def test_drift_adaptation_hatc():
rng = random.Random(42)
dataset = iter(synth.Sine(seed=8, classification_function=0, has_noise=True))
model = tree.HoeffdingAdaptiveTreeClassifier(
leaf_prediction="mc",
grace_period=10,
adwin_confidence=0.1,
split_confidence=0.1,
drift_window_threshold=2,
seed=42,
max_depth=3,
)
for i in range(1000):
if i % 200 == 0 and i > 0:
dataset = iter(
synth.Sine(
seed=8, classification_function=rng.randint(0, 3), has_noise=False
)
)
x, y = next(dataset)
model.learn_one(x, y)
assert model._n_switch_alternate_trees > 0
from river import preprocessing
from river import evaluate
from river import metrics
from river import datasets
from river import tree
from river import compose
from river import optim
X_y = synth.PredictionInfluenceStream(stream=[
synth.RandomRBF(seed_model=42,
seed_sample=42,
n_classes=2,
n_features=4,
n_centroids=20),
synth.RandomRBF(seed_model=41,
seed_sample=49,
n_classes=2,
n_features=4,
n_centroids=20)
])
model = preprocessing.StandardScaler()
model |= tree.HoeffdingAdaptiveTreeClassifier(grace_period=100,
split_confidence=1e-5,
leaf_prediction='nb',
nb_threshold=10,
seed=0)
metric = metrics.Accuracy()
evaluate.evaluate_influential(X_y, model, metric, print_every=100)
param_grid=CLASSIFICATION_PARAM_GRID,
sampling_rate=SAMPLING_RATE)),
('EvoAutoML Bagging Best',
EvolutionaryBaggingClassifier(population_size=POPULATION_SIZE,
model=AUTOML_CLASSIFICATION_PIPELINE,
param_grid=CLASSIFICATION_PARAM_GRID,
sampling_rate=SAMPLING_RATE)),
('ARF', ensemble.AdaptiveRandomForestClassifier()),
('Leveraging Bagging',
ensemble.LeveragingBaggingClassifier(model=ENSEMBLE_CLASSIFIER())),
('Bagging',
ensemble.BaggingClassifier(model=ENSEMBLE_CLASSIFIER(), n_models=10)),
('SRPC', ensemble.SRPClassifier(n_models=10)),
('Hoeffding Tree', tree.HoeffdingTreeClassifier()),
('Logistic Regression', linear_model.LogisticRegression()),
('HAT', tree.HoeffdingAdaptiveTreeClassifier()),
('GaussianNB', naive_bayes.GaussianNB()),
('KNN', neighbors.KNNClassifier()),
]
if __name__ == '__main__':
RESULT_PATH.mkdir(parents=True, exist_ok=True)
#output = evaluate_ensemble(CLASSIFICATION_TRACKS[1], ENSEMBLE_EVALUATION_MODELS[2])
pool = Pool(60) # Create a multiprocessing Pool
output = pool.starmap(
evaluate_ensemble,
list(
itertools.product(CLASSIFICATION_TRACKS,
ENSEMBLE_EVALUATION_MODELS)))
(
get_classification_data(),
tree.HoeffdingTreeClassifier(
leaf_prediction="mc",
max_size=0.025,
grace_period=50,
memory_estimate_period=50,
splitter=tree.splitter.ExhaustiveSplitter(),
),
),
(
get_classification_data(),
tree.HoeffdingAdaptiveTreeClassifier(
leaf_prediction="mc",
max_size=0.025,
grace_period=50,
memory_estimate_period=50,
splitter=tree.splitter.ExhaustiveSplitter(),
),
),
(
get_classification_data(),
tree.ExtremelyFastDecisionTreeClassifier(
leaf_prediction="mc",
max_size=0.025,
grace_period=50,
memory_estimate_period=50,
splitter=tree.splitter.ExhaustiveSplitter(),
),
),
],