def test_node2vec_wiki_pos(show_figure=False, block_figure_on_end=False):
graph, labels, walks = demo.load_wikipos()
y = labels
x = np.array(range(len(labels)))
model = Node2Vec(
model_name='Node2Vec',
emb_size=16,
window=3,
num_walks=2,
walk_length=10,
p=1.0,
q=1.0,
num_workers=4,
directed=False,
)
model.fit(x, y, walks=walks)
train_idx, test_idx = next(
ShuffleSplit(n_splits=1, test_size=0.1,
random_state=random_seed()).split(x))
x_train, y_train = model.transform(x[train_idx]), y[train_idx]
x_test, y_test = model.transform(x[test_idx]), y[test_idx]
clf = GLM(model_name="GLM_multilogit",
task='multilabel',
link='logit',
loss='multilogit',
random_state=random_seed())
clf.fit(x_train, y_train)
train_f1 = clf.score(x_train, y_train)
test_f1 = clf.score(x_test, y_test)
print("Training weighted-F1-macro = %.4f" % train_f1)
print("Testing weighted-F1-macro = %.4f" % test_f1)
def test_save_load():
print("========== Test save and load models ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
clf = GLM(model_name="iris_glm_softmax",
link='softmax',
loss='softmax',
random_state=random_seed(),
verbose=1)
clf.fit(x_train, y_train)
print("After training:")
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
save_file_path = clf.save()
clf1 = Model.load_model(save_file_path)
print("After save and load:")
train_err1 = 1.0 - clf1.score(x_train, y_train)
test_err1 = 1.0 - clf1.score(x_test, y_test)
print("Training error = %.4f" % train_err1)
print("Testing error = %.4f" % test_err1)
assert abs(train_err - train_err1) < 1e-6
assert abs(test_err - test_err1) < 1e-6
def test_glm_regression():
print("========== Test GLM for regression ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_housing()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
clf = GLM(
model_name="GLM_regression",
task='regression',
link='linear', # link function
loss='quadratic', # loss function
l2_penalty=0.0, # ridge regularization
l1_penalty=0.0, # Lasso regularization
l1_smooth=1E-5, # smoothing for Lasso regularization
l1_method='pseudo_huber', # approximation method for L1-norm
random_state=random_seed())
clf.fit(x_train, y_train)
train_err = -clf.score(x_train, y_train)
test_err = -clf.score(x_test, y_test)
print("Training MSE = %.4f" % train_err)
print("Testing MSE = %.4f" % test_err)
def test_glm_softmax():
print("========== Test GLM for multiclass classification ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
clf = GLM(model_name="GLM_softmax",
link='softmax',
loss='softmax',
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
clf = GLM(model_name="GLM_softmax",
optimizer='sgd',
link='softmax',
loss='softmax',
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_auc():
print("========== Test AUC score ==========")
(x_train, y_train), (x_test, y_test) = demo.load_pima()
model = GLM(model_name="GLM_logit",
l1_penalty=0.0,
l2_penalty=0.0,
random_state=random_seed())
model.fit(x_train, y_train)
train_auc = auc(y_train, model.predict(x_train))
test_auc = auc(y_test, model.predict(x_test))
print("Training AUC = %.4f" % train_auc)
print("Testing AUC = %.4f" % test_auc)
def test_continue_training():
print("========== Test continue training the models ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
num_epochs = 5
clf = GLM(model_name="iris_glm_softmax",
link='softmax',
loss='softmax',
optimizer='sgd',
batch_size=10,
num_epochs=num_epochs,
random_state=random_seed(),
verbose=1)
clf.fit(x_train, y_train)
print("After training for {0:d} epochs".format(num_epochs))
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
clf.num_epochs = 10
print("Set number of epoch to {0:d}, then continue training...".format(
clf.num_epochs))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
save_file_path = clf.save()
clf1 = Model.load_model(save_file_path)
clf1.num_epochs = 15
print("Save, load, set number of epoch to {0:d}, "
"then continue training...".format(clf.num_epochs))
clf1.fit(x_train, y_train)
train_err = 1.0 - clf1.score(x_train, y_train)
test_err = 1.0 - clf1.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_checkpoint():
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
x = np.vstack([x_train, x_test])
y = np.concatenate([y_train, y_test])
filepath = os.path.join(
model_dir(), "male/glm/checkpoint_{epoch:04d}_{val_loss:.6f}.pkl")
checkpoint = ModelCheckpoint(filepath,
mode='min',
monitor='val_loss',
verbose=1,
save_best_only=True)
optz = SGD(learning_rate=0.01)
clf = GLM(model_name="checkpoint_callback",
link='softmax',
loss='softmax',
optimizer=optz,
