def train():
#train_data_names = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
train_data_names = ['p10a','p011','p013']
valid_data = ['p09b','p023','p035','p038']
test_data = ['p09a','p033']
train_reader = ICHISeqDataReader(train_data_names)
#get data divided on sequences with respect to labels
train_set_x, train_set_y = train_reader.read_all_for_second_hmm()
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all_for_second_hmm()
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all_for_second_hmm()
datasets = [(train_set_x, train_set_y), (valid_set_x, valid_set_y),
(test_set_x, test_set_y)]
debug_file.write('data is got')
rank = 1
base = pow(10, rank) + 1
n_visible_labels = pow(base, 3)
trained_HMM = HMM_second(n_visible=n_visible_labels,
train_set=(train_set_x, train_set_y),
train_patient_list = train_data_names)
gc.collect()
debug_file.write('Hmm created')
debug_file.write('Start validation')
validation(HMM = trained_HMM,
patient_list = valid_data,
valid_set = (valid_set_x, valid_set_y))
def train_all_data():
# train_data_names = ['p10a','p011','p013','p014','p020','p022','p040','p045','p048']
train_data_names = ["p10a"]
valid_data = ["p09b", "p023", "p035", "p038"]
# valid_data=['p10a']
test_data = ["p09a", "p033"]
n_train_patients = len(train_data_names)
n_valid_patients = len(valid_data)
n_test_patients = len(test_data)
rank = 1
start_base = 5
base = pow(start_base, rank) + 1
train_reader = ICHISeqDataReader(train_data_names)
# get data divided on sequences with respect to labels
train_set_x, train_set_y = train_reader.read_all_for_second_hmm(rank=rank, start_base=start_base)
valid_reader = ICHISeqDataReader(valid_data)
valid_set_x, valid_set_y = valid_reader.read_all_for_second_hmm(rank=rank, start_base=start_base)
test_reader = ICHISeqDataReader(test_data)
test_set_x, test_set_y = test_reader.read_all_for_second_hmm(rank=rank, start_base=start_base)
print("data is got")
n_visible_labels = pow(base, 3)
n_hidden = 7
window_size = 1
new_train_set_x, new_train_set_y = change_data_for_ws(
dataset=(train_set_x, train_set_y),
window_size=window_size,
base_for_labels=n_visible_labels,
n_patients=n_train_patients,
)
new_valid_set_x, new_valid_set_y = change_data_for_ws(
dataset=(valid_set_x, valid_set_y),
window_size=window_size,
base_for_labels=n_visible_labels,
n_patients=n_valid_patients,
)
new_test_set_x, new_test_set_y = change_data_for_ws(
dataset=(test_set_x, test_set_y),
window_size=window_size,
base_for_labels=n_visible_labels,
n_patients=n_test_patients,
)
trained_HMM = create_hmm_for_all_data(
n_hidden=n_hidden,
n_visible=pow(n_visible_labels, window_size),
train_set=(new_train_set_x, new_train_set_y),
n_patients=n_train_patients,
window_size=window_size,
)
gc.collect()
print("Hmm created")
get_error_on_model(
model=trained_HMM, n_patients=n_valid_patients, test_set=(new_valid_set_x, new_valid_set_y), window_size=1
)
