def test_trainer(self):
"""
to see if it can produce parameters file and produce figure
"""
self.individual_debug = True
self.init_test('test_trainer')
self.init_trainer_instance()
training_data = DataSet(os.path.join(cbv_const.CBV_SAMPLE_DATASET_DIR,
'training_dataset'))
validation_data = DataSet(os.path.join(cbv_const.CBV_SAMPLE_DATASET_DIR,
'validation_dataset'))
trainer = Trainer(training_data,
validation_data,
seed=20,
n_hidden_nodes=7,
figure_dir=self.working_dir)
trainer.train(iterations=50)
params_file = os.path.join(self.working_dir,
'params.npz')
trainer.export_best_parameters(params_file=params_file)
self.assertTrue(os.path.exists(params_file),
msg='Trainer does not functional properly')
figure_file = os.path.join(self.working_dir,
'07.eps')
self.assertTrue(os.path.exists(figure_file),
msg='Trainer does not functional properly')
def train_combivep_using_cbv_data(training_data_file,
params_out_file=cbv_const.USER_PARAMS_FILE,
random_seed=cbv_const.DFLT_SEED,
n_hidden_nodes=cbv_const.DFLT_HIDDEN_NODES,
figure_dir=cbv_const.DFLT_FIGURE_DIR,
iterations=cbv_const.DFLT_ITERATIONS,
cfg_file=cbv_const.CBV_CFG_FILE,
):
"""
CBV (CombiVEP format) is a parsed format intended to be used by CombiVEP.
CBV has 5 fields:
- CHROM
- POS
- REF
- ALT
- EFFECT(1=deleterious, 0=neutral)
All are tab separated.
Required arguments
- neutral_data_file : list of SNPs with no harmful effect, CBV format
- pathognice_data_file : list of SNPs with deleterious effect, CBV format
"""
#pre-processing dataset
print >> sys.stderr, 'pre-processing dataset, this may take a while (around 750 SNPs/mins). . .'
dm = DataSetManager(cfg_file=cfg_file)
dm.load_data(training_data_file, file_type=cbv_const.FILE_TYPE_CBV)
dm.validate_data()
dm.calculate_scores()
dm.set_shuffle_seed(random_seed)
dm.shuffle_data()
dm.partition_data()
#partition data
training_data = dm.get_training_data()
validation_data = dm.get_validation_data()
#train !!!
print >> sys.stderr, 'Training CombiVEP, please wait (around 500 SNPs/mins) . . .'
trainer = Trainer(training_data,
validation_data,
random_seed,
n_hidden_nodes,
figure_dir)
trainer.train(iterations)
if not os.path.exists(cbv_const.USER_PARAMS_DIR):
os.makedirs(cbv_const.USER_PARAMS_DIR)
trainer.export_best_parameters(params_out_file)
def fast_training(training_data_file,
params_out_file=cbv_const.USER_PARAMS_FILE,
random_seed=cbv_const.DFLT_SEED,
n_hidden_nodes=cbv_const.DFLT_HIDDEN_NODES,
figure_dir=cbv_const.DFLT_FIGURE_DIR,
iterations=cbv_const.DFLT_ITERATIONS,
cfg_file=cbv_const.CBV_CFG_FILE,
):
"""
CBV (CombiVEP format) is a parsed format intended to be used by CombiVEP.
CBV has 5 fields, CHROM, POS, REF, ALT, EFFECT (1=deleterious, 0=neutr).
All are tab separated
Required arguments
- neutr_data_file : list of SNPs with no harmful effect, CBV format
- pathognice_data_file : list of SNPs with deleterious effect, CBV format
"""
#pre-processing dataset
info('pre-processing dataset, this may take a while (around 750 SNPs/mins). . .')
dm = FastDataSetManager(cfg_file=cfg_file)
dm.load_data(training_data_file, file_type=dev_const.FILE_TYPE_SCORES)
dm.set_shuffle_seed(random_seed)
dm.shuffle_data()
dm.partition_data()
#partition data
training_dataset = dm.get_training_data()
validation_dataset = dm.get_validation_data()
#train !!!
info('Training CombiVEP, please wait (around 500 SNPs/mins) . . .')
trainer = Trainer(training_dataset,
validation_dataset,
random_seed,
n_hidden_nodes,
figure_dir)
trainer.train(iterations)
if not os.path.exists(cbv_const.USER_PARAMS_DIR):
os.makedirs(cbv_const.USER_PARAMS_DIR)
trainer.export_best_parameters(params_out_file)
def test_trainer(self):
"""
to see if it can produce parameters file and produce figure
"""
self.individual_debug = True
self.init_test("test_trainer")
self.init_trainer_instance()
training_dataset = DataSet(
os.path.join(combivep_settings.COMBIVEP_CENTRAL_TEST_DATASET_DIR, "training_dataset")
)
validation_dataset = DataSet(
os.path.join(combivep_settings.COMBIVEP_CENTRAL_TEST_DATASET_DIR, "validation_dataset")
)
trainer = Trainer(training_dataset, validation_dataset, seed=20, n_hidden_nodes=7, figure_dir=self.working_dir)
trainer.train(iterations=50)
params_file = os.path.join(self.working_dir, "params.npz")
trainer.export_best_parameters(params_file=params_file)
self.assertTrue(os.path.exists(params_file), msg="Trainer does not functional properly")
figure_file = os.path.join(self.working_dir, "07.eps")
self.assertTrue(os.path.exists(figure_file), msg="Trainer does not functional properly")