def q4(argv=None):
dataset, method_name, k, latex = wrapper_args(
argv, 'q4',
['Digits'],
['MyLogisticRegGen', 'LogisticRegression'])
Digits_X, Digits_y = prepare_digits(want_noise=False)
default_order = [
('MyLogisticRegGen', 'Digits'),
('LogisticRegression', 'Digits')
]
methods = {
('MyLogisticRegGen', 'Digits'):
(MyLogisticRegGen(verbose=False), Digits_X, Digits_y),
('LogisticRegression', 'Digits'):
(LogisticRegression(), Digits_X, Digits_y)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, latex=latex)
def q3(argv=None):
dataset, method_name, k, latex = wrapper_args(
argv, 'q3', ['Boston50', 'Boston75', 'Digits'])
x_boston, y_boston = load_dataset(load_boston)
x_digits, y_digits = prepare_digits(True)
x_boston_50, y_boston_50 = percentileAssignment(50, x_boston, y_boston)
x_boston_75, y_boston_75 = percentileAssignment(75, x_boston, y_boston)
default_order = [('MultiGaussClassify_WithFullMatrix', 'Boston50'),
('MultiGaussClassify_WithFullMatrix', 'Boston75'),
('MultiGaussClassify_WithFullMatrix', 'Digits'),
('MultiGaussClassify_WithDiagonal', 'Boston50'),
('MultiGaussClassify_WithDiagonal', 'Boston75'),
('MultiGaussClassify_WithDiagonal', 'Digits'),
('LogisticRegression', 'Boston50'),
('LogisticRegression', 'Boston75'),
('LogisticRegression', 'Digits')]
methods = {
('MultiGaussClassify_WithFullMatrix', 'Boston50'):
(MultiGaussClassify(len(np.unique(y_boston_50)),
x_boston_50.shape[1]), x_boston_50, y_boston_50),
('MultiGaussClassify_WithFullMatrix', 'Boston75'):
(MultiGaussClassify(len(np.unique(y_boston_75)),
x_boston_50.shape[1]), x_boston_75, y_boston_75),
('MultiGaussClassify_WithFullMatrix', 'Digits'):
(MultiGaussClassify(len(np.unique(y_digits)),
x_digits.shape[1]), x_digits, y_digits),
('MultiGaussClassify_WithDiagonal', 'Boston50'):
(MultiGaussClassify(len(np.unique(y_boston_50)), x_boston_50.shape[1],
True), x_boston_50, y_boston_50),
('MultiGaussClassify_WithDiagonal', 'Boston75'):
(MultiGaussClassify(len(np.unique(y_boston_75)), x_boston_50.shape[1],
True), x_boston_75, y_boston_75),
('MultiGaussClassify_WithDiagonal', 'Digits'):
(MultiGaussClassify(len(np.unique(y_digits)), x_digits.shape[1],
True), x_digits, y_digits),
('LogisticRegression', 'Boston50'): (LogisticRegression(), x_boston_50,
y_boston_50),
('LogisticRegression', 'Boston75'): (LogisticRegression(), x_boston_75,
y_boston_75),
('LogisticRegression', 'Digits'): (LogisticRegression(), x_digits,
y_digits)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, True)
def q3ii(argv=None):
dataset, method_name, k, pi, latex = wrapper_args(
argv, 'q3ii', ['Boston50', 'Boston75', 'Digits'], include_pi=True)
x_boston, y_boston = load_dataset(load_boston)
x_digits, y_digits = load_dataset(load_digits)
x_boston_50, y_boston_50 = percentileAssignment(50, x_boston, y_boston)
x_boston_75, y_boston_75 = percentileAssignment(75, x_boston, y_boston)
default_order = [('LinearSVC', 'Boston50'), ('LinearSVC', 'Boston75'),
('LinearSVC', 'Digits'), ('SVC', 'Boston50'),
('SVC', 'Boston75'), ('SVC', 'Digits'),
('LogisticRegression', 'Boston50'),
('LogisticRegression', 'Boston75'),
('LogisticRegression', 'Digits')]
methods = {
('LinearSVC', 'Boston50'):
(LinearSVC(max_iter=2000), x_boston_50, y_boston_50),
('LinearSVC', 'Boston75'): (LinearSVC(max_iter=2000), x_boston_75,
y_boston_75),
('LinearSVC', 'Digits'): (LinearSVC(max_iter=2000), x_digits,
y_digits),
('SVC', 'Boston50'): (SVC(gamma='scale',
C=10), x_boston_50, y_boston_50),
('SVC', 'Boston75'): (SVC(gamma='scale',
C=10), x_boston_75, y_boston_75),
('SVC', 'Digits'): (SVC(gamma='scale', C=10), x_digits, y_digits),
('LogisticRegression', 'Boston50'):
(LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=5000), x_boston_50, y_boston_50),
('LogisticRegression', 'Boston75'):
(LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=5000), x_boston_75, y_boston_75),
('LogisticRegression', 'Digits'):
(LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=5000), x_digits, y_digits)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_train_test(method, X, y, 0.75, k)
report(name, dataset, scores, latex=latex)
def q3i(argv=None):
dataset, method_name, k, latex = wrapper_args(
argv, 'q3i', ['Boston50', 'Boston75', 'Digits'])
Boston50_X, Boston50_y = prepare_boston50()
Boston75_X, Boston75_y = prepare_boston75()
Digits_X, Digits_y = prepare_digits()
default_order = [
('LinearSVC', 'Boston50'),