num_epochs=5,
batch_size=10,
task='classification',
metrics=['loss', 'err'],
callbacks=[checkpoint],
cv=[-1] * x_train.shape[0] + [0] * x_test.shape[0],
random_state=random_seed(),
verbose=1)
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
model_filepath = filepath.format(epoch=5, val_loss=0.968786)
print("Load model at checkpoint: ", model_filepath, ", and predict:")
clf1 = Model.load_model(model_filepath)
train_err = 1.0 - clf1.score(x_train, y_train)
test_err = 1.0 - clf1.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_image_saver_callback():
np.random.seed(random_seed())
(x_train, y_train), (_, _) = demo.load_mnist()
(cifar10_train, _), (_, _) = demo.load_cifar10()
imgsaver1 = ImageSaver(freq=1,
filepath=os.path.join(
model_dir(), "male/callbacks/imagesaver/"
"mnist/mnist_{epoch:04d}.png"),
monitor={
'metrics': 'x_data',
'img_size': (28, 28, 1),
'tile_shape': (10, 10),
'images': x_train[:100].reshape([-1, 28, 28, 1])
})
imgsaver2 = ImageSaver(freq=1,
filepath=os.path.join(
model_dir(), "male/callbacks/imagesaver/"
"cifar10/cifar10_{epoch:04d}.png"),
monitor={
'metrics':
'x_data',
'img_size': (32, 32, 3),
'tile_shape': (10, 10),
'images':
cifar10_train[:100].reshape([-1, 32, 32, 3])
})
optz = SGD(learning_rate=0.001)
clf = GLM(model_name="imagesaver_callback",
link='softmax',
loss='softmax',
optimizer=optz,
num_epochs=4,
batch_size=100,
task='classification',
callbacks=[imgsaver1, imgsaver2],
random_state=random_seed(),
verbose=1)
clf.fit(x_train, y_train)
def test_glm_multilogit():
print("========== Test GLM for multilabel classification ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_yeast()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
clf = GLM(model_name="GLM_multilogit",
task='multilabel',
link='logit',
loss='multilogit',
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_f1 = clf.score(x_train, y_train)
test_f1 = clf.score(x_test, y_test)
print("Training weighted-F1-macro = %.4f" % train_f1)
print("Testing weighted-F1-macro = %.4f" % test_f1)
optz = SGD(learning_rate=0.1, momentum=0.9, nesterov=True)
clf = GLM(model_name="GLM_multilogit",
task='multilabel',
optimizer=optz,
link='logit',
loss='multilogit',
random_state=random_seed(),
verbose=1)
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_f1 = clf.score(x_train, y_train)
test_f1 = clf.score(x_test, y_test)
print("Training weighted-F1-macro = %.4f" % train_f1)
print("Testing weighted-F1-macro = %.4f" % test_f1)
def test_rmsprop_glm():
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
print("Training GLM using RMSProp with default parameters...")
clf = GLM(model_name="rmsprop_glm",
optimizer='rmsprop',
num_epochs=10,
link='softmax',
loss='softmax',
random_state=random_seed())
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
print("Training GLM using RMSProp with customized parameters...")
optz = RMSProp(learning_rate=0.01)
clf = GLM(model_name="rmsprop_glm",
optimizer=optz,
num_epochs=10,
link='softmax',
loss='softmax',
random_state=random_seed())
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_glm_logit():
print("========== Test GLM for binary classification ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_pima()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
clf = GLM(model_name="GLM_logit",
l1_penalty=0.0,
l2_penalty=0.0,
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
clf = GLM(model_name="GLM_logit",
optimizer='sgd',
l1_penalty=0.0,
l2_penalty=0.0,
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
optz = SGD(learning_rate=0.01, momentum=0.9, nesterov=True)
clf = GLM(model_name="GLM_logit",
optimizer=optz,
l1_penalty=0.0,
l2_penalty=0.0,
random_state=random_seed())
print("Use {} optimizer".format(clf.optimizer))
clf.fit(x_train, y_train)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_early_stopping():
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
x = np.vstack([x_train, x_test])
y = np.concatenate([y_train, y_test])
early_stopping = EarlyStopping(monitor='val_err', patience=2, verbose=1)
optz = SGD(learning_rate=0.01)
clf = GLM(model_name="early_stopping_callback",
link='softmax',
loss='softmax',
optimizer=optz,
num_epochs=20,
batch_size=10,
task='classification',
metrics=['loss', 'err'],
callbacks=[early_stopping],
cv=[-1] * x_train.shape[0] + [0] * x_test.shape[0],
random_state=random_seed(),
verbose=1)
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Model has been stopped at epoch #{0:d}".format(clf.epoch))
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
print("Continue training...")
