def test_dense(self):
"""Tests only dense inputs."""
op = sparse_ops._sparse_cross([
constant_op.constant([['batch1-FC1-F1', 'batch1-FC1-F2'],
['batch2-FC1-F1', 'batch2-FC1-F2']],
dtypes.string),
constant_op.constant([['batch1-FC2-F1', 'batch1-FC2-F2'],
['batch2-FC2-F1', 'batch2-FC2-F2']],
dtypes.string),
])
expected_out = self._sparse_tensor(
[[
'batch1-FC1-F1_X_batch1-FC2-F1',
'batch1-FC1-F1_X_batch1-FC2-F2',
'batch1-FC1-F2_X_batch1-FC2-F1',
'batch1-FC1-F2_X_batch1-FC2-F2'
],
[
'batch2-FC1-F1_X_batch2-FC2-F1',
'batch2-FC1-F1_X_batch2-FC2-F2',
'batch2-FC1-F2_X_batch2-FC2-F1',
'batch2-FC1-F2_X_batch2-FC2-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_large_batch(self):
"""Tests with large batch size to force multithreading."""
batch_size = 5000
col1 = []
col2 = []
col3 = []
for b in range(batch_size):
col1.append([
'batch%d-FC1-F1' % b,
'batch%d-FC1-F2' % b,
'batch%d-FC1-F3' % b
])
col2.append(['batch%d-FC2-F1' % b])
col3.append(['batch%d-FC3-F1' % b, 'batch%d-FC3-F2' % b])
op = sparse_ops._sparse_cross([
self._sparse_tensor(col1),
self._sparse_tensor(col2),
self._sparse_tensor(col3)
])
col_out = []
for b in range(batch_size):
col_out.append([
'batch%d-FC1-F1_X_batch%d-FC2-F1_X_batch%d-FC3-F1' % (b, b, b),
'batch%d-FC1-F1_X_batch%d-FC2-F1_X_batch%d-FC3-F2' % (b, b, b),
'batch%d-FC1-F2_X_batch%d-FC2-F1_X_batch%d-FC3-F1' % (b, b, b),
'batch%d-FC1-F2_X_batch%d-FC2-F1_X_batch%d-FC3-F2' % (b, b, b),
'batch%d-FC1-F3_X_batch%d-FC2-F1_X_batch%d-FC3-F1' % (b, b, b),
'batch%d-FC1-F3_X_batch%d-FC2-F1_X_batch%d-FC3-F2' % (b, b, b)
])
expected_out = self._sparse_tensor(col_out)
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def serving_input_receiver_fn():
ads_serialized_examples = array_ops.placeholder(dtype=dtypes.string)
user_serialized_example = array_ops.placeholder(dtype=dtypes.string)
receiver_tensors = {'ads_data': ads_serialized_examples, 'user_data': user_serialized_example}
user_serialized_examples = tf.tile(user_serialized_example, [tf.shape(ads_serialized_examples)[0]])
ads_features = parsing_ops.parse_example(ads_serialized_examples, ads_feature_spec)
user_features = parsing_ops.parse_example(user_serialized_examples, user_feature_spec)
user_features.update(ads_features)
user_features["cross_adcad2feature"] = _sparse_cross([user_features['user_adc_features'], ads_features['ad2_features']])
user_features["cross_adcad2weights"] = _sparse_cross([user_features['user_adc_weights'], ads_features['ad2_weights']])
user_features["cross_adoffad2feature"] = _sparse_cross([user_features['user_adoff_features'], ads_features['ad2_features']])
user_features["cross_adoffad2weights"] = _sparse_cross([user_features['user_adoff_weights'], ads_features['ad2_weights']])
return ServingInputReceiver(user_features, receiver_tensors)
def test_all_columns_empty(self):
"""Tests when all columns are empty.
The crossed tensor should be empty.
"""
op = sparse_ops._sparse_cross([
self._sparse_tensor([]),
self._sparse_tensor([]),
self._sparse_tensor([])
])
with self.test_session() as sess:
self._assert_sparse_tensor_empty(sess.run(op))
def test_one_column_empty(self):
"""Tests when one column is empty.
The crossed tensor should be empty.
"""
op = sparse_ops._sparse_cross([
self._sparse_tensor([['batch1-FC1-F1', 'batch1-FC1-F2']]),
self._sparse_tensor([], 1),
self._sparse_tensor([['batch1-FC3-F1', 'batch1-FC3-F2']])
])
with self.test_session() as sess:
self._assert_sparse_tensor_empty(sess.run(op))
def get_next_batch(self):
(_, records) = self.reader.read_up_to(self.filename_queue, num_records = self.batch_size)
samples = tf.decode_csv(records, record_defaults = self.column_defaults, field_delim = ',')
label = tf.cast(samples[self.column_dict["label"]], dtype = tf.int32)
feature_dict = {}
for (key, value) in self.column_dict.items():
if key == "label" or value < 0 or value >= len(samples):
continue
if key in ["user_adc_features","user_adoff_features","user_news_features","user_tt_features","user_gg_features","user_sea_features","user_dmp0_features","user_dmp1_features","user_dmp2_features","user_inl_features","user_cpd_features","date_wh_features","position_features","ad1_features","ad2_features","ad3_features"]:
feature_dict[key] = tf.string_split(samples[value], delimiter = ';')
if key in ["user_adc_weights","user_adoff_weights","user_news_weights","user_tt_weights","user_gg_weights","user_sea_weights","user_dmp0_weights","user_dmp1_weights","user_dmp2_weights","user_inl_weights","user_cpd_weights","date_wh_weights","position_weights","ad1_weights","ad2_weights","ad3_weights"]:
feature_dict[key] = self.string_to_number(
tf.string_split(samples[value], delimiter = ';'),
dtype = tf.float32)
feature_dict["cross_adcad2feature"] = _sparse_cross([feature_dict['user_adc_features'], feature_dict['ad2_features']])
feature_dict["cross_adcad2weights"] = _sparse_cross([feature_dict['user_adc_weights'], feature_dict['ad2_weights']])
feature_dict["cross_adoffad2feature"] = _sparse_cross([feature_dict['user_adoff_features'], feature_dict['ad2_features']])
feature_dict["cross_adoffad2weights"] = _sparse_cross([feature_dict['user_adoff_weights'], feature_dict['ad2_weights']])
return feature_dict, label
def test_integer_mixed_string_sparse(self):
"""Tests mixed type."""
