{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "pycharm": {} }, "outputs": [], "source": [ "%matplotlib inline\n", "\n", "import matplotlib.pyplot as plt\n", "import seaborn as sns\n", "import numpy as np\n", "import pandas as pd\n", "\n", "import sys\n", "sys.path.append('/Users/kaonpark/workspace/github.com/likejazz/kaon-learn')\n", "import kaonlearn\n", "\n", "from kaonlearn.plots import plot_decision_regions" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "pycharm": {} }, "outputs": [], "source": [ "from sklearn import svm, datasets\n", "\n", "# import some data to play with\n", "iris = datasets.load_iris()\n", "X = iris.data[:, :2] # we only take the first two features. We could\n", " # avoid this ugly slicing by using a two-dim dataset\n", "y = iris.target\n", "\n", "h = .02 # step size in the mesh\n", "\n", "# we create an instance of SVM and fit out data. We do not scale our\n", "# data since we want to plot the support vectors\n", "C = 1.0 # SVM regularization parameter\n", "svc = svm.SVC(kernel='linear', C=C).fit(X, y)\n", "rbf_svc = svm.SVC(kernel='rbf', gamma=0.7, C=C).fit(X, y)\n", "poly_svc = svm.SVC(kernel='poly', degree=3, C=C).fit(X, y)\n", "lin_svc = svm.LinearSVC(C=C).fit(X, y)" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('SVC with linear kernel')\n", "plot_decision_regions(X, y, clf=svc, legend=0)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('LinearSVC (linear kernel)')\n", "plot_decision_regions(X, y, clf=lin_svc, legend=0)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('SVC with RBF kernel')\n", "plot_decision_regions(X, y, clf=rbf_svc, legend=0)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('SVC with polynomial (degree 3) kernel')\n", "plot_decision_regions(X, y, clf=poly_svc, legend=0)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "pycharm": {} }, "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=42,\n", " splitter='best')" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.tree import DecisionTreeClassifier\n", "\n", "tree_clf = DecisionTreeClassifier(max_depth=2, random_state=42)\n", "tree_clf.fit(X, y)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", "\n", "\n", "\n", "Tree\n", "\n", "\n", "\n", "0\n", "\n", "petal length (cm) ≤ 5.45\n", "gini = 0.667\n", "samples = 150\n", "value = [50, 50, 50]\n", "class = setosa\n", "\n", "\n", "\n", "1\n", "\n", "petal width (cm) ≤ 2.8\n", "gini = 0.237\n", "samples = 52\n", "value = [45, 6, 1]\n", "class = setosa\n", "\n", "\n", "\n", "0->1\n", "\n", "\n", "True\n", "\n", "\n", "\n", "4\n", "\n", "petal length (cm) ≤ 6.15\n", "gini = 0.546\n", "samples = 98\n", "value = [5, 44, 49]\n", "class = virginica\n", "\n", "\n", "\n", "0->4\n", "\n", "\n", "False\n", "\n", "\n", "\n", "2\n", "\n", "gini = 0.449\n", "samples = 7\n", "value = [1, 5, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "1->2\n", "\n", "\n", "\n", "\n", "\n", "3\n", "\n", "gini = 0.043\n", "samples = 45\n", "value = [44, 1, 0]\n", "class = setosa\n", "\n", "\n", "\n", "1->3\n", "\n", "\n", "\n", "\n", "\n", "5\n", "\n", "gini = 0.508\n", "samples = 43\n", "value = [5, 28, 10]\n", "class = versicolor\n", "\n", "\n", "\n", "4->5\n", "\n", "\n", "\n", "\n", "\n", "6\n", "\n", "gini = 0.413\n", "samples = 55\n", "value = [0, 16, 39]\n", "class = virginica\n", "\n", "\n", "\n", "4->6\n", "\n", "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "import os\n", "from tempfile import mkstemp\n", "import subprocess\n", "\n", "from sklearn.tree.export import export_graphviz\n", "\n", "def convert_decision_tree_to_ipython_image(clf, feature_names=None, class_names=None, tmp_dir=None):\n", " dot_filename = mkstemp(suffix='.dot', dir=tmp_dir)[1]\n", " with open(dot_filename, \"w\") as out_file:\n", " export_graphviz(clf, out_file=out_file,\n", " feature_names=feature_names,\n", " class_names=class_names,\n", " filled=True, rounded=True,\n", " special_characters=True)\n", "\n", " import graphviz\n", " from IPython.display import display\n", "\n", " with open(dot_filename) as f:\n", " dot_graph = f.read()\n", " display(graphviz.Source(dot_graph))\n", " os.remove(dot_filename)\n", "\n", "convert_decision_tree_to_ipython_image(tree_clf, feature_names=iris.feature_names[2:], class_names=iris.target_names)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('Decision Tree max_depth=2')\n", "plot_decision_regions(X, y, clf=tree_clf, legend=0)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "image/svg+xml": [ "\n", "\n", "\n", "\n", "\n", "\n", "Tree\n", "\n", "\n", "\n", "0\n", "\n", "petal length (cm) ≤ 5.45\n", "gini = 0.667\n", "samples = 150\n", "value = [50, 50, 50]\n", "class = setosa\n", "\n", "\n", "\n", "1\n", "\n", "petal width (cm) ≤ 2.8\n", "gini = 0.237\n", "samples = 52\n", "value = [45, 6, 1]\n", "class = setosa\n", "\n", "\n", "\n", "0->1\n", "\n", "\n", "True\n", "\n", "\n", "\n", "14\n", "\n", "petal length (cm) ≤ 6.15\n", "gini = 0.546\n", "samples = 98\n", "value = [5, 44, 49]\n", "class = virginica\n", "\n", "\n", "\n", "0->14\n", "\n", "\n", "False\n", "\n", "\n", "\n", "2\n", "\n", "petal length (cm) ≤ 4.7\n", "gini = 0.449\n", "samples = 7\n", "value = [1, 5, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "1->2\n", "\n", "\n", "\n", "\n", "\n", "9\n", "\n", "petal length (cm) ≤ 5.35\n", "gini = 0.043\n", "samples = 45\n", "value = [44, 1, 0]\n", "class = setosa\n", "\n", "\n", "\n", "1->9\n", "\n", "\n", "\n", "\n", "\n", "3\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [1, 0, 0]\n", "class = setosa\n", "\n", "\n", "\n", "2->3\n", "\n", "\n", "\n", "\n", "\n", "4\n", "\n", "petal length (cm) ≤ 4.95\n", "gini = 0.278\n", "samples = 6\n", "value = [0, 5, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "2->4\n", "\n", "\n", "\n", "\n", "\n", "5\n", "\n", "petal width (cm) ≤ 2.45\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "4->5\n", "\n", "\n", "\n", "\n", "\n", "8\n", "\n", "gini = 0.0\n", "samples = 4\n", "value = [0, 4, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "4->8\n", "\n", "\n", "\n", "\n", "\n", "6\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "5->6\n", "\n", "\n", "\n", "\n", "\n", "7\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "5->7\n", "\n", "\n", "\n", "\n", "\n", "10\n", "\n", "gini = 0.0\n", "samples = 39\n", "value = [39, 0, 0]\n", "class = setosa\n", "\n", "\n", "\n", "9->10\n", "\n", "\n", "\n", "\n", "\n", "11\n", "\n", "petal width (cm) ≤ 3.2\n", "gini = 0.278\n", "samples = 6\n", "value = [5, 1, 0]\n", "class = setosa\n", "\n", "\n", "\n", "9->11\n", "\n", "\n", "\n", "\n", "\n", "12\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "11->12\n", "\n", "\n", "\n", "\n", "\n", "13\n", "\n", "gini = 0.0\n", "samples = 5\n", "value = [5, 0, 0]\n", "class = setosa\n", "\n", "\n", "\n", "11->13\n", "\n", "\n", "\n", "\n", "\n", "15\n", "\n", "petal width (cm) ≤ 3.45\n", "gini = 0.508\n", "samples = 43\n", "value = [5, 28, 10]\n", "class = versicolor\n", "\n", "\n", "\n", "14->15\n", "\n", "\n", "\n", "\n", "\n", "52\n", "\n", "petal length (cm) ≤ 7.05\n", "gini = 0.413\n", "samples = 55\n", "value = [0, 16, 39]\n", "class = virginica\n", "\n", "\n", "\n", "14->52\n", "\n", "\n", "\n", "\n", "\n", "16\n", "\n", "petal length (cm) ≤ 5.75\n", "gini = 0.388\n", "samples = 38\n", "value = [0, 28, 10]\n", "class = versicolor\n", "\n", "\n", "\n", "15->16\n", "\n", "\n", "\n", "\n", "\n", "51\n", "\n", "gini = 0.0\n", "samples = 5\n", "value = [5, 0, 0]\n", "class = setosa\n", "\n", "\n", "\n", "15->51\n", "\n", "\n", "\n", "\n", "\n", "17\n", "\n", "petal width (cm) ≤ 2.85\n", "gini = 0.208\n", "samples = 17\n", "value = [0, 15, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "16->17\n", "\n", "\n", "\n", "\n", "\n", "30\n", "\n", "petal width (cm) ≤ 3.1\n", "gini = 0.472\n", "samples = 21\n", "value = [0, 13, 8]\n", "class = versicolor\n", "\n", "\n", "\n", "16->30\n", "\n", "\n", "\n", "\n", "\n", "18\n", "\n", "petal length (cm) ≤ 5.55\n", "gini = 0.278\n", "samples = 12\n", "value = [0, 10, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "17->18\n", "\n", "\n", "\n", "\n", "\n", "29\n", "\n", "gini = 0.0\n", "samples = 5\n", "value = [0, 5, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "17->29\n", "\n", "\n", "\n", "\n", "\n", "19\n", "\n", "gini = 0.0\n", "samples = 5\n", "value = [0, 5, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "18->19\n", "\n", "\n", "\n", "\n", "\n", "20\n", "\n", "petal width (cm) ≤ 2.55\n", "gini = 0.408\n", "samples = 7\n", "value = [0, 5, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "18->20\n", "\n", "\n", "\n", "\n", "\n", "21\n", "\n", "petal length (cm) ≤ 5.65\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "20->21\n", "\n", "\n", "\n", "\n", "\n", "24\n", "\n", "petal length (cm) ≤ 5.65\n", "gini = 0.32\n", "samples = 5\n", "value = [0, 4, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "20->24\n", "\n", "\n", "\n", "\n", "\n", "22\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "21->22\n", "\n", "\n", "\n", "\n", "\n", "23\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "21->23\n", "\n", "\n", "\n", "\n", "\n", "25\n", "\n", "petal width (cm) ≤ 2.75\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "24->25\n", "\n", "\n", "\n", "\n", "\n", "28\n", "\n", "gini = 0.0\n", "samples = 3\n", "value = [0, 3, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "24->28\n", "\n", "\n", "\n", "\n", "\n", "26\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "25->26\n", "\n", "\n", "\n", "\n", "\n", "27\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "25->27\n", "\n", "\n", "\n", "\n", "\n", "31\n", "\n", "petal width (cm) ≤ 2.95\n", "gini = 0.488\n", "samples = 19\n", "value = [0, 11, 8]\n", "class = versicolor\n", "\n", "\n", "\n", "30->31\n", "\n", "\n", "\n", "\n", "\n", "50\n", "\n", "gini = 0.0\n", "samples = 2\n", "value = [0, 2, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "30->50\n", "\n", "\n", "\n", "\n", "\n", "32\n", "\n", "petal