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_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 SpamClassifier(features, skclassifier, myclassifier):
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
k = 10
if features != 'all':
# Only use the features passed in the features array
new = []
t = utils.transpose_array(data)
for i in xrange(len(t)):
if i in features:
new.append(t[i])
data = utils.transpose_array(t)
all_folds = hw3u.partition_folds(data, k)
kf_train, kf_test = dl.get_train_and_test(all_folds, 0)
y, X = hw4u.split_truth_from_data(kf_train)
y_test, X_test = hw4u.split_truth_from_data(kf_test)
print 'start MyKNN'
knn = hw7u.KNN(classifier=myclassifier)
print 'start scikit'
knnsci = hw7u.KNN(classifier=skclassifier)
print 'start my pred'
y_pred = knn.predict(X_test, X, y)
print 'My Accuracy: {}'.format(accuracy_score(fix_y(y_test), fix_y(y_pred)))
print 'start sk pred'
y_sci = knnsci.predict(X_test, X, y)
print 'SciKit Accuracy: {} My Accuracy: {}'.format(accuracy_score(fix_y(y_test), fix_y(y_sci)), accuracy_score(fix_y(y_test), fix_y(y_pred)))
def q1a():
"""SVM on Spam Data
length train: 4140 length test 461
train acc: 0.806763285024 test acc: 0.819956616052
"""
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
svm_q1(data, svm.SVC(kernel='poly'))
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]
def relief(n):
max_iters = 1
j = 0
i = 1
n_neighbors = [1, 3, 7]
metric = ['minkowski', 'cosine', 'gaussian', 'poly2']
ma = hw7u.Kernel(ktype=metric[j]).compute
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
k = 10
all_folds = hw3u.partition_folds(data, k)
kf_train, kf_test = dl.get_train_and_test(all_folds, 0)
y, X = hw4u.split_truth_from_data(kf_train)
y_test, X_test = hw4u.split_truth_from_data(kf_test)
loops = 0
weights = np.zeros(len(X[0]))
loops += 1
n_features = len(X[0])
n_samples = len(X)
for j in range(n_features): #feature
for i in range(n_samples): # data
closest_same = None
closest_opp = None
for z_i in range(n_samples):
if z_i == i:
continue
diff = (X[z_i][j] - X[i][j]) ** 2
if y[z_i] == y[i]: # same
if closest_same is None or diff < closest_same:
closest_same = diff
else: # opp
if closest_opp is None or diff < closest_opp:
closest_opp = diff
weights[j] += (-closest_same + closest_opp)
if i % 1000 == 0:
print 'feature {} of {}, sample {} of {}'.format(j, n_features, i, n_samples)
print weights
return sorted(zip(weights, range(len(weights))), reverse=True)[:n][1]
def runSpamDensity(_i, j, features='all'):
metric = ['gaussian', 'poly2', 'cosine_similarity', 'gaussian_density']
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
k = 10
all_folds = hw3u.partition_folds(data, k)
kf_train, kf_test = dl.get_train_and_test(all_folds, 0)
y, X = hw4u.split_truth_from_data(kf_train)
y_test, X_test = hw4u.split_truth_from_data(kf_test)
print(len(X))
print(len(X_test))
myclassifier = hw7u.MyKNN(metric=metric[j], density=True)
print 'start MyKNN'
myclassifier.fit(X, y)
#print 'start scikit'
#knnsci = skclassifier.fit(X, y)
print 'start my pred'
y_pred = myclassifier.predict(X_test)
print(y_pred)
#print 'start sk pred'
#y_sci = knnsci.score(X_test)
#print 'SciKit Accuracy: {} My Accuracy: {}'.format(accuracy_score(fix_y(y_test), fix_y(y_sci)), accuracy_score(fix_y(y_test), fix_y(y_pred)))
print '2b: My Accuracy: {}'.format(accuracy_score(fix_y(y_test), fix_y(y_pred)))
def load_and_normalize_spambase():
return utils.load_and_normalize_spam_data()
def analyze_spambase_hw1():
""" HW1 - problem 2 """
spamData = utils.load_and_normalize_spam_data()
mystats.k_folds(spamData, 10)
def q2_kernel_poly():
# c = 1, tol = 1-e2, passes = 1
#
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
svm_q1(data, mysvm.SVC(mysvm.SMO, Kernel('poly')))
def q2():
# c= 1, tol = 1-e2, passes = 1
# train acc: 0.904830917874 test acc: 0.917570498915
data = utils.pandas_to_data(utils.load_and_normalize_spam_data())
svm_q1(data, mysvm.SVC(mysvm.SMO, Kernel('linear')))
