],\n",
       "        [ 6.3,  3.3,  6. ,  2.5],\n",
       "        [ 5.8,  2.7,  5.1,  1.9],\n",
       "        [ 7.1,  3. ,  5.9,  2.1],\n",
       "        [ 6.3,  2.9,  5.6,  1.8],\n",
       "        [ 6.5,  3. ,  5.8,  2.2],\n",
       "        [ 7.6,  3. ,  6.6,  2.1],\n",
       "        [ 4.9,  2.5,  4.5,  1.7],\n",
       "        [ 7.3,  2.9,  6.3,  1.8],\n",
       "        [ 6.7,  2.5,  5.8,  1.8],\n",
       "        [ 7.2,  3.6,  6.1,  2.5],\n",
       "        [ 6.5,  3.2,  5.1,  2. ],\n",
       "        [ 6.4,  2.7,  5.3,  1.9],\n",
       "        [ 6.8,  3. ,  5.5,  2.1],\n",
       "        [ 5.7,  2.5,  5. ,  2. ],\n",
       "        [ 5.8,  2.8,  5.1,  2.4],\n",
       "        [ 6.4,  3.2,  5.3,  2.3],\n",
       "        [ 6.5,  3. ,  5.5,  1.8],\n",
       "        [ 7.7,  3.8,  6.7,  2.2],\n",
       "        [ 7.7,  2.6,  6.9,  2.3],\n",
       "        [ 6. ,  2.2,  5. ,  1.5],\n",
       "        [ 6.9,  3.2,  5.7,  2.3],\n",
       "        [ 5.6,  2.8,  4.9,  2. ],\n",
       "        [ 7.7,  2.8,  6.7,  2. ],\n",
       "        [ 6.3,  2.7,  4.9,  1.8],\n",
       "        [ 6.7,  3.3,  5.7,  2.1],\n",
       "        [ 7.2,  3.2,  6. ,  1.8],\n",
       "        [ 6.2,  2.8,  4.8,  1.8],\n",
       "        [ 6.1,  3. ,  4.9,  1.8],\n",
       "        [ 6.4,  2.8,  5.6,  2.1],\n",
       "        [ 7.2,  3. ,  5.8,  1.6],\n",
       "        [ 7.4,  2.8,  6.1,  1.9],\n",
       "        [ 7.9,  3.8,  6.4,  2. ],\n",
       "        [ 6.4,  2.8,  5.6,  2.2],\n",
       "        [ 6.3,  2.8,  5.1,  1.5],\n",
       "        [ 6.1,  2.6,  5.6,  1.4],\n",
       "        [ 7.7,  3. ,  6.1,  2.3],\n",
       "        [ 6.3,  3.4,  5.6,  2.4],\n",
       "        [ 6.4,  3.1,  5.5,  1.8],\n",
       "        [ 6. ,  3. ,  4.8,  1.8],\n",
       "        [ 6.9,  3.1,  5.4,  2.1],\n",
       "        [ 6.7,  3.1,  5.6,  2.4],\n",
       "        [ 6.9,  3.1,  5.1,  2.3],\n",
       "        [ 5.8,  2.7,  5.1,  1.9],\n",
       "        [ 6.8,  3.2,  5.9,  2.3],\n",
       "        [ 6.7,  3.3,  5.7,  2.5],\n",
       "        [ 6.7,  3. ,  5.2,  2.3],\n",
       "        [ 6.3,  2.5,  5. ,  1.9],\n",
       "        [ 6.5,  3. ,  5.2,  2. ],\n",
       "        [ 6.2,  3.4,  5.4,  2.3],\n",
       "        [ 5.9,  3. ,  5.1,  1.8]]),\n",
       " 'feature_names': ['sepal length (cm)',\n",
       "  'sepal width (cm)',\n",
       "  'petal length (cm)',\n",
       "  'petal width (cm)'],\n",
       " 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "        0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
       "        1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
       "        2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]),\n",
       " 'target_names': array(['setosa', 'versicolor', 'virginica'],\n",
       "       dtype='<U10')}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "iris"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X = iris.data\n",
    "y = iris.target"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(150, 4)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(150,)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Split train and test datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(112, 4)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(38, 4)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_test.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1, 0, 2, 0, 2, 0, 1, 1, 1, 2, 1, 1, 1, 1, 0, 1, 1, 0, 0, 2, 1, 0,\n",
       "       0, 2, 0, 0, 1, 1, 0, 2, 1, 0, 2, 2, 1, 0, 1])"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train and test a model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "estimator = DecisionTreeClassifier(max_depth=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=2,\n",
       "            max_features=None, 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, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=2,\n",
       "            max_features=None, 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, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estimator.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y_predict = estimator.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1, 0, 2, 0, 2, 0, 1, 1, 1, 2, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0,\n",
       "       0, 1, 0, 0, 1, 1, 0, 2, 1, 0, 1, 2, 1, 0, 2])"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1, 0, 2, 0, 2, 0, 1, 1, 1, 2, 1, 1, 1, 1, 0, 1, 1, 0, 0, 2, 1, 0,\n",
       "       0, 2, 0, 0, 1, 1, 0, 2, 1, 0, 2, 2, 1, 0, 1])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "34"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "correct_labels = sum(y_predict == y_test)\n",
    "correct_labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "38"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.894737\n"
     ]
    }
   ],
   "source": [
    "print(\"Accuracy: %f\" % (correct_labels/len(y_predict)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5.1,  3.5,  1.4,  0.2],\n",
