how to Set up a scikit-learn pipeline to handle missing values in numeric features code example

Example: replace missing values, encoded as np.nan, using the mean value of the columns

# Univariate feature imputation

import numpy as np
from sklearn.impute import SimpleImputer
imp = SimpleImputer(missing_values=np.nan, strategy='mean')
imp.fit([[1, 2], [np.nan, 3], [7, 6]])
# SimpleImputer()
X = [[np.nan, 2], [6, np.nan], [7, 6]]
print(imp.transform(X))
# [[4.          2.        ]
#  [6.          3.666...]
#  [7.          6.        ]]

# SimpleImputer class also supports categorical data

import pandas as pd
df = pd.DataFrame([["a", "x"],
                   [np.nan, "y"],
                   ["a", np.nan],
                   ["b", "y"]], dtype="category")

imp = SimpleImputer(strategy="most_frequent")
print(imp.fit_transform(df))
# [['a' 'x']
#  ['a' 'y']
#  ['a' 'y']
#  ['b' 'y']]