############################################################################
# TODO #
# You will change this line to vary C. #
############################################################################
C = 1
############################################################################
svm = LinearSVM_twoclass()
svm.theta = np.zeros((XX.shape[1], ))
svm.train(XX, yy, learning_rate=1e-4, C=C, num_iters=50000, verbose=True)
# classify the training data
y_pred = svm.predict(XX)
print "Accuracy on training data = ", metrics.accuracy_score(yy, y_pred)
# visualize the decision boundary
utils.plot_decision_boundary(scaleX, y, svm, 'x1', 'x2', ['neg', 'pos'])
plt.savefig('fig2.pdf')
############################################################################
# Part 3: Training SVM with a kernel #
# We train an SVM with an RBF kernel on the data set and the plot the #
# learned decision boundary #
############################################################################
# test your Gaussian kernel implementation
for x2 in X_train
]).reshape(X_val.shape[0], X_train.shape[0])
scaleKval = scaler.transform(Kval)
KKval = np.hstack([np.ones((scaleKval.shape[0], 1)), scaleKval])
for Cval in Cvals:
for learning_rate in learning_rates:
for iteration in iterations:
svm = LinearSVM_twoclass()
svm.theta = np.zeros((KK.shape[1], ))
svm.train(KK,
y_train,
learning_rate=learning_rate,
C=Cval,
num_iters=iteration,
verbose=True)
y_pred = svm.predict(KKval)
acc = np.mean(y_pred == y_val)
if acc > best_acc:
best_acc = acc
best_C = Cval
best_sigma = sigma_val
best_iteration = iteration
best_learning_rate = learning_rate
print "For gussian kernel: "
print "the best acc is ", best_acc
print "the best c is ", best_C
print "the best sigma is ", best_sigma
print "the best learning rate is ", best_learning_rate
print "the best iteration is ", best_iteration
'''
K = rbf_kernel(X, X, gamma=1 / (2 * sigma ** 2)).reshape(X.shape[0], X.shape[0])
scaler = preprocessing.StandardScaler().fit(K)
scaleK = scaler.transform(K)
KK = np.vstack([np.ones((scaleK.shape[0],)), scaleK]).T
Kval = rbf_kernel(Xval, X, gamma=1 / (2 * sigma ** 2)).reshape(Xval.shape[0], X.shape[0])
scaleKval = scaler.transform(Kval)
KKval = np.vstack([np.ones((scaleKval.shape[0],)), scaleKval.T]).T
print "Done!"
for C in Cvals:
print "sigma=", sigma, ", C=", C
sys.stdout.flush()
svm.theta = np.zeros((KK.shape[1],))
svm.train(KK, yy, learning_rate=lr, C=C, num_iters=it)
y_train_pred = svm.predict(KK)
acc = metrics.accuracy_score(yy, y_train_pred)
print "C=", C, "sigma=", sigma, "TrainAccuracy:", acc
y_pred = svm.predict(KKval)
acc = metrics.accuracy_score(yyval, y_pred)
print "C=", C, "sigma=", sigma, "ValAccuracy:", acc
if acc > best_acc:
best_acc = acc
best_C = C
best_sigma = sigma
print "Best C is ", best_C, ", best sigma is ", best_sigma
sys.stdout.flush()
svm = LinearSVM_twoclass()
############################################################################
# TODO #
# You will change this line to vary C. #
############################################################################
C = 100.