       "       [ 4.9,  3. ,  1.4,  0.2],\n",
       "       [ 4.7,  3.2,  1.3,  0.2],\n",
       "       [ 4.6,  3.1,  1.5,  0.2],\n",
       "       [ 5. ,  3.6,  1.4,  0.2],\n",
       "       [ 5.4,  3.9,  1.7,  0.4],\n",
       "       [ 4.6,  3.4,  1.4,  0.3],\n",
       "       [ 5. ,  3.4,  1.5,  0.2],\n",
       "       [ 4.4,  2.9,  1.4,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 5.4,  3.7,  1.5,  0.2],\n",
       "       [ 4.8,  3.4,  1.6,  0.2],\n",
       "       [ 4.8,  3. ,  1.4,  0.1],\n",
       "       [ 4.3,  3. ,  1.1,  0.1],\n",
       "       [ 5.8,  4. ,  1.2,  0.2],\n",
       "       [ 5.7,  4.4,  1.5,  0.4],\n",
       "       [ 5.4,  3.9,  1.3,  0.4],\n",
       "       [ 5.1,  3.5,  1.4,  0.3],\n",
       "       [ 5.7,  3.8,  1.7,  0.3],\n",
       "       [ 5.1,  3.8,  1.5,  0.3],\n",
       "       [ 5.4,  3.4,  1.7,  0.2],\n",
       "       [ 5.1,  3.7,  1.5,  0.4],\n",
       "       [ 4.6,  3.6,  1. ,  0.2],\n",
       "       [ 5.1,  3.3,  1.7,  0.5],\n",
       "       [ 4.8,  3.4,  1.9,  0.2],\n",
       "       [ 5. ,  3. ,  1.6,  0.2],\n",
       "       [ 5. ,  3.4,  1.6,  0.4],\n",
       "       [ 5.2,  3.5,  1.5,  0.2],\n",
       "       [ 5.2,  3.4,  1.4,  0.2],\n",
       "       [ 4.7,  3.2,  1.6,  0.2],\n",
       "       [ 4.8,  3.1,  1.6,  0.2],\n",
       "       [ 5.4,  3.4,  1.5,  0.4],\n",
       "       [ 5.2,  4.1,  1.5,  0.1],\n",
       "       [ 5.5,  4.2,  1.4,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 5. ,  3.2,  1.2,  0.2],\n",
       "       [ 5.5,  3.5,  1.3,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 4.4,  3. ,  1.3,  0.2],\n",
       "       [ 5.1,  3.4,  1.5,  0.2],\n",
       "       [ 5. ,  3.5,  1.3,  0.3],\n",
       "       [ 4.5,  2.3,  1.3,  0.3],\n",
       "       [ 4.4,  3.2,  1.3,  0.2],\n",
       "       [ 5. ,  3.5,  1.6,  0.6],\n",
       "       [ 5.1,  3.8,  1.9,  0.4],\n",
       "       [ 4.8,  3. ,  1.4,  0.3],\n",
       "       [ 5.1,  3.8,  1.6,  0.2],\n",
       "       [ 4.6,  3.2,  1.4,  0.2],\n",
       "       [ 5.3,  3.7,  1.5,  0.2],\n",
       "       [ 5. ,  3.3,  1.4,  0.2],\n",
       "       [ 7. ,  3.2,  4.7,  1.4],\n",
       "       [ 6.4,  3.2,  4.5,  1.5],\n",
       "       [ 6.9,  3.1,  4.9,  1.5],\n",
       "       [ 5.5,  2.3,  4. ,  1.3],\n",
       "       [ 6.5,  2.8,  4.6,  1.5],\n",
       "       [ 5.7,  2.8,  4.5,  1.3],\n",
       "       [ 6.3,  3.3,  4.7,  1.6],\n",
       "       [ 4.9,  2.4,  3.3,  1. ],\n",
       "       [ 6.6,  2.9,  4.6,  1.3],\n",
       "       [ 5.2,  2.7,  3.9,  1.4],\n",
       "       [ 5. ,  2. ,  3.5,  1. ],\n",
       "       [ 5.9,  3. ,  4.2,  1.5],\n",
       "       [ 6. ,  2.2,  4. ,  1. ],\n",
       "       [ 6.1,  2.9,  4.7,  1.4],\n",
       "       [ 5.6,  2.9,  3.6,  1.3],\n",
       "       [ 6.7,  3.1,  4.4,  1.4],\n",
       "       [ 5.6,  3. ,  4.5,  1.5],\n",
       "       [ 5.8,  2.7,  4.1,  1. ],\n",
       "       [ 6.2,  2.2,  4.5,  1.5],\n",
       "       [ 5.6,  2.5,  3.9,  1.1],\n",
       "       [ 5.9,  3.2,  4.8,  1.8],\n",
       "       [ 6.1,  2.8,  4. ,  1.3],\n",
       "       [ 6.3,  2.5,  4.9,  1.5],\n",
       "       [ 6.1,  2.8,  4.7,  1.2],\n",
       "       [ 6.4,  2.9,  4.3,  1.3],\n",
       "       [ 6.6,  3. ,  4.4,  1.4],\n",
       "       [ 6.8,  2.8,  4.8,  1.4],\n",
       "       [ 6.7,  3. ,  5. ,  1.7],\n",
       "       [ 6. ,  2.9,  4.5,  1.5],\n",
       "       [ 5.7,  2.6,  3.5,  1. ],\n",
       "       [ 5.5,  2.4,  3.8,  1.1],\n",
       "       [ 5.5,  2.4,  3.7,  1. ],\n",
       "       [ 5.8,  2.7,  3.9,  1.2],\n",
       "       [ 6. ,  2.7,  5.1,  1.6],\n",
       "       [ 5.4,  3. ,  4.5,  1.5],\n",
       "       [ 6. ,  3.4,  4.5,  1.6],\n",
       "       [ 6.7,  3.1,  4.7,  1.5],\n",
       "       [ 6.3,  2.3,  4.4,  1.3],\n",
       "       [ 5.6,  3. ,  4.1,  1.3],\n",
       "       [ 5.5,  2.5,  4. ,  1.3],\n",
       "       [ 5.5,  2.6,  4.4,  1.2],\n",
       "       [ 6.1,  3. ,  4.6,  1.4],\n",
       "       [ 5.8,  2.6,  4. ,  1.2],\n",
       "       [ 5. ,  2.3,  3.3,  1. ],\n",
       "       [ 5.6,  2.7,  4.2,  1.3],\n",
       "       [ 5.7,  3. ,  4.2,  1.2],\n",
       "       [ 5.7,  2.9,  4.2,  1.3],\n",
       "       [ 6.2,  2.9,  4.3,  1.3],\n",
       "       [ 5.1,  2.5,  3. ,  1.1],\n",
       "       [ 5.7,  2.8,  4.1,  1.3],\n",
       "       [ 6.3,  3.3,  6. ,  2.5],\n",
       "       [ 5.8,  2.7,  5.1,  1.9],\n",
       "       [ 7.1,  3. ,  5.9,  2.1],\n",
       "       [ 6.3,  2.9,  5.6,  1.8],\n",
       "       [ 6.5,  3. ,  5.8,  2.2],\n",
       "       [ 7.6,  3. ,  6.6,  2.1],\n",
       "       [ 4.9,  2.5,  4.5,  1.7],\n",
       "       [ 7.3,  2.9,  6.3,  1.8],\n",
       "       [ 6.7,  2.5,  5.8,  1.8],\n",
       "       [ 7.2,  3.6,  6.1,  2.5],\n",
       "       [ 6.5,  3.2,  5.1,  2. ],\n",
       "       [ 6.4,  2.7,  5.3,  1.9],\n",
       "       [ 6.8,  3. ,  5.5,  2.1],\n",
       "       [ 5.7,  2.5,  5. ,  2. ],\n",
