def test_all_params():
learning_rates = [0.0001]
window_sizes = [13]
train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
valid_data = ['p09b','p023','p035','p038']
test_data = ['p09a','p033']
train_reader = ICHISeqDataReader(train_data)
train_set_x, train_set_y = train_reader.read_all()
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all()
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all()
datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),
(test_set_x, test_set_y)]
output_folder=('[%s], [%s], [%s]')%(",".join(train_data), ",".join(valid_data), ",".join(test_data))
for lr in learning_rates:
for ws in window_sizes:
test_params(learning_rate=lr,
n_epochs=1,
window_size = ws,
datasets=datasets,
output_folder=output_folder,
base_folder='regression_plots')
def test_da_params(corruption_level):
learning_rates = [0.001, 0.003, 0.005, 0.007, 0.009, 0.011, 0.013, 0.015]
window_sizes = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
valid_data = ['p09b','p023','p035','p038']
test_data = ['p09a','p033']
train_reader = ICHISeqDataReader(train_data)
train_set, train_labels = train_reader.read_all()
valid_reader = ICHISeqDataReader(valid_data)
valid_set, valid_labels = valid_reader.read_all()
test_reader = ICHISeqDataReader(test_data)
test_set, test_labels = test_reader.read_all()
output_folder=('[%s], [%s], [%s]')%(",".join(train_data), ",".join(valid_data), ",".join(test_data))
for lr in learning_rates:
for ws in window_sizes:
train_dA(learning_rate=lr,
training_epochs=1,
window_size = ws,
corruption_level=corruption_level,
n_hidden=ws*2,
train_set=train_set,
output_folder=output_folder,
base_folder='dA_plots')
def test_all_params():
window_sizes = [13]
train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
valid_data = ['p09b','p023','p035','p038']
test_data = ['p09a','p033']
train_reader = ICHISeqDataReader(train_data)
train_set_x, train_set_y = train_reader.read_all()
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all()
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all()
datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),
(test_set_x, test_set_y)]
output_folder=('[%s], [%s], [%s]')%(",".join(train_data), ",".join(valid_data), ",".join(test_data))
for ws in window_sizes:
test_SdA(datasets=datasets,
output_folder=output_folder,
base_folder='SdA_cg_plots',
window_size=ws,
pretraining_epochs=100,
training_epochs=1000)
def test_sda(sda, test_names, base, window_size=1, algo='viterbi'):
test_reader = ICHISeqDataReader(test_names)
test_set_x, test_set_y = test_reader.read_all()
n_test_patients = len(test_names)
for test_patient in xrange(n_test_patients):
#get data divided on sequences with respect to labels
test_set_x, test_set_y = test_reader.read_next_doc()
test_x_array = test_set_x.get_value()
n_test_times = test_x_array.shape[0] - window_size + 1
test_visible_after_sda = numpy.array([sda.get_da_output(
test_x_array[time: time+window_size]).ravel()
for time in xrange(n_test_times)]).ravel()
new_test_visible, new_test_hidden = change_data_for_one_patient(
hiddens_patient=test_set_y.eval(),
visibles_patient=test_visible_after_sda,
window_size=sda.da_layers_output_size,
base_for_labels=base
)
patient_error = get_error_on_patient(
model=sda.hmmLayer,
visible_set=new_test_visible,
hidden_set=new_test_hidden,
algo=algo
)
print(patient_error, ' error for patient ' + str(test_patient))
gc.collect()
def test_all_params():
window_sizes = [1]
train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
valid_data = ['p09b','p023','p035','p038']
test_data = ['p09a','p033']
train_reader = ICHISeqDataReader(train_data)
train_set_x, train_set_y = train_reader.read_all()
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all()
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all()
datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),
(test_set_x, test_set_y)]
output_folder=('[%s], [%s], [%s]')%(",".join(train_data), ",".join(valid_data), ",".join(test_data))
corruption_levels = [.1, .2]
pretrain_lr=.03
rank = 1
start_base=5
base = pow(start_base, rank) + 1
for ws in window_sizes:
trained_sda = train_SdA(
datasets=datasets,
train_names=train_data,
output_folder=output_folder,
base_folder='SdA_second_hmm_without_window',
window_size=ws,
corruption_levels=corruption_levels,
pretrain_lr=pretrain_lr,
base=base,
pretraining_epochs=15
)
test_sda(sda=trained_sda,
test_names=test_data,
base = base
)
def test_all_params():
window_sizes = [10]
# train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
train_data = ["p10a"]
valid_data = ["p09b", "p023", "p035", "p038"]
test_data = ["p09a", "p033"]
train_reader = ICHISeqDataReader(train_data)
train_set_x, train_set_y = train_reader.read_all()
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all()
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all()
datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y), (test_set_x, test_set_y)]
output_folder = ("[%s], [%s], [%s]") % (",".join(train_data), ",".join(valid_data), ",".join(test_data))
corruption_levels = [0.1, 0.2]
pretrain_lr = 0.03
finetune_lr = 0.03
for ws in window_sizes:
test_SdA(
datasets=datasets,
output_folder=output_folder,
base_folder="SdA_sgd_cg_plots",
window_size=ws,
corruption_levels=corruption_levels,
pretrain_lr=pretrain_lr,
finetune_lr=finetune_lr,
pretraining_epochs=1,
training_epochs=1,
)
def test_da_params(corruption_level):
window_sizes = [13, 30, 50, 75, 100]
train_data = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
train_reader = ICHISeqDataReader(train_data)
train_set, train_labels = train_reader.read_all()
output_folder=('[%s]')%(",".join(train_data))
for ws in window_sizes:
train_dA(training_epochs=1,
window_size = ws,
corruption_level=corruption_level,
n_hidden=ws*2,
dataset=train_set,
output_folder=output_folder,
base_folder='dA_cg_plots')
def test_sda(sda, test_names, rank, start_base, window_size=1, algo='viterbi'):
test_reader = ICHISeqDataReader(test_names)
test_set_x, test_set_y = test_reader.read_all()
n_test_patients = len(test_names)
for test_patient in xrange(n_test_patients):
#get data divided on sequences with respect to labels
test_set_x, test_set_y = test_reader.read_next_doc()
test_set_x = test_set_x.get_value()
test_set_y = test_set_y.eval()
n_test_times = test_set_x.shape[0] - window_size
test_visible_after_sda = numpy.array([sda.get_da_output(
test_set_x[time: time+window_size]).ravel()
for time in xrange(n_test_times)])
new_test_visible = create_labels_after_das(
da_output_matrix=test_visible_after_sda,
rank=rank,
start_base=start_base,
window_size=window_size
)
n_patient_samples = len(test_set_y)
half_window_size = int(window_size/2)
new_test_hidden=test_set_y[half_window_size:n_patient_samples-half_window_size]
patient_error = get_error_on_patient(
model=sda.hmmLayer,
visible_set=new_test_visible,
hidden_set=new_test_hidden,
algo=algo
)
print(patient_error, ' error for patient ' + str(test_patient))
gc.collect()
