Note
Click here to download the full example code or to run this example in your browser via Binder
Random Search¶
A crucial feature of auto-sklearn is automatically optimizing the hyperparameters through SMAC, introduced here. Additionally, it is possible to use random search instead of SMAC, as demonstrated in the example below. Furthermore, the example also demonstrates how to use Random Online Aggressive Racing (ROAR) as yet another alternative optimizatino strategy. Both examples are intended to show how the optimization strategy in auto-sklearn can be adapted.
from pprint import pprint
import sklearn.model_selection
import sklearn.datasets
import sklearn.metrics
from smac.facade.roar_facade import ROAR
from smac.scenario.scenario import Scenario
import autosklearn.classification
Data Loading¶
X, y = sklearn.datasets.load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
X, y, random_state=1
)
Fit a classifier using ROAR¶
def get_roar_object_callback(
scenario_dict,
seed,
ta,
ta_kwargs,
metalearning_configurations,
n_jobs,
dask_client,
multi_objective_algorithm, # This argument will be ignored as ROAR does not yet support multi-objective optimization
multi_objective_kwargs,
):
"""Random online adaptive racing."""
if n_jobs > 1 or (dask_client and len(dask_client.nthreads()) > 1):
raise ValueError(
"Please make sure to guard the code invoking Auto-sklearn by "
"`if __name__ == '__main__'` and remove this exception."
)
scenario = Scenario(scenario_dict)
return ROAR(
scenario=scenario,
rng=seed,
tae_runner=ta,
tae_runner_kwargs=ta_kwargs,
run_id=seed,
dask_client=dask_client,
n_jobs=n_jobs,
)
automl = autosklearn.classification.AutoSklearnClassifier(
time_left_for_this_task=60,
per_run_time_limit=15,
tmp_folder="/tmp/autosklearn_random_search_example_tmp",
initial_configurations_via_metalearning=0,
# The callback to get the SMAC object
get_smac_object_callback=get_roar_object_callback,
)
automl.fit(X_train, y_train, dataset_name="breast_cancer")
print("#" * 80)
print("Results for ROAR.")
# Print the final ensemble constructed by auto-sklearn via ROAR.
pprint(automl.show_models(), indent=4)
predictions = automl.predict(X_test)
# Print statistics about the auto-sklearn run such as number of
# iterations, number of models failed with a time out.
print(automl.sprint_statistics())
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, predictions))
################################################################################
Results for ROAR.
{ 2: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d3b2c4c0>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1e35a30>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3b2c280>,
'model_id': 2,
'rank': 1,
'sklearn_classifier': RandomForestClassifier(max_features=5, n_estimators=512, n_jobs=1,
random_state=1, warm_start=True)},
3: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1bb37c0>,
'cost': 0.07092198581560283,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d4452910>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d4495520>,
'model_id': 3,
'rank': 2,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.10318256510142626, average=True, max_iter=32,
random_state=1, tol=0.0013607858153657413,
warm_start=True)},
4: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1b2b9a0>,
'cost': 0.08510638297872342,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d3b2c8e0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d154f970>,
'model_id': 4,
'rank': 3,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.000505280701827856, max_iter=32, random_state=1,
tol=0.06421873693006744, warm_start=True)},
5: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1417490>,
'cost': 0.021276595744680882,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1aa6e50>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1417100>,
'model_id': 5,
'rank': 4,
'sklearn_classifier': HistGradientBoostingClassifier(early_stopping=True,
l2_regularization=1.4469619760002166e-09,
learning_rate=0.12309321429220763, max_iter=256,
max_leaf_nodes=10, min_samples_leaf=17,
n_iter_no_change=16, random_state=1,
validation_fraction=None, warm_start=True)},
7: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d458d8e0>,
'cost': 0.36879432624113473,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d2413730>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d4547af0>,
'model_id': 7,
'rank': 5,
'sklearn_classifier': BernoulliNB(alpha=0.020898102999400082)},
8: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1a524c0>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d4133610>,
'ensemble_weight': 0.1,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1a52c70>,
'model_id': 8,
'rank': 6,
'sklearn_classifier': PassiveAggressiveClassifier(C=5.4951544593926646e-05, average=True, max_iter=16,
random_state=1, tol=0.012344344043531127,
warm_start=True)},
9: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1c152b0>,
'cost': 0.12056737588652477,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d6234430>,
'ensemble_weight': 0.08,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1c15940>,
'model_id': 9,
'rank': 7,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.09581923415311244, max_iter=64, random_state=1,
tol=0.000145918046557035, warm_start=True)},
10: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d411bfd0>,
'cost': 0.16312056737588654,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d614df70>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d411b700>,
'model_id': 10,
'rank': 8,
'sklearn_classifier': ExtraTreesClassifier(criterion='entropy', max_features=2, min_samples_leaf=11,
min_samples_split=19, n_estimators=512, n_jobs=1,
random_state=1, warm_start=True)},
11: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05ca2e0b50>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d3d35e50>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d681f490>,