       "       [ 5.8,  2.8,  5.1,  2.4],\n",
       "       [ 6.4,  3.2,  5.3,  2.3],\n",
       "       [ 6.5,  3. ,  5.5,  1.8],\n",
       "       [ 7.7,  3.8,  6.7,  2.2],\n",
       "       [ 7.7,  2.6,  6.9,  2.3],\n",
       "       [ 6. ,  2.2,  5. ,  1.5],\n",
       "       [ 6.9,  3.2,  5.7,  2.3],\n",
       "       [ 5.6,  2.8,  4.9,  2. ],\n",
       "       [ 7.7,  2.8,  6.7,  2. ],\n",
       "       [ 6.3,  2.7,  4.9,  1.8],\n",
       "       [ 6.7,  3.3,  5.7,  2.1],\n",
       "       [ 7.2,  3.2,  6. ,  1.8],\n",
       "       [ 6.2,  2.8,  4.8,  1.8],\n",
       "       [ 6.1,  3. ,  4.9,  1.8],\n",
       "       [ 6.4,  2.8,  5.6,  2.1],\n",
       "       [ 7.2,  3. ,  5.8,  1.6],\n",
       "       [ 7.4,  2.8,  6.1,  1.9],\n",
       "       [ 7.9,  3.8,  6.4,  2. ],\n",
       "       [ 6.4,  2.8,  5.6,  2.2],\n",
       "       [ 6.3,  2.8,  5.1,  1.5],\n",
       "       [ 6.1,  2.6,  5.6,  1.4],\n",
       "       [ 7.7,  3. ,  6.1,  2.3],\n",
       "       [ 6.3,  3.4,  5.6,  2.4],\n",
       "       [ 6.4,  3.1,  5.5,  1.8],\n",
       "       [ 6. ,  3. ,  4.8,  1.8],\n",
       "       [ 6.9,  3.1,  5.4,  2.1],\n",
       "       [ 6.7,  3.1,  5.6,  2.4],\n",
       "       [ 6.9,  3.1,  5.1,  2.3],\n",
       "       [ 5.8,  2.7,  5.1,  1.9],\n",
       "       [ 6.8,  3.2,  5.9,  2.3],\n",
       "       [ 6.7,  3.3,  5.7,  2.5],\n",
       "       [ 6.7,  3. ,  5.2,  2.3],\n",
       "       [ 6.3,  2.5,  5. ,  1.9],\n",
       "       [ 6.5,  3. ,  5.2,  2. ],\n",
       "       [ 6.2,  3.4,  5.4,  2.3],\n",
       "       [ 5.9,  3. ,  5.1,  1.8]])"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import export_graphviz\n",
    "export_graphviz(estimator, out_file=\"tree.dot\", class_names=iris.target_names,\n",
    "                feature_names=iris.feature_names, impurity=False, filled=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\r\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\r\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\r\n",
       "<!-- Generated by graphviz version 2.38.0 (20140413.2041)\r\n",
       " -->\r\n",
       "<!-- Title: Tree Pages: 1 -->\r\n",
       "<svg width=\"339pt\" height=\"269pt\"\r\n",
       " viewBox=\"0.00 0.00 339.00 269.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\r\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 265)\">\r\n",
       "<title>Tree</title>\r\n",
       "<polygon fill=\"white\" stroke=\"none\" points=\"-4,4 -4,-265 335,-265 335,4 -4,4\"/>\r\n",
       "<!-- 0 -->\r\n",
       "<g id=\"node1\" class=\"node\"><title>0</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.054902\" stroke=\"black\" points=\"211,-261 53,-261 53,-193 211,-193 211,-261\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"132\" y=\"-245.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal length (cm) &lt;= 2.35</text>\r\n",
       "<text text-anchor=\"middle\" x=\"132\" y=\"-230.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 112</text>\r\n",
       "<text text-anchor=\"middle\" x=\"132\" y=\"-215.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [37, 34, 41]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"132\" y=\"-200.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 1 -->\r\n",
       "<g id=\"node2\" class=\"node\"><title>1</title>\r\n",
       "<polygon fill=\"#e58139\" stroke=\"black\" points=\"112,-149.5 7.10543e-015,-149.5 7.10543e-015,-96.5 112,-96.5 112,-149.5\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"56\" y=\"-134.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 37</text>\r\n",
       "<text text-anchor=\"middle\" x=\"56\" y=\"-119.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [37, 0, 0]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"56\" y=\"-104.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = setosa</text>\r\n",
       "</g>\r\n",
       "<!-- 0&#45;&gt;1 -->\r\n",
       "<g id=\"edge1\" class=\"edge\"><title>0&#45;&gt;1</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M107.325,-192.884C98.9666,-181.666 89.6234,-169.126 81.223,-157.852\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"83.7963,-155.448 75.0149,-149.52 78.1831,-159.63 83.7963,-155.448\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"71.4015\" y=\"-170.557\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">True</text>\r\n",
       "</g>\r\n",
       "<!-- 2 -->\r\n",
       "<g id=\"node3\" class=\"node\"><title>2</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.172549\" stroke=\"black\" points=\"288,-157 130,-157 130,-89 288,-89 288,-157\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-141.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal length (cm) &lt;= 4.95</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-126.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 75</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-111.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 34, 41]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-96.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 0&#45;&gt;2 -->\r\n",
