def build_estimator(tf_transform_dir, config, hidden_units=None):
"""Build an estimator for predicting the tipping behavior of taxi riders.
Args:
tf_transform_dir: directory in which the tf-transform model was written
during the preprocessing step.
config: tf.contrib.learn.RunConfig defining the runtime environment for the
estimator (including model_dir).
hidden_units: [int], the layer sizes of the DNN (input layer first)
Returns:
Resulting DNNLinearCombinedClassifier.
"""
metadata_dir = os.path.join(tf_transform_dir,
transform_fn_io.TRANSFORMED_METADATA_DIR)
transformed_metadata = metadata_io.read_metadata(metadata_dir)
transformed_feature_spec = transformed_metadata.schema.as_feature_spec()
transformed_feature_spec.pop(taxi.transformed_name(taxi.LABEL_KEY))
real_valued_columns = [
tf.feature_column.numeric_column(key, shape=())
for key in taxi.transformed_names(taxi.DENSE_FLOAT_FEATURE_KEYS)
]
categorical_columns = [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=taxi.VOCAB_SIZE + taxi.OOV_SIZE, default_value=0)
for key in taxi.transformed_names(taxi.VOCAB_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=taxi.FEATURE_BUCKET_COUNT, default_value=0)
for key in taxi.transformed_names(taxi.BUCKET_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=num_buckets, default_value=0)
for key, num_buckets in zip(
taxi.transformed_names(taxi.CATEGORICAL_FEATURE_KEYS), #
taxi.MAX_CATEGORICAL_FEATURE_VALUES)
]
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])
def build_estimator(tf_transform_output, config, hidden_units=None):
"""Build an estimator for predicting the tipping behavior of taxi riders.
Args:
tf_transform_output: A TFTransformOutput.
config: tf.contrib.learn.RunConfig defining the runtime environment for the
estimator (including model_dir).
hidden_units: [int], the layer sizes of the DNN (input layer first)
Returns:
Resulting DNNLinearCombinedClassifier.
"""
transformed_feature_spec = (
tf_transform_output.transformed_feature_spec().copy())
transformed_feature_spec.pop(taxi.transformed_name(taxi.LABEL_KEY))
real_valued_columns = [
tf.feature_column.numeric_column(key, shape=())
for key in taxi.transformed_names(taxi.DENSE_FLOAT_FEATURE_KEYS)
]
categorical_columns = [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=taxi.VOCAB_SIZE + taxi.OOV_SIZE, default_value=0)
for key in taxi.transformed_names(taxi.VOCAB_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=taxi.FEATURE_BUCKET_COUNT, default_value=0)
for key in taxi.transformed_names(taxi.BUCKET_FEATURE_KEYS)
]
categorical_columns += [
tf.feature_column.categorical_column_with_identity(
key, num_buckets=num_buckets, default_value=0)
for key, num_buckets in zip(
taxi.transformed_names(taxi.CATEGORICAL_FEATURE_KEYS), #
taxi.MAX_CATEGORICAL_FEATURE_VALUES)
]
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])