def test_fixed_effect_lr_lbfgs_model_creation(self):
fe_model = ModelFactory.get_model(
base_training_params=setup_fake_base_training_params(training_stage=constants.FIXED_EFFECT,
model_type=constants.LOGISTIC_REGRESSION),
raw_model_params=self.model_params)
# Assert the type of model
self.assertIsInstance(fe_model, FixedEffectLRModelLBFGS)
def test_random_effect_driver_wiring(self):
re_driver = DriverFactory.get_driver(
base_training_params=setup_fake_base_training_params(
constants.RANDOM_EFFECT),
raw_model_params=self.model_params)
# Assert the type of driver
self.assertIsInstance(re_driver, RandomEffectDriver)
def _get_params(paths, max_iters):
"""
Get the various parameter for model initialization.
:param paths: An AllPaths namedtuple.
:return: Three different parameter sets.
"""
base_training_params = setup_fake_base_training_params(
training_stage=constants.FIXED_EFFECT)
base_training_params.training_output_dir = paths.training_score_path
base_training_params.validation_output_dir = paths.validation_score_path
schema_params = setup_fake_schema_params()
raw_model_params = [
'--' + constants.FEATURE_BAGS, 'global',
'--' + constants.TRAIN_DATA_PATH, paths.training_data_path,
'--' + constants.VALIDATION_DATA_PATH, paths.validation_data_path,
'--' + constants.METADATA_FILE, paths.metadata_file,
'--' + constants.FEATURE_FILE, paths.feature_file,
'--' + constants.NUM_OF_LBFGS_ITERATIONS, f"{max_iters}",
'--' + constants.MODEL_OUTPUT_DIR, paths.model_output_dir,
'--' + constants.COPY_TO_LOCAL, 'False', '--' + constants.BATCH_SIZE,
'16', '--' + constants.L2_REG_WEIGHT, f"{_L2_REG_WEIGHT}",
"--" + constants.REGULARIZE_BIAS, 'True',
"--" + constants.DELAYED_EXIT_IN_SECONDS, '1'
]
return base_training_params, schema_params, raw_model_params
def test_fixed_effect_driver_wiring(self):
fe_driver = DriverFactory.get_driver(
base_training_params=setup_fake_base_training_params(
constants.FIXED_EFFECT),
raw_model_params=self.model_params)
# Assert the type of driver
self.assertIsInstance(fe_driver, FixedEffectDriver)
def get_raw_params(self,
partition_entity='memberId',
num_of_lbfgs_iterations=None):
base_training_params = setup_fake_base_training_params(
training_stage=constants.RANDOM_EFFECT)
base_training_params.batch_size = 2
# flatten the params
raw_params = list(base_training_params.__to_argv__())
model_params = setup_fake_raw_model_params(
training_stage=constants.RANDOM_EFFECT)
raw_params.extend(model_params)
raw_params.extend(['--' + constants.MODEL_IDS_DIR, test_dataset_path])
raw_params.extend([
'--' + constants.FEATURE_FILE,
os.path.join(test_dataset_path, fake_feature_file)
])
raw_params.extend(
['--' + constants.PARTITION_ENTITY, partition_entity])
raw_params.extend(['--' + constants.LABEL, 'response'])
raw_params.extend(['--' + constants.L2_REG_WEIGHT, '0.1'])
if num_of_lbfgs_iterations:
raw_params.extend([
'--' + constants.NUM_OF_LBFGS_ITERATIONS,
f'{num_of_lbfgs_iterations}'
])
return base_training_params, raw_params
def get_raw_params(self,
partition_entity='memberId',
num_of_lbfgs_iterations=None,
intercept_only=False):
base_training_params = setup_fake_base_training_params(
training_stage=constants.RANDOM_EFFECT)
base_training_params.batch_size = 2
# flatten the params
raw_params = list(base_training_params.__to_argv__())
model_params = setup_fake_raw_model_params(
training_stage=constants.RANDOM_EFFECT)
raw_params.extend(model_params)
raw_params.extend(['--' + constants.MODEL_IDS_DIR, test_dataset_path])
raw_params.extend([
'--' + constants.FEATURE_FILE,
os.path.join(test_dataset_path, fake_feature_file)
])
raw_params.extend(
['--' + constants.PARTITION_ENTITY, partition_entity])
raw_params.extend(['--' + constants.LABEL_COLUMN_NAME, 'response'])
raw_params.extend(['--' + constants.L2_REG_WEIGHT, '0.1'])
if num_of_lbfgs_iterations:
raw_params.extend([
'--' + constants.NUM_OF_LBFGS_ITERATIONS,
f'{num_of_lbfgs_iterations}'
])
if intercept_only:
feature_bag_index = raw_params.index(f'--{constants.FEATURE_BAG}')
raw_params.pop(feature_bag_index)
raw_params.pop(feature_bag_index)
assert (f'--{constants.FEATURE_BAG}' not in raw_params)
assert ('per_member' not in raw_params)
return base_training_params, raw_params
def _get_params(paths, max_iters, intercept_only):
"""
Get the various parameter for model initialization.