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Model has been stopped at epoch #{0:d}".format(clf.epoch))
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
print("Disable early stopping and continue training to the end...")
clf.callbacks = []
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_glm_save_load(show=False, block_figure_on_end=False):
print("========== Test Save and Load functions for GLM ==========")
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_iris()
print("Number of training samples = {}".format(x_train.shape[0]))
print("Number of testing samples = {}".format(x_test.shape[0]))
x = np.vstack([x_train, x_test])
y = np.concatenate([y_train, y_test])
early_stopping = EarlyStopping(monitor='val_err', patience=5, verbose=1)
filepath = os.path.join(model_dir(),
"male/GLM/iris_{epoch:04d}_{val_err:.6f}.pkl")
checkpoint = ModelCheckpoint(filepath,
mode='min',
monitor='val_err',
verbose=0,
save_best_only=True)
loss_display = Display(title="Learning curves",
dpi='auto',
layout=(3, 1),
freq=1,
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",
},
])
weight_display = Display(title="Filters",
dpi='auto',
layout=(1, 1),
figsize=(6, 15),
freq=1,
show=show,
block_on_end=block_figure_on_end,
monitor=[
{
'metrics': ['weights'],
'title': "Learned weights",
'type': 'img',
'disp_dim': (2, 2),
'tile_shape': (3, 1),
},
])
clf = GLM(
model_name="GLM_softmax_cv",
link='softmax',
loss='softmax',
optimizer='sgd',
num_epochs=4,
batch_size=10,
task='classification',
metrics=['loss', 'err'],
callbacks=[early_stopping, checkpoint, loss_display, weight_display],
cv=[-1] * x_train.shape[0] + [0] * x_test.shape[0],
random_state=random_seed(),
verbose=1)
clf.fit(x, y)
train_err = 1.0 - clf.score(x_train, y_train)
test_err = 1.0 - clf.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
save_file_path = os.path.join(model_dir(), "male/GLM/saved_model.pkl")
clf.save(file_path=save_file_path)
clf1 = Model.load_model(save_file_path)
clf1.num_epochs = 10
clf1.fit(x, y)
train_err = 1.0 - clf1.score(x_train, y_train)
test_err = 1.0 - clf1.score(x_test, y_test)
print("Training error = %.4f" % train_err)
print("Testing error = %.4f" % test_err)
def test_display_callbacks(show=False, block_figure_on_end=False):
np.random.seed(random_seed())
(x_train, y_train), (x_test, y_test) = demo.load_mnist()
idx_train = np.random.permutation(x_train.shape[0])
x_train = x_train[idx_train]
y_train = y_train[idx_train]
print("Number of training samples = {}".format(x_train.shape[0]))
idx_test = np.random.permutation(x_test.shape[0])
x_test = x_test[idx_test]
y_test = y_test[idx_test]
print("Number of testing samples = {}".format(x_test.shape[0]))
x = np.vstack([x_train, x_test])
y = np.concatenate([y_train, y_test])
err_display = Display(title="Error curves",
dpi='auto',
layout=(1, 1),
freq=1,
show=show,
block_on_end=block_figure_on_end,
monitor=[{
'metrics': ['err', 'val_err'],
'type': 'line',
'title': "Learning errors",
'xlabel': "epoch",
'ylabel': "error",
}])
loss_display = Display(
title="Learning curves",
dpi='auto',
layout=(3, 1),
freq=1,
show=show,
block_on_end=block_figure_on_end,
filepath=[
os.path.join(model_dir(), "male/callbacks/"
"display/loss/loss_{epoch:04d}.png"),
os.path.join(model_dir(), "male/callbacks/"
"display/loss/loss_{epoch:04d}.pdf")
],
monitor=[
{
'metrics': ['loss', 'val_loss'],
'type': 'line',
'labels': ["training loss", "validation loss"],
'title': "Learning losses",
'xlabel': "epoch",
'xlabel_params': {
'fontsize': 50
},
'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",
},
])
weight_display = Display(title="Filters",
dpi='auto',
layout=(1, 1),
figsize=(6, 15),
freq=1,
show=show,
block_on_end=block_figure_on_end,
filepath=os.path.join(
model_dir(), "male/callbacks/display/"
"weights/weights_{epoch:04d}.png"),
monitor=[
{
'metrics': ['weights'],
'title': "Learned weights",
'type': 'img',
'tile_shape': (5, 2),
},
])
optz = SGD(learning_rate=0.001)
clf = GLM(model_name="display_callbacks",
link='softmax',
loss='softmax',
optimizer=optz,
num_epochs=20,
batch_size=100,
task='classification',
metrics=['loss', 'err'],
callbacks=[loss_display, weight_display, err_display],
cv=[-1] * x_train.shape[0] + [0] * x_test.shape[0],
random_state=random_seed(),
verbose=1)
clf.fit(x, y)
print("Training error = %.4f" % (1.0 - clf.score(x_train, y_train)))
print("Testing error = %.4f" % (1.0 - clf.score(x_test, y_test)))