def test_hyper_dt(self):
rs = RandomSearcher(mini_dt_space, optimize_direction=OptimizeDirection.Maximize, )
hdt = HyperDT(rs,
callbacks=[SummaryCallback()],
reward_metric='accuracy',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
cache_preprocessed_data=True,
cache_home=homedir + '/cache'
)
x1 = np.random.randint(0, 10, size=(100), dtype='int')
x2 = np.random.randint(0, 2, size=(100)).astype('str')
x3 = np.random.randint(0, 2, size=(100)).astype('str')
x4 = np.random.normal(0.0, 1.0, size=(100))
y = np.random.randint(0, 2, size=(100), dtype='int')
df = pd.DataFrame({'x1': x1, 'x2': x2, 'x3': x3, 'x4': x4})
hdt.search(df, y, df, y, max_trials=3, epochs=1)
best_trial = hdt.get_best_trial()
model = hdt.load_estimator(best_trial.model_file)
assert model
score = model.predict(df)
result = model.evaluate(df, y)
assert len(score) == 100
assert result
assert isinstance(model, DeepTable)
estimator = hdt.final_train(best_trial.space_sample, df, y, epochs=1)
score = estimator.predict(df)
result = estimator.evaluate(df, y)
assert len(score) == 100
assert result
assert isinstance(estimator.model, DeepTable)
def train(self, X, y, X_test):
searcher = EvolutionSearcher(
mini_dt_space,
optimize_direction=OptimizeDirection.Maximize,
population_size=30,
sample_size=10,
regularized=True,
candidates_size=10)
es = EarlyStoppingCallback(self.earlystop_rounds,
'max',
time_limit=self.time_limit,
expected_reward=self.expected_reward)
hdt = HyperDT(
searcher,
callbacks=[es],
reward_metric=self.reward_metric,
cache_preprocessed_data=True,
)
stratify = y
if self.task == 'regression':
stratify = None
X_train, X_eval, y_train, y_eval = train_test_split(X,
y,
test_size=0.3,
random_state=9527,
stratify=stratify)
hdt.search(X_train,
y_train,
X_eval,
y_eval,
max_trials=self.max_trials,
epochs=self.epochs)
best_trial = hdt.get_best_trial()
self.estimator = hdt.load_estimator(best_trial.model_file)