I'm Implementing Missforest (using Scikit-Learn) for my mixed type data but it doesn't work correctly for my categorical features. For example, 1.6 is replaced for Gender instead of 1 or 0 and doesn't calculate mode for categorical variables. I have used these lines in python.
import sklearn.neighbors._base
sys.modules['sklearn.neighbors.base'] = sklearn.neighbors._base
from missingpy import MissForest
Imputer = MissForest()
X_imputed = imputer.fit_transform(data)