pythonはランダム森林モデルで数値変数の欠落値を補充する

# data_df: DataFrame     
# obj_column：         
# missing_other_column：           
##########      

def fill_miss_byRandomForest(data_df , obj_column, missing_other_column ):
    ##             missing_other_column
    data_df = data_df.drop(missing_other_column , axis = 1)
    #                 
    known = data_df[data_df[obj_column].notnull()]
    unknown = data_df[data_df[obj_column].isnull()]
    # y      
    y_know = known[obj_column]
    # X      
    X_know= known.drop(obj_column , axis = 1)
    from sklearn.ensemble import RandomForestRegressor
    rfr = RandomForestRegressor(random_state=0, n_estimators=200,max_depth=3,n_jobs=-1)
    rfr.fit(X_know,y_know)
    #                
    # X      
    X_unknow= unknown.drop(obj_column , axis = 1)
    predicted = rfr.predict(X_unknow).round(0)
    data_df.loc[(data_df[obj_column].isnull()), obj_column] = predicted
    return data_df

if __name__ == '__main__':
    import pandas as pd
    import numpy as np
    data = pd.read_csv('data/cs-training.csv')
    data.describe()
    data.columns.tolist()
    ###   fill_miss_byRandomForest  ，  MonthlyIncome    
    data1_MonthlyIncome=fill_miss_byRandomForest(data , 'MonthlyIncome' , 'NumberOfDependents')#       MonthlyIncome