'model_id': 11,
'rank': 9,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.039339489121391846)},
12: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d2403640>,
'cost': 0.13475177304964536,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d45bd820>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05cb155400>,
'model_id': 12,
'rank': 10,
'sklearn_classifier': LinearDiscriminantAnalysis(tol=0.0004182629077658861)},
13: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d61cdac0>,
'cost': 0.36879432624113473,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d25bfe20>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3f33850>,
'model_id': 13,
'rank': 11,
'sklearn_classifier': ExtraTreesClassifier(bootstrap=True, criterion='entropy', max_features=1,
min_samples_leaf=20, min_samples_split=20,
n_estimators=512, n_jobs=1, random_state=1,
warm_start=True)},
14: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1ea3f70>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05cb2442b0>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1ea36a0>,
'model_id': 14,
'rank': 12,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.013943862590174107)},
15: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d60168e0>,
'cost': 0.16312056737588654,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d248cbe0>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1a42040>,
'model_id': 15,
'rank': 13,
'sklearn_classifier': DecisionTreeClassifier(class_weight='balanced', criterion='entropy',
max_depth=1, min_samples_leaf=3, min_samples_split=13,
random_state=1)},
16: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1c00d90>,
'cost': 0.06382978723404253,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05c6e48fd0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1c00340>,
'model_id': 16,
'rank': 14,
'sklearn_classifier': GaussianNB()},
17: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05ce652e20>,
'cost': 0.07801418439716312,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d43afc40>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05ce652d00>,
'model_id': 17,
'rank': 15,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.04885675602027957, average=True, max_iter=64,
random_state=1, tol=0.0002678322187543955,
warm_start=True)},
18: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d3e68a90>,
'cost': 0.1063829787234043,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d21436d0>,
'ensemble_weight': 0.1,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3e68460>,
'model_id': 18,
'rank': 16,
'sklearn_classifier': SGDClassifier(alpha=0.0002548862311968591, average=True,
eta0=4.278565071229579e-05, learning_rate='constant',
loss='squared_hinge', max_iter=1024, random_state=1,
tol=5.482673674397374e-05, warm_start=True)},
19: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d684e610>,
'cost': 0.09219858156028371,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d0f2ebe0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d684eca0>,
'model_id': 19,
'rank': 17,
'sklearn_classifier': AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=7),
learning_rate=0.035867722843024794, n_estimators=70,
random_state=1)},
23: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d19ad940>,
'cost': 0.07801418439716312,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05cc69a1c0>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d19ad2b0>,
'model_id': 23,
'rank': 18,
'sklearn_classifier': MLPClassifier(activation='tanh', alpha=0.02522490081077779, beta_1=0.999,
beta_2=0.9, early_stopping=True, hidden_layer_sizes=(35,),
learning_rate_init=0.026536043936270744, max_iter=32,
n_iter_no_change=32, random_state=1, verbose=0, warm_start=True)},
24: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1b78d90>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d2001670>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1b787c0>,
'model_id': 24,
'rank': 19,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.001678686694320821)},
25: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d62b9e50>,
'cost': 0.021276595744680882,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1efefd0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d62b9400>,
'model_id': 25,
'rank': 20,
'sklearn_classifier': HistGradientBoostingClassifier(early_stopping=True,
l2_regularization=2.1928852428306468e-08,
learning_rate=0.29557366541255203, max_iter=64,
max_leaf_nodes=70, min_samples_leaf=24,
random_state=1,
validation_fraction=0.13252036572629863,
warm_start=True)},
26: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d61d3700>,
'cost': 0.08510638297872342,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1df5100>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d154f040>,
'model_id': 26,
'rank': 21,
'sklearn_classifier': KNeighborsClassifier(n_neighbors=80, p=1)}}
auto-sklearn results:
Dataset name: breast_cancer
Metric: accuracy
Best validation score: 0.978723
Number of target algorithm runs: 26
Number of successful target algorithm runs: 25
Number of crashed target algorithm runs: 0
Number of target algorithms that exceeded the time limit: 1
Number of target algorithms that exceeded the memory limit: 0
Accuracy score 0.965034965034965
Fit a classifier using Random Search¶
def get_random_search_object_callback(
scenario_dict,
seed,
ta,
ta_kwargs,
metalearning_configurations,
n_jobs,
dask_client,
multi_objective_algorithm, # This argument will be ignored as ROAR does not yet support multi-objective optimization
multi_objective_kwargs,
):
"""Random search"""
if n_jobs > 1 or (dask_client and len(dask_client.nthreads()) > 1):
raise ValueError(
"Please make sure to guard the code invoking Auto-sklearn by "
"`if __name__ == '__main__'` and remove this exception."
