AssertionError: Control group level 0 not found in treatment vector.

[hossein-amini67]

from causalml.inference.meta import LRSRegressor
from causalml.inference.meta import XGBTRegressor, MLPTRegressor
from causalml.inference.meta import BaseXRegressor
from causalml.inference.meta import BaseRRegressor
from xgboost import XGBRegressor
from causalml.dataset import synthetic_data
import numpy as np
import pandas as pd

df = pd.read_csv('sample_data/configuration_900.out',sep = "\s+",header = None)

df.columns = ['x','y','s','theta','curvature','near']

MIDD = 500


def find_midd(input_list): #middleIndex %2 != 0:
    middleIndex = int(float(len(input_list))) /2
    if middleIndex %2 == 0:
        return middleIndex 
    else:
        return middleIndex - 0.5

excess = df.iloc[:,-1]

middleindex = find_midd(excess)
middleindex = int(middleindex)

new_theta_up = df.iloc[:middleindex,3]
new_cur_up   = df.iloc[:middleindex,4]
new_exc_up   = df.iloc[:middleindex,5]


df_up = {'col1':new_theta_up,'col2':new_cur_up,'col3':new_exc_up}

df_up = pd.DataFrame(df_up)

df_up.columns = ['theta','Curvature','Target']

targ = excess[middleindex]

new_targ = np.repeat(targ,len(df_down))

y = new_targ


X = df_up

y = new_targ

treatment = df_down

lr = LRSRegressor()
te, lb, ub = lr.estimate_ate(X, treatment, y)
print('Average Treatment Effect (Linear Regression): {:.2f} ({:.2f}, {:.2f})'.format(te[0], lb[0], ub[0]))

Just in this case that the data made up on my own, the X's shape is 682x3 as my control group, the treatment's shape is 682x3 as my treatment group and y is my target that is 682.
But I faced the error above. All suggestions will be appreciated.

[paullo0106]

Thanks for initializing a discussion! Replied yesterday on the comment here to #382 (comment)