('LinearSVC', 'Boston75'),
('LinearSVC', 'Digits'),
('SVC', 'Boston50'),
('SVC', 'Boston75'),
('SVC', 'Digits'),
('LogisticRegression', 'Boston50'),
('LogisticRegression', 'Boston75'),
('LogisticRegression', 'Digits')
]
methods = {('LinearSVC', 'Boston50'):
(LinearSVC(), Boston50_X, Boston50_y),
('LinearSVC', 'Boston75'):
(LinearSVC(), Boston75_X, Boston75_y),
('LinearSVC', 'Digits'):
(LinearSVC(), Digits_X, Digits_y),
('SVC', 'Boston50'):
(SVC(), Boston50_X, Boston50_y),
('SVC', 'Boston75'):
(SVC(), Boston75_X, Boston75_y),
('SVC', 'Digits'):
(SVC(), Digits_X, Digits_y),
('LogisticRegression', 'Boston50'):
(LogisticRegression(), Boston50_X, Boston50_y),
('LogisticRegression', 'Boston75'):
(LogisticRegression(), Boston75_X, Boston75_y),
('LogisticRegression', 'Digits'):
(LogisticRegression(), Digits_X, Digits_y)}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, latex=latex)
def q4(argv):
x_digits, y_digits = load_dataset(load_digits)
dataset, method_name, k, latex = wrapper_args(argv, 'q4',
['X1', 'X2', 'X3'])
X1 = rand_proj(x_digits, 32)
X2 = quad_proj(x_digits)
default_order = [
('LinearSVC', 'X1'),
('LinearSVC', 'X2'),
('SVC', 'X1'),
('SVC', 'X2'),
('LogisticRegression', 'X1'),
('LogisticRegression', 'X2'),
]
methods = {
('LinearSVC', 'X1'): (LinearSVC(max_iter=2000), X1, y_digits),
('LinearSVC', 'X2'): (LinearSVC(max_iter=2000), X2, y_digits),
('SVC', 'X1'): (SVC(gamma='scale', C=10), X1, y_digits),
('SVC', 'X2'): (SVC(gamma='scale', C=10), X2, y_digits),
('LogisticRegression', 'X1'):
(LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=5000), X1, y_digits),
('LogisticRegression', 'X2'):
(LogisticRegression(penalty='l2',
solver='lbfgs',
multi_class='multinomial',
max_iter=5000), X2, y_digits)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(name, dataset))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, latex=latex)
def q3(argv=None):
dataset, method_name, k, latex = wrapper_args(
argv, 'q3', ['Boston50', 'Boston75', 'Digits'])
Boston50_X, Boston50_y = prepare_boston50()
Boston75_X, Boston75_y = prepare_boston75()
# Note that prepare_digits adds gaussian noise to the data to
# avoid singlar covariance matrices. For details, see
# datasets.prepare_digits
Digits_X, Digits_y = prepare_digits()
default_order = [
('MultiGaussClassify', 'Boston50'),
('MultiGaussClassify', 'Boston75'),
('MultiGaussClassify', 'Digits'),
('LogisticRegression', 'Boston50'),
('LogisticRegression', 'Boston75'),
('LogisticRegression', 'Digits')
]
methods = {
('MultiGaussClassify', 'Boston50'):
(MultiGaussClassify(), Boston50_X, Boston50_y),
('MultiGaussClassify', 'Boston75'):
(MultiGaussClassify(), Boston75_X, Boston75_y),
('MultiGaussClassify', 'Digits'):
(MultiGaussClassify(linear=False), Digits_X, Digits_y),
('LogisticRegression', 'Boston50'):
(LogisticRegression(), Boston50_X, Boston50_y),
('LogisticRegression', 'Boston75'):
(LogisticRegression(), Boston75_X, Boston75_y),
('LogisticRegression', 'Digits'):
(LogisticRegression(), Digits_X, Digits_y)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, latex=latex)
def q3(argv=None):
dataset, method_name, k, latex = wrapper_args(
argv, 'q3', ['Boston50', 'Boston75'],
['MyFLDA2', 'LogisticRegression'])
Boston50_X, Boston50_y = prepare_boston50()
Boston75_X, Boston75_y = prepare_boston75()
default_order = [('MyFLDA2', 'Boston50'), ('MyFLDA2', 'Boston75'),
('LogisticRegression', 'Boston50'),
('LogisticRegression', 'Boston75')]
# Find the optimal separation for the training set
print('Finding optimal threshold for MyFLDA2 on Boston50 ...')
myflda_boston50 = find_best_myflda2(MyFLDA2, Boston50_X, Boston50_y, k)
print('Finding optimal threshold for MyFLDA2 on Boston75 ...')
myflda_boston75 = find_best_myflda2(MyFLDA2, Boston75_X, Boston75_y, k)
print('Done.')
methods = {
('MyFLDA2', 'Boston50'): (myflda_boston50, Boston50_X, Boston50_y),
('MyFLDA2', 'Boston75'): (myflda_boston75, Boston75_X, Boston75_y),
('LogisticRegression', 'Boston50'):
(LogisticRegression(), Boston50_X, Boston50_y),
('LogisticRegression', 'Boston75'):
(LogisticRegression(), Boston75_X, Boston75_y)
}
if dataset == 'all':
order = default_order
else:
order = [(method_name, dataset)]
for key in order:
name, dataset = key
method, X, y = methods[key]
print('==============')
print('method: {}, dataset: {}'.format(key[0], key[1]))
scores = my_cross_val(method, X, y, k)
report(name, dataset, scores, latex=latex)