def test_read_higgs_data(self):
"""Tests read_higgs_data() function."""
# Error when a wrong data_dir is given.
with self.assertRaisesRegexp(RuntimeError, "Error loading data.*"):
train_data, eval_data = train_higgs.read_higgs_data(
self.data_dir + "non-existing-path",
train_start=0, train_count=15, eval_start=15, eval_count=5)
# Loading fine with the correct data_dir.
train_data, eval_data = train_higgs.read_higgs_data(
self.data_dir,
train_start=0, train_count=15, eval_start=15, eval_count=5)
self.assertEqual((15, 29), train_data.shape)
self.assertEqual((5, 29), eval_data.shape)
def test_read_higgs_data(self):
"""Tests read_higgs_data() function."""
# Error when a wrong data_dir is given.
with self.assertRaisesRegexp(RuntimeError, 'Error loading data.*'):
train_data, eval_data = train_higgs.read_higgs_data(
self.data_dir + 'non-existing-path',
train_start=0, train_count=15, eval_start=15, eval_count=5)
# Loading fine with the correct data_dir.
train_data, eval_data = train_higgs.read_higgs_data(
self.data_dir,
train_start=0, train_count=15, eval_start=15, eval_count=5)
self.assertEqual((15, 29), train_data.shape)
self.assertEqual((5, 29), eval_data.shape)
def test_make_inputs_from_np_arrays(self):
"""Tests make_inputs_from_np_arrays() function."""
train_data, _ = train_higgs.read_higgs_data(self.data_dir,
train_start=0,
train_count=15,
eval_start=15,
eval_count=5)
(input_fn, feature_names,
feature_columns) = train_higgs.make_inputs_from_np_arrays(
features_np=train_data[:, 1:], label_np=train_data[:, 0:1])
# Check feature_names.
self.assertAllEqual(feature_names,
["feature_%02d" % (i + 1) for i in range(28)])
# Check feature columns.
self.assertEqual(28, len(feature_columns))
bucketized_column_type = type(
tf.feature_column.bucketized_column(
tf.feature_column.numeric_column("feature_01"),
boundaries=[0, 1, 2])) # dummy boundaries.
for feature_column in feature_columns:
self.assertIsInstance(feature_column, bucketized_column_type)
# At least 2 boundaries.
self.assertGreaterEqual(len(feature_column.boundaries), 2)
# Tests that the source column names of the bucketized columns match.
self.assertAllEqual(
feature_names, [col.source_column.name for col in feature_columns])
# Check features.
features, labels = input_fn().make_one_shot_iterator().get_next()
with tf.Session() as sess:
features, labels = sess.run((features, labels))
self.assertIsInstance(features, dict)
self.assertAllEqual(feature_names, sorted(features.keys()))
self.assertAllEqual([[15, 1]] * 28,
[features[name].shape for name in feature_names])
# Validate actual values of some features.
self.assertAllClose([
0.869293, 0.907542, 0.798834, 1.344384, 1.105009, 1.595839,
0.409391, 0.933895, 1.405143, 1.176565, 0.945974, 0.739356,
1.384097, 1.383548, 1.343652
], np.squeeze(features[feature_names[0]], 1))
self.assertAllClose([
-0.653674, -0.213641, 1.540659, -0.676015, 1.020974, 0.643109,
-1.038338, -2.653732, 0.567342, 0.534315, 0.720819, -0.481741,
1.409523, -0.307865, 1.474605
], np.squeeze(features[feature_names[10]], 1))
def test_make_inputs_from_np_arrays(self):
"""Tests make_inputs_from_np_arrays() function."""
train_data, _ = train_higgs.read_higgs_data(
self.data_dir,
train_start=0, train_count=15, eval_start=15, eval_count=5)
(input_fn, feature_names,
feature_columns) = train_higgs.make_inputs_from_np_arrays(
features_np=train_data[:, 1:], label_np=train_data[:, 0:1])
# Check feature_names.
self.assertAllEqual(feature_names,
["feature_%02d" % (i+1) for i in range(28)])
# Check feature columns.
self.assertEqual(28, len(feature_columns))
bucketized_column_type = type(
tf.feature_column.bucketized_column(
tf.feature_column.numeric_column("feature_01"),
boundaries=[0, 1, 2])) # dummy boundaries.
for feature_column in feature_columns:
self.assertIsInstance(feature_column, bucketized_column_type)
# At least 2 boundaries.
self.assertGreaterEqual(len(feature_column.boundaries), 2)
# Tests that the source column names of the bucketized columns match.
self.assertAllEqual(feature_names,
[col.source_column.name for col in feature_columns])
# Check features.
features, labels = input_fn().make_one_shot_iterator().get_next()
with tf.Session() as sess:
features, labels = sess.run((features, labels))
self.assertIsInstance(features, dict)
self.assertAllEqual(feature_names, sorted(features.keys()))
self.assertAllEqual([[15, 1]] * 28,
[features[name].shape for name in feature_names])
# Validate actual values of some features.
self.assertAllClose(
[0.869293, 0.907542, 0.798834, 1.344384, 1.105009, 1.595839,
0.409391, 0.933895, 1.405143, 1.176565, 0.945974, 0.739356,
1.384097, 1.383548, 1.343652],
np.squeeze(features[feature_names[0]], 1))
self.assertAllClose(
[-0.653674, -0.213641, 1.540659, -0.676015, 1.020974, 0.643109,
-1.038338, -2.653732, 0.567342, 0.534315, 0.720819, -0.481741,
1.409523, -0.307865, 1.474605],
np.squeeze(features[feature_names[10]], 1))