def naive_bayes_with_lda():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
lda = LDA(n_components=100)
train = lda.fit_transform(train, train_target)
test = lda.transform(test)
print lda
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
cf = GaussianNaiveBayes()
cf.fit(train, train_target)
raw_predicts = cf.predict(test)
predict_class = cf.predict_class(raw_predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print "Error rate: %f, accuracy: %f, FPR: %f, TPR: %f" % (er, acc, fpr, tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def naive_bayes_with_lda():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
lda = LDA(n_components=100)
train = lda.fit_transform(train, train_target)
test = lda.transform(test)
print lda
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
cf = GaussianNaiveBayes()
cf.fit(train, train_target)
raw_predicts = cf.predict(test)
predict_class = cf.predict_class(raw_predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (
cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr,
tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def polluted_spambase(T=100):
train, train_target, test, test_target = load_polluted_spambase()
train_target = np.array(map(lambda v: -1.0 if v == 0 else 1.0, train_target))
test_target = np.array(map(lambda v: -1.0 if v == 0 else 1.0, test_target))
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
boost = AdaBoost()
start = timeit.default_timer()
boost.boost(train, train_target, test, test_target, T)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def polluted_spambase(T=100):
train, train_target, test, test_target = load_polluted_spambase()
train_target = np.array(
map(lambda v: -1.0 if v == 0 else 1.0, train_target))
test_target = np.array(map(lambda v: -1.0 if v == 0 else 1.0, test_target))
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
boost = AdaBoost()
start = timeit.default_timer()
boost.boost(train, train_target, test, test_target, T)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
def ridged_logistic_regression():
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
scaler = normalize(train)
scaler.scale_test(test)
train = append_new_column(train, 1.0, 0)
test = append_new_column(test, 1.0, 0)
cf = RidgedLogisticRegression()
cf.fit(train, train_target)
predict_values = cf.predict(test)
predict_classes = cf.convert_to_binary(predict_values)
cm = confusion_matrix(test_target, predict_classes)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr, tpr)
def ski_lasso(alpha, max_iter):
train, train_target, test, test_target = load_polluted_spambase()
print "Train data: %s, Train Label: %s" % (train.shape, train_target.shape)
print "Test data: %s, Test Label: %s" % (test.shape, test_target.shape)
start = timeit.default_timer()
clf = linear_model.Lasso(alpha=alpha, max_iter=max_iter)
print clf
clf.fit(train, train_target)
predicts = clf.predict(test)
predict_class = map(lambda v: 0 if v <= 0.42 else 1, predicts)
cm = confusion_matrix(test_target, predict_class)
print "confusion matrix: TN: %s, FP: %s, FN: %s, TP: %s" % (cm[0, 0], cm[0, 1], cm[1, 0], cm[1, 1])
er, acc, fpr, tpr = confusion_matrix_analysis(cm)
print 'Error rate: %f, accuracy: %f, FPR: %f, TPR: %f' % (er, acc, fpr, tpr)
stop = timeit.default_timer()
print "Total Run Time: %s secs" % (stop - start)