       "<g id=\"edge2\" class=\"edge\"><title>0&#45;&gt;2</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M157,-192.884C163.589,-184.154 170.783,-174.625 177.661,-165.514\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"180.631,-167.389 183.862,-157.299 175.044,-163.172 180.631,-167.389\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"187.32\" y=\"-178.359\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">False</text>\r\n",
       "</g>\r\n",
       "<!-- 3 -->\r\n",
       "<g id=\"node4\" class=\"node\"><title>3</title>\r\n",
       "<polygon fill=\"#39e581\" fill-opacity=\"0.909804\" stroke=\"black\" points=\"201,-53 85,-53 85,-0 201,-0 201,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 36</text>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 33, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = versicolor</text>\r\n",
       "</g>\r\n",
       "<!-- 2&#45;&gt;3 -->\r\n",
       "<g id=\"edge3\" class=\"edge\"><title>2&#45;&gt;3</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M185.916,-88.9485C179.719,-80.0749 173.007,-70.4648 166.773,-61.5388\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"169.57,-59.4311 160.975,-53.2367 163.831,-63.4392 169.57,-59.4311\"/>\r\n",
       "</g>\r\n",
       "<!-- 4 -->\r\n",
       "<g id=\"node5\" class=\"node\"><title>4</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.972549\" stroke=\"black\" points=\"331,-53 219,-53 219,-0 331,-0 331,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"275\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 39</text>\r\n",
       "<text text-anchor=\"middle\" x=\"275\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 38]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"275\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 2&#45;&gt;4 -->\r\n",
       "<g id=\"edge4\" class=\"edge\"><title>2&#45;&gt;4</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M232.084,-88.9485C238.281,-80.0749 244.993,-70.4648 251.227,-61.5388\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"254.169,-63.4392 257.025,-53.2367 248.43,-59.4311 254.169,-63.4392\"/>\r\n",
       "</g>\r\n",
       "</g>\r\n",
       "</svg>\r\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x21809189780>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import graphviz\n",
    "\n",
    "with open(\"tree.dot\") as f:\n",
    "    dot_graph = f.read()\n",
    "display(graphviz.Source(dot_graph))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "# Improve the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "estimator = DecisionTreeClassifier(max_depth=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=5,\n",
       "            max_features=None, 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, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estimator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=5,\n",
       "            max_features=None, 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, presort=False, random_state=None,\n",
       "            splitter='best')"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "estimator.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "y_predict = estimator.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1, 0, 2, 0, 2, 0, 1, 1, 1, 2, 1, 1, 1, 1, 0, 1, 1, 0, 0, 2, 1, 0,\n",
       "       0, 2, 0, 0, 1, 1, 0, 2, 1, 0, 2, 2, 1, 0, 2])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([2, 1, 0, 2, 0, 2, 0, 1, 1, 1, 2, 1, 1, 1, 1, 0, 1, 1, 0, 0, 2, 1, 0,\n",
       "       0, 2, 0, 0, 1, 1, 0, 2, 1, 0, 2, 2, 1, 0, 1])"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "37"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "correct_labels = sum(y_predict == y_test)\n",
    "correct_labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "38"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(y_predict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.973684\n"
     ]
    }
   ],
   "source": [
    "print(\"Accuracy: %f\" % (correct_labels/len(y_predict)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5.1,  3.5,  1.4,  0.2],\n",
       "       [ 4.9,  3. ,  1.4,  0.2],\n",
       "       [ 4.7,  3.2,  1.3,  0.2],\n",
       "       [ 4.6,  3.1,  1.5,  0.2],\n",
       "       [ 5. ,  3.6,  1.4,  0.2],\n",
       "       [ 5.4,  3.9,  1.7,  0.4],\n",
       "       [ 4.6,  3.4,  1.4,  0.3],\n",
       "       [ 5. ,  3.4,  1.5,  0.2],\n",
       "       [ 4.4,  2.9,  1.4,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 5.4,  3.7,  1.5,  0.2],\n",
       "       [ 4.8,  3.4,  1.6,  0.2],\n",
       "       [ 4.8,  3. ,  1.4,  0.1],\n",
       "       [ 4.3,  3. ,  1.1,  0.1],\n",
       "       [ 5.8,  4. ,  1.2,  0.2],\n",
       "       [ 5.7,  4.4,  1.5,  0.4],\n",
       "       [ 5.4,  3.9,  1.3,  0.4],\n",
       "       [ 5.1,  3.5,  1.4,  0.3],\n",
       "       [ 5.7,  3.8,  1.7,  0.3],\n",
       "       [ 5.1,  3.8,  1.5,  0.3],\n",
