v Lasso Regression - Machine Learning

Lasso Regression

Preliminaries

# Load library
from sklearn.linear_model import Lasso
from sklearn.datasets import load_boston
from sklearn.preprocessing import StandardScaler

Load Boston Housing Dataset

# Load data
boston = load_boston()
X = boston.data
y = boston.target

Standardize Features

# Standarize features
scaler = StandardScaler()
X_std = scaler.fit_transform(X)

Fit Ridge Regression

The hyperparameter, \(\alpha\), lets us control how much we penalize the coefficients, with higher values of \(\alpha\) creating simpler modelers. The ideal value of \(\alpha\) should be tuned like any other hyperparameter. In scikit-learn, \(\alpha\) is set using the alpha parameter.

# Create lasso regression with alpha value
regr = Lasso(alpha=0.5)

# Fit the linear regression
model = regr.fit(X_std, y)