def __init__(
self,
featurewise_center: BooleanValue(),
samplewise_center: BooleanValue(),
featurewise_std_normalization: BooleanValue(),
samplewise_std_normalization: BooleanValue(),
rotation_range: DiscreteValue(0, 15),
width_shift_range: ContinuousValue(0, 0.25),
height_shift_range: ContinuousValue(0, 0.25),
shear_range: ContinuousValue(0, 15),
zoom_range: ContinuousValue(0, 0.25),
horizontal_flip: BooleanValue(),
vertical_flip: BooleanValue(),
):
super().__init__(
featurewise_center=featurewise_center,
samplewise_center=samplewise_center,
featurewise_std_normalization=featurewise_std_normalization,
samplewise_std_normalization=samplewise_std_normalization,
rotation_range=rotation_range,
width_shift_range=width_shift_range,
height_shift_range=height_shift_range,
shear_range=shear_range,
zoom_range=zoom_range,
horizontal_flip=horizontal_flip,
vertical_flip=vertical_flip,
)
def __init__(
self,
merge_mode: CategoricalValue("sum", "mul", "concat", "ave"),
units: DiscreteValue(32, 1024),
activation_fn: CategoricalValue("tanh", "sigmoid", "relu",
"linear"),
recurrent_activation_fn: CategoricalValue("tanh", "sigmoid",
"relu", "linear"),
dropout: ContinuousValue(0, 0.5),
recurrent_dropout: ContinuousValue(0, 0.5),
):
super().__init__(
layer=_LSTM(
units=units,
activation=activation_fn,
recurrent_activation=recurrent_activation_fn,
dropout=dropout,
recurrent_dropout=recurrent_dropout,
return_sequences=True,
),
merge_mode=merge_mode,
)
self.activation_fn = activation_fn
self.recurrent_activation_fn = recurrent_activation_fn
def __init__(
self,
extract_word: BooleanValue() = True,
window_size: DiscreteValue(0, 5) = 0,
):
self.extract_word = extract_word
self.window_size = window_size
def __init__(
self, cutoff: DiscreteValue(min=0, max=10),
):
self.cutoff = cutoff
self.tagger = _UnigramTagger
self.values = dict(cutoff=cutoff)
NltkTagger.__init__(self)
def __init__(
self,
# min_length tomará valores entre cero y cinco de forma automática para diferentes pipelines.
# Este parámetro está permitiendo buscar distintos tamaños de palabra y probar cual de ellos será mejor
min_length: DiscreteValue(min=0, max=5),
# lower es un parámetro que en algunos casos será True y en otros False. Podemos utilizarlo
# para llevar o no a minúsculas el texto.
lower: BooleanValue(),
):
self.min_length = min_length
self.lower = lower
def _get_arg_values(arg, value, cls):
if isinstance(value, bool):
return BooleanValue()
if isinstance(value, int):
return DiscreteValue(*_get_integer_values(arg, value, cls))
if isinstance(value, float):
return ContinuousValue(*_get_float_values(arg, value, cls))
if isinstance(value, str):
values = _find_parameter_values(arg, cls)
return CategoricalValue(*values) if values else None
return None
def __init__(
self,
Trained: BooleanValue(),
N: DiscreteValue(min=500, max=2000),
C: BooleanValue(),
):
self.Trained = Trained
self.N = N
self.C = C
NltkTrainedTagger.__init__(self)
_TnT.__init__(self, Trained=Trained, N=N, C=C)
def test_sample_subset():
class A:
def __init__(self, features: Subset("Subset", DiscreteValue(1, 5),
"Hello", 1, None)):
self.features = features
g = generate_cfg(A)
selected_features = g.sample().features
selected = set([repr(feature) for feature in selected_features])
assert selected.issubset(
[repr(feature) for feature in [DiscreteValue(1, 5), "Hello", 1, None]])
def __init__(self, filters: DiscreteValue(2, 8),
kernel_size: CategoricalValue(3, 5, 7),
l1: ContinuousValue(0, 1e-3), l2: ContinuousValue(0, 1e-3),
**kwargs):
self.l1 = l1
self.l2 = l2
super().__init__(filters=2**filters,
kernel_size=(kernel_size, kernel_size),
kernel_regularizer=regularizers.l1_l2(l1=l1, l2=l2),
padding="same",
data_format="channels_last",
**kwargs)
def __init__(
self,
dm: DiscreteValue(min=0, max=2),
dbow_words: DiscreteValue(min=-100, max=100),
dm_concat: DiscreteValue(min=-100, max=100),
dm_tag_count: DiscreteValue(min=0, max=2),
alpha: ContinuousValue(min=0.001, max=0.075),
epochs: DiscreteValue(min=2, max=10),
window: DiscreteValue(min=2, max=10),
inner_tokenizer: algorithm(Sentence, Seq[Word]),