       "       [ 5.4,  3.4,  1.7,  0.2],\n",
       "       [ 5.1,  3.7,  1.5,  0.4],\n",
       "       [ 4.6,  3.6,  1. ,  0.2],\n",
       "       [ 5.1,  3.3,  1.7,  0.5],\n",
       "       [ 4.8,  3.4,  1.9,  0.2],\n",
       "       [ 5. ,  3. ,  1.6,  0.2],\n",
       "       [ 5. ,  3.4,  1.6,  0.4],\n",
       "       [ 5.2,  3.5,  1.5,  0.2],\n",
       "       [ 5.2,  3.4,  1.4,  0.2],\n",
       "       [ 4.7,  3.2,  1.6,  0.2],\n",
       "       [ 4.8,  3.1,  1.6,  0.2],\n",
       "       [ 5.4,  3.4,  1.5,  0.4],\n",
       "       [ 5.2,  4.1,  1.5,  0.1],\n",
       "       [ 5.5,  4.2,  1.4,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 5. ,  3.2,  1.2,  0.2],\n",
       "       [ 5.5,  3.5,  1.3,  0.2],\n",
       "       [ 4.9,  3.1,  1.5,  0.1],\n",
       "       [ 4.4,  3. ,  1.3,  0.2],\n",
       "       [ 5.1,  3.4,  1.5,  0.2],\n",
       "       [ 5. ,  3.5,  1.3,  0.3],\n",
       "       [ 4.5,  2.3,  1.3,  0.3],\n",
       "       [ 4.4,  3.2,  1.3,  0.2],\n",
       "       [ 5. ,  3.5,  1.6,  0.6],\n",
       "       [ 5.1,  3.8,  1.9,  0.4],\n",
       "       [ 4.8,  3. ,  1.4,  0.3],\n",
       "       [ 5.1,  3.8,  1.6,  0.2],\n",
       "       [ 4.6,  3.2,  1.4,  0.2],\n",
       "       [ 5.3,  3.7,  1.5,  0.2],\n",
       "       [ 5. ,  3.3,  1.4,  0.2],\n",
       "       [ 7. ,  3.2,  4.7,  1.4],\n",
       "       [ 6.4,  3.2,  4.5,  1.5],\n",
       "       [ 6.9,  3.1,  4.9,  1.5],\n",
       "       [ 5.5,  2.3,  4. ,  1.3],\n",
       "       [ 6.5,  2.8,  4.6,  1.5],\n",
       "       [ 5.7,  2.8,  4.5,  1.3],\n",
       "       [ 6.3,  3.3,  4.7,  1.6],\n",
       "       [ 4.9,  2.4,  3.3,  1. ],\n",
       "       [ 6.6,  2.9,  4.6,  1.3],\n",
       "       [ 5.2,  2.7,  3.9,  1.4],\n",
       "       [ 5. ,  2. ,  3.5,  1. ],\n",
       "       [ 5.9,  3. ,  4.2,  1.5],\n",
       "       [ 6. ,  2.2,  4. ,  1. ],\n",
       "       [ 6.1,  2.9,  4.7,  1.4],\n",
       "       [ 5.6,  2.9,  3.6,  1.3],\n",
       "       [ 6.7,  3.1,  4.4,  1.4],\n",
       "       [ 5.6,  3. ,  4.5,  1.5],\n",
       "       [ 5.8,  2.7,  4.1,  1. ],\n",
       "       [ 6.2,  2.2,  4.5,  1.5],\n",
       "       [ 5.6,  2.5,  3.9,  1.1],\n",
       "       [ 5.9,  3.2,  4.8,  1.8],\n",
       "       [ 6.1,  2.8,  4. ,  1.3],\n",
       "       [ 6.3,  2.5,  4.9,  1.5],\n",
       "       [ 6.1,  2.8,  4.7,  1.2],\n",
       "       [ 6.4,  2.9,  4.3,  1.3],\n",
       "       [ 6.6,  3. ,  4.4,  1.4],\n",
       "       [ 6.8,  2.8,  4.8,  1.4],\n",
       "       [ 6.7,  3. ,  5. ,  1.7],\n",
       "       [ 6. ,  2.9,  4.5,  1.5],\n",
       "       [ 5.7,  2.6,  3.5,  1. ],\n",
       "       [ 5.5,  2.4,  3.8,  1.1],\n",
       "       [ 5.5,  2.4,  3.7,  1. ],\n",
       "       [ 5.8,  2.7,  3.9,  1.2],\n",
       "       [ 6. ,  2.7,  5.1,  1.6],\n",
       "       [ 5.4,  3. ,  4.5,  1.5],\n",
       "       [ 6. ,  3.4,  4.5,  1.6],\n",
       "       [ 6.7,  3.1,  4.7,  1.5],\n",
       "       [ 6.3,  2.3,  4.4,  1.3],\n",
       "       [ 5.6,  3. ,  4.1,  1.3],\n",
       "       [ 5.5,  2.5,  4. ,  1.3],\n",
       "       [ 5.5,  2.6,  4.4,  1.2],\n",
       "       [ 6.1,  3. ,  4.6,  1.4],\n",
       "       [ 5.8,  2.6,  4. ,  1.2],\n",
       "       [ 5. ,  2.3,  3.3,  1. ],\n",
       "       [ 5.6,  2.7,  4.2,  1.3],\n",
       "       [ 5.7,  3. ,  4.2,  1.2],\n",
       "       [ 5.7,  2.9,  4.2,  1.3],\n",
       "       [ 6.2,  2.9,  4.3,  1.3],\n",
       "       [ 5.1,  2.5,  3. ,  1.1],\n",
       "       [ 5.7,  2.8,  4.1,  1.3],\n",
       "       [ 6.3,  3.3,  6. ,  2.5],\n",
       "       [ 5.8,  2.7,  5.1,  1.9],\n",
       "       [ 7.1,  3. ,  5.9,  2.1],\n",
       "       [ 6.3,  2.9,  5.6,  1.8],\n",
       "       [ 6.5,  3. ,  5.8,  2.2],\n",
       "       [ 7.6,  3. ,  6.6,  2.1],\n",
       "       [ 4.9,  2.5,  4.5,  1.7],\n",
       "       [ 7.3,  2.9,  6.3,  1.8],\n",
       "       [ 6.7,  2.5,  5.8,  1.8],\n",
       "       [ 7.2,  3.6,  6.1,  2.5],\n",
       "       [ 6.5,  3.2,  5.1,  2. ],\n",
       "       [ 6.4,  2.7,  5.3,  1.9],\n",
       "       [ 6.8,  3. ,  5.5,  2.1],\n",
       "       [ 5.7,  2.5,  5. ,  2. ],\n",
       "       [ 5.8,  2.8,  5.1,  2.4],\n",
       "       [ 6.4,  3.2,  5.3,  2.3],\n",
       "       [ 6.5,  3. ,  5.5,  1.8],\n",
       "       [ 7.7,  3.8,  6.7,  2.2],\n",
       "       [ 7.7,  2.6,  6.9,  2.3],\n",
       "       [ 6. ,  2.2,  5. ,  1.5],\n",
       "       [ 6.9,  3.2,  5.7,  2.3],\n",
       "       [ 5.6,  2.8,  4.9,  2. ],\n",
       "       [ 7.7,  2.8,  6.7,  2. ],\n",
       "       [ 6.3,  2.7,  4.9,  1.8],\n",
       "       [ 6.7,  3.3,  5.7,  2.1],\n",
       "       [ 7.2,  3.2,  6. ,  1.8],\n",
       "       [ 6.2,  2.8,  4.8,  1.8],\n",
       "       [ 6.1,  3. ,  4.9,  1.8],\n",
       "       [ 6.4,  2.8,  5.6,  2.1],\n",
       "       [ 7.2,  3. ,  5.8,  1.6],\n",
       "       [ 7.4,  2.8,  6.1,  1.9],\n",
       "       [ 7.9,  3.8,  6.4,  2. ],\n",
