imputation sklearn training code example
Example: replace missing values, encoded as np.nan, using the mean value of the columns
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]])
X = [[np.nan, 2], [6, np.nan], [7, 6]]
print(imp.transform(X))
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))