def test_automl_sklearn_model_with_base_estimator(tmpdir):
grad_boost = GradientBoostingRegressor()
bagged_regressor = BaggingRegressor(grad_boost, random_state=5, n_jobs=-1)
wrapped_bagged_regressor = SKLearnWrapper(
bagged_regressor,
HyperparameterSpace({
"n_estimators": RandInt(10, 100),
"max_features": Uniform(0.6, 1.0)
}),
# return_all_sklearn_default_params_on_get=True
)
_test_within_auto_ml_loop(tmpdir, wrapped_bagged_regressor)
def main():
def accuracy(data_inputs, expected_outputs):
return np.mean(
np.argmax(np.array(data_inputs), axis=1) == np.argmax(
np.array(expected_outputs), axis=1))
# load the dataset
df = read_csv('data/winequality-white.csv', sep=';')
data_inputs = df.values
data_inputs[:, -1] = data_inputs[:, -1] - 1
n_features = data_inputs.shape[1] - 1
n_classes = 10
p = Pipeline([
TrainOnlyWrapper(DataShuffler()),
ColumnTransformerInputOutput(
input_columns=[(
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10], ToNumpy(np.float32)
)],
output_columns=[(11, Identity())]
),
OutputTransformerWrapper(PlotDistribution(column=-1)),
MiniBatchSequentialPipeline([
Tensorflow2ModelStep(
create_model=create_model,
create_loss=create_loss,
create_optimizer=create_optimizer
) \
.set_hyperparams(HyperparameterSamples({
'n_dense_layers': 2,
'input_dim': n_features,
'optimizer': 'adam',
'activation': 'relu',
'kernel_initializer': 'he_uniform',
'learning_rate': 0.01,
'hidden_dim': 20,
'n_classes': 3
})).set_hyperparams_space(HyperparameterSpace({
'n_dense_layers': RandInt(2, 4),
'hidden_dim_layer_multiplier': Uniform(0.30, 1),
'input_dim': FixedHyperparameter(n_features),
'optimizer': Choice([
OPTIMIZERS.ADAM.value,
OPTIMIZERS.SGD.value,
OPTIMIZERS.ADAGRAD.value
]),
'activation': Choice([
ACTIVATIONS.RELU.value,
ACTIVATIONS.TANH.value,
ACTIVATIONS.SIGMOID.value,
ACTIVATIONS.ELU.value,
]),
'kernel_initializer': Choice([
KERNEL_INITIALIZERS.GLOROT_NORMAL.value,
KERNEL_INITIALIZERS.GLOROT_UNIFORM.value,
KERNEL_INITIALIZERS.HE_UNIFORM.value
]),
'learning_rate': LogUniform(0.005, 0.01),
'hidden_dim': RandInt(3, 80),
'n_classes': FixedHyperparameter(n_classes)
}))
], batch_size=33),
OutputTransformerWrapper(Pipeline([
ExpandDim(),
OneHotEncoder(nb_columns=n_classes, name='classes')
]))
])
auto_ml = AutoML(
pipeline=p,
hyperparams_repository=InMemoryHyperparamsRepository(
cache_folder='trials'),
hyperparams_optimizer=RandomSearchHyperparameterSelectionStrategy(),
validation_splitter=ValidationSplitter(test_size=0.30),
scoring_callback=ScoringCallback(accuracy,
higher_score_is_better=True),
callbacks=[
MetricCallback(
name='classification_report_imbalanced_metric',
metric_function=classificaiton_report_imbalanced_metric,
higher_score_is_better=True),
MetricCallback(name='f1',
metric_function=f1_score_weighted,
higher_score_is_better=True),
MetricCallback(name='recall',
metric_function=recall_score_weighted,
higher_score_is_better=True),
MetricCallback(name='precision',
metric_function=precision_score_weighted,
higher_score_is_better=True),
EarlyStoppingCallback(max_epochs_without_improvement=3)
],
n_trials=200,
refit_trial=True,
epochs=75)
auto_ml = auto_ml.fit(data_inputs=data_inputs)
HyperparameterSpace({
'add':
Choice(choice_list=[0, 1.5, 2, 3.5, 4, 5, 6]),
})),
AddN(0.).set_hyperparams_space(
HyperparameterSpace({
'add':
Choice(choice_list=[0, 1.5, 2, 3.5, 4, 5, 6]),
}))
])),
(3.5,
Pipeline([
FitTransformCallbackStep().set_name('callback'),
AddN(0.).set_hyperparams_space(
HyperparameterSpace({
'add': Quantized(hd=Uniform(0, 10)),
})),
AddN(0.).set_hyperparams_space(
HyperparameterSpace({
'add': Quantized(hd=Uniform(0, 10)),
}))
])),
(3.5,
Pipeline([
FitTransformCallbackStep().set_name('callback'),
AddN(0.).set_hyperparams_space(
HyperparameterSpace({
'add':
LogUniform(min_included=1.0, max_included=5.0),
})),
AddN(0.).set_hyperparams_space(