def test_shared_embedding_column_with_non_sequence_categorical(self):
"""Tests that error is raised for non-sequence shared embedding column."""
vocabulary_size = 3
sparse_input_a = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
sparse_input_b = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
categorical_column_b = fc.categorical_column_with_identity(
key='bbb', num_buckets=vocabulary_size)
shared_embedding_columns = fc.shared_embedding_columns(
[categorical_column_a, categorical_column_b], dimension=2)
with self.assertRaisesRegexp(
ValueError,
r'In embedding_column: aaa_shared_embedding\. categorical_column must '
r'be of type _SequenceCategoricalColumn to use sequence_input_layer\.'):
_, _ = sfc.sequence_input_layer(
features={
'aaa': sparse_input_a,
'bbb': sparse_input_b
},
feature_columns=shared_embedding_columns)
def sequence_categorical_column_with_identity(key,
num_buckets,
default_value=None):
return _SequenceCategoricalColumn(
fc.categorical_column_with_identity(key=key,
num_buckets=num_buckets,
default_value=default_value))
def testWarmStart_SparseColumnIntegerized(self):
# Create feature column.
sc_int = fc.categorical_column_with_identity("sc_int", num_buckets=10)
# Save checkpoint from which to warm-start.
_, prev_int_val = self._create_prev_run_var(
"linear_model/sc_int/weights", shape=[10, 1], initializer=ones())
# Verify we initialized the values correctly.
self.assertAllEqual(np.ones([10, 1]), prev_int_val)
partitioner = lambda shape, dtype: [1] * len(shape)
# New graph, new session WITHOUT warm-starting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model([sc_int], partitioner)
sess.run(variables.global_variables_initializer())
# Without warm-starting, the weights should be initialized using default
# initializer (which is init_ops.zeros_initializer).
self._assert_cols_to_vars(cols_to_vars, {sc_int: [np.zeros([10, 1])]},
sess)
# New graph, new session with warm-starting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model([sc_int], partitioner)
ws_util._warm_start(
ws_util.WarmStartSettings(
self.get_temp_dir(), vars_to_warm_start=".*sc_int.*"))
sess.run(variables.global_variables_initializer())
# Verify weights were correctly warm-started.
self._assert_cols_to_vars(cols_to_vars, {sc_int: [prev_int_val]}, sess)
def testWarmStart_SparseColumnIntegerized(self):
# Create feature column.
sc_int = fc.categorical_column_with_identity("sc_int", num_buckets=10)
# Save checkpoint from which to warm-start.
_, prev_int_val = self._create_prev_run_var(
"linear_model/sc_int/weights", shape=[10, 1], initializer=ones())
# Verify we initialized the values correctly.
self.assertAllEqual(np.ones([10, 1]), prev_int_val)
partitioner = lambda shape, dtype: [1] * len(shape)
# New graph, new session WITHOUT warmstarting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model([sc_int], partitioner)
sess.run(variables.global_variables_initializer())
# Without warmstarting, the weights should be initialized using default
# initializer (which is init_ops.zeros_initializer).
self._assert_cols_to_vars(cols_to_vars, {sc_int: [np.zeros([10, 1])]},
sess)
# New graph, new session with warmstarting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model([sc_int], partitioner)
ws_util._warmstart(ws_util._WarmStartSettings(
self.get_temp_dir(),
vars_to_warmstart=".*sc_int.*"))
sess.run(variables.global_variables_initializer())
# Verify weights were correctly warmstarted.
self._assert_cols_to_vars(cols_to_vars, {sc_int: [prev_int_val]}, sess)
def _test_parsed_sequence_example(
self, col_name, col_fn, col_arg, shape, values):
"""Helper function to check that each FeatureColumn parses correctly.
Args:
col_name: string, name to give to the feature column. Should match
the name that the column will parse out of the features dict.
col_fn: function used to create the feature column. For example,
sequence_numeric_column.
col_arg: second arg that the target feature column is expecting.
shape: the expected dense_shape of the feature after parsing into
a SparseTensor.
values: the expected values at index [0, 2, 6] of the feature
after parsing into a SparseTensor.
