def _train_and_evaluate(estimator, dataset, output_dir):
"""Runs model training and evaluation.
Args:
estimator: (pipeline.Pipeline), Pipeline instance, assemble pre-processing
steps and model training
dataset: (pandas.DataFrame), DataFrame containing training data
output_dir: (string), directory that the trained model will be exported
Returns:
None
"""
x_train, y_train, x_val, y_val = utils.data_train_test_split(dataset)
estimator.fit(x_train, y_train)
# Write model and eval metrics to `output_dir`
model_output_path = os.path.join(output_dir, 'model',
metadata.MODEL_FILE_NAME)
utils.dump_object(estimator, model_output_path)
if metadata.METRIC_FILE_NAME is not None:
# Note: for now, use `cross_val_score` defaults (i.e. 3-fold)
scores = model_selection.cross_val_score(estimator, x_val, y_val, cv=3)
logging.info('Scores: %s', scores)
metric_output_path = os.path.join(output_dir, 'experiment',
metadata.METRIC_FILE_NAME)
utils.dump_object(scores, metric_output_path)
# The default name of the metric is training/hptuning/metric.
# We recommend that you assign a custom name
# The only functional difference is that if you use a custom name,
# you must set the hyperparameterMetricTag value in the
# HyperparameterSpec object in the job request to match your chosen name
hpt = hypertune.HyperTune()
hpt.report_hyperparameter_tuning_metric(
hyperparameter_metric_tag='my_metric_tag',
metric_value=np.mean(scores),
global_step=1000)
def _train_and_evaluate(estimator, dataset, output_dir):
"""Runs model training and evaluation.
Args:
estimator: (pipeline.Pipeline), Pipeline instance, assemble pre-processing
steps and model training
dataset: (pandas.DataFrame), DataFrame containing training data
output_dir: (string), directory that the trained model will be exported
Returns:
None
"""
x_train, y_train, x_val, y_val = utils.data_train_test_split(dataset)
estimator.fit(x_train, y_train)
# Note: for now, use `cross_val_score` defaults (i.e. 3-fold)
scores = model_selection.cross_val_score(estimator, x_val, y_val, cv=3)
logging.info(scores)
# Write model and eval metrics to `output_dir`
model_output_path = os.path.join(
output_dir, 'model', metadata.MODEL_FILE_NAME)
metric_output_path = os.path.join(
output_dir, 'experiment', metadata.METRIC_FILE_NAME)
utils.dump_object(estimator, model_output_path)
utils.dump_object(scores, metric_output_path)
# The default name of the metric is training/hptuning/metric.
# We recommend that you assign a custom name
# The only functional difference is that if you use a custom name,
# you must set the hyperparameterMetricTag value in the
# HyperparameterSpec object in your job request to match your chosen name.
hpt = hypertune.HyperTune()
hpt.report_hyperparameter_tuning_metric(
hyperparameter_metric_tag='my_metric_tag',
metric_value=np.mean(scores),
global_step=1000)