       "       [ 6.4,  2.8,  5.6,  2.2],\n",
       "       [ 6.3,  2.8,  5.1,  1.5],\n",
       "       [ 6.1,  2.6,  5.6,  1.4],\n",
       "       [ 7.7,  3. ,  6.1,  2.3],\n",
       "       [ 6.3,  3.4,  5.6,  2.4],\n",
       "       [ 6.4,  3.1,  5.5,  1.8],\n",
       "       [ 6. ,  3. ,  4.8,  1.8],\n",
       "       [ 6.9,  3.1,  5.4,  2.1],\n",
       "       [ 6.7,  3.1,  5.6,  2.4],\n",
       "       [ 6.9,  3.1,  5.1,  2.3],\n",
       "       [ 5.8,  2.7,  5.1,  1.9],\n",
       "       [ 6.8,  3.2,  5.9,  2.3],\n",
       "       [ 6.7,  3.3,  5.7,  2.5],\n",
       "       [ 6.7,  3. ,  5.2,  2.3],\n",
       "       [ 6.3,  2.5,  5. ,  1.9],\n",
       "       [ 6.5,  3. ,  5.2,  2. ],\n",
       "       [ 6.2,  3.4,  5.4,  2.3],\n",
       "       [ 5.9,  3. ,  5.1,  1.8]])"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from sklearn.tree import export_graphviz\n",
    "export_graphviz(estimator, out_file=\"tree.dot\", class_names=iris.target_names,\n",
    "                feature_names=iris.feature_names, impurity=False, filled=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\r\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\r\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\r\n",
       "<!-- Generated by graphviz version 2.38.0 (20140413.2041)\r\n",
       " -->\r\n",
       "<!-- Title: Tree Pages: 1 -->\r\n",
       "<svg width=\"601pt\" height=\"477pt\"\r\n",
       " viewBox=\"0.00 0.00 601.00 477.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\r\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 473)\">\r\n",
       "<title>Tree</title>\r\n",
       "<polygon fill=\"white\" stroke=\"none\" points=\"-4,4 -4,-473 597,-473 597,4 -4,4\"/>\r\n",
       "<!-- 0 -->\r\n",
       "<g id=\"node1\" class=\"node\"><title>0</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.054902\" stroke=\"black\" points=\"293.5,-469 144.5,-469 144.5,-401 293.5,-401 293.5,-469\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"219\" y=\"-453.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal width (cm) &lt;= 0.8</text>\r\n",
       "<text text-anchor=\"middle\" x=\"219\" y=\"-438.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 112</text>\r\n",
       "<text text-anchor=\"middle\" x=\"219\" y=\"-423.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [37, 34, 41]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"219\" y=\"-408.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 1 -->\r\n",
       "<g id=\"node2\" class=\"node\"><title>1</title>\r\n",
       "<polygon fill=\"#e58139\" stroke=\"black\" points=\"199,-357.5 87,-357.5 87,-304.5 199,-304.5 199,-357.5\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-342.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 37</text>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-327.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [37, 0, 0]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"143\" y=\"-312.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = setosa</text>\r\n",
       "</g>\r\n",
       "<!-- 0&#45;&gt;1 -->\r\n",
       "<g id=\"edge1\" class=\"edge\"><title>0&#45;&gt;1</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M194.325,-400.884C185.967,-389.666 176.623,-377.126 168.223,-365.852\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"170.796,-363.448 162.015,-357.52 165.183,-367.63 170.796,-363.448\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"158.402\" y=\"-378.557\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">True</text>\r\n",
       "</g>\r\n",
       "<!-- 2 -->\r\n",
       "<g id=\"node3\" class=\"node\"><title>2</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.172549\" stroke=\"black\" points=\"375,-365 217,-365 217,-297 375,-297 375,-365\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"296\" y=\"-349.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal length (cm) &lt;= 4.95</text>\r\n",
       "<text text-anchor=\"middle\" x=\"296\" y=\"-334.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 75</text>\r\n",
       "<text text-anchor=\"middle\" x=\"296\" y=\"-319.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 34, 41]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"296\" y=\"-304.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 0&#45;&gt;2 -->\r\n",
       "<g id=\"edge2\" class=\"edge\"><title>0&#45;&gt;2</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M244,-400.884C250.589,-392.154 257.783,-382.625 264.661,-373.514\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"267.631,-375.389 270.862,-365.299 262.044,-371.172 267.631,-375.389\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"274.32\" y=\"-386.359\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">False</text>\r\n",
       "</g>\r\n",
       "<!-- 3 -->\r\n",
       "<g id=\"node4\" class=\"node\"><title>3</title>\r\n",