op = sparse_ops._sparse_cross([
self._sparse_tensor([[11], [333, 55555]]),
self._sparse_tensor([['batch1-FC2-F1'],
['batch2-FC2-F1', 'batch2-FC2-F2']])
])
expected_out = self._sparse_tensor([['11_X_batch1-FC2-F1'],
[
'333_X_batch2-FC2-F1',
'333_X_batch2-FC2-F2',
'55555_X_batch2-FC2-F1',
'55555_X_batch2-FC2-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_integer_sparse_input(self):
"""Tests mixed type sparse and dense inputs."""
op = sparse_ops._sparse_cross([
self._sparse_tensor([[11], [333, 5555]]),
constant_op.constant([['batch1-FC2-F1', 'batch1-FC2-F2'],
['batch2-FC2-F1', 'batch2-FC2-F2']],
dtypes.string),
])
expected_out = self._sparse_tensor(
[['11_X_batch1-FC2-F1', '11_X_batch1-FC2-F2'],
[
'333_X_batch2-FC2-F1', '333_X_batch2-FC2-F2',
'5555_X_batch2-FC2-F1', '5555_X_batch2-FC2-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_simple(self):
"""Tests a simple scenario."""
op = sparse_ops._sparse_cross([
self._sparse_tensor([['batch1-FC1-F1'],
['batch2-FC1-F1', 'batch2-FC1-F2']]),
self._sparse_tensor([['batch1-FC2-F1'],
['batch2-FC2-F1', 'batch2-FC2-F2']])
])
expected_out = self._sparse_tensor(
[['batch1-FC1-F1_X_batch1-FC2-F1'],
[
'batch2-FC1-F1_X_batch2-FC2-F1',
'batch2-FC1-F1_X_batch2-FC2-F2',
'batch2-FC1-F2_X_batch2-FC2-F1',
'batch2-FC1-F2_X_batch2-FC2-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_some_columns_empty(self):
"""Tests when more than one columns are empty.
Cross for the corresponding batch should be empty.
"""
op = sparse_ops._sparse_cross([
self._sparse_tensor([['batch1-FC1-F1', 'batch1-FC1-F2']], 2),
self._sparse_tensor([['batch1-FC2-F1'], ['batch2-FC2-F1']], 2),
self._sparse_tensor([['batch1-FC3-F1', 'batch1-FC3-F2']], 2)
])
expected_out = self._sparse_tensor([[
'batch1-FC1-F1_X_batch1-FC2-F1_X_batch1-FC3-F1',
'batch1-FC1-F1_X_batch1-FC2-F1_X_batch1-FC3-F2',
'batch1-FC1-F2_X_batch1-FC2-F1_X_batch1-FC3-F1',
'batch1-FC1-F2_X_batch1-FC2-F1_X_batch1-FC3-F2'
]], 2)
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_permutation_3x1x2(self):
"""Tests 3x1x2 permutation."""
op = sparse_ops._sparse_cross([
self._sparse_tensor(
[['batch1-FC1-F1', 'batch1-FC1-F2', 'batch1-FC1-F3']]),
self._sparse_tensor([['batch1-FC2-F1']]),
self._sparse_tensor([['batch1-FC3-F1', 'batch1-FC3-F2']])
])
expected_out = self._sparse_tensor([[
'batch1-FC1-F1_X_batch1-FC2-F1_X_batch1-FC3-F1',
'batch1-FC1-F1_X_batch1-FC2-F1_X_batch1-FC3-F2',
'batch1-FC1-F2_X_batch1-FC2-F1_X_batch1-FC3-F1',
'batch1-FC1-F2_X_batch1-FC2-F1_X_batch1-FC3-F2',
'batch1-FC1-F3_X_batch1-FC2-F1_X_batch1-FC3-F1',
'batch1-FC1-F3_X_batch1-FC2-F1_X_batch1-FC3-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))
def test_integer_mixed_string_dense(self):
"""Tests mixed dense inputs."""
op = sparse_ops._sparse_cross([
constant_op.constant([[11, 333], [55555, 999999]], dtypes.int64),
constant_op.constant([['batch1-FC2-F1', 'batch1-FC2-F2'],
['batch2-FC2-F1', 'batch2-FC2-F2']],
dtypes.string),
])
expected_out = self._sparse_tensor([[
'11_X_batch1-FC2-F1', '11_X_batch1-FC2-F2', '333_X_batch1-FC2-F1',
'333_X_batch1-FC2-F2'
],
[
'55555_X_batch2-FC2-F1',
'55555_X_batch2-FC2-F2',
'999999_X_batch2-FC2-F1',
'999999_X_batch2-FC2-F2'
]])
with self.test_session() as sess:
self._assert_sparse_tensor_equals(expected_out, sess.run(op))