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))
# Plug your model with Tensorflow
return tf.estimator.DNNLinearCombinedClassifier(
config=config,
n_classes=5,
linear_feature_columns=categorical_columns,
dnn_feature_columns=real_valued_columns,
# dnn_hidden_units=hidden_units or [100, 70, 50, 25],
dnn_hidden_units=[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))
def _build_keras_model(
hparams: kerastuner.HyperParameters,
tf_transform_output: tft.TFTransformOutput) -> tf.keras.Model:
"""Creates a Keras WideDeep Classifier model.
Args:
hparams: Holds HyperParameters for tuning.
tf_transform_output: A TFTransformOutput.
Returns:
A keras Model.
"""
real_keys = features.NUMERIC_FEATURE_KEYS
sparse_keys = features.VOCAB_FEATURE_KEYS + features.BUCKET_FEATURE_KEYS + features.CATEGORICAL_FEATURE_KEYS
# Defines deep feature columns and input layers.
deep_columns = [
tf.feature_column.numeric_column(key=features.transformed_name(key),
shape=())
for key in features.NUMERIC_FEATURE_KEYS
]
input_layers = {
column.key: tf.keras.layers.Input(name=column.key,
shape=(),
dtype=tf.float32)
for column in deep_columns
}
# Defines wide feature columns and input layers.
categorical_columns = [
tf.feature_column.categorical_column_with_identity(
key=features.transformed_name(key),
num_buckets=tf_transform_output.
num_buckets_for_transformed_feature(
features.transformed_name(key)),
default_value=0) for key in features.CATEGORICAL_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)
]
wide_columns = [
tf.feature_column.indicator_column(categorical_column)
for categorical_column in categorical_columns
]
input_layers.update({
column.categorical_column.key:
tf.keras.layers.Input(name=column.categorical_column.key,
shape=(),
dtype=tf.int32)
for column in wide_columns
})
# Build Keras model using hparams.
deep = tf.keras.layers.DenseFeatures(deep_columns)(input_layers)
for n in range(int(hparams.get('n_layers'))):
deep = tf.keras.layers.Dense(units=hparams.get('n_units_' +
str(n + 1)))(deep)
wide = tf.keras.layers.DenseFeatures(wide_columns)(input_layers)
# output = tf.keras.layers.Dense(features.NUM_CLASSES, activation='softmax')(
# tf.keras.layers.concatenate([deep, wide]))
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=hparams.get('learning_rate')),
# metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
metrics=[
tf.keras.metrics.TruePositives(name='tp'),
tf.keras.metrics.FalsePositives(name='fp'),
tf.keras.metrics.TrueNegatives(name='tn'),
tf.keras.metrics.FalseNegatives(name='fn'),
tf.keras.metrics.BinaryAccuracy(name='binary_accuracy'),
tf.keras.metrics.Precision(name='precision'),
tf.keras.metrics.Recall(name='recall'),
tf.keras.metrics.AUC(name='auc'),
])
model.summary(print_fn=absl.logging.info)
return model