Code
machine-learning
import numpy as np
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
from sklearn.impute import SimpleImputer
X = np.array([[1, 2], [3, np.nan], [5, 6], [7, 8]])
# Impute missing values
imputer = SimpleImputer(strategy="mean")
X_imp = imputer.fit_transform(X)
# Standardize (zero mean, unit variance)
scaler = StandardScaler()
X_std = scaler.fit_transform(X_imp)
# Scale to [0, 1]
minmax = MinMaxScaler()
X_mm = minmax.fit_transform(X_imp)
# One-hot encode categorical features
enc = OneHotEncoder(sparse_output=False, handle_unknown="ignore")
X_cat = enc.fit_transform([["red"], ["green"], ["blue"], ["red"]])
print(X_std, X_cat)