def decision_spambase_set_no_libs():
"""
Solution for HW1 prob 1
"""
print('Homework 1 problem 1 - No Libraries - Regression Decision tree')
print('Spambase Dataset')
spam_data = utils.load_and_normalize_spam_data()
test, train = utils.split_test_and_train(spam_data)
print str(len(train)) + " # in training set <--> # in test " + str(len(test))
node = mytree.Node(np.ones(len(train)))
branch_node(node, train, 5, 'is_spam')
#node.show_children_tree()
node.show_children_tree(follow=False)
model = mytree.Tree(node)
model.print_leaves()
print 'Trained model error is : ' + str(model.error())
node.presence = np.ones(len(test))
test_node(node, test, 'is_spam')
test_tree = mytree.Tree(node)
prediction = test_tree.predict_obj()
test_tree.print_leaves_test()
print 'predict sum: ' + str(sum(prediction))
print 'MSE:' + str(test_tree.error_test())
[tp, tn, fp, fn] = mystats.get_performance_stats(test['is_spam'].as_matrix(), prediction)
print 'TP: {}\tFP: {}\nTN: {}\tFN: {}'.format(tp, fp, tn, fn)
print 'Accuracy: ' + str(mystats.compute_accuracy(tp,tn, fp,fn))
print 'MSE: ' + str(mystats.compute_MSE_arrays(prediction, test['is_spam']))
def regression_line_spam_no_libs():
"""
Solution for HW1 prob 2
"""
print('Homework 1 problem 2 - No Libraries - Regression Line')
print('Spam Dataset')
spam_data = utils.load_and_normalize_spam_data()
test, train = utils.split_test_and_train(spam_data)
columns = train.columns[:-1]
Y_fit = mystats.linear_regression_points(train[columns], train['is_spam'])
#print 'Y_fit'
#print Y_fit
#for i in range(0, len(Y_fit)):
# print str(Y_fit[i]) + ' -- ' + str(train['is_spam'][i])
col_MSE = {}
for i, col in enumerate(columns):
col_fit = Y_fit[i] + Y_fit[-1]
col_MSE[col] = mystats.compute_MSE_arrays(col_fit, train['is_spam'])
print col_MSE
RMSE = np.sqrt(col_MSE.values())
average_MSE = utils.average(col_MSE.values())
average_RMSE = utils.average(RMSE)
print 'Average MSE: ' + str(average_MSE)
print 'Average RMSE: ' + str(average_RMSE)
def decision_spambase_set():
"""
Solution for HW1 prob 1
"""
print('Homework 1 problem 1 - Regression Decision tree')
print('Spambase Dataset')
spam_data = utils.load_and_normalize_spam_data()
test, train = utils.split_test_and_train(spam_data)
print str(len(train)) + " # in training set <--> # in test " + str(len(test))
dt = train_decision_tree(train)
predicted = test_decision_tree(dt, test)
#print predicted
#print test['is_spam']
error = mystats.calculate_binary_error(predicted, test['is_spam'])
print 'Error: ' + str(error)
def q_1():
h_test, h_train = utils.load_and_normalize_housing_set()
h_results = []
s_results = []
# h_results.append(dec_or_reg_tree(h_train, h_test, 'MEDV')) # MSE - 568 test- 448
# h_results.append(linear_reg_errors(h_train, h_test, 'MEDV')) # MSE - 27 test -14
# h_results.append(linear_reg_errors(h_train, h_test, 'MEDV', True)) # 24176 - 68289
# h_results.append(linear_gd(h_train, h_test, 'MEDV')) # works but MSE too low? .0022 - .0013
# h_results.append(logistic_gd(h_train, h_test, 'MEDV')) # 1.46e_13 - 1.17e+13
s_test, s_train = utils.split_test_and_train(utils.load_and_normalize_spam_data())
s_results.append(dec_or_reg_tree(s_train, s_test, "is_spam")) # works .845 - .86
s_results.append(linear_reg_errors(s_train, s_test, "is_spam")) # works .8609 - .903
s_results.append(linear_reg_errors(s_train, s_test, "is_spam", True)) # works .8416 - .8543
s_results.append(k_folds_linear_gd(s_train, s_test, "is_spam")) # does not work .6114 - .6114
s_results.append(logistic_gd(s_train, s_test, "is_spam")) # returns perfect... 1- 1
print_results_1(s_results, h_results)
def testLogisticGradient():
""" logistic gradient descent """
df_test, df_train = utils.split_test_and_train(utils.load_and_normalize_spam_data())
Y = 'is_spam'
binary = utils.check_binary(df_train[Y])
model = gd.logistic_gradient(df_train, df_train[Y], .1, max_iterations=5)
#print model
#raw_input()
predict = gd.predict(df_train, model, binary, True)
print predict
error_train = mystats.get_error(predict, df_train[Y], binary)
#raw_input()
predict = gd.predict(df_test, model, binary, True)
print predict
error_test = mystats.get_error(predict, df_test[Y], binary)
print 'error train {} error_test {}'.format(error_train, error_test)
return [error_train, error_test]
