def default_dt_space():
space = HyperSpace()
with space.as_default():
p_nets = MultipleChoice([
'dnn_nets', 'linear', 'cin_nets', 'fm_nets', 'afm_nets',
'pnn_nets', 'cross_nets', 'cross_dnn_nets', 'dcn_nets',
'autoint_nets', 'fgcnn_dnn_nets', 'fibi_dnn_nets'
],
num_chosen_most=3)
dt_module = DTModuleSpace(
nets=p_nets,
auto_categorize=Bool(),
cat_remain_numeric=Bool(),
auto_discrete=Bool(),
apply_gbm_features=Bool(),
gbm_feature_type=Choice([
DT_consts.GBM_FEATURE_TYPE_DENSE,
DT_consts.GBM_FEATURE_TYPE_EMB
]),
embeddings_output_dim=Choice([4, 10, 20]),
embedding_dropout=Choice([0, 0.1, 0.2, 0.3, 0.4, 0.5]),
stacking_op=Choice(
[DT_consts.STACKING_OP_ADD, DT_consts.STACKING_OP_CONCAT]),
output_use_bias=Bool(),
apply_class_weight=Bool(),
earlystopping_patience=Choice([1, 3, 5]))
dnn = DnnModule()(dt_module)
fit = DTFit(batch_size=Choice([128, 256]))(dt_module)
return space
def cnn_search_space(input_shape, output_units, output_activation='softmax', block_num_choices=[2, 3, 4, 5, 6],
activation_choices=['relu'], filters_choices=[32, 64], kernel_size_choices=[(1, 1), (3, 3)]):
space = HyperSpace()
with space.as_default():
hp_use_bn = Bool()
hp_pooling = Choice(list(range(2)))
hp_filters = Choice(filters_choices)
hp_kernel_size = Choice(kernel_size_choices)
hp_fc_units = Choice([1024, 2048, 4096])
if len(activation_choices) == 1:
hp_activation = activation_choices[0]
else:
hp_activation = Choice(activation_choices)
hp_bn_act = Choice([seq for seq in itertools.permutations(range(2))])
input = Input(shape=input_shape)
blocks = Repeat(
lambda step: conv_block(
block_no=step,
hp_pooling=hp_pooling,
hp_filters=hp_filters,
hp_kernel_size=hp_kernel_size,
hp_use_bn=hp_use_bn,
hp_activation=hp_activation,
hp_bn_act=hp_bn_act),
repeat_times=block_num_choices)(input)
x = Flatten()(blocks)
x = Dense(units=hp_fc_units, activation=hp_activation, name='fc1')(x)
x = Dense(units=hp_fc_units, activation=hp_activation, name='fc2')(x)
x = Dense(output_units, activation=output_activation, name='predictions')(x)
return space
def mini_dt_space():
space = HyperSpace()
with space.as_default():
p_nets = MultipleChoice(['dnn_nets', 'linear', 'fm_nets'],
num_chosen_most=2)
dt_module = DTModuleSpace(nets=p_nets,
auto_categorize=Bool(),
cat_remain_numeric=Bool(),
auto_discrete=Bool(),
apply_gbm_features=Bool(),
gbm_feature_type=Choice([
DT_consts.GBM_FEATURE_TYPE_DENSE,
DT_consts.GBM_FEATURE_TYPE_EMB
]),
embeddings_output_dim=Choice([4, 10]),
embedding_dropout=Choice([0, 0.5]),
stacking_op=Choice([
DT_consts.STACKING_OP_ADD,
DT_consts.STACKING_OP_CONCAT
]),
output_use_bias=Bool(),
apply_class_weight=Bool(),
earlystopping_patience=Choice([1, 3, 5]))
dnn = DnnModule(hidden_units=Choice([100, 200]),
reduce_factor=Choice([1, 0.8]),
dnn_dropout=Choice([0, 0.3]),
use_bn=Bool(),
dnn_layers=2,
activation='relu')(dt_module)
fit = DTFit(batch_size=Choice([128, 256]))(dt_module)
return space
def get_space():
space = HyperSpace()
with space.as_default():
name_prefix = 'test_'
filters = 64
in1 = Input(shape=(
28,
28,
1,
))
in2 = Input(shape=(
28,
28,
1,
))
ic1 = InputChoice([in1, in2], 1)([in1, in2])
or1 = ModuleChoice([
sepconv5x5(name_prefix, filters),
sepconv3x3(name_prefix, filters),
avgpooling3x3(name_prefix, filters),
maxpooling3x3(name_prefix, filters),
identity(name_prefix)
])(ic1)
