AttributeError: 'bool' object has no attribute 'sum' when use UpliftTreeClassifier fill()

[zz0807]

Describe the bug
I used the fill() function of UpliftTreeClassifier according to the documentation, where the parameters are specified as NumPy arrays

However, I encountered a bug.

uplift_model.fill(X=X_val, treatment=treatment_val, y=y_val)
File "causalml/inference/tree/uplift.pyx", line 534, in causalml.inference.tree.uplift.UpliftTreeClassifier.fill
File "causalml/inference/tree/uplift.pyx", line 557, in causalml.inference.tree.uplift.UpliftTreeClassifier.fillTree
File "causalml/inference/tree/uplift.pyx", line 846, in causalml.inference.tree.uplift.UpliftTreeClassifier.tree_node_summary
File "causalml/inference/tree/uplift.pyx", line 667, in causalml.inference.tree.uplift.UpliftTreeClassifier.group_uniqueCounts
AttributeError: 'bool' object has no attribute 'sum'

To Reproduce
`import numpy as np
import pandas as pd
from causalml.inference.tree import UpliftTreeClassifier
from sklearn.model_selection import train_test_split

data = pd.DataFrame({
'feature1': np.random.rand(1000000),
'feature2': np.random.rand(1000000),
'treatment': np.random.choice([0, 1], 1000000),
'outcome': np.random.choice([0, 1], 1000000)
})

X = data[['feature1', 'feature2']]
treatment = np.where(data['treatment'] == 0, 'control', 'treatment') #
y = data['outcome']

X_train, X_val, treatment_train, treatment_val, y_train, y_val = train_test_split(
X, treatment, y, test_size=0.2, random_state=42
)

uplift_model = UpliftTreeClassifier(
max_depth=3,
min_samples_leaf=200,
min_samples_treatment=5,
n_reg=100,
evaluationFunction='KL',
control_name='control'
)

uplift_model.fit(X=X_train.values, treatment=treatment_train, y=y_train.values)

uplift_model.fill(X=X_val.values, treatment=treatment_val, y=y_val.values)`

Environment (please complete the following information):

• OS:linux
• Python Version: 3.7,7