def train(_):
training_dir = pjoin(FLAGS.training_set, FLAGS.train_subdir)
feature_context = Datasets.get_context(training_dir)
(feature_names, label_names) = feature_context.multispec_feature_groups
training_dataset = Datasets.dict.read_dataset(training_dir)
(feature_train_data,
labels_train_data) = transform_dataset(feature_context, training_dataset)
params = {
'objective': 'multi:softprob',
'verbose': False,
'num_class': len(label_names),
'max_depth': 6,
'nthread': 4,
'silent': 1
}
xg_train = xgb.DMatrix(feature_train_data, label=labels_train_data)
xg_model = xgb.train(params, xg_train, FLAGS.rounds)
model_path = pjoin(FLAGS.local_dir, "iterator.model")
xg_model.save_model(model_path)
output_path = pjoin(FLAGS.training_set, "xgboost/iterator.model")
file_io.copy(model_path, output_path, overwrite=True)
def main(_):
from examples_utils import get_data_dir
import tempfile
config = Trainer.get_default_run_config(tempfile.mkdtemp())
feature_context = Datasets.get_context(get_data_dir("train"))
(feature_names, label_names) = feature_context.multispec_feature_groups
features = [tf.feature_column.numeric_column(x) for x in feature_names]
def split_features_label_fn(spec):
label = spec.pop(label_names[0])
return spec, label
classifier = tf.estimator.LinearClassifier(features, config=config)
Trainer.run(estimator=classifier,
training_data_dir=get_data_dir("train"),
eval_data_dir=get_data_dir("eval"),
split_features_label_fn=split_features_label_fn,
run_config=config)
def test_trainer_shouldnt_crash(self):
context = Datasets.get_context(self.test_resources_dir)
(feature_names, label_names) = context.multispec_feature_groups
feature_columns = [tf.feature_column.numeric_column(name) for name in feature_names]
config = Trainer.get_default_run_config(job_dir=tempfile.mkdtemp())
estimator = tf.estimator.LinearClassifier(feature_columns=feature_columns,
config=config)
def split_features_label_fn(parsed_features):
self.assertEqual(len(label_names), 1)
label = parsed_features.pop(label_names[0])
return parsed_features, label
Trainer.run(estimator,
training_data_dir=self.test_resources_dir,
eval_data_dir=self.test_resources_dir,
split_features_label_fn=split_features_label_fn,
run_config=config)