############################################################################
svm = LinearSVM_twoclass()
svm.theta = np.zeros((XX.shape[1],))
svm.train(XX,yy,learning_rate=1e-4,C=C,num_iters=50000,verbose=True)
# classify the training data
y_pred = svm.predict(XX)
print "Accuracy on training data = ", metrics.accuracy_score(yy,y_pred)
# visualize the decision boundary
utils.plot_decision_boundary(scaleX,y,svm,'x1','x2',['neg','pos'])
plt.savefig('fig2.pdf')
############################################################################
# Part 3: Training SVM with a kernel #
# We train an SVM with an RBF kernel on the data set and the plot the #
# learned decision boundary #
############################################################################
# test your Gaussian kernel implementation
best_C = 0.1 best_lr = 1e-1 best_it = 10000 svm.train(X, yy, learning_rate=1e-1, C=best_C, num_iters=best_it, verbose=True) ############################################################################# # end of your code # ############################################################################# ############################################################################# # what is the accuracy of the best model on the training data itself? # ############################################################################# # 2 lines of code expected y_pred = svm.predict(X) print "Accuracy of model on training data is: ", metrics.accuracy_score(yy, y_pred) ############################################################################# # what is the accuracy of the best model on the test data? # ############################################################################# # 2 lines of code expected yy_test = np.ones(y_test.shape) yy_test[y_test == 0] = -1 test_pred = svm.predict(X_test) print "Accuracy of model on test data is: ", metrics.accuracy_score(yy_test, test_pred)
best_acc = 0
for sigma_val in sigma_vals:
K = np.array([utils.gaussian_kernel(x1,x2,sigma_val) for x1 in X_train for x2 in X_train]).reshape(X_train.shape[0],X_train.shape[0])
scaler = preprocessing.StandardScaler().fit(K)
scaleK = scaler.transform(K)
KK = np.hstack([np.ones((scaleK.shape[0],1)),scaleK])
Kval = np.array([utils.gaussian_kernel(x1,x2,sigma_val) for x1 in X_val for x2 in X_train]).reshape(X_val.shape[0],X_train.shape[0])
scaleKval = scaler.transform(Kval)
KKval = np.hstack([np.ones((scaleKval.shape[0],1)),scaleKval])
for Cval in Cvals:
for learning_rate in learning_rates:
for iteration in iterations:
svm = LinearSVM_twoclass()
svm.theta = np.zeros((KK.shape[1],))
svm.train(KK,y_train,learning_rate=learning_rate,C=Cval,num_iters=iteration,verbose=True)
y_pred = svm.predict(KKval)
acc = np.mean(y_pred == y_val)
if acc > best_acc:
best_acc = acc
best_C=Cval
best_sigma = sigma_val
best_iteration = iteration
best_learning_rate = learning_rate
print "For gussian kernel: "
print "the best acc is ", best_acc
print "the best c is ", best_C
print "the best sigma is ", best_sigma
print "the best learning rate is ", best_learning_rate
print "the best iteration is ", best_iteration
X_train, X_val, y_train, y_val = train_test_split(X, yy, test_size=0.2)
iters = list(np.array(range(1601)) * 5)
trace = {}
for sigma in [10]:
trace[sigma] = []
K = metrics.pairwise.rbf_kernel(X_train, X_train, 1 / sigma ** 2)
scaler = preprocessing.StandardScaler().fit(K)
scaleK = scaler.transform(K)
KK = np.vstack([np.ones((scaleK.shape[0],)), scaleK]).T
Kval = metrics.pairwise.rbf_kernel(X_val, X_train, 1 / sigma ** 2)
scaler_val = preprocessing.StandardScaler().fit(Kval)
scaleKval = scaler_val.transform(Kval)
KKval = np.vstack([np.ones((scaleKval.shape[0],)), scaleKval.T]).T
svm.theta = np.zeros((KK.shape[1],))
trace[sigma].append(metrics.accuracy_score(y_val, svm.predict(KKval)))
for i in range(0, 1600):
svm.train(KK, y_train, learning_rate=0.01, C=2, num_iters=5, verbose=True)
a = metrics.accuracy_score(y_train, svm.predict(KK))
b = metrics.accuracy_score(y_val, svm.predict(KKval))
trace[sigma].append(a)
print ("%.2f,%d,%f,%f\d" % (sigma, i, a, b))
plt.plot(iters, trace[sigma], label="sigma=%.2f" % sigma)
plt.xlabel("iterations")
plt.ylabel("Accurancy on validation set")
plt.legend(bbox_to_anchor=(0.9, 0.9))
plt.savefig("kernal_sigma.pdf")
# svm.train(X,yy,learning_rate=0.1,C=0.1,num_iters=2000,verbose=True)
<<<<<<< HEAD
C = 100.0
=======
C = 1
>>>>>>> 89dd6a53aa0ff700b713b57c5d8d001424557b1d
############################################################################
svm = LinearSVM_twoclass()
svm.theta = np.zeros((XX.shape[1],))
svm.train(XX,yy,learning_rate=1e-4,C=C,num_iters=50000,verbose=False)
# classify the training data
y_pred = svm.predict(XX)
print "Accuracy on training data = ", metrics.accuracy_score(yy,y_pred)
# visualize the decision boundary
utils.plot_decision_boundary(scaleX,y,svm,'x1','x2',['neg','pos'])
plt.savefig('fig2.pdf')
############################################################################
# Part 3: Training SVM with a kernel #
# We train an SVM with an RBF kernel on the data set and the plot the #
# learned decision boundary #
############################################################################
# test your Gaussian kernel implementation