def test_boston(self):
print("Loading datasets...")
boston_dataset = load_boston()
df_train = pd.DataFrame(boston_dataset.data)
df_train.columns = boston_dataset.feature_names
self.y = pd.Series(boston_dataset.target)
self.X = df_train
self.X_train, \
self.X_test, \
self.y_train, \
self.y_test = train_test_split(self.X, self.y, test_size=0.2, random_state=42)
rs = RandomSearcher(tiny_dt_space, optimize_direction=OptimizeDirection.Maximize, )
hdt = HyperDT(rs,
callbacks=[SummaryCallback(), FileStorageLoggingCallback(rs, output_dir=f'hotexamples_com/hyn_logs')],
reward_metric='RootMeanSquaredError',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
)
hdt.search(self.X_train, self.y_train, self.X_test, self.y_test, max_trials=3)
best_trial = hdt.get_best_trial()
estimator = hdt.final_train(best_trial.space_sample, self.X, self.y)
score = estimator.predict(self.X_test)
result = estimator.evaluate(self.X_test, self.y_test)
assert result
assert isinstance(estimator.model, DeepTable)
def test_fit_one_shot_model_epoch(self):
rs = RandomSearcher(self.get_space_simple,
optimize_direction=OptimizeDirection.Maximize)
hk = HyperKeras(rs,
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
callbacks=[SummaryCallback()],
one_shot_mode=True,
one_shot_train_sampler=rs)
x, y = self.get_x_y_1()
hk.fit_one_shot_model_epoch(x, y)
def test_build_dataset_iter(self):
rs = RandomSearcher(self.get_space,
optimize_direction=OptimizeDirection.Maximize)
hk = HyperKeras(rs,
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
callbacks=[SummaryCallback()])
x, y = self.get_x_y_1()
ds_iter = hk.build_dataset_iter(x, y, batch_size=10)
batch_counter = 0
for x_b, y_b in ds_iter:
# x_b, y_b = next()
assert len(x_b) == 10
assert len(y_b) == 10
batch_counter += 1
assert batch_counter == 10
ds_iter = hk.build_dataset_iter(x, y, batch_size=32)
batch_counter = 0
for x_b, y_b in ds_iter:
# x_b, y_b = next()
if batch_counter < 3:
assert len(x_b) == 32
assert len(y_b) == 32
else:
assert len(x_b) == 4
assert len(y_b) == 4
batch_counter += 1
assert batch_counter == 4
ds_iter = hk.build_dataset_iter(x, y, batch_size=32, repeat_count=2)
batch_counter = 0
for x_b, y_b in ds_iter:
# x_b, y_b = next()
if batch_counter < 6:
assert len(x_b) == 32
assert len(y_b) == 32
else:
assert len(x_b) == 8
assert len(y_b) == 8
batch_counter += 1
assert batch_counter == 7
def test_model_with_hp(self):
rs = RandomSearcher(self.get_space,
optimize_direction=OptimizeDirection.Maximize)
hk = HyperKeras(rs,
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'],
callbacks=[SummaryCallback()])
x, y = self.get_x_y()
hk.search(x, y, x, y, max_trails=3)
best_trial = hk.get_best_trail()
estimator = hk.final_train(best_trial.space_sample, x, y)
score = estimator.predict(x)
result = estimator.evaluate(x, y)
assert len(score) == 100
assert result
def test_bankdata(self):
rs = RandomSearcher(
tiny_dt_space,
optimize_direction=OptimizeDirection.Maximize,
)
hdt = HyperDT(
rs,
callbacks=[
SummaryCallback(),
FileStorageLoggingCallback(rs,
output_dir=f'hotexamples_com/hyn_logs')
],
# reward_metric='accuracy',
reward_metric='AUC',
dnn_params={
'hidden_units': ((256, 0, False), (256, 0, False)),
'dnn_activation': 'relu',
},
)
df = dsutils.load_bank().sample(n=2000, random_state=9527)
df.drop(['id'], axis=1, inplace=True)
df_train, df_test = train_test_split(df,
test_size=0.2,
random_state=42)
y = df_train.pop('y')
y_test = df_test.pop('y')
hdt.search(
df_train,
y,
df_test,
y_test,
max_trials=3,
)
best_trial = hdt.get_best_trial()
assert best_trial
estimator = hdt.final_train(best_trial.space_sample, df_train, y)
score = estimator.predict(df_test)
result = estimator.evaluate(df_test, y_test)
assert len(score) == len(y_test)
assert result
assert isinstance(estimator.model, DeepTable)
def test_hyper_dt(self):
rs = RandomSearcher(
tiny_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,
)
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, DTEstimator)
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, DTEstimator)
assert isinstance(estimator.model, DeepTable)