3.2.3.1.5. sklearn.linear_model.LassoCV¶
- class sklearn.linear_model.LassoCV(eps=0.001, n_alphas=100, alphas=None, fit_intercept=True, normalize=False, precompute='auto', max_iter=1000, tol=0.0001, copy_X=True, cv=None, verbose=False)¶
Lasso linear model with iterative fitting along a regularization path
The best model is selected by cross-validation.
The optimization objective for Lasso is:
(1 / (2 * n_samples)) * ||y - Xw||^2_2 + alpha * ||w||_1
Parameters : eps : float, optional
Length of the path. eps=1e-3 means that alpha_min / alpha_max = 1e-3.
n_alphas : int, optional
Number of alphas along the regularization path
alphas : numpy array, optional
List of alphas where to compute the models. If None alphas are set automatically
precompute : True | False | ‘auto’ | array-like
Whether to use a precomputed Gram matrix to speed up calculations. If set to 'auto' let us decide. The Gram matrix can also be passed as argument.
max_iter: int, optional :
The maximum number of iterations
tol: float, optional :
The tolerance for the optimization: if the updates are smaller than tol, the optimization code checks the dual gap for optimality and continues until it is smaller than tol.
cv : integer or cross-validation generator, optional
If an integer is passed, it is the number of fold (default 3). Specific cross-validation objects can be passed, see the sklearn.cross_validation module for the list of possible objects.
verbose : bool or integer
amount of verbosity
See also
Notes
See examples/linear_model/lasso_path_with_crossvalidation.py for an example.
To avoid unnecessary memory duplication the X argument of the fit method should be directly passed as a Fortran-contiguous numpy array.
Attributes
alpha_ float The amount of penalization chosen by cross validation coef_ array, shape = (n_features,) | (n_targets, n_features) parameter vector (w in the cost function formula) intercept_ float | array, shape = (n_targets,) independent term in decision function. mse_path_ array, shape = (n_alphas, n_folds) mean square error for the test set on each fold, varying alpha alphas_ numpy array The grid of alphas used for fitting l1_ratio_ int An artifact of the super class LinearModelCV. In this case, l1_ratio_ = 1 because the Lasso estimator uses an L1 penalty by definition. Typically it is a float between 0 and 1 passed to an estimator such as ElasticNet (scaling between l1 and l2 penalties). For l1_ratio = 0 the penalty is an L2 penalty. For l1_ratio = 1 it is an L1 penalty. dual_gap_ numpy array The dual gap at the end of the optimization for the optimal alpha (alpha_). Methods
decision_function(X) Decision function of the linear model. fit(X, y) Fit linear model with coordinate descent get_params([deep]) Get parameters for this estimator. path(X, y[, eps, n_alphas, alphas, ...]) Compute Lasso path with coordinate descent predict(X) Predict using the linear model score(X, y) Returns the coefficient of determination R^2 of the prediction. set_params(**params) Set the parameters of this estimator. - __init__(eps=0.001, n_alphas=100, alphas=None, fit_intercept=True, normalize=False, precompute='auto', max_iter=1000, tol=0.0001, copy_X=True, cv=None, verbose=False)¶
- decision_function(X)¶
Decision function of the linear model.
Parameters : X : {array-like, sparse matrix}, shape = (n_samples, n_features)
Samples.
Returns : C : array, shape = (n_samples,)
Returns predicted values.
- fit(X, y)¶
Fit linear model with coordinate descent
Fit is on grid of alphas and best alpha estimated by cross-validation.
Parameters : X : {array-like, sparse matrix}, shape (n_samples, n_features)
Training data. Pass directly as float64, Fortran-contiguous data to avoid unnecessary memory duplication
y : array-like, shape (n_samples,) or (n_samples, n_targets)
Target values
- get_params(deep=True)¶
Get parameters for this estimator.
Parameters : deep: boolean, optional :
If True, will return the parameters for this estimator and contained subobjects that are estimators.
Returns : params : mapping of string to any
Parameter names mapped to their values.
