imputation

imputation.py

from sklearn.preprocessing import Imputer
import numpy as np

imputer = Imputer(strategy='mean', axis=0)
imputer.fit(np.array([[4, 400, 30],
                      [5, 300, 25]]))
print(imputer.statistics_)
# [4.5     350     27.5]
              
print(imputer.transform([[4,        800,       np.nan],
                         [np.nan,   500,       40],
                         [2,        np.nan,    32]]))
# [[4      800     27.5],
#  [4.5    500     40],
#  [2      350     32]]