"""
example = _make_sequence_example()
columns = [
fc.categorical_column_with_identity('int_ctx', num_buckets=100),
fc.numeric_column('float_ctx'),
col_fn(col_name, col_arg)
]
context, seq_features = parsing_ops.parse_single_sequence_example(
example.SerializeToString(),
context_features=fc.make_parse_example_spec(columns[:2]),
sequence_features=fc.make_parse_example_spec(columns[2:]))
with self.cached_session() as sess:
ctx_result, seq_result = sess.run([context, seq_features])
self.assertEqual(list(seq_result[col_name].dense_shape), shape)
self.assertEqual(
list(seq_result[col_name].values[[0, 2, 6]]), values)
self.assertEqual(list(ctx_result['int_ctx'].dense_shape), [1])
self.assertEqual(ctx_result['int_ctx'].values[0], 5)
self.assertEqual(list(ctx_result['float_ctx'].shape), [1])
self.assertAlmostEqual(ctx_result['float_ctx'][0], 123.6, places=1)
def sequence_categorical_column_with_identity(
key, num_buckets, default_value=None):
return _SequenceCategoricalColumn(
fc.categorical_column_with_identity(
key=key,
num_buckets=num_buckets,
default_value=default_value))
def _build_feature_columns(self):
col = fc.categorical_column_with_identity(
'int_ctx', num_buckets=100)
ctx_cols = [
fc.embedding_column(col, dimension=10),
fc.numeric_column('float_ctx')]
identity_col = sfc.sequence_categorical_column_with_identity(
'int_list', num_buckets=10)
bucket_col = sfc.sequence_categorical_column_with_hash_bucket(
'bytes_list', hash_bucket_size=100)
seq_cols = [
fc.embedding_column(identity_col, dimension=10),
fc.embedding_column(bucket_col, dimension=20)]
return ctx_cols, seq_cols
def sequence_categorical_column_with_identity(
key, num_buckets, default_value=None):
"""Returns a feature column that represents sequences of integers.
Pass this to `embedding_column` or `indicator_column` to convert sequence
categorical data into dense representation for input to sequence NN, such as
RNN.
Example:
```python
watches = sequence_categorical_column_with_identity(
'watches', num_buckets=1000)
watches_embedding = embedding_column(watches, dimension=10)
columns = [watches_embedding]
features = tf.parse_example(..., features=make_parse_example_spec(columns))
input_layer, sequence_length = sequence_input_layer(features, columns)
rnn_cell = tf.nn.rnn_cell.BasicRNNCell(hidden_size)
outputs, state = tf.nn.dynamic_rnn(
rnn_cell, inputs=input_layer, sequence_length=sequence_length)
```
Args:
key: A unique string identifying the input feature.
num_buckets: Range of inputs. Namely, inputs are expected to be in the
range `[0, num_buckets)`.
default_value: If `None`, this column's graph operations will fail for
out-of-range inputs. Otherwise, this value must be in the range
`[0, num_buckets)`, and will replace out-of-range inputs.
Returns:
A `_SequenceCategoricalColumn`.
Raises:
ValueError: if `num_buckets` is less than one.
ValueError: if `default_value` is not in range `[0, num_buckets)`.
"""
return fc_old._SequenceCategoricalColumn(
fc_old.categorical_column_with_identity(
key=key,
num_buckets=num_buckets,
default_value=default_value))
def sequence_categorical_column_with_identity(
key, num_buckets, default_value=None):
"""Returns a feature column that represents sequences of integers.
Pass this to `embedding_column` or `indicator_column` to convert sequence
categorical data into dense representation for input to sequence NN, such as
RNN.
Example:
```python
watches = sequence_categorical_column_with_identity(
'watches', num_buckets=1000)
watches_embedding = embedding_column(watches, dimension=10)
columns = [watches_embedding]
features = tf.parse_example(..., features=make_parse_example_spec(columns))
input_layer, sequence_length = sequence_input_layer(features, columns)
rnn_cell = tf.nn.rnn_cell.BasicRNNCell(hidden_size)
outputs, state = tf.nn.dynamic_rnn(
rnn_cell, inputs=input_layer, sequence_length=sequence_length)
```
Args:
key: A unique string identifying the input feature.
num_buckets: Range of inputs. Namely, inputs are expected to be in the
range `[0, num_buckets)`.
default_value: If `None`, this column's graph operations will fail for
out-of-range inputs. Otherwise, this value must be in the range
`[0, num_buckets)`, and will replace out-of-range inputs.
Returns:
A `_SequenceCategoricalColumn`.
Raises:
ValueError: if `num_buckets` is less than one.
ValueError: if `default_value` is not in range `[0, num_buckets)`.