       "<polygon fill=\"#39e581\" fill-opacity=\"0.909804\" stroke=\"black\" points=\"286.5,-261 131.5,-261 131.5,-193 286.5,-193 286.5,-261\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-245.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal width (cm) &lt;= 1.65</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-230.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 36</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-215.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 33, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"209\" y=\"-200.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = versicolor</text>\r\n",
       "</g>\r\n",
       "<!-- 2&#45;&gt;3 -->\r\n",
       "<g id=\"edge3\" class=\"edge\"><title>2&#45;&gt;3</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M267.754,-296.884C260.156,-287.976 251.848,-278.235 243.934,-268.957\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"246.555,-266.636 237.402,-261.299 241.229,-271.179 246.555,-266.636\"/>\r\n",
       "</g>\r\n",
       "<!-- 8 -->\r\n",
       "<g id=\"node9\" class=\"node\"><title>8</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.972549\" stroke=\"black\" points=\"463,-261 305,-261 305,-193 463,-193 463,-261\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-245.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">petal length (cm) &lt;= 5.05</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-230.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 39</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-215.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 38]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-200.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 2&#45;&gt;8 -->\r\n",
       "<g id=\"edge8\" class=\"edge\"><title>2&#45;&gt;8</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M324.571,-296.884C332.256,-287.976 340.66,-278.235 348.665,-268.957\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"351.389,-271.157 355.271,-261.299 346.089,-266.585 351.389,-271.157\"/>\r\n",
       "</g>\r\n",
       "<!-- 4 -->\r\n",
       "<g id=\"node5\" class=\"node\"><title>4</title>\r\n",
       "<polygon fill=\"#39e581\" stroke=\"black\" points=\"116,-149.5 0,-149.5 0,-96.5 116,-96.5 116,-149.5\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"58\" y=\"-134.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 32</text>\r\n",
       "<text text-anchor=\"middle\" x=\"58\" y=\"-119.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 32, 0]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"58\" y=\"-104.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = versicolor</text>\r\n",
       "</g>\r\n",
       "<!-- 3&#45;&gt;4 -->\r\n",
       "<g id=\"edge4\" class=\"edge\"><title>3&#45;&gt;4</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M159.975,-192.884C142.065,-180.786 121.88,-167.151 104.223,-155.224\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"106.025,-152.217 95.7795,-149.52 102.107,-158.018 106.025,-152.217\"/>\r\n",
       "</g>\r\n",
       "<!-- 5 -->\r\n",
       "<g id=\"node6\" class=\"node\"><title>5</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.666667\" stroke=\"black\" points=\"285.5,-157 134.5,-157 134.5,-89 285.5,-89 285.5,-157\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"210\" y=\"-141.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">sepal width (cm) &lt;= 3.1</text>\r\n",
       "<text text-anchor=\"middle\" x=\"210\" y=\"-126.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 4</text>\r\n",
       "<text text-anchor=\"middle\" x=\"210\" y=\"-111.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"210\" y=\"-96.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 3&#45;&gt;5 -->\r\n",
       "<g id=\"edge5\" class=\"edge\"><title>3&#45;&gt;5</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M209.325,-192.884C209.404,-184.778 209.49,-175.982 209.574,-167.472\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"213.075,-167.333 209.674,-157.299 206.076,-167.265 213.075,-167.333\"/>\r\n",
       "</g>\r\n",
       "<!-- 6 -->\r\n",
       "<g id=\"node7\" class=\"node\"><title>6</title>\r\n",
       "<polygon fill=\"#8139e5\" stroke=\"black\" points=\"144.5,-53 37.5,-53 37.5,-0 144.5,-0 144.5,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"91\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 3</text>\r\n",
       "<text text-anchor=\"middle\" x=\"91\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 0, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"91\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 5&#45;&gt;6 -->\r\n",
       "<g id=\"edge6\" class=\"edge\"><title>5&#45;&gt;6</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M168.38,-88.9485C156.399,-79.4346 143.352,-69.074 131.444,-59.6175\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"133.417,-56.7147 123.409,-53.2367 129.064,-62.1965 133.417,-56.7147\"/>\r\n",
       "</g>\r\n",
       "<!-- 7 -->\r\n",
       "<g id=\"node8\" class=\"node\"><title>7</title>\r\n",