)
scenario_dict["minR"] = len(scenario_dict["instances"])
scenario_dict["initial_incumbent"] = "RANDOM"
scenario = Scenario(scenario_dict)
return ROAR(
scenario=scenario,
rng=seed,
tae_runner=ta,
tae_runner_kwargs=ta_kwargs,
run_id=seed,
dask_client=dask_client,
n_jobs=n_jobs,
)
automl = autosklearn.classification.AutoSklearnClassifier(
time_left_for_this_task=60,
per_run_time_limit=15,
tmp_folder="/tmp/autosklearn_random_search_example_tmp",
initial_configurations_via_metalearning=0,
# Passing the callback to get the SMAC object
get_smac_object_callback=get_random_search_object_callback,
)
automl.fit(X_train, y_train, dataset_name="breast_cancer")
print("#" * 80)
print("Results for random search.")
# Print the final ensemble constructed by auto-sklearn via random search.
pprint(automl.show_models(), indent=4)
# Print statistics about the auto-sklearn run such as number of
# iterations, number of models failed with a time out.
print(automl.sprint_statistics())
predictions = automl.predict(X_test)
print("Accuracy score", sklearn.metrics.accuracy_score(y_test, predictions))
################################################################################
Results for random search.
{ 3: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d618d640>,
'cost': 0.08510638297872342,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d618d820>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d618df40>,
'model_id': 3,
'rank': 1,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.000505280701827856, max_iter=32, random_state=1,
tol=0.06421873693006744, warm_start=True)},
4: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1df5070>,
'cost': 0.021276595744680882,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d16ce850>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1df5ca0>,
'model_id': 4,
'rank': 2,
'sklearn_classifier': HistGradientBoostingClassifier(early_stopping=True,
l2_regularization=1.4469619760002166e-09,
learning_rate=0.12309321429220763, max_iter=256,
max_leaf_nodes=10, min_samples_leaf=17,
n_iter_no_change=16, random_state=1,
validation_fraction=None, warm_start=True)},
5: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d684ea90>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05cc052df0>,
'ensemble_weight': 0.14,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d684e070>,
'model_id': 5,
'rank': 3,
'sklearn_classifier': RandomForestClassifier(max_features=5, n_estimators=512, n_jobs=1,
random_state=1, warm_start=True)},
6: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d3e68190>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d611da60>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1d96220>,
'model_id': 6,
'rank': 4,
'sklearn_classifier': LinearDiscriminantAnalysis(tol=0.08622878828999171)},
7: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d4024820>,
'cost': 0.36879432624113473,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d4573b20>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d6403370>,
'model_id': 7,
'rank': 5,
'sklearn_classifier': BernoulliNB(alpha=0.020898102999400082)},
9: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d103b790>,
'cost': 0.12056737588652477,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d448d3d0>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d103bd30>,
'model_id': 9,
'rank': 6,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.09581923415311244, max_iter=64, random_state=1,
tol=0.000145918046557035, warm_start=True)},
10: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1ad43d0>,
'cost': 0.16312056737588654,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05cb27baf0>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1ad4310>,
'model_id': 10,
'rank': 7,
'sklearn_classifier': ExtraTreesClassifier(criterion='entropy', max_features=2, min_samples_leaf=11,
min_samples_split=19, n_estimators=512, n_jobs=1,
random_state=1, warm_start=True)},
11: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d61e5be0>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d221fe50>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d457f9a0>,
'model_id': 11,
'rank': 8,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.039339489121391846)},
12: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d25bf490>,
'cost': 0.13475177304964536,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1ea3460>,
'ensemble_weight': 0.08,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1e27820>,
'model_id': 12,
'rank': 9,
'sklearn_classifier': LinearDiscriminantAnalysis(tol=0.0004182629077658861)},
13: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d0caa700>,
'cost': 0.36879432624113473,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d62fd250>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d0caae20>,
'model_id': 13,
'rank': 10,
'sklearn_classifier': ExtraTreesClassifier(bootstrap=True, criterion='entropy', max_features=1,
min_samples_leaf=20, min_samples_split=20,
n_estimators=512, n_jobs=1, random_state=1,
warm_start=True)},
14: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d0f45820>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05cc0528b0>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d45474c0>,
'model_id': 14,
'rank': 11,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.013943862590174107)},