space.set_inputs([in1, in2])
return space
def get_space():
space = HyperSpace()
with space.as_default():
id1 = Identity(p1=Choice(['a', 'b']),
p2=Int(1, 100),
p3=Real(0, 1.0))
return space
def get_space():
space = HyperSpace()
with space.as_default():
p1 = Int(1, 100)
p2 = Choice(['a', 'b', 'c'])
p3 = Bool()
p4 = Real(0.0, 1.0)
id1 = Identity(p1=p1)
id2 = Identity(p2=p2)(id1)
id3 = Identity(p3=p3)(id2)
id4 = Identity(p4=p4)(id3)
return space
def get_space():
space = HyperSpace()
with space.as_default():
filters = 64
in1 = Input(shape=(
28,
28,
1,
))
conv_layer(hp_dict, 'normal', 0, [in1, in1], filters, 5)
space.set_inputs(in1)
return space
def get_space():
space = HyperSpace()
with space.as_default():
filters = 64
in1 = Input(shape=(
28,
28,
1,
), dtype='float32')
conv_node(hp_dict, 'normal', 0, 0, [in1, in1], filters)
space.set_inputs(in1)
return space
def func_space(func):
space = HyperSpace()
with space.as_default():
params = {
name: copy.copy(v)
for name, v in zip(func.__code__.co_varnames, func.__defaults__)
if isinstance(v, ParameterSpace)
}
for _, v in params.items():
v.attach_to_space(space, v.name)
input = HyperInput()
id1 = Identity(**params)(input)
space.set_outputs([id1])
return space
def get_space_p_in_p():
space = HyperSpace()
with space.as_default():
p1 = Pipeline(
[SimpleImputer(name='imputer1'),
StandardScaler(name='scaler1')],
name='p1')
p2 = Pipeline(
[SimpleImputer(name='imputer2'),
StandardScaler(name='scaler2')],
name='p2')
input = HyperInput(name='input1')
p3 = Pipeline([p1, p2], name='p3')(input)
space.set_inputs(input)
return space
def get_space_num_cat_pipeline_complex(dataframe_mapper_default=False,
lightgbm_fit_kwargs={},
xgb_fit_kwargs={},
catboost_fit_kwargs={}):
space = HyperSpace()
with space.as_default():
input = HyperInput(name='input1')
p1 = numeric_pipeline_complex()(input)
p2 = categorical_pipeline_complex()(input)
# p2 = categorical_pipeline_simple()(input)
p3 = DataFrameMapper(default=dataframe_mapper_default,
input_df=True,
df_out=True,
df_out_dtype_transforms=[(column_object, 'int')
])([p1, p2])
lightgbm_init_kwargs = {
'boosting_type': Choice(['gbdt', 'dart', 'goss']),
'num_leaves': Choice([11, 31, 101, 301, 501]),
'learning_rate': Real(0.001, 0.1, step=0.005),
'n_estimators': 100,
'max_depth': -1,
'tree_learner': 'data' # add for dask
# subsample_for_bin = 200000, objective = None, class_weight = None,
# min_split_gain = 0., min_child_weight = 1e-3, min_child_samples = 20,
}
lightgbm_est = LightGBMDaskEstimator(task='binary',
fit_kwargs=lightgbm_fit_kwargs,
**lightgbm_init_kwargs)
xgb_init_kwargs = {
'tree_method': 'approx' # add for dask
}
xgb_est = XGBoostDaskEstimator(task='binary',
fit_kwargs=xgb_fit_kwargs,
**xgb_init_kwargs)
# catboost_init_kwargs = {
# 'silent': True
# }
# catboost_est = CatBoostEstimator(task='binary', fit_kwargs=catboost_fit_kwargs, **catboost_init_kwargs)
# or_est = ModuleChoice([lightgbm_est, xgb_est, catboost_est], name='estimator_options')(p3)
or_est = ModuleChoice([lightgbm_est, xgb_est],
name='estimator_options')(p3)
space.set_inputs(input)
return space
def get_space_column_transformer():
space = HyperSpace()
with space.as_default():
input = HyperInput(name='input1')
p1 = Pipeline(
[SimpleImputer(name='imputer1'),
StandardScaler(name='scaler1')],
columns=['a', 'b', 'c'],
name='p1')(input)
