def test_config(self):
r2_obj = RSquare(name="r_square")
self.assertEqual(r2_obj.name, "r_square")
self.assertEqual(r2_obj.dtype, tf.float32)
# Check save and restore config
r2_obj2 = RSquare.from_config(r2_obj.get_config())
self.assertEqual(r2_obj2.name, "r_square")
self.assertEqual(r2_obj2.dtype, tf.float32)
def test_config():
r2_obj = RSquare(name="r_square")
assert r2_obj.name == "r_square"
assert r2_obj.dtype == tf.float32
# Check save and restore config
r2_obj2 = RSquare.from_config(r2_obj.get_config())
assert r2_obj2.name == "r_square"
assert r2_obj2.dtype == tf.float32
def test_config(multioutput):
r2_obj = RSquare(multioutput=multioutput, name="r_square")
assert r2_obj.name == "r_square"
assert r2_obj.dtype == tf.float32
assert r2_obj.multioutput == multioutput
# Check save and restore config
r2_obj2 = RSquare.from_config(r2_obj.get_config())
assert r2_obj2.name == "r_square"
assert r2_obj2.dtype == tf.float32
assert r2_obj2.multioutput == multioutput
def test_keras_fit():
model = tf.keras.Sequential([tf.keras.layers.Dense(1)])
model.compile(loss="mse", metrics=[RSquare(y_shape=(1, ))])
data = tf.data.Dataset.from_tensor_slices(
(tf.random.normal(shape=(100, 1)), tf.random.normal(shape=(100, 1))))
data = data.batch(10)
model.fit(x=data, validation_data=data)
def _build_model(self) -> Sequential:
model = Sequential()
for state in self.sequence:
if isinstance(state, Input):
model.add(layers.Input(shape=(state.units,)))
elif isinstance(state, Hidden):
model.add(layers.Dense(units=state.units, activation=state.activation))
elif isinstance(state, Dropout):
model.add(layers.Dropout(rate=state.rate))
elif isinstance(state, Output):
model.add(layers.Dense(units=state.units, activation=state.activation))
optimizer = OPTIMIZER
if optimizer == 'adam':
optimizer = Adam(LEARNING_RATE)
elif optimizer == 'nadam':
optimizer = Nadam(LEARNING_RATE)
elif optimizer == 'rmsprop':
optimizer = RMSprop(LEARNING_RATE)
metrics = []
for metric in METRICS:
if metric == 'r_square':
metric = RSquare(name=metric, y_shape=(1,))
elif metric == 'rmse':
metric = RootMeanSquaredError(metric)
metrics.append(metric)
model.compile(
optimizer=optimizer,
loss=LOSS,
metrics=metrics
)
return model
def initialize_vars(
y_shape=(),
multioutput: str = "uniform_average",
num_regressors: tf.int32 = 0,
):
return RSquare(y_shape=y_shape,
multioutput=multioutput,
num_regressors=num_regressors)
def initialize_vars(self):
r2_obj = RSquare()
self.evaluate(tf.compat.v1.variables_initializer(r2_obj.variables))
return r2_obj
def initialize_vars(y_shape=(), multioutput: str = "uniform_average"):
return RSquare(y_shape=y_shape, multioutput=multioutput)
def initialize_vars(self, y_shape=(), multioutput: str = "uniform_average"):
r2_obj = RSquare(y_shape=y_shape, multioutput=multioutput)
self.evaluate(tf.compat.v1.variables_initializer(r2_obj.variables))
return r2_obj
