def transform(self, fp):
found_feature = False
for f in fp:
if f.name == self.name:
yield Feature.apply_config(
f,
feature_type=FeatureType.TARGET
)
found_feature = True
else:
yield Feature.apply_config(
f,
feature_type=FeatureType.PREDICTOR
)
assert found_feature, "Feature `{}` is not found in the FeaturePool".format(self.name)
def transform(self, fp):
train_a, test_a = train_test_split(
FeaturePool(fp).array(),
test_size = self.test_size,
random_state = self.random_state,
)
for f_id, f in enumerate(fp):
yield Feature.apply_config(
Feature(f.name, train_a[:, f_id], f.st),
split_type=SplitType.TRAIN
)
for f_id, f in enumerate(fp):
yield Feature.apply_config(
Feature(f.name, test_a[:, f_id], f.st),
split_type=SplitType.TEST
)
def transform(self, fp):
fm, train_x, train_y = FeaturePool.to_train_arrays(fp)
os = SMOTE(random_state = self.random_state)
os_train_x, os_train_y = os.fit_sample(train_x, train_y[:, 0])
os_train_y = os_train_y.reshape((os_train_y.shape[0], 1))
for f in FeaturePool.from_train_arrays(fm, os_train_x, os_train_y):
yield Feature.apply_config(f, is_over_sampled=True)
for f in fp:
if f.split_type == SplitType.TEST:
yield f