plot_kanker_dada.py

print(__doc__)

import numpy as np
import matplotlib.pyplot as plt
import random as rand
from sklearn import svm, datasets


def make_meshgrid(x, y, h=.02):
    """Create a mesh of points to plot in

    Parameters
    ----------
    x: data to base x-axis meshgrid on
    y: data to base y-axis meshgrid on
    h: stepsize for meshgrid, optional

    Returns
    -------
    xx, yy : ndarray
    """
    x_min, x_max = x.min() - 1, x.max() + 1
    y_min, y_max = y.min() - 1, y.max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))
    return xx, yy


def plot_contours(ax, clf, xx, yy, **params):
    """Plot the decision boundaries for a classifier.

    Parameters
    ----------
    ax: matplotlib axes object
    clf: a classifier
    xx: meshgrid ndarray
    yy: meshgrid ndarray
    params: dictionary of params to pass to contourf, optional
    """
    Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    out = ax.contourf(xx, yy, Z, **params)
    return out


# import some data to play with
# iris = datasets.load_iris()
# Take the first two features. We could avoid this by using a two-dim dataset
# X = iris.data[:, :2]
# y = iris.target[:]

features = [
    'Sample code number',
    'Clump Thickness',
 	'Uniformity of Cell Size',
 	'Uniformity of Cell Shape',
	'Marginal Adhesion',
 	'Single Epithelial Cell Size',
	'Bare Nuclei',
 	'Bland Chromatin',
 	'Normal Nucleoli',
 	'Mitoses',
	'Class'
    # Class 2 -> benign tumor
    # Class 4 -> malignant tumor
]

for i in range(1):

    rand.seed()
    feature = rand.sample(range(1, 10), 2)
    feature1 = feature[0]
    feature2 = feature[1]

    X = np.genfromtxt("../data/breast-cancer-wisconsin.data",delimiter=",",usecols=(feature1,feature2),missing_values='?',filling_values=0)
    y = np.genfromtxt("../data/breast-cancer-wisconsin.data",delimiter=",",usecols=10)


    # we create an instance of SVM and fit out data. We do not scale our
    # data since we want to plot the support vectors
    C = 1.0  # SVM regularization parameter
    models = (svm.SVC(kernel='linear', C=C),
              svm.LinearSVC(C=C),
              svm.SVC(kernel='rbf', gamma=0.7, C=C),
              svm.SVC(kernel='poly', degree=3, C=C))
    models = (clf.fit(X, y) for clf in models)

    # title for the plots
    titles = ('SVC with linear kernel',
              'LinearSVC (linear kernel)',
              'SVC with RBF kernel',
              'SVC with polynomial (degree 3) kernel')

    # Set-up 2x2 grid for plotting.
    fig, sub = plt.subplots(2, 2)
    plt.subplots_adjust(wspace=0.4, hspace=0.4)

    X0, X1 = X[:, 0], X[:, 1]
    xx, yy = make_meshgrid(X0, X1)

    for clf, title, ax in zip(models, titles, sub.flatten()):
        im = plot_contours(ax, clf, xx, yy,
                      cmap=plt.cm.coolwarm, alpha=0.8)
        ax.scatter(X0, X1, c=y, cmap=plt.cm.coolwarm, s=20, edgecolors='k')
        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xlabel(features[feature1])
        ax.set_ylabel(features[feature2])
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(title)

    fig.colorbar(im)
    plt.show()