width (cm) ≤ 2.85\n", "gini = 0.459\n", "samples = 14\n", "value = [0, 9, 5]\n", "class = versicolor\n", "\n", "\n", "\n", "31->32\n", "\n", "\n", "\n", "\n", "\n", "45\n", "\n", "petal length (cm) ≤ 5.95\n", "gini = 0.48\n", "samples = 5\n", "value = [0, 2, 3]\n", "class = virginica\n", "\n", "\n", "\n", "31->45\n", "\n", "\n", "\n", "\n", "\n", "33\n", "\n", "petal length (cm) ≤ 5.9\n", "gini = 0.486\n", "samples = 12\n", "value = [0, 7, 5]\n", "class = versicolor\n", "\n", "\n", "\n", "32->33\n", "\n", "\n", "\n", "\n", "\n", "44\n", "\n", "gini = 0.0\n", "samples = 2\n", "value = [0, 2, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "32->44\n", "\n", "\n", "\n", "\n", "\n", "34\n", "\n", "petal width (cm) ≤ 2.65\n", "gini = 0.5\n", "samples = 6\n", "value = [0, 3, 3]\n", "class = versicolor\n", "\n", "\n", "\n", "33->34\n", "\n", "\n", "\n", "\n", "\n", "39\n", "\n", "petal width (cm) ≤ 2.65\n", "gini = 0.444\n", "samples = 6\n", "value = [0, 4, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "33->39\n", "\n", "\n", "\n", "\n", "\n", "35\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "34->35\n", "\n", "\n", "\n", "\n", "\n", "36\n", "\n", "petal width (cm) ≤ 2.75\n", "gini = 0.48\n", "samples = 5\n", "value = [0, 2, 3]\n", "class = virginica\n", "\n", "\n", "\n", "34->36\n", "\n", "\n", "\n", "\n", "\n", "37\n", "\n", "gini = 0.5\n", "samples = 4\n", "value = [0, 2, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "36->37\n", "\n", "\n", "\n", "\n", "\n", "38\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "36->38\n", "\n", "\n", "\n", "\n", "\n", "40\n", "\n", "petal length (cm) ≤ 6.05\n", "gini = 0.444\n", "samples = 3\n", "value = [0, 1, 2]\n", "class = virginica\n", "\n", "\n", "\n", "39->40\n", "\n", "\n", "\n", "\n", "\n", "43\n", "\n", "gini = 0.0\n", "samples = 3\n", "value = [0, 3, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "39->43\n", "\n", "\n", "\n", "\n", "\n", "41\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "40->41\n", "\n", "\n", "\n", "\n", "\n", "42\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "40->42\n", "\n", "\n", "\n", "\n", "\n", "46\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "45->46\n", "\n", "\n", "\n", "\n", "\n", "47\n", "\n", "petal length (cm) ≤ 6.05\n", "gini = 0.444\n", "samples = 3\n", "value = [0, 1, 2]\n", "class = virginica\n", "\n", "\n", "\n", "45->47\n", "\n", "\n", "\n", "\n", "\n", "48\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "47->48\n", "\n", "\n", "\n", "\n", "\n", "49\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "47->49\n", "\n", "\n", "\n", "\n", "\n", "53\n", "\n", "petal width (cm) ≤ 2.4\n", "gini = 0.467\n", "samples = 43\n", "value = [0, 16, 27]\n", "class = virginica\n", "\n", "\n", "\n", "52->53\n", "\n", "\n", "\n", "\n", "\n", "92\n", "\n", "gini = 0.0\n", "samples = 12\n", "value = [0, 0, 12]\n", "class = virginica\n", "\n", "\n", "\n", "52->92\n", "\n", "\n", "\n", "\n", "\n", "54\n", "\n", "gini = 0.0\n", "samples = 2\n", "value = [0, 2, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "53->54\n", "\n", "\n", "\n", "\n", "\n", "55\n", "\n", "petal length (cm) ≤ 6.95\n", "gini = 0.45\n", "samples = 41\n", "value = [0, 14, 27]\n", "class = virginica\n", "\n", "\n", "\n", "53->55\n", "\n", "\n", "\n", "\n", "\n", "56\n", "\n", "petal width (cm) ≤ 3.15\n", "gini = 0.439\n", "samples = 40\n", "value = [0, 13, 27]\n", "class = virginica\n", "\n", "\n", "\n", "55->56\n", "\n", "\n", "\n", "\n", "\n", "91\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "55->91\n", "\n", "\n", "\n", "\n", "\n", "57\n", "\n", "petal length (cm) ≤ 6.55\n", "gini = 0.471\n", "samples = 29\n", "value = [0, 11, 18]\n", "class = virginica\n", "\n", "\n", "\n", "56->57\n", "\n", "\n", "\n", "\n", "\n", "84\n", "\n", "petal length (cm) ≤ 6.45\n", "gini = 0.298\n", "samples = 11\n", "value = [0, 2, 9]\n", "class = virginica\n", "\n", "\n", "\n", "56->84\n", "\n", "\n", "\n", "\n", "\n", "58\n", "\n", "petal width (cm) ≤ 2.95\n", "gini = 0.375\n", "samples = 16\n", "value = [0, 4, 12]\n", "class = virginica\n", "\n", "\n", "\n", "57->58\n", "\n", "\n", "\n", "\n", "\n", "71\n", "\n", "petal length (cm) ≤ 6.65\n", "gini = 0.497\n", "samples = 13\n", "value = [0, 7, 6]\n", "class = versicolor\n", "\n", "\n", "\n", "57->71\n", "\n", "\n", "\n", "\n", "\n", "59\n", "\n", "petal length (cm) ≤ 6.45\n", "gini = 0.444\n", "samples = 12\n", "value = [0, 4, 8]\n", "class = virginica\n", "\n", "\n", "\n", "58->59\n", "\n", "\n", "\n", "\n", "\n", "70\n", "\n", "gini = 0.0\n", "samples = 4\n", "value = [0, 0, 4]\n", "class = virginica\n", "\n", "\n", "\n", "58->70\n", "\n", "\n", "\n", "\n", "\n", "60\n", "\n", "petal width (cm) ≤ 2.85\n", "gini = 0.397\n", "samples = 11\n", "value = [0, 3, 8]\n", "class = virginica\n", "\n", "\n", "\n", "59->60\n", "\n", "\n", "\n", "\n", "\n", "69\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "59->69\n", "\n", "\n", "\n", "\n", "\n", "61\n", "\n", "petal width (cm) ≤ 2.6\n", "gini = 0.219\n", "samples = 8\n", "value = [0, 1, 7]\n", "class = virginica\n", "\n", "\n", "\n", "60->61\n", "\n", "\n", "\n", "\n", "\n", "64\n", "\n", "petal length (cm) ≤ 6.25\n", "gini = 0.444\n", "samples = 3\n", "value = [0, 2, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "60->64\n", "\n", "\n", "\n", "\n", "\n", "62\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "61->62\n", "\n", "\n", "\n", "\n", "\n", "63\n", "\n", "gini = 0.0\n", "samples = 6\n", "value = [0, 0, 6]\n", "class = virginica\n", "\n", "\n", "\n", "61->63\n", "\n", "\n", "\n", "\n", "\n", "65\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "64->65\n", "\n", "\n", "\n", "\n", "\n", "66\n", "\n", "petal length (cm) ≤ 6.35\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "64->66\n", "\n", "\n", "\n", "\n", "\n", "67\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "66->67\n", "\n", "\n", "\n", "\n", "\n", "68\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "66->68\n", "\n", "\n", "\n", "\n", "\n", "72\n", "\n", "gini = 0.0\n", "samples = 2\n", "value = [0, 2, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "71->72\n", "\n", "\n", "\n", "\n", "\n", "73\n", "\n", "petal width (cm) ≤ 2.65\n", "gini = 0.496\n", "samples = 11\n", "value = [0, 5, 6]\n", "class = virginica\n", "\n", "\n", "\n", "71->73\n", "\n", "\n", "\n", "\n", "\n", "74\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "73->74\n", "\n", "\n", "\n", "\n", "\n", "75\n", "\n", "petal width (cm) ≤ 2.9\n", "gini = 0.5\n", "samples = 10\n", "value = [0, 5, 5]\n", "class = versicolor\n", "\n", "\n", "\n", "73->75\n", "\n", "\n", "\n", "\n", "\n", "76\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 1, 0]\n", "class = versicolor\n", "\n", "\n", "\n", "75->76\n", "\n", "\n", "\n", "\n", "\n", "77\n", "\n", "petal length (cm) ≤ 6.75\n", "gini = 0.494\n", "samples = 9\n", "value = [0, 4, 5]\n", "class = virginica\n", "\n", "\n", "\n", "75->77\n", "\n", "\n", "\n", "\n", "\n", "78\n", "\n", "petal width (cm) ≤ 3.05\n", "gini = 0.48\n", "samples = 5\n", "value = [0, 3, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "77->78\n", "\n", "\n", "\n", "\n", "\n", "81\n", "\n", "petal width (cm) ≤ 3.05\n", "gini = 0.375\n", "samples = 4\n", "value = [0, 1, 3]\n", "class = virginica\n", "\n", "\n", "\n", "77->81\n", "\n", "\n", "\n", "\n", "\n", "79\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "78->79\n", "\n", "\n", "\n", "\n", "\n", "80\n", "\n", "gini = 0.444\n", "samples = 3\n", "value = [0, 2, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "78->80\n", "\n", "\n", "\n", "\n", "\n", "82\n", "\n", "gini = 0.0\n", "samples = 1\n", "value = [0, 0, 1]\n", "class = virginica\n", "\n", "\n", "\n", "81->82\n", "\n", "\n", "\n", "\n", "\n", "83\n", "\n", "gini = 0.444\n", "samples = 3\n", "value = [0, 1, 2]\n", "class = virginica\n", "\n", "\n", "\n", "81->83\n", "\n", "\n", "\n", "\n", "\n", "85\n", "\n", "petal width (cm) ≤ 3.35\n", "gini = 0.444\n", "samples = 6\n", "value = [0, 2, 4]\n", "class = virginica\n", "\n", "\n", "\n", "84->85\n", "\n", "\n", "\n", "\n", "\n", "90\n", "\n", "gini = 0.0\n", "samples = 5\n", "value = [0, 0, 5]\n", "class = virginica\n", "\n", "\n", "\n", "84->90\n", "\n", "\n", "\n", "\n", "\n", "86\n", "\n", "petal width (cm) ≤ 3.25\n", "gini = 0.5\n", "samples = 4\n", "value = [0, 2, 2]\n", "class = versicolor\n", "\n", "\n", "\n", "85->86\n", "\n", "\n", "\n", "\n", "\n", "89\n", "\n", "gini = 0.0\n", "samples = 2\n", "value = [0, 0, 2]\n", "class = virginica\n", "\n", "\n", "\n", "85->89\n", "\n", "\n", "\n", "\n", "\n", "87\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "86->87\n", "\n", "\n", "\n", "\n", "\n", "88\n", "\n", "gini = 0.5\n", "samples = 2\n", "value = [0, 1, 1]\n", "class = versicolor\n", "\n", "\n", "\n", "86->88\n", "\n", "\n", "\n", "\n", "\n" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "tree2_clf = DecisionTreeClassifier(random_state=42)\n", "tree2_clf.fit(X, y)\n", "convert_decision_tree_to_ipython_image(tree2_clf, feature_names=iris.feature_names[2:], class_names=iris.target_names)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('Decision Tree')\n", "plot_decision_regions(X, y, clf=tree2_clf, legend=0)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n", " max_depth=None, 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=10, n_jobs=1,\n", " oob_score=False, random_state=42, verbose=0, warm_start=False)" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.ensemble import RandomForestClassifier\n", "\n", "rf_clf = RandomForestClassifier(random_state=42)\n", "rf_clf.fit(X, y)" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "pycharm": {} }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.title('Random Forest')\n", "plot_decision_regions(X, y, clf=rf_clf, legend=0)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.7.0" } }, "nbformat": 4, "nbformat_minor": 2 }