def q2():
models = ['Bernoulli', 'Gaussian', '4-bins', '9-bins']
spamData = hw3.pandas_to_data(hw3.load_and_normalize_spambase())
k = 10
k_folds = hw3.partition_folds(spamData, k)
for model_type in range(4):
print '\nModel: {}'.format(models[model_type])
train_acc_sum = 0
nb_models = []
for ki in range(k - 1):
alpha = .001 if model_type==0 else 0
nb_model = nb.NaiveBayes(model_type, alpha=alpha)
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(k_folds[ki])
nb_model.train(data_rows, truth_rows)
predict = nb_model.predict(data_rows)
print predict
accuracy = hw3.get_accuracy(predict, truth_rows)
train_acc_sum += accuracy
print_output(ki, accuracy)
nb_models.append(nb_model)
nb_combined = nb.NaiveBayes(model_type, alpha=.001)
if model_type < 2:
nb_combined.aggregate_model(nb_models)
else:
nb_combined.aggregate_model3(nb_models)
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(k_folds[k - 1])
test_predict = nb_combined.predict(data_rows)
test_accuracy = hw3.get_accuracy(test_predict, truth_rows)
print_test_output(test_accuracy, float(train_acc_sum)/(k-1))
#print len(k_folds[0])
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(spamData)
def q2_plots():
models = ['Bernoulli', 'Gaussian', '4-bins', '9-bins']
spamData = hw3.pandas_to_data(hw3.load_and_normalize_spambase())
k = 10
num_points = 50
k_folds = hw3.partition_folds(spamData, k)
for model_type in range(4):
roc = ROC.ROC()
print '\nModel: {}'.format(models[model_type])
train_acc_sum = 0
nb_models = []
for ki in [0]:
alpha = .001 if model_type==0 else 0
nb_model = nb.NaiveBayes(model_type, alpha=alpha)
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(k_folds[ki])
nb_model.train(data_rows, truth_rows)
for ti in range(num_points + 2):
theta = ti * 1./(num_points + 1)
predict = nb_model.predict(data_rows, theta)
print predict
accuracy = hw3.get_accuracy(predict, truth_rows)
train_acc_sum += accuracy
roc.add_tp_tn(predict, truth_rows, theta)
#print_plot_output(ki, accuracy, theta)
roc.plot_ROC('/Users/Admin/Dropbox/ML/MachineLearning_CS6140/CS6140_A_MacLeay/Homeworks/roc_{}.pdf'.format(model_type))
roc.print_info()
def test_NaiveBayes():
bayes = nb.NaiveBayes(2)
arr = get_nb_data()
print arr
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(arr)
bayes.train(data_rows, truth_rows)
print bayes.model
return bayes
def test_NaiveBayes_predict():
bayes = nb.NaiveBayes(2)
arr = get_nb_data()
test = get_nb_test_data(5)
print arr
truth_rows, data_rows, data_mus, y_mu = hw3.get_data_and_mus(arr)
bayes.train(data_rows, truth_rows)
print data_mus
print bayes.model
print bayes.predict(test)
