def test_SVR(): """ Test Support Vector Regression """ diabetes = datasets.load_diabetes() for clf in (svm.NuSVR(kernel='linear', nu=.4), svm.SVR(kernel='linear', C=10.), svm.sparse.NuSVR(kernel='linear', nu=.4), svm.sparse.SVR(kernel='linear', C=10.)): clf.fit(diabetes.data, diabetes.target) assert clf.score(diabetes.data, diabetes.target) > 0.02
def test_bayesian_on_diabetes(): """ Test BayesianRidge on diabetes """ diabetes = datasets.load_diabetes() X, y = diabetes.data, diabetes.target clf = BayesianRidge(compute_score=True) # Test with more samples than features clf.fit(X, y) # Test that scores are increasing at each iteration assert_array_equal(np.diff(clf.all_score_) > 0, True) # Test with more features than samples X = X[:5, :] y = y[:5] clf.fit(X, y) # Test that scores are increasing at each iteration assert_array_equal(np.diff(clf.all_score_) > 0, True)
def test_bayesian_on_diabetes(): """ Test BayesianRidge on diabetes """ raise nose.SkipTest("XFailed Test") diabetes = datasets.load_diabetes() X, y = diabetes.data, diabetes.target clf = BayesianRidge(compute_score=True) # Test with more samples than features clf.fit(X, y) # Test that scores are increasing at each iteration assert_array_equal(np.diff(clf.scores_) > 0, True) # Test with more features than samples X = X[:5, :] y = y[:5] clf.fit(X, y) # Test that scores are increasing at each iteration assert_array_equal(np.diff(clf.scores_) > 0, True)
import numpy as np from numpy.testing import (assert_array_almost_equal, assert_almost_equal) from nose.tools import assert_equal, assert_true from ..lars import lars_path, LassoLARS, LARS from ..coordinate_descent import Lasso from scikits.learn import datasets n, m = 10, 10 np.random.seed (0) diabetes = datasets.load_diabetes() X, y = diabetes.data, diabetes.target def test_simple(): """ Principle of LARS is to keep covariances tied and decreasing """ max_pred = 10 alphas_, active, coef_path_ = lars_path(diabetes.data, diabetes.target, max_iter=max_pred, method="lar") for (i, coef_) in enumerate(coef_path_.T): res = y - np.dot(X, coef_) cov = np.dot(X.T, res) C = np.max(abs(cov)) eps = 1e-3 ocur = len(cov[ C - eps < abs(cov)]) if i < max_pred: assert ocur == i+1
determination (R2) without reperforming MLE, using the set of correlation parameters found on the whole dataset. """ print __doc__ # Author: Vincent Dubourg <*****@*****.**> # License: BSD style import numpy as np from scikits.learn import datasets from scikits.learn.gaussian_process import GaussianProcess from scikits.learn.cross_val import cross_val_score, KFold from scikits.learn.metrics import r2_score # Load the dataset from scikits' data sets diabetes = datasets.load_diabetes() X, y = diabetes.data, diabetes.target # Instanciate a GP model gp = GaussianProcess(regr='constant', corr='absolute_exponential', theta0=[1e-4] * 10, thetaL=[1e-12] * 10, thetaU=[1e-2] * 10, nugget=1e-2, optimizer='Welch') # Fit the GP model to the data performing maximum likelihood estimation gp.fit(X, y) # Deactivate maximum likelihood estimation for the cross-validation loop
"On the degrees of freedom of the lasso" Hui Zou, Trevor Hastie, and Robert Tibshirani Ann. Statist. Volume 35, Number 5 (2007), 2173-2192. """ print __doc__ # Author: Alexandre Gramfort <*****@*****.**> # License: BSD Style. from math import log import numpy as np from scikits.learn.linear_model import lars_path from scikits.learn.datasets import load_diabetes diabetes = load_diabetes() X, y = diabetes.data, diabetes.target # add garbage features rng = np.random.RandomState(42) X = np.c_[X, rng.randn(X.shape[0], 10)] n_samples = X.shape[0] # Standardize the data to avoid intercept problems y -= np.mean(y) X -= np.mean(X, axis=0) X /= np.std(X, axis=0) print "Computing regularization path using the LARS ..." alphas, features, coefs = lars_path(X, y, method='lasso', verbose=True)