plot_classifier_comparison.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

import numpy as np
import matplotlib
matplotlib.use('Agg') # for linux server without display
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
#from sklearn.svm import SVC
from sklearn.grid_search import GridSearchCV
from rsvm import SVM, RSVM, CSSVM


h = .02  # step size in the mesh

names = ["SVM(linear)", "SVM(rbf)", "RSVM(rbf)", "CSSVM(rbf)"]
"""
classifiers = [SVM(C=1, kernel='linear', gamma='auto'), 
               SVM(C=1, kernel='rbf', gamma='auto'), 
               RSVM(C=1, kernel='rbf', gamma='auto'), 
               CSSVM(C=1, kernel='rbf', gamma='auto')]
"""
tuned_parameters_l = [{'kernel': ['linear'],
                     'C': [0.01, 0.1, 1, 10, 100]
                    }]
tuned_parameters_rbf = [{'kernel': ['rbf'],
                     'C': [0.01, 0.1, 1, 10, 100]
                    }]
classifiers = [GridSearchCV(SVM(C=1, kernel='linear', gamma='auto'), tuned_parameters_l, cv=5, scoring=None, n_jobs=20),
               GridSearchCV(SVM(C=1, kernel='rbf', gamma='auto'), tuned_parameters_rbf, cv=5, scoring=None, n_jobs=20),
               GridSearchCV(RSVM(C=1, kernel='rbf', gamma='auto'), tuned_parameters_rbf, cv=5, scoring=None, n_jobs=20),
               GridSearchCV(CSSVM(C=1, kernel='rbf', gamma='auto'), tuned_parameters_rbf, cv=5, scoring=None, n_jobs=20)]

X, y = make_classification(n_samples=500, n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)

datasets = [make_moons(n_samples=500, noise=0.3, random_state=0),
            make_circles(n_samples=500, noise=0.2, factor=0.5, random_state=1),
            linearly_separable
            ]

figure = plt.figure()
i = 1
# iterate over datasets
for ds in datasets:
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)

    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))

    # just plot the dataset first
    cm = plt.cm.RdBu
    cm_bright = ListedColormap(['#0000FF', '#FF0000'])
    ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
    dot_size = 5000.0/len(X)
    # Plot the training points
    #ax.scatter(X_train[:, 0], X_train[:, 1], s=dot_size, c=y_train, cmap=cm_bright)
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], s=dot_size, c=y_test, cmap=cm_bright, alpha=0.6)
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1

    # iterate over classifiers
    for name, clf in zip(names, classifiers):
        ax = plt.subplot(len(datasets), len(classifiers) + 1, i)
        print name
        clf.fit(X_train, y_train)
        score = clf.score(X_test, y_test)
        for params, mean_score, scores in clf.grid_scores_:
            print("%0.3f (+/-%0.03f) for %r"
                  % (mean_score, scores.std() * 2, params))
            print()
        # Plot the decision boundary. For that, we will assign a color to each
        # point in the mesh [x_min, m_max]x[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
        else:
            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # Plot also the training points
        #ax.scatter(X_train[:, 0], X_train[:, 1], s=dot_size, c=y_train, cmap=cm_bright)
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], s=dot_size, c=y_test, cmap=cm_bright,
                   alpha=0.6)

        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(name)
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
                size=15, horizontalalignment='right')
        i += 1

figure.subplots_adjust(left=.02, right=.98)
#plt.show()
plt.savefig('comparison.png',dpi=500)