def _wide_and_deep_classifier(wide_columns, deep_columns, dnn_hidden_units,
learning_rate):
"""Build a simple keras wide and deep model.
Args:
wide_columns: Feature columns wrapped in indicator_column for wide (linear)
part of the model.
deep_columns: Feature columns for deep part of the model.
dnn_hidden_units: [int], the layer sizes of the hidden DNN.
learning_rate: [float], learning rate of the Adam optimizer.
Returns:
A Wide and Deep Keras model
"""
# Keras needs the feature definitions at compile time.
# TODO(b/139081439): Automate generation of input layers from FeatureColumn.
input_layers = {
colname: tf.keras.layers.Input(name=colname,
shape=(),
dtype=tf.float32)
for colname in features.transformed_names(
features.DENSE_FLOAT_FEATURE_KEYS)
}
input_layers.update({
colname: tf.keras.layers.Input(name=colname, shape=(), dtype='int32')
for colname in features.transformed_names(features.VOCAB_FEATURE_KEYS)
})
input_layers.update({
colname: tf.keras.layers.Input(name=colname, shape=(), dtype='int32')
for colname in features.transformed_names(features.BUCKET_FEATURE_KEYS)
})
input_layers.update({
colname: tf.keras.layers.Input(name=colname, shape=(), dtype='int32')
for colname in features.transformed_names(
features.CATEGORICAL_FEATURE_KEYS)
})
# TODO(b/161952382): Replace with Keras premade models and
# Keras preprocessing layers.
deep = tf.keras.layers.DenseFeatures(deep_columns)(input_layers)
for numnodes in dnn_hidden_units:
deep = tf.keras.layers.Dense(numnodes)(deep)
wide = tf.keras.layers.DenseFeatures(wide_columns)(input_layers)
output = tf.keras.layers.Dense(1, activation='sigmoid')(
tf.keras.layers.concatenate([deep, wide]))
output = tf.squeeze(output, -1)
model = tf.keras.Model(input_layers, output)
model.compile(loss='binary_crossentropy',
optimizer=tf.keras.optimizers.Adam(lr=learning_rate),
metrics=[tf.keras.metrics.BinaryAccuracy()])
model.summary(print_fn=logging.info)
return model
def _build_keras_model(hidden_units, learning_rate):
"""Creates a DNN Keras model for classifying taxi data.
Args:
hidden_units: [int], the layer sizes of the DNN (input layer first).
learning_rate: [float], learning rate of the Adam optimizer.
Returns:
A keras Model.
"""
real_valued_columns = [
tf.feature_column.numeric_column(key, shape=()) for key in
features.transformed_names(features.DENSE_FLOAT_FEATURE_KEYS)
]
categorical_columns = [
tf.feature_column.categorical_column_with_identity( # pylint: disable=g-complex-comprehension
key,
num_buckets=features.VOCAB_SIZE + features.OOV_SIZE,
default_value=0)
for key in features.transformed_names(features.VOCAB_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity( # pylint: disable=g-complex-comprehension
key,
num_buckets=num_buckets,
default_value=0) for key, num_buckets in zip(
features.transformed_names(features.BUCKET_FEATURE_KEYS),
features.BUCKET_FEATURE_BUCKET_COUNT)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity( # pylint: disable=g-complex-comprehension
key,
num_buckets=num_buckets,
default_value=0) for key, num_buckets in zip(
features.transformed_names(features.CATEGORICAL_FEATURE_KEYS),
features.CATEGORICAL_FEATURE_MAX_VALUES)
]
indicator_column = [
tf.feature_column.indicator_column(categorical_column)
for categorical_column in categorical_columns
]
model = _wide_and_deep_classifier(
# TODO(b/140320729) Replace with premade wide_and_deep keras model
wide_columns=indicator_column,
deep_columns=real_valued_columns,
dnn_hidden_units=hidden_units,
learning_rate=learning_rate)
return model
def _build_estimator(config, hidden_units=None, warm_start_from=None):
"""Build an estimator for predicting the tipping behavior of taxi riders.
Args:
config: tf.estimator.RunConfig defining the runtime environment for the
estimator (including model_dir).
hidden_units: [int], the layer sizes of the DNN (input layer first)
warm_start_from: Optional directory to warm start from.
Returns:
A dict of the following:
- estimator: The estimator that will be used for training and eval.
- train_spec: Spec for training.
- eval_spec: Spec for eval.
- eval_input_receiver_fn: Input function for eval.
"""
real_valued_columns = [
tf.feature_column.numeric_column(key, shape=())
for key in features.transformed_names(features.DENSE_FLOAT_FEATURE_KEYS)
]
categorical_columns = []
for key in features.transformed_names(features.VOCAB_FEATURE_KEYS):
categorical_columns.append(
tf.feature_column.categorical_column_with_identity(
key,
num_buckets=features.VOCAB_SIZE + features.OOV_SIZE,
default_value=0))
for key, num_buckets in zip(
features.transformed_names(features.BUCKET_FEATURE_KEYS),
features.BUCKET_FEATURE_BUCKET_COUNT):
categorical_columns.append(
tf.feature_column.categorical_column_with_identity(
key, num_buckets=num_buckets, default_value=0))
for key, num_buckets in zip(
features.transformed_names(features.CATEGORICAL_FEATURE_KEYS),
features.CATEGORICAL_FEATURE_MAX_VALUES):
categorical_columns.append(
tf.feature_column.categorical_column_with_identity(
key, num_buckets=num_buckets, default_value=0))
return tf.estimator.DNNLinearCombinedClassifier(
config=config,
linear_feature_columns=categorical_columns,
dnn_feature_columns=real_valued_columns,
dnn_hidden_units=hidden_units or [100, 70, 50, 25],
warm_start_from=warm_start_from)
def testTransformedNames(self):
names = ["f1", "cf"]
self.assertEqual(["f1_xf", "cf_xf"], features.transformed_names(names))