"""
return fc._SequenceCategoricalColumn(
fc.categorical_column_with_identity(
key=key,
num_buckets=num_buckets,
default_value=default_value))
def test_indicator_column_with_non_sequence_categorical(self):
"""Tests that error is raised for non-sequence categorical column."""
vocabulary_size = 3
sparse_input = sparse_tensor.SparseTensorValue(
# example 0, ids [2]
# example 1, ids [0, 1]
indices=((0, 0), (1, 0), (1, 1)),
values=(2, 0, 1),
dense_shape=(2, 2))
categorical_column_a = fc.categorical_column_with_identity(
key='aaa', num_buckets=vocabulary_size)
indicator_column_a = fc.indicator_column(categorical_column_a)
with self.assertRaisesRegexp(
ValueError,
r'In indicator_column: aaa_indicator\. categorical_column must be of '
r'type _SequenceCategoricalColumn to use sequence_input_layer\.'):
_, _ = sfc.sequence_input_layer(
features={'aaa': sparse_input},
feature_columns=[indicator_column_a])
def testWarmStart_MultipleCols(self):
# Create vocab for sparse column "sc_vocab".
vocab_path = self._write_vocab(["apple", "banana", "guava", "orange"],
"vocab")
# Create feature columns.
sc_int = fc.categorical_column_with_identity("sc_int", num_buckets=10)
sc_hash = fc.categorical_column_with_hash_bucket(
"sc_hash", hash_bucket_size=15)
sc_keys = fc.categorical_column_with_vocabulary_list(
"sc_keys", vocabulary_list=["a", "b", "c", "e"])
sc_vocab = fc.categorical_column_with_vocabulary_file(
"sc_vocab", vocabulary_file=vocab_path, vocabulary_size=4)
real = fc.numeric_column("real")
real_bucket = fc.bucketized_column(real, boundaries=[0., 1., 2., 3.])
cross = fc.crossed_column([sc_keys, sc_vocab], hash_bucket_size=20)
all_linear_cols = [sc_int, sc_hash, sc_keys, sc_vocab, real_bucket, cross]
# Save checkpoint from which to warm-start. Also create a bias variable,
# so we can check that it's also warm-started.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
sc_int_weights = variable_scope.get_variable(
"linear_model/sc_int/weights", shape=[10, 1], initializer=ones())
sc_hash_weights = variable_scope.get_variable(
"linear_model/sc_hash/weights", shape=[15, 1], initializer=norms())
sc_keys_weights = variable_scope.get_variable(
"linear_model/sc_keys/weights", shape=[4, 1], initializer=rand())
sc_vocab_weights = variable_scope.get_variable(
"linear_model/sc_vocab/weights", shape=[4, 1], initializer=ones())
real_bucket_weights = variable_scope.get_variable(
"linear_model/real_bucketized/weights",
shape=[5, 1],
initializer=norms())
cross_weights = variable_scope.get_variable(
"linear_model/sc_keys_X_sc_vocab/weights",
shape=[20, 1],
initializer=rand())
bias = variable_scope.get_variable(
"linear_model/bias_weights",
shape=[1],
initializer=rand())
self._write_checkpoint(sess)
(prev_int_val, prev_hash_val, prev_keys_val, prev_vocab_val,
prev_bucket_val, prev_cross_val, prev_bias_val) = sess.run([
sc_int_weights, sc_hash_weights, sc_keys_weights, sc_vocab_weights,
real_bucket_weights, cross_weights, bias
])
partitioner = lambda shape, dtype: [1] * len(shape)
# New graph, new session WITHOUT warm-starting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model(all_linear_cols, partitioner)
sess.run(variables.global_variables_initializer())
# Without warm-starting, all weights should be initialized using default
# initializer (which is init_ops.zeros_initializer).
self._assert_cols_to_vars(cols_to_vars, {
sc_int: [np.zeros([10, 1])],
sc_hash: [np.zeros([15, 1])],
sc_keys: [np.zeros([4, 1])],
sc_vocab: [np.zeros([4, 1])],
real_bucket: [np.zeros([5, 1])],
cross: [np.zeros([20, 1])],
}, sess)
# New graph, new session with warm-starting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model(all_linear_cols, partitioner)
vocab_info = ws_util.VocabInfo(
new_vocab=sc_vocab.vocabulary_file,
new_vocab_size=sc_vocab.vocabulary_size,
num_oov_buckets=sc_vocab.num_oov_buckets,
old_vocab=vocab_path)
ws_util._warm_start(
ws_util.WarmStartSettings(
self.get_temp_dir(),
var_name_to_vocab_info={
"linear_model/sc_vocab/weights": vocab_info
}))
sess.run(variables.global_variables_initializer())
