FYS-STK4155/doc/MathFoundationML/PythonCode_Regressions.ipynb

Documents for the Linear, Ridge and Lasso regressions in the sklearn package:

Linear: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html

Ridge: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html

Lasso: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html

In [7]:

from sklearn import linear_model
import numpy as np

# Form the coefficient matrix of the linear system
X_transpose = np.array([[1, 1], [1, 2], [2, 2], [2, 3]])


# The underlying linear function is y = 1 * x_1 + 2 * x_2 + epsilon
epsilon = np.random.rand(4,)
y = np.dot(X_transpose, np.array([1, 2])) + epsilon


# Various regression models
#clf = linear_model.LinearRegression()
#clf = linear_model.Ridge(alpha=0.1)
clf = linear_model.Lasso(alpha=0.1)

# Fit the model to the data
clf.fit(X_transpose, y)


# Print the regression coefficients
print(clf.coef_)

[0.15631421 2.24887843]

In [ ]: