def get_model(show_summary=True):
"""
This function defines a Keras model and returns the model as a
Keras object.
"""
# one-hot categorical features
input_features = []
for key, dim in ONE_HOT_FEATURES.items():
input_features.append(
tf.keras.Input(shape=(dim + 1, ), name=transformed_name(key)))
# adding bucketized features
for key, dim in BUCKET_FEATURES.items():
input_features.append(
tf.keras.Input(shape=(dim + 1, ), name=transformed_name(key)))
# adding text input features
input_texts = []
for key in TEXT_FEATURES.keys():
input_texts.append(
tf.keras.Input(shape=(1, ),
name=transformed_name(key),
dtype=tf.string))
# embed text features
MODULE_URL = "https://tfhub.dev/google/universal-sentence-encoder/4"
embed = hub.KerasLayer(MODULE_URL)
reshaped_narrative = tf.reshape(input_texts[0], [-1])
embed_narrative = embed(reshaped_narrative)
deep_ff = tf.keras.layers.Reshape((512, ),
input_shape=(1, 512))(embed_narrative)
deep = tf.keras.layers.Dense(256, activation="relu")(deep_ff)
deep = tf.keras.layers.Dense(64, activation="relu")(deep)
deep = tf.keras.layers.Dense(16, activation="relu")(deep)
wide_ff = tf.keras.layers.concatenate(input_features)
wide = tf.keras.layers.Dense(16, activation="relu")(wide_ff)
both = tf.keras.layers.concatenate([deep, wide])
output = tf.keras.layers.Dense(1, activation="sigmoid")(both)
inputs = input_features + input_texts
keras_model = tf.keras.models.Model(inputs, output)
keras_model.compile(
optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
loss="binary_crossentropy",
metrics=[
tf.keras.metrics.BinaryAccuracy(),
tf.keras.metrics.TruePositives(),
],
)
if show_summary:
keras_model.summary()
return keras_model
def _input_fn(file_pattern, tf_transform_output, batch_size=64):
"""Generates features and label for tuning/training.
Args:
file_pattern: input tfrecord file pattern.
tf_transform_output: A TFTransformOutput.
batch_size: representing the number of consecutive elements of
returned dataset to combine in a single batch
Returns:
A dataset that contains (features, indices) tuple where features
is a dictionary of Tensors, and indices is a single Tensor of
label indices.
"""
transformed_feature_spec = (
tf_transform_output.transformed_feature_spec().copy())
dataset = tf.data.experimental.make_batched_features_dataset(
file_pattern=file_pattern,
batch_size=batch_size,
features=transformed_feature_spec,
reader=_gzip_reader_fn,
label_key=transformed_name(LABEL_KEY),
)
return dataset
def serve_tf_examples_fn(serialized_tf_examples):
"""Returns the output to be used in the serving signature."""
feature_spec = tf_transform_output.raw_feature_spec()
feature_spec.pop(LABEL_KEY)
parsed_features = tf.io.parse_example(serialized_tf_examples, feature_spec)
transformed_features = model.tft_layer(parsed_features)
transformed_features.pop(transformed_name(LABEL_KEY))
outputs = model(transformed_features)
return {'outputs': outputs}