# Verify weights were correctly warm-started.
self._assert_cols_to_vars(cols_to_vars, {
sc_int: [prev_int_val],
sc_hash: [prev_hash_val],
sc_keys: [prev_keys_val],
sc_vocab: [prev_vocab_val],
real_bucket: [prev_bucket_val],
cross: [prev_cross_val],
"bias": [prev_bias_val],
}, sess)
def testWarmStart_MultipleCols(self):
# Create vocab for sparse column "sc_vocab".
vocab_path = self._write_vocab(["apple", "banana", "guava", "orange"],
"vocab")
# Create feature columns.
sc_int = fc.categorical_column_with_identity("sc_int", num_buckets=10)
sc_hash = fc.categorical_column_with_hash_bucket(
"sc_hash", hash_bucket_size=15)
sc_keys = fc.categorical_column_with_vocabulary_list(
"sc_keys", vocabulary_list=["a", "b", "c", "e"])
sc_vocab = fc.categorical_column_with_vocabulary_file(
"sc_vocab", vocabulary_file=vocab_path, vocabulary_size=4)
real = fc.numeric_column("real")
real_bucket = fc.bucketized_column(real, boundaries=[0., 1., 2., 3.])
cross = fc.crossed_column([sc_keys, sc_vocab], hash_bucket_size=20)
all_linear_cols = [sc_int, sc_hash, sc_keys, sc_vocab, real_bucket, cross]
# Save checkpoint from which to warm-start. Also create a bias variable,
# so we can check that it's also warmstarted.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
sc_int_weights = variable_scope.get_variable(
"linear_model/sc_int/weights", shape=[10, 1], initializer=ones())
sc_hash_weights = variable_scope.get_variable(
"linear_model/sc_hash/weights", shape=[15, 1], initializer=norms())
sc_keys_weights = variable_scope.get_variable(
"linear_model/sc_keys/weights", shape=[4, 1], initializer=rand())
sc_vocab_weights = variable_scope.get_variable(
"linear_model/sc_vocab/weights", shape=[4, 1], initializer=ones())
real_bucket_weights = variable_scope.get_variable(
"linear_model/real_bucketized/weights",
shape=[5, 1],
initializer=norms())
cross_weights = variable_scope.get_variable(
"linear_model/sc_keys_X_sc_vocab/weights",
shape=[20, 1],
initializer=rand())
bias = variable_scope.get_variable(
"linear_model/bias_weights",
shape=[1],
initializer=rand())
self._write_checkpoint(sess)
(prev_int_val, prev_hash_val, prev_keys_val, prev_vocab_val,
prev_bucket_val, prev_cross_val, prev_bias_val) = sess.run([
sc_int_weights, sc_hash_weights, sc_keys_weights, sc_vocab_weights,
real_bucket_weights, cross_weights, bias
])
partitioner = lambda shape, dtype: [1] * len(shape)
# New graph, new session WITHOUT warmstarting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model(all_linear_cols, partitioner)
sess.run(variables.global_variables_initializer())
# Without warmstarting, all weights should be initialized using default
# initializer (which is init_ops.zeros_initializer).
self._assert_cols_to_vars(cols_to_vars, {
sc_int: [np.zeros([10, 1])],
sc_hash: [np.zeros([15, 1])],
sc_keys: [np.zeros([4, 1])],
sc_vocab: [np.zeros([4, 1])],
real_bucket: [np.zeros([5, 1])],
cross: [np.zeros([20, 1])],
}, sess)
# New graph, new session with warmstarting.
with ops.Graph().as_default() as g:
with self.test_session(graph=g) as sess:
cols_to_vars = self._create_linear_model(all_linear_cols, partitioner)
vocab_info = ws_util._VocabInfo(
new_vocab=sc_vocab.vocabulary_file,
new_vocab_size=sc_vocab.vocabulary_size,
num_oov_buckets=sc_vocab.num_oov_buckets,
old_vocab=vocab_path
)
ws_util._warmstart(
ws_util._WarmStartSettings(
self.get_temp_dir(),
var_name_to_vocab_info={
"linear_model/sc_vocab/weights": vocab_info
}))
sess.run(variables.global_variables_initializer())
# Verify weights were correctly warmstarted.
self._assert_cols_to_vars(cols_to_vars, {
sc_int: [prev_int_val],
sc_hash: [prev_hash_val],
sc_keys: [prev_keys_val],
sc_vocab: [prev_vocab_val],
real_bucket: [prev_bucket_val],
cross: [prev_cross_val],
"bias": [prev_bias_val],
}, sess)
