- "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn import clone\nfrom sklearn.datasets import load_iris\nfrom sklearn.ensemble import (RandomForestClassifier, ExtraTreesClassifier,\n AdaBoostClassifier)\nfrom sklearn.externals.six.moves import xrange\nfrom sklearn.tree import DecisionTreeClassifier\n\n# Parameters\nn_classes = 3\nn_estimators = 30\nplot_colors = \"ryb\"\ncmap = plt.cm.RdYlBu\nplot_step = 0.02 # fine step width for decision surface contours\nplot_step_coarser = 0.5 # step widths for coarse classifier guesses\nRANDOM_SEED = 13 # fix the seed on each iteration\n\n# Load data\niris = load_iris()\n\nplot_idx = 1\n\nmodels = [DecisionTreeClassifier(max_depth=None),\n RandomForestClassifier(n_estimators=n_estimators),\n ExtraTreesClassifier(n_estimators=n_estimators),\n AdaBoostClassifier(DecisionTreeClassifier(max_depth=3),\n n_estimators=n_estimators)]\n\nfor pair in ([0, 1], [0, 2], [2, 3]):\n for model in models:\n # We only take the two corresponding features\n X = iris.data[:, pair]\n y = iris.target\n\n # Shuffle\n idx = np.arange(X.shape[0])\n np.random.seed(RANDOM_SEED)\n np.random.shuffle(idx)\n X = X[idx]\n y = y[idx]\n\n # Standardize\n mean = X.mean(axis=0)\n std = X.std(axis=0)\n X = (X - mean) / std\n\n # Train\n clf = clone(model)\n clf = model.fit(X, y)\n\n scores = clf.score(X, y)\n # Create a title for each column and the console by using str() and\n # slicing away useless parts of the string\n model_title = str(type(model)).split(\".\")[-1][:-2][:-len(\"Classifier\")]\n model_details = model_title\n if hasattr(model, \"estimators_\"):\n model_details += \" with {} estimators\".format(len(model.estimators_))\n print( model_details + \" with features\", pair, \"has a score of\", scores )\n\n plt.subplot(3, 4, plot_idx)\n if plot_idx <= len(models):\n # Add a title at the top of each column\n plt.title(model_title)\n\n # Now plot the decision boundary using a fine mesh as input to a\n # filled contour plot\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 # Plot either a single DecisionTreeClassifier or alpha blend the\n # decision surfaces of the ensemble of classifiers\n if isinstance(model, DecisionTreeClassifier):\n Z = model.predict(np.c_[xx.ravel(), yy.ravel()])\n Z = Z.reshape(xx.shape)\n cs = plt.contourf(xx, yy, Z, cmap=cmap)\n else:\n # Choose alpha blend level with respect to the number of estimators\n # that are in use (noting that AdaBoost can use fewer estimators\n # than its maximum if it achieves a good enough fit early on)\n estimator_alpha = 1.0 / len(model.estimators_)\n for tree in model.estimators_:\n Z = tree.predict(np.c_[xx.ravel(), yy.ravel()])\n Z = Z.reshape(xx.shape)\n cs = plt.contourf(xx, yy, Z, alpha=estimator_alpha, cmap=cmap)\n\n # Build a coarser grid to plot a set of ensemble classifications\n # to show how these are different to what we see in the decision\n # surfaces. These points are regularly space and do not have a black outline\n xx_coarser, yy_coarser = np.meshgrid(np.arange(x_min, x_max, plot_step_coarser),\n np.arange(y_min, y_max, plot_step_coarser))\n Z_points_coarser = model.predict(np.c_[xx_coarser.ravel(), yy_coarser.ravel()]).reshape(xx_coarser.shape)\n cs_points = plt.scatter(xx_coarser, yy_coarser, s=15, c=Z_points_coarser, cmap=cmap, edgecolors=\"none\")\n\n # Plot the training points, these are clustered together and have a\n # black outline\n for i, c in zip(xrange(n_classes), plot_colors):\n idx = np.where(y == i)\n plt.scatter(X[idx, 0], X[idx, 1], c=c, label=iris.target_names[i],\n cmap=cmap)\n\n plot_idx += 1 # move on to the next plot in sequence\n\nplt.suptitle(\"Classifiers on feature subsets of the Iris dataset\")\nplt.axis(\"tight\")\n\nplt.show()"
0 commit comments