:param paths: An AllPaths namedtuple.
:param max_iters: maximum l-BFGS iterations.
:param intercept_only: whether the model has intercept only, no other features.
:return: Three different parameter sets.
"""
base_training_params = setup_fake_base_training_params(
training_stage=constants.FIXED_EFFECT)
base_training_params.training_score_dir = paths.training_score_dir
base_training_params.validation_score_dir = paths.validation_score_dir
schema_params = setup_fake_schema_params()
raw_model_params = [
'--' + constants.TRAINING_DATA_DIR, paths.training_data_dir,
'--' + constants.VALIDATION_DATA_DIR, paths.validation_data_dir,
'--' + constants.METADATA_FILE, paths.metadata_file,
'--' + constants.NUM_OF_LBFGS_ITERATIONS, f"{max_iters}",
'--' + constants.OUTPUT_MODEL_DIR, paths.output_model_dir,
'--' + constants.COPY_TO_LOCAL, 'False', '--' + constants.BATCH_SIZE,
'16', '--' + constants.L2_REG_WEIGHT, f"{_L2_REG_WEIGHT}",
"--" + constants.REGULARIZE_BIAS, 'True',
"--" + constants.DELAYED_EXIT_IN_SECONDS, '1'
]
if not intercept_only:
raw_model_params.extend([
'--' + constants.FEATURE_BAG, 'global',
'--' + constants.FEATURE_FILE, paths.feature_file
])
return base_training_params, schema_params, raw_model_params
def test_random_effect_custom_logistic_regression_model_creation(self):
re_model = ModelFactory.get_model(
base_training_params=setup_fake_base_training_params(
training_stage=constants.RANDOM_EFFECT,
model_type=constants.LOGISTIC_REGRESSION),
raw_model_params=self.model_params)
self.assertIsInstance(re_model, RandomEffectLRLBFGSModel)
def setUp(self):
self.task_type = "worker"
self.worker_index = 0
self.num_workers = 5
set_fake_tf_config(task_type=self.task_type,
worker_index=self.worker_index)
self.params = setup_fake_base_training_params()
self.model_params = setup_fake_raw_model_params()
def _get_params(paths, max_iters, intercept_only, has_validation_data_dir=True,
disable_fixed_effect_scoring_after_training=False, has_intercept=True,
model_type=constants.LOGISTIC_REGRESSION,
fixed_effect_variance_mode=None, l2_reg_weight=_L2_REG_WEIGHT):
"""
Get the various parameter for model initialization.
:param paths: An AllPaths namedtuple.
:param max_iters: maximum l-BFGS iterations.
:param intercept_only: whether the model has intercept only, no other features.
:param has_validation_data_dir: whether to use validation data
:param disable_fixed_effect_scoring_after_training: whether to disable scoring
:param has_intercept: whether to include intercept in the model
:param model_type: the type of linear model to use (e.g, "linear_regression", "logistic_regression", etc.)
:param fixed_effect_variance_mode: fixed effect variance mode, support "None", "FULL" and "SIMPLE".
:param l2_reg_weight: l2 regularization weight.
:return: Three different parameter sets.