15: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05cc79a910>,
'cost': 0.16312056737588654,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1ef6310>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3d93940>,
'model_id': 15,
'rank': 12,
'sklearn_classifier': DecisionTreeClassifier(class_weight='balanced', criterion='entropy',
max_depth=1, min_samples_leaf=3, min_samples_split=13,
random_state=1)},
16: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1c0eeb0>,
'cost': 0.06382978723404253,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d2165070>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1c0e7c0>,
'model_id': 16,
'rank': 13,
'sklearn_classifier': GaussianNB()},
17: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1e355b0>,
'cost': 0.07801418439716312,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d0fc0790>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1e35850>,
'model_id': 17,
'rank': 14,
'sklearn_classifier': PassiveAggressiveClassifier(C=0.04885675602027957, average=True, max_iter=64,
random_state=1, tol=0.0002678322187543955,
warm_start=True)},
18: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d3dcb370>,
'cost': 0.1063829787234043,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05ca268730>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3dcb190>,
'model_id': 18,
'rank': 15,
'sklearn_classifier': SGDClassifier(alpha=0.0002548862311968591, average=True,
eta0=4.278565071229579e-05, learning_rate='constant',
loss='squared_hinge', max_iter=1024, random_state=1,
tol=5.482673674397374e-05, warm_start=True)},
19: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05ca2e0700>,
'cost': 0.09219858156028371,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d0ccb430>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05ca2e0340>,
'model_id': 19,
'rank': 16,
'sklearn_classifier': AdaBoostClassifier(base_estimator=DecisionTreeClassifier(max_depth=7),
learning_rate=0.035867722843024794, n_estimators=70,
random_state=1)},
20: { 'balancing': Balancing(random_state=1),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d3b2c4f0>,
'cost': 0.07092198581560283,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d0fd70a0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3b2c970>,
'model_id': 20,
'rank': 17,
'sklearn_classifier': AdaBoostClassifier(algorithm='SAMME',
base_estimator=DecisionTreeClassifier(max_depth=9),
learning_rate=0.21684295401135145, n_estimators=72,
random_state=1)},
23: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1c62880>,
'cost': 0.07801418439716312,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d2413fd0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1c62580>,
'model_id': 23,
'rank': 18,
'sklearn_classifier': MLPClassifier(activation='tanh', alpha=0.02522490081077779, beta_1=0.999,
beta_2=0.9, early_stopping=True, hidden_layer_sizes=(35,),
learning_rate_init=0.026536043936270744, max_iter=32,
n_iter_no_change=32, random_state=1, verbose=0, warm_start=True)},
24: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d624be50>,
'cost': 0.028368794326241176,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d3aee2e0>,
'ensemble_weight': 0.06,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d624bd90>,
'model_id': 24,
'rank': 19,
'sklearn_classifier': LinearDiscriminantAnalysis(shrinkage='auto', solver='lsqr',
tol=0.001678686694320821)},
25: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d1bf6280>,
'cost': 0.021276595744680882,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d0c32c40>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d1bf6d00>,
'model_id': 25,
'rank': 20,
'sklearn_classifier': HistGradientBoostingClassifier(early_stopping=True,
l2_regularization=2.1928852428306468e-08,
learning_rate=0.29557366541255203, max_iter=64,
max_leaf_nodes=70, min_samples_leaf=24,
random_state=1,
validation_fraction=0.13252036572629863,
warm_start=True)},
26: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d62efb20>,
'cost': 0.08510638297872342,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1c62ca0>,
'ensemble_weight': 0.02,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d3b0e820>,
'model_id': 26,
'rank': 21,
'sklearn_classifier': KNeighborsClassifier(n_neighbors=80, p=1)},
27: { 'balancing': Balancing(random_state=1, strategy='weighting'),
'classifier': <autosklearn.pipeline.components.classification.ClassifierChoice object at 0x7f05d438e1f0>,
'cost': 0.375886524822695,
'data_preprocessor': <autosklearn.pipeline.components.data_preprocessing.DataPreprocessorChoice object at 0x7f05d1b2bbe0>,
'ensemble_weight': 0.04,
'feature_preprocessor': <autosklearn.pipeline.components.feature_preprocessing.FeaturePreprocessorChoice object at 0x7f05d482d310>,
'model_id': 27,
'rank': 22,
'sklearn_classifier': BernoulliNB(alpha=9.144520523203797)}}
auto-sklearn results:
Dataset name: breast_cancer
Metric: accuracy
Best validation score: 0.978723
Number of target algorithm runs: 26
Number of successful target algorithm runs: 26
Number of crashed target algorithm runs: 0
Number of target algorithms that exceeded the time limit: 0
Number of target algorithms that exceeded the memory limit: 0
Accuracy score 0.972027972027972
Total running time of the script: ( 1 minutes 56.774 seconds)
