def get_hyper_preprocessors(self):
hyper_preprocessors = []
if self.column_names:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CategoricalToNumericalPreprocessor(
column_names=self.column_names,
column_types=self.column_types,
)))
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.SlidingWindow(lookback=self.lookback,
batch_size=self.batch_size)))
return hyper_preprocessors
def test_serialize_and_deserialize_default_hpps_categorical():
x_train = np.array([["a", "ab", 2.1], ["b", "bc", 1.0], ["a", "bc",
"nan"]])
preprocessor = preprocessors.CategoricalToNumericalPreprocessor(
column_names=["column_a", "column_b", "column_c"],
column_types={
"column_a": "categorical",
"column_b": "categorical",
"column_c": "numerical",
},
)
hyper_preprocessor = hyper_preprocessors.DefaultHyperPreprocessor(
preprocessor)
dataset = tf.data.Dataset.from_tensor_slices(x_train).batch(32)
hyper_preprocessor.preprocessor.fit(
tf.data.Dataset.from_tensor_slices(x_train).batch(32))
hyper_preprocessor = hyper_preprocessors.deserialize(
hyper_preprocessors.serialize(hyper_preprocessor))
assert isinstance(
hyper_preprocessor.preprocessor,
preprocessors.CategoricalToNumericalPreprocessor,
)
result = hyper_preprocessor.preprocessor.transform(dataset)
assert result[0][0] == result[2][0]
assert result[0][0] != result[1][0]
assert result[0][1] != result[1][1]
assert result[0][1] != result[2][1]
assert result[2][2] == 0
assert result.dtype == tf.float32
def get_hyper_preprocessors(self):
hyper_preprocessors = []
if self._add_one_dimension:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.AddOneDimension()))
return hyper_preprocessors
def get_hyper_preprocessors(self):
hyper_preprocessors = []
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.SlidingWindow(lookback=self.lookback,
batch_size=self.batch_size)))
return hyper_preprocessors
def test_serialize_and_deserialize_default_hpps():
preprocessor = preprocessors.AddOneDimension()
hyper_preprocessor = hyper_preprocessors.DefaultHyperPreprocessor(preprocessor)
hyper_preprocessor = hyper_preprocessors.deserialize(
hyper_preprocessors.serialize(hyper_preprocessor)
)
assert isinstance(hyper_preprocessor.preprocessor, preprocessors.AddOneDimension)
def get_hyper_preprocessors(self):
hyper_preprocessors = []
if not self.has_channel_dim:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.AddOneDimension()))
return hyper_preprocessors
def get_hyper_preprocessors(self):
hyper_preprocessors = []
if self.dtype != tf.string:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CastToString()))
return hyper_preprocessors
def get_hyper_preprocessors(self):
hyper_preprocessors = []
if self._add_one_dimension:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.AddOneDimension()))
if self.dtype in [tf.uint8, tf.uint16, tf.uint32, tf.uint64]:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CastToInt32()))
if not self._encoded and self.dtype != tf.string:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CastToString()))
if self._encoded_for_sigmoid:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.SigmoidPostprocessor()))
elif self._encoded_for_softmax:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.SoftmaxPostprocessor()))
elif self.num_classes == 2:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.LabelEncoder(self._labels)))
else:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.OneHotEncoder(self._labels)))
return hyper_preprocessors
def get_hyper_preprocessors(self):
hyper_preprocessors = []
if self._add_one_dimension:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.AddOneDimension()))
if self._dtype in [tf.uint8, tf.uint16, tf.uint32, tf.uint64]:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CastToInt32()))
if not self._encoded and self._dtype != tf.string:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.CastToString()))
if self.multi_label:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.MultiLabelEncoder()))
if not self._encoded:
if self.num_classes == 2 and not self.multi_label:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.LabelEncoder(self._labels)))
else:
hyper_preprocessors.append(
hpps_module.DefaultHyperPreprocessor(
preprocessors.OneHotEncoder(self._labels)))
return hyper_preprocessors
