def _test_ridge_loo(filter_):
# test that can work with both dense or sparse matrices
n_samples = X_diabetes.shape[0]
ret = []
ridge_gcv = _RidgeGCV(fit_intercept=False)
ridge = Ridge(fit_intercept=False)
# generalized cross-validation (efficient leave-one-out)
K, v, Q = ridge_gcv._pre_compute(X_diabetes, y_diabetes)
errors, c = ridge_gcv._errors(v, Q, y_diabetes, 1.0)
values, c = ridge_gcv._values(K, v, Q, y_diabetes, 1.0)
# brute-force leave-one-out: remove one example at a time
errors2 = []
values2 = []
for i in range(n_samples):
sel = np.arange(n_samples) != i
X_new = X_diabetes[sel]
y_new = y_diabetes[sel]
ridge.fit(X_new, y_new)
value = ridge.predict([X_diabetes[i]])[0]
error = (y_diabetes[i] - value)**2
errors2.append(error)
values2.append(value)
# check that efficient and brute-force LOO give same results
assert_almost_equal(errors, errors2)
assert_almost_equal(values, values2)
# check best alpha
ridge_gcv.fit(filter_(X_diabetes), y_diabetes)
best_alpha = ridge_gcv.best_alpha
ret.append(best_alpha)
# check that we get same best alpha with custom loss_func
ridge_gcv2 = _RidgeGCV(fit_intercept=False, loss_func=mean_square_error)
ridge_gcv2.fit(filter_(X_diabetes), y_diabetes)
assert_equal(ridge_gcv2.best_alpha, best_alpha)
# check that we get same best alpha with sample weights
ridge_gcv.fit(filter_(X_diabetes),
y_diabetes,
sample_weight=np.ones(n_samples))
assert_equal(ridge_gcv.best_alpha, best_alpha)
# simulate several responses
Y = np.vstack((y_diabetes, y_diabetes)).T
ridge_gcv.fit(filter_(X_diabetes), Y)
Y_pred = ridge_gcv.predict(filter_(X_diabetes))
ridge_gcv.fit(filter_(X_diabetes), y_diabetes)
y_pred = ridge_gcv.predict(filter_(X_diabetes))
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred, decimal=5)
return ret
def _test_ridge_loo(filter_):
# test that can work with both dense or sparse matrices
n_samples = X_diabetes.shape[0]
ret = []
ridge_gcv = _RidgeGCV(fit_intercept=False)
ridge = Ridge(fit_intercept=False)
# generalized cross-validation (efficient leave-one-out)
K, v, Q = ridge_gcv._pre_compute(X_diabetes, y_diabetes)
errors, c = ridge_gcv._errors(v, Q, y_diabetes, 1.0)
values, c = ridge_gcv._values(K, v, Q, y_diabetes, 1.0)
# brute-force leave-one-out: remove one example at a time
errors2 = []
values2 = []
for i in range(n_samples):
sel = np.arange(n_samples) != i
X_new = X_diabetes[sel]
y_new = y_diabetes[sel]
ridge.fit(X_new, y_new)
value = ridge.predict([X_diabetes[i]])[0]
error = (y_diabetes[i] - value) ** 2
errors2.append(error)
values2.append(value)
# check that efficient and brute-force LOO give same results
assert_almost_equal(errors, errors2)
assert_almost_equal(values, values2)
# check best alpha
ridge_gcv.fit(filter_(X_diabetes), y_diabetes)
best_alpha = ridge_gcv.best_alpha
ret.append(best_alpha)
# check that we get same best alpha with custom loss_func
ridge_gcv2 = _RidgeGCV(fit_intercept=False, loss_func=mean_square_error)
ridge_gcv2.fit(filter_(X_diabetes), y_diabetes)
assert_equal(ridge_gcv2.best_alpha, best_alpha)
# check that we get same best alpha with sample weights
ridge_gcv.fit(filter_(X_diabetes), y_diabetes,
sample_weight=np.ones(n_samples))
assert_equal(ridge_gcv.best_alpha, best_alpha)
# simulate several responses
Y = np.vstack((y_diabetes,y_diabetes)).T
ridge_gcv.fit(filter_(X_diabetes), Y)
Y_pred = ridge_gcv.predict(filter_(X_diabetes))
ridge_gcv.fit(filter_(X_diabetes), y_diabetes)
y_pred = ridge_gcv.predict(filter_(X_diabetes))
assert_array_almost_equal(np.vstack((y_pred,y_pred)).T,
Y_pred, decimal=5)
return ret
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert score >= score2
def _test_tolerance(filter_):
ridge = Ridge(tol=1e-5)
ridge.fit(filter_(X_diabetes), y_diabetes)
score = ridge.score(filter_(X_diabetes), y_diabetes)
ridge2 = Ridge(tol=1e-3)
ridge2.fit(filter_(X_diabetes), y_diabetes)
score2 = ridge2