def main(train_ratio=0.9):
options['show_progress'] = False
xs, ys = shuffle_args(*retrieve_data(as_list=True, negative_label=-1.0, positive_label=1.0, insert_bias=False))
xs_train, xs_test = split_with_ratio(xs, train_ratio)
ys_train, ys_test = split_with_ratio(ys, train_ratio)
C = optimal_regularizer(xs_train, ys_train, linear_kernel)
print('best C=%4.1e' % C)
w, b = train_svm(xs_train, ys_train, C, linear_kernel)
stats = {'tp': 0, 'tn': 0, 'fp': 0, 'fn': 0}
for x, y in zip(xs_test, ys_test):
yc = classify(x, w, b)
if int(y) == -1:
key = 'tn' if yc == -1 else 'fp'
stats[key] += 1
if int(y) == 1:
key = 'tp' if yc == 1 else 'fn'
stats[key] += 1
precision = safe_division(stats['tp'], stats['tp'] + stats['fp'])
recall = safe_division(stats['tp'], stats['tp'] + stats['fn'])
f1 = safe_division(2 * precision * recall, precision + recall)
print('precision = %6.2f%%' % (100 * precision))
print('recall = %6.2f%%' % (100 * recall))
print('F1 measure = %6.2f' % f1)
def main(train_ratio=0.9):
options['show_progress'] = False
xs, ys = shuffle_args(*retrieve_data(as_list=True,
negative_label=-1.0,
positive_label=1.0,
insert_bias=False))
xs_train, xs_test = split_with_ratio(xs, train_ratio)
ys_train, ys_test = split_with_ratio(ys, train_ratio)
C = optimal_regularizer(xs_train, ys_train, linear_kernel)
print('best C=%4.1e' % C)
w, b = train_svm(xs_train, ys_train, C, linear_kernel)
stats = {'tp': 0, 'tn': 0, 'fp': 0, 'fn': 0}
for x, y in zip(xs_test, ys_test):
yc = classify(x, w, b)
if int(y) == -1:
key = 'tn' if yc == -1 else 'fp'
stats[key] += 1
if int(y) == 1:
key = 'tp' if yc == 1 else 'fn'
stats[key] += 1
precision = safe_division(stats['tp'], stats['tp'] + stats['fp'])
recall = safe_division(stats['tp'], stats['tp'] + stats['fn'])
f1 = safe_division(2 * precision * recall, precision + recall)
print('precision = %6.2f%%' % (100 * precision))
print('recall = %6.2f%%' % (100 * recall))
print('F1 measure = %6.2f' % f1)
def main(test_fraction):
xs, ys = retrieve_data()
test_size = int(len(xs) * test_fraction)
w = train_perceptron(xs[:-test_size], ys[:-test_size], iters=10000)
# 'tp' — true positive
# 'tn' — true negative
# 'fp' — false positive
# 'fn' — false negative
stats = {'tp': 0, 'tn': 0, 'fp': 0, 'fn': 0}
for x, y in zip(xs[-test_size:], ys[-test_size:]):
yc = classify(w, x)
if y == -1:
key = 'tn' if yc == -1 else 'fp'
stats[key] += 1
if y == 1:
key = 'tp' if yc == 1 else 'fn'
stats[key] += 1
precision = safe_division(stats['tp'], stats['tp'] + stats['fp'])
recall = safe_division(stats['tp'], stats['tp'] + stats['fn'])
f1 = safe_division(2 * precision * recall, precision + recall)
print('precision = %6.2f%%' % (100 * precision))
print('recall = %6.2f%%' % (100 * recall))
print('F1 measure = %6.2f' % f1)
def main(test_fraction):
xs, ys = retrieve_data()
test_size = int(len(xs) * test_fraction)
w = train_perceptron(xs[:-test_size], ys[:-test_size], iters=10000)
# 'tp' — true positive
# 'tn' — true negative
# 'fp' — false positive
# 'fn' — false negative
stats = {'tp': 0, 'tn': 0, 'fp': 0, 'fn': 0}
for x, y in zip(xs[-test_size:], ys[-test_size:]):
yc = classify(w, x)
if y == -1:
key = 'tn' if yc == -1 else 'fp'
stats[key] += 1
if y == 1:
key = 'tp' if yc == 1 else 'fn'
stats[key] += 1
precision = safe_division(stats['tp'], stats['tp'] + stats['fp'])
recall = safe_division(stats['tp'], stats['tp'] + stats['fn'])
f1 = safe_division(2 * precision * recall, precision + recall)
print('precision = %6.2f%%' % (100 * precision))
print('recall = %6.2f%%' % (100 * recall))
print('F1 measure = %6.2f' % f1)
def main():
xs, ys = retrieve_data(as_list=True)
print('debug: data retrieved')
ratio = 0.9
xs_train, xs_test = split_with_ratio(xs, ratio)
ys_train, ys_test = split_with_ratio(ys, ratio)
train = (xs_train, ys_train)
test = (xs_test, ys_test)
C = 1e2
check_kernel(train, test, C, linear_kernel, 'linear')
for i in range(2, 5):
check_kernel(train, test, C, poly_kernel_wrapper(i), 'polynomial %d' % i)
check_kernel(train, test, C, gaussian_kernel_wrapper(1.0), 'gaussian')
def main(test_fraction=0.1):
xs, ys = retrieve_data(as_list=True, negative_label=0)
test_size = int(len(xs) * test_fraction)
train_xs = xs[:-test_size]
train_ys = ys[:-test_size]
C = best_regularization(train_xs, train_ys)
model = svm.LinearSVC(C=C)
model.fit(train_xs, train_ys)
errors = 0
for x, x_pred in zip(list(ys[-test_size:]), list(model.predict(xs[-test_size:]))):
if x != x_pred:
errors += 1
print("error on test set: %6.2f%%" % (100 * errors / test_size))
print("regularization constant is 1e-%d" % round(log(C, 0.1)))
def main(test_fraction=0.1):
xs, ys = retrieve_data(as_list=True, negative_label=0)
test_size = int(len(xs) * test_fraction)
train_xs = xs[:-test_size]
train_ys = ys[:-test_size]
C = best_regularization(train_xs, train_ys)
model = svm.LinearSVC(C=C)
model.fit(train_xs, train_ys)
errors = 0
for x, x_pred in zip(list(ys[-test_size:]),
list(model.predict(xs[-test_size:]))):
if x != x_pred:
errors += 1
print("error on test set: %6.2f%%" % (100 * errors / test_size))
print("regularization constant is 1e-%d" % round(log(C, 0.1)))
