mlutils1.py

import numpy as np
import matplotlib.pyplot as plt

def plot_2d_clf_problem(X, y, h=None):
    '''
    Plots a two-dimensional labeled dataset (X,y) and, if function h(x) is given, 
    the decision surfaces.
    '''
    assert X.shape[1] == 2, "Dataset is not two-dimensional"
    if h!=None : 
        # Create a mesh to plot in
        r = 0.02  # mesh resolution
        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
        xx, yy = np.meshgrid(np.arange(x_min, x_max, r),
                             np.arange(y_min, y_max, r))
        XX=np.c_[xx.ravel(), yy.ravel()]
        try:
            Z_test = h(XX)
            if Z_test.shape == ():
                # h returns a scalar when applied to a matrix; map explicitly
                Z = np.array(map(h,XX))
            else :
                Z = Z_test
        except ValueError:
            # can't apply to a matrix; map explicitly
            Z = np.array(map(h,XX))
        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        plt.contourf(xx, yy, Z, cmap=plt.cm.Pastel1)

    # Plot the dataset
    plt.scatter(X[:,0],X[:,1], c=y, cmap=plt.cm.Paired, marker='o', s=50)
    #plt.show()

def plot_2d_svc_problem(X, y, svc=None):
    '''
    Plots a two-dimensional labeled dataset (X,y) and, if SVC object is given, 
    the decision surfaces (with margin as well).
    '''
    assert X.shape[1] == 2, "Dataset is not two-dimensional"
    if svc!=None : 
        # Create a mesh to plot in
        r = 0.03  # mesh resolution
        x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
        y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
        xx, yy = np.meshgrid(np.arange(x_min, x_max, r),
                             np.arange(y_min, y_max, r))
        XX=np.c_[xx.ravel(), yy.ravel()]
        Z = np.array([svc_predict(svc, x) for x in XX])
        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        plt.contourf(xx, yy, Z, cmap=plt.cm.Pastel1)

    # Plot the dataset
    plt.scatter(X[:,0],X[:,1], c=y, cmap=plt.cm.Paired, marker='o', s=50)
    #plt.show()

def svc_predict(svc, x) : 
    h = svc.decision_function([x])
    if h >= -1 and h <= 1:
        return 0.5
    else: 
        return max(-1, min(1, h))

def plot_error_surface(err,(c1,c2),(g1,g2)) :
    plt.xticks(range(0,g2-g1+1,5),range(g1,g2,5)); plt.xlabel("gamma")
    plt.yticks(range(0,c2-c1+1,5),range(c1,c2,5)); plt.ylabel("C")
    p = plt.contour(err);
    plt.imshow(1-err, interpolation='bilinear', origin='lower',cmap=plt.cm.gray)
    plt.clabel(p, inline=1, fontsize=10)
    #plt.show()