"""
base_training_params = setup_fake_base_training_params(training_stage=constants.FIXED_EFFECT,
model_type=model_type)
base_training_params.training_score_dir = paths.training_score_dir
base_training_params.validation_score_dir = paths.validation_score_dir
schema_params = setup_fake_schema_params()
raw_model_params = ['--' + constants.TRAINING_DATA_DIR, paths.training_data_dir,
'--' + constants.METADATA_FILE, paths.metadata_file,
'--' + constants.NUM_OF_LBFGS_ITERATIONS, f"{max_iters}",
'--' + constants.OUTPUT_MODEL_DIR, paths.output_model_dir,
'--' + constants.COPY_TO_LOCAL, 'False',
'--' + constants.BATCH_SIZE, '16',
'--' + constants.L2_REG_WEIGHT, f"{l2_reg_weight}",
"--" + constants.REGULARIZE_BIAS, 'True',
"--" + constants.DELAYED_EXIT_IN_SECONDS, '1']
if has_validation_data_dir:
raw_model_params.extend(['--' + constants.VALIDATION_DATA_DIR, paths.validation_data_dir])
if disable_fixed_effect_scoring_after_training:
raw_model_params.extend(['--disable_fixed_effect_scoring_after_training', 'True'])
if not intercept_only:
raw_model_params.extend(['--' + constants.FEATURE_BAG, 'global',
'--' + constants.FEATURE_FILE, paths.feature_file])
if has_intercept:
raw_model_params.extend(['--has_intercept', 'True'])
else:
raw_model_params.extend(['--has_intercept', 'False', '--regularize_bias', 'False'])
if fixed_effect_variance_mode is not None:
raw_model_params.extend(['--fixed_effect_variance_mode', fixed_effect_variance_mode])
return base_training_params, schema_params, raw_model_params
def get_raw_params(self, partition_entity='memberId'):
base_training_params = setup_fake_base_training_params(
training_stage=constants.RANDOM_EFFECT)
base_training_params[constants.BATCH_SIZE] = 2
# flatten the params
raw_params = [
x for key in base_training_params
for x in ['--' + key, str(base_training_params[key])]
]
model_params = setup_fake_raw_model_params(
training_stage=constants.RANDOM_EFFECT)
raw_params.extend(model_params)
raw_params.extend(['--' + constants.MODEL_IDS_DIR, test_dataset_path])
raw_params.extend([
'--' + constants.FEATURE_FILE,
os.path.join(test_dataset_path, fake_feature_file)
])
raw_params.extend(
['--' + constants.PARTITION_ENTITY, partition_entity])
raw_params.extend(['--' + constants.LABEL, 'response'])
raw_params.extend(['--' + constants.L2_REG_WEIGHT, '0.1'])
return base_training_params, raw_params
def _get_params(self):
base_training_params = setup_fake_base_training_params(
training_stage=constants.FIXED_EFFECT)
base_training_params[
constants.TRAINING_OUTPUT_DIR] = self.training_score_dir
base_training_params[
constants.VALIDATION_OUTPUT_DIR] = self.validation_score_dir
schema_params = setup_fake_schema_params()
raw_model_params = [
'--' + constants.FEATURE_BAGS,
'global',
'--' + constants.TRAIN_DATA_PATH,
self.train_data_path,
'--' + constants.VALIDATION_DATA_PATH,
self.validation_data_path,
'--' + constants.METADATA_FILE,
self.metadata_file,
'--' + constants.FEATURE_FILE,
self.feature_file,
'--' + constants.NUM_OF_LBFGS_ITERATIONS,
'1',
'--' + constants.MODEL_OUTPUT_DIR,
self.model_output_dir,
'--' + constants.COPY_TO_LOCAL,
'False',
# Batch size > number samples to make sure
# there is no shuffling of data among batches
'--' + constants.BATCH_SIZE,
'64',
'--' + constants.L2_REG_WEIGHT,
'0.01',
"--" + constants.REGULARIZE_BIAS,
'True'
]
return base_training_params, schema_params, raw_model_params
def setUp(self):
self.params = setup_fake_base_training_params()
self.model_params = setup_fake_raw_model_params()
