def test_categorical_to_numerical(): block = preprocessing.CategoricalToNumerical() block.column_names = ['a'] block.column_types = {'a': 'num'} utils.block_basic_exam( block, tf.keras.Input(shape=(1, ), dtype=tf.string), [], )
def build(self, hp, inputs=None): input_node = nest.flatten(inputs)[0] output_node = input_node if self.categorical_encoding: block = preprocessing.CategoricalToNumerical() block.column_types = self.column_types block.column_names = self.column_names output_node = block.build(hp, output_node) output_node = basic.DenseBlock().build(hp, output_node) return output_node
def build_categorical_encoding(self, hp, input_node): output_node = input_node categorical_encoding = self.categorical_encoding if categorical_encoding is None: categorical_encoding = hp.Choice('categorical_encoding', [True, False], default=True) if categorical_encoding: block = preprocessing.CategoricalToNumerical() block.column_types = self.column_types block.column_names = self.column_names output_node = block.build(hp, output_node) return output_node
def build(self, hp, inputs=None): input_node = nest.flatten(inputs)[0] output_node = input_node if self.categorical_encoding: block = preprocessing.CategoricalToNumerical() block.column_types = self.column_types block.column_names = self.column_names output_node = block.build(hp, output_node) if self.normalize is None and hp.Boolean(NORMALIZE): with hp.conditional_scope(NORMALIZE, [True]): output_node = preprocessing.Normalization().build(hp, output_node) elif self.normalize: output_node = preprocessing.Normalization().build(hp, output_node) output_node = basic.DenseBlock().build(hp, output_node) return output_node