- static path(X, y, eps=0.001, n_alphas=100, alphas=None, precompute='auto', Xy=None, fit_intercept=None, normalize=None, copy_X=True, coef_init=None, verbose=False, return_models=False, **params)¶
Compute Lasso path with coordinate descent
The optimization objective for Lasso is:
(1 / (2 * n_samples)) * ||y - Xw||^2_2 + alpha * ||w||_1
Parameters : X : {array-like, sparse matrix}, shape (n_samples, n_features)
Training data. Pass directly as Fortran-contiguous data to avoid unnecessary memory duplication
y : ndarray, shape = (n_samples,)
Target values
eps : float, optional
Length of the path. eps=1e-3 means that alpha_min / alpha_max = 1e-3
n_alphas : int, optional
Number of alphas along the regularization path
alphas : ndarray, optional
List of alphas where to compute the models. If None alphas are set automatically
precompute : True | False | ‘auto’ | array-like
Whether to use a precomputed Gram matrix to speed up calculations. If set to 'auto' let us decide. The Gram matrix can also be passed as argument.
Xy : array-like, optional
Xy = np.dot(X.T, y) that can be precomputed. It is useful only when the Gram matrix is precomputed.
fit_intercept : bool
Fit or not an intercept. WARNING : will be deprecated in 0.16
normalize : boolean, optional, default False
If True, the regressors X will be normalized before regression. WARNING : will be deprecated in 0.16
copy_X : boolean, optional, default True
If True, X will be copied; else, it may be overwritten.
coef_init : array, shape (n_features, ) | None
The initial values of the coefficients.
verbose : bool or integer
Amount of verbosity
return_models : boolean, optional, default True
If True, the function will return list of models. Setting it to False will change the function output returning the values of the alphas and the coefficients along the path. Returning the model list will be removed in version 0.16.
params : kwargs
keyword arguments passed to the coordinate descent solver.
Returns : models : a list of models along the regularization path
(Is returned if return_models is set True (default).
alphas : array, shape: [n_alphas + 1]
The alphas along the path where models are computed. (Is returned, along with coefs, when return_models is set to False)
coefs : shape (n_features, n_alphas + 1)
Coefficients along the path. (Is returned, along with alphas, when return_models is set to False).
dual_gaps : shape (n_alphas + 1)
The dual gaps at the end of the optimization for each alpha. (Is returned, along with alphas, when return_models is set to False).
See also
lars_path, Lasso, LassoLars, LassoCV, LassoLarsCV, sklearn.decomposition.sparse_encode
Notes
See examples/linear_model/plot_lasso_coordinate_descent_path.py for an example.
To avoid unnecessary memory duplication the X argument of the fit method should be directly passed as a Fortran-contiguous numpy array.
Note that in certain cases, the Lars solver may be significantly faster to implement this functionality. In particular, linear interpolation can be used to retrieve model coefficients between the values output by lars_path
Deprecation Notice: Setting return_models to False will make the Lasso Path return an output in the style used by lars_path. This will be become the norm as of version 0.16. Leaving return_models set to True will let the function return a list of models as before.
Examples
Comparing lasso_path and lars_path with interpolation:
>>> X = np.array([[1, 2, 3.1], [2.3, 5.4, 4.3]]).T >>> y = np.array([1, 2, 3.1]) >>> # Use lasso_path to compute a coefficient path >>> _, coef_path, _ = lasso_path(X, y, alphas=[5., 1., .5], ... fit_intercept=False) >>> print(coef_path) [[ 0. 0. 0.46874778] [ 0.2159048 0.4425765 0.23689075]]
>>> # Now use lars_path and 1D linear interpolation to compute the >>> # same path >>> from sklearn.linear_model import lars_path >>> alphas, active, coef_path_lars = lars_path(X, y, method='lasso') >>> from scipy import interpolate >>> coef_path_continuous = interpolate.interp1d(alphas[::-1], ... coef_path_lars[:, ::-1]) >>> print(coef_path_continuous([5., 1., .5])) [[ 0. 0. 0.46915237] [ 0.2159048 0.4425765 0.23668876]]
- predict(X)¶
Predict using the linear model
Parameters : X : {array-like, sparse matrix}, shape = (n_samples, n_features)
Samples.
Returns : C : array, shape = (n_samples,)
Returns predicted values.
- score(X, y)¶
Returns the coefficient of determination R^2 of the prediction.
The coefficient R^2 is defined as (1 - u/v), where u is the regression sum of squares ((y_true - y_pred) ** 2).sum() and v is the residual sum of squares ((y_true - y_true.mean()) ** 2).sum(). Best possible score is 1.0, lower values are worse.
Parameters : X : array-like, shape = (n_samples, n_features)
Test samples.
y : array-like, shape = (n_samples,)
True values for X.
Returns : score : float
R^2 of self.predict(X) wrt. y.
- set_params(**params)¶
Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as pipelines). The former have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.
Returns : self :