       "<polygon fill=\"#39e581\" stroke=\"black\" points=\"279,-53 163,-53 163,-0 279,-0 279,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"221\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 1</text>\r\n",
       "<text text-anchor=\"middle\" x=\"221\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 0]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"221\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = versicolor</text>\r\n",
       "</g>\r\n",
       "<!-- 5&#45;&gt;7 -->\r\n",
       "<g id=\"edge7\" class=\"edge\"><title>5&#45;&gt;7</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M213.847,-88.9485C214.816,-80.6238 215.861,-71.6509 216.844,-63.2027\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"220.324,-63.5743 218.004,-53.2367 213.371,-62.7649 220.324,-63.5743\"/>\r\n",
       "</g>\r\n",
       "<!-- 9 -->\r\n",
       "<g id=\"node10\" class=\"node\"><title>9</title>\r\n",
       "<polygon fill=\"#8139e5\" fill-opacity=\"0.666667\" stroke=\"black\" points=\"463,-157 305,-157 305,-89 463,-89 463,-157\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-141.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">sepal width (cm) &lt;= 2.75</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-126.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 4</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-111.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"384\" y=\"-96.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 8&#45;&gt;9 -->\r\n",
       "<g id=\"edge9\" class=\"edge\"><title>8&#45;&gt;9</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M384,-192.884C384,-184.778 384,-175.982 384,-167.472\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"387.5,-167.299 384,-157.299 380.5,-167.299 387.5,-167.299\"/>\r\n",
       "</g>\r\n",
       "<!-- 12 -->\r\n",
       "<g id=\"node13\" class=\"node\"><title>12</title>\r\n",
       "<polygon fill=\"#8139e5\" stroke=\"black\" points=\"593,-149.5 481,-149.5 481,-96.5 593,-96.5 593,-149.5\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"537\" y=\"-134.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 35</text>\r\n",
       "<text text-anchor=\"middle\" x=\"537\" y=\"-119.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 0, 35]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"537\" y=\"-104.3\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 8&#45;&gt;12 -->\r\n",
       "<g id=\"edge12\" class=\"edge\"><title>8&#45;&gt;12</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M433.675,-192.884C451.821,-180.786 472.273,-167.151 490.164,-155.224\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"492.341,-157.979 498.72,-149.52 488.458,-152.155 492.341,-157.979\"/>\r\n",
       "</g>\r\n",
       "<!-- 10 -->\r\n",
       "<g id=\"node11\" class=\"node\"><title>10</title>\r\n",
       "<polygon fill=\"#8139e5\" stroke=\"black\" points=\"426.5,-53 319.5,-53 319.5,-0 426.5,-0 426.5,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"373\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 3</text>\r\n",
       "<text text-anchor=\"middle\" x=\"373\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 0, 3]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"373\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = virginica</text>\r\n",
       "</g>\r\n",
       "<!-- 9&#45;&gt;10 -->\r\n",
       "<g id=\"edge10\" class=\"edge\"><title>9&#45;&gt;10</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M380.153,-88.9485C379.184,-80.6238 378.139,-71.6509 377.156,-63.2027\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"380.629,-62.7649 375.996,-53.2367 373.676,-63.5743 380.629,-62.7649\"/>\r\n",
       "</g>\r\n",
       "<!-- 11 -->\r\n",
       "<g id=\"node12\" class=\"node\"><title>11</title>\r\n",
       "<polygon fill=\"#39e581\" stroke=\"black\" points=\"561,-53 445,-53 445,-0 561,-0 561,-53\"/>\r\n",
       "<text text-anchor=\"middle\" x=\"503\" y=\"-37.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">samples = 1</text>\r\n",
       "<text text-anchor=\"middle\" x=\"503\" y=\"-22.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">value = [0, 1, 0]</text>\r\n",
       "<text text-anchor=\"middle\" x=\"503\" y=\"-7.8\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">class = versicolor</text>\r\n",
       "</g>\r\n",
       "<!-- 9&#45;&gt;11 -->\r\n",
       "<g id=\"edge11\" class=\"edge\"><title>9&#45;&gt;11</title>\r\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M425.62,-88.9485C437.601,-79.4346 450.648,-69.074 462.556,-59.6175\"/>\r\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"464.936,-62.1965 470.591,-53.2367 460.583,-56.7147 464.936,-62.1965\"/>\r\n",
       "</g>\r\n",
       "</g>\r\n",
       "</svg>\r\n"
      ],
      "text/plain": [
       "<graphviz.files.Source at 0x2180afd96d8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import graphviz\n",
    "\n",
    "with open(\"tree.dot\") as f:\n",
    "    dot_graph = f.read()\n",
    "display(graphviz.Source(dot_graph))"
   ]
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}