def test_sgd_visualization_2d(show=False, block_figure_on_end=False):
(x_train, y_train), (_, _) = demo.load_synthetic_2d()
display = Display(freq=10,
dpi='auto',
show=show,
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['predict'],
'title': "Learning losses",
'xlabel': "X1",
'ylabel': "X2",
'grid_size': 10,
'marker_size': 10,
'left': None,
'right': None,
'top': None,
'bottom': None
}]
)
learner = KSGD(lbd=0.0001,
eps=0.001,
gamma=30,
kernel='gaussian',
loss='hinge',
batch_size=1,
callbacks=[display],
avg_weight=False,
random_state=random_seed())
learner.fit(x_train, y_train)
print("Training error = %.4f" % (1 - learner.score(x_train, y_train)))
def test_bank_2d(show=False, block_figure_on_end=False):
print("========== Test BaNK on 2D data ==========")
(x_train, y_train), (_, _) = demo.load_synthetic_2d()
# Being careful at this point
y_train[y_train == -1] = 0
learner = BaNK(gamma=20,
rf_dim=400,
inner_regularization=0.125,
alpha=1.0,
kappa=1.0,
inner_max_loop=1,
max_outer_loop=2,
batch_size=5)
learner.fit(x_train, y_train)
y_train_pred = learner.predict(x_train)
print(np.unique(y_train))
print(np.unique(y_train_pred))
print("Training error = %.4f" %
(1 - metrics.accuracy_score(y_train, y_train_pred)))
visualize_classification_prediction(learner,
x_train,
y_train,
grid_size=50,
show=show,
epoch=0,
marker_size=20,
block_on_end=block_figure_on_end)
def test_svrg_s_visualization_2d(show=False, block_figure_on_end=False):
(x_train, y_train), (_, _) = demo.load_synthetic_2d()
print('num_samples: {}'.format(x_train.shape[0]))
predict_display = Display(
freq=10,
dpi='auto',
show=show,
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['predict'],
'title': "Visualization",
'xlabel': "X1",
'ylabel': "X2",
'grid_size': 100,
'marker_size': 10,
'left': None,
'right': None,
'top': None,
'bottom': None
}]
)
loss_display = Display(
freq=1,
dpi='auto',
show=show,
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['train_loss', 'obj_func'],
'type': 'line',
'title': "Learning losses",
'xlabel': "data points",
'ylabel': "loss",
}]
)
learner = SVRG(
regular_param=0.01,
learning_rate_scale=1.0,
gamma=10,
rf_dim=400,
num_epochs=2,
cache_size=6,
freq_update_full_model=10,
oracle=SVRG.COVERAGE,
core_max=10,
coverage_radius=100.0,
loss_func=SVRG.LOGISTIC,
smooth_hinge_theta=0.5,
smooth_hinge_tau=0.5,
callbacks=[loss_display, predict_display],
metrics=['train_loss', 'obj_func'],
freq_calc_metrics=50,
random_state=random_seed())
learner.fit(x_train, y_train)
y_train_pred = learner.predict(x_train)
print("Training error = %.4f" % (1 - metrics.accuracy_score(y_train, y_train_pred)))
def test_sgd_visualization_2d(block_figure_on_end=False):
(x_train, y_train), (_, _) = demo.load_synthetic_2d()
predict_display = Display(
freq=1,
dpi='auto',
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['predict'],
'title': "Visualization",
'xlabel': "X1",
'ylabel': "X2",
'grid_size': 100,
'marker_size': 10,
'left': None,
'right': None,
'top': None,
'bottom': None
}]
)
display = Display(
freq=1,
dpi='auto',
block_on_end=block_figure_on_end,
monitor=[{'metrics': ['mistake_rate'],
'type': 'line',
'title': "Mistake Rate",
'xlabel': "data points",
'ylabel': "Error",
}]
)
learner = OnlineDualSVRG(
regular_param=0.01,
learning_rate_scale=1.0,
gamma=10,
rf_dim=400,
cache_size=6,
freq_update_full_model=10,
oracle='budget',
core_max=10,
coverage_radius=0.5,
loss_func='hinge',
smooth_hinge_theta=0.5,
smooth_hinge_tau=0.5,
callbacks=[display],
metrics=['mistake_rate'],
random_state=random_seed())
learner.fit(x_train, y_train)
y_train_pred = learner.predict(x_train)
print("Training error = %.4f" % (1 - metrics.accuracy_score(y_train, y_train_pred)))
def test_kmm_syn2d(show=False, block_figure_on_end=False):
print("========== Test KMM on 2D data ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_synthetic_2d()
idx_train, idx_test = next(
iter(
StratifiedShuffleSplit(n_splits=1,
test_size=40,
random_state=random_seed()).split(
x_train, y_train)))
x0 = x_train[idx_train]
y0 = y_train[idx_train]
x1 = x_train[idx_test]
y1 = y_train[idx_test]
x = np.vstack([x0, x1])
y = np.concatenate([y0, y1])
early_stopping = EarlyStopping(monitor='val_loss', patience=2, verbose=1)
filepath = os.path.join(
model_dir(), "male/KMM/syn2d_data_{epoch:04d}_{val_err:.6f}.pkl")
checkpoint = ModelCheckpoint(filepath,
mode='min',
monitor='val_err',
verbose=0,
save_best_only=True)
display = Display(layout=(3, 1),
dpi='auto',
show=show,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['loss', 'val_loss'],
'type': 'line',
'labels': ["training loss", "validation loss"],
'title': "Learning losses",
'xlabel': "epoch",
'ylabel': "loss",
},
{
'metrics': ['err', 'val_err'],
'type': 'line',
'title': "Learning errors",
'xlabel': "epoch",
'ylabel': "error",
},
{
'metrics': ['err'],
'type': 'line',
'labels': ["training error"],
'title': "Learning errors",
'xlabel': "epoch",
'ylabel': "error",
},
])
clf = KMM(model_name="KMM_hinge",
D=10,
lbd=0.0,
gamma=0.5,
mode='batch',
loss='hinge',
num_kernels=4,
batch_size=4,
temperature=0.1,
num_epochs=10,
num_nested_epochs=0,
learning_rate=0.001,
learning_rate_mu=0.0,
learning_rate_gamma=0.001,
learning_rate_alpha=0.001,
metrics=['loss', 'err'],
callbacks=[display, early_stopping, checkpoint],
cv=[-1] * x0.shape[0] + [0] * x1.shape[0],
random_state=random_seed())
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
print("Training error = %.4f" % train_err)
if block_figure_on_end:
# save predictions
y_test_pred = clf.predict(x_test)
x_test[x_test == 0] = 1e-4
dump_svmlight_file(x_test,
y_test_pred,
os.path.join(
data_dir(),
"demo/synthetic_2D_data_test_predict.libsvm"),
zero_based=False)
