[ plotting linear SVM ]
I tried following the example here but i am having trouble applying it when i have 16 features.
lin_svc is trained with those 16 features (i deleted the line to re-train it again from the example). it works and i tried it and also extracted
import numpy as np import matplotlib.pyplot as plt from sklearn import svm #features is an array of 16 #lin_svc variable is available #train is a pandas DF X = train[features].as_matrix() y = train.outcome h = .02 # step size in the mesh # create a mesh to plot in 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, h), np.arange(y_min, y_max, h)) # title for the plots titles = ['SVC with linear kernel'] for i, clf in enumerate([lin_svc]): # 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]. plt.subplot(2, 2, i + 1) plt.subplots_adjust(wspace=0.4, hspace=0.4) Z = clf.predict(X) # Put the result into a color plot Z = Z.reshape(xx.shape) plt.contourf(xx, yy, Z, cmap=plt.cm.Paired, alpha=0.8) # Plot also the training points plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.Paired) plt.xlabel('Sepal length') plt.ylabel('Sepal width') plt.xlim(xx.min(), xx.max()) plt.ylim(yy.min(), yy.max()) plt.xticks(()) plt.yticks(()) plt.title(titles[i]) plt.show()
The error i am getting is:
ValueError Traceback (most recent call last) <ipython-input-8-d52ca252fc3a> in <module>() 24 25 # Put the result into a color plot ---> 26 Z = Z.reshape(xx.shape) 27 plt.contourf(xx, yy, Z, cmap=plt.cm.Paired, alpha=0.8) 28 ValueError: total size of new array must be unchanged
I've encountered this same issue myself. Since you're really interested in plotting Z as a function of xx and yy, you should be passing those to clf.predict() rathan than passing X. Try replacing
Z = clf.predict(X)
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
and the plot should show nicely (assuming no other bugs).
Also you may want to change the title of your question to something like "Plotting 2-D Decision Boundary," since this has nothing to do with SVMs specifically. You'll encounter this kind of issue with any of the sklearn classifiers.