scikits.learn.glm.sparse.Lasso¶

class scikits.learn.glm.sparse.Lasso(alpha=1.0, coef_=None, fit_intercept=False)¶

Linear Model trained with L1 prior as regularizer

This implementation works on scipy.sparse X and dense coef_. Technically this is the same as Elastic Net with the L2 penalty set to zero.

Parameters :

alpha : float

Constant that multiplies the L1 term. Defaults to 1.0

coef_ : ndarray of shape n_features

The initial coeffients to warm-start the optimization

fit_intercept: bool :

Whether the intercept should be estimated or not. If False, the data is assumed to be already centered.

Methods

fit(X, Y, maxit=1000, tol=0.0001, **params)¶

Fit current model with coordinate descent

X is expected to be a sparse matrix. For maximum efficiency, use a sparse matrix in CSC format (scipy.sparse.csc_matrix)

predict(X)¶

Predict using the linear model

Parameters :	X : scipy.sparse matrix of shape [n_samples, n_features]
Returns :	array, shape = [n_samples] with the predicted real values :

score(X, y)¶

Returns the explained variance of the prediction

Parameters :

X : array-like, shape = [n_samples, n_features]

Training set.

y : array-like, shape = [n_samples]

Returns :

z : float