inner_stemmer: algorithm(Word, Stem),
inner_stopwords: algorithm(Seq[Word], Seq[Word]),
lowercase: BooleanValue(),
stopwords_remove: BooleanValue(),
):
self.inner_tokenizer = inner_tokenizer
self.inner_stemmer = inner_stemmer
self.inner_stopwords = inner_stopwords
self.lowercase = lowercase
self.stopwords_remove = stopwords_remove
super().__init__(
dm=dm,
dbow_words=dbow_words,
dm_concat=dm_concat,
dm_tag_count=dm_tag_count,
alpha=alpha,
epochs=epochs,
window=window,
)
def __init__(
self,
affix_length: DiscreteValue(min=2, max=6),
min_stem_length: DiscreteValue(min=1, max=4),
cutoff: DiscreteValue(min=0, max=10),
backoff: algorithm(
Seq[Seq[Word]], Supervised[Seq[Seq[Postag]]], Seq[Seq[Postag]]
),
):
self.affix_length = affix_length
self.min_stem_length = min_stem_length
self.cutoff = cutoff
self.backoff = backoff
self.tagger = _AffixTagger
self.values = dict(
affix_length=affix_length,
min_stem_length=min_stem_length,
cutoff=cutoff,
backoff=backoff,
)
NltkTagger.__init__(self)
def _get_integer_values(arg, value, cls):
if value > 0:
min_value = 0
max_value = 2 * value
elif value == 0:
min_value = -100
max_value = 100
else:
return None
# binary search for minimum value
left = min_value
right = value
while left < right:
current_value = int((left + right) / 2)
if current_value in [left, right]:
break
if _try(cls, arg, current_value):
right = current_value
else:
left = current_value
min_value = right
# binary search for maximum value
left = value
right = max_value
while left < right:
current_value = int((left + right) / 2)
if current_value in [left, right]:
break
if _try(cls, arg, current_value):
left = current_value
else:
right = current_value
max_value = left
if min_value < max_value:
return DiscreteValue(min=min_value, max=max_value)
return None
def __init__(self, units: DiscreteValue(32, 1024),
activation_fn: CategoricalValue("tanh", "sigmoid", "relu",
"linear"),
recurrent_activation_fn: CategoricalValue(
"tanh", "sigmoid", "relu",
"linear"), dropout: ContinuousValue(0, 0.5),
recurrent_dropout: ContinuousValue(0, 0.5), **kwargs):
super().__init__(units=units,
activation=activation_fn,
recurrent_activation=recurrent_activation_fn,
dropout=dropout,
recurrent_dropout=recurrent_dropout,
return_sequences=False,
**kwargs)
self.activation_fn = activation_fn
self.recurrent_activation_fn = recurrent_activation_fn
def __init__(
self,
dm: DiscreteValue(min=0, max=2),
dbow_words: DiscreteValue(min=-100, max=100),
dm_concat: DiscreteValue(min=-100, max=100),
dm_tag_count: DiscreteValue(min=0, max=2),
alpha: ContinuousValue(min=0.001, max=0.075),
epochs: DiscreteValue(min=2, max=10),
window: DiscreteValue(min=2, max=10),
):
self.dm = int(dm)
self.dbow_words = int(dbow_words)
self.dm_concat = int(dm_concat)
self.dm_tag_count = int(dm_tag_count)
self.alpha = alpha
self.epochs = int(epochs)
self.window = int(window)
def __init__(self, features: Subset("Subset", DiscreteValue(1, 5),
"Hello", 1, None)):
self.features = features
def __init__(self, output_dim: DiscreteValue(32, 128), **kwargs):
super().__init__(input_dim=1000, output_dim=output_dim, **kwargs)
def __init__(self, ngram: DiscreteValue(1, 3), use_idf: BooleanValue()):
super().__init__(ngram_range=(1, ngram), use_idf=use_idf)
self.ngram = ngram
def f(x: DiscreteValue(1, 5)):
pass
def __init__(self, x: DiscreteValue(1, 5)):
pass
def __init__(self, n: DiscreteValue(50, 200)):
super().__init__(n_components=n)
self.n = n
def __init__(self, ngram: DiscreteValue(1, 3)):
super().__init__(ngram_range=(1, ngram))
self.ngram = ngram
def __init__(self, filters: DiscreteValue(2, 8),
kernel_size: CategoricalValue(3, 5, 7), **kwargs):
super().__init__(filters=2**filters,
kernel_size=kernel_size,
padding="causal",
**kwargs)
def __init__(
self,
features: Subset("Subset", DiscreteValue(1, 5),
CategoricalValue("adam", "sgd")),
):
pass
def __init__(self, x: DiscreteValue(-10, 10), y: DiscreteValue(-10, 10)):
self.x = x
self.y = y
def __init__(self, units: DiscreteValue(128, 1024), **kwargs):
super().__init__(units=units, **kwargs)