p2 = Pipeline(
[SimpleImputer(name='imputer2'),
StandardScaler(name='scaler2')],
columns=['c', 'd'],
name='p2')(input)
p3 = ColumnTransformer()([p1, p2])
space.set_inputs(input)
return space
def __call__(self, *args, **kwargs):
space = HyperSpace()
with space.as_default():
hyper_input = HyperInput(name='input1')
estimators = []
if self.enable_dt:
estimators.append(self.dt)
if self.enable_dtr:
estimators.append(self.dtr)
if self.enable_lr:
estimators.append(self.lr)
if self.enable_nn:
estimators.append(self.nn)
modules = [ModuleSpace(name=f'{e["cls"].__name__}', **e) for e in estimators]
outputs = ModuleChoice(modules)(hyper_input)
space.set_inputs(hyper_input)
return space
def tiny_dt_space(**hyperparams):
space = HyperSpace()
with space.as_default():
dt_module = DTModuleSpace(nets=['dnn_nets'],
auto_categorize=Bool(),
cat_remain_numeric=Bool(),
auto_discrete=False,
apply_gbm_features=False,
stacking_op=Choice([
DT_consts.STACKING_OP_ADD,
DT_consts.STACKING_OP_CONCAT
]),
output_use_bias=Bool(),
apply_class_weight=Bool(),
earlystopping_patience=Choice([1, 3, 5]))
dnn = DnnModule(hidden_units=Choice([10, 20]),
reduce_factor=1,
dnn_dropout=Choice([0, 0.3]),
use_bn=False,
dnn_layers=2,
activation='relu')(dt_module)
fit = DTFit(**hyperparams)(dt_module)
return space
def get_space():
space = HyperSpace()
with space.as_default():
filters = 64
in1 = Input(shape=(
28,
28,
1,
))
conv = conv_cell(hp_dict, 'normal', 0, 0, 'L', [in1, in1],
filters)
space.set_inputs([in1, in1])
space.set_outputs(conv)
return space
def enas_micro_search_space(arch='NRNR',
input_shape=(28, 28, 1),
init_filters=64,
node_num=4,
data_format=None,
classes=10,
classification_dropout=0,
hp_dict={},
use_input_placeholder=True,
weights_cache=None):
space = HyperSpace()
with space.as_default():
if use_input_placeholder:
input = Input(shape=input_shape, name='0_input')
else:
input = None
stem, input = stem_op(input, init_filters, data_format)
node0 = stem
node1 = stem
reduction_no = 0
normal_no = 0
for l in arch:
if l == 'N':
normal_no += 1
type = 'normal'
cell_no = normal_no
is_reduction = False
else:
reduction_no += 1
type = 'reduction'
cell_no = reduction_no
is_reduction = True
filters = (2**reduction_no) * init_filters
if is_reduction:
node0 = FactorizedReduction(
filters, f'{normal_no + reduction_no}_{type}_C{cell_no}_0',
data_format)(node0)
node1 = FactorizedReduction(
filters, f'{normal_no + reduction_no}_{type}_C{cell_no}_1',
data_format)(node1)
x = conv_layer(hp_dict, f'{normal_no + reduction_no}_{type}',
cell_no, [node0, node1], filters, node_num,
is_reduction)
node0 = node1
node1 = x
logit = classification(x, classes, classification_dropout, data_format)
space.set_inputs(input)
if weights_cache is not None:
space.weights_cache = weights_cache
return space
def get_space():
space = HyperSpace()
with space.as_default():
id1 = Identity(p1=Int(0, 10), p2=Choice(['a', 'b']))
id2 = Identity(p3=Real(0., 1.), p4=Bool())(id1)
return space
def get_space_2inputs():
space = HyperSpace()
with space.as_default():
Pipeline([tow_inputs(), StandardScaler()])
return space
def get_space():
space = HyperSpace()
with space.as_default():
Pipeline([SimpleImputer(), StandardScaler()])
return space
def get_space_2outputs():
space = HyperSpace()
with space.as_default():
Pipeline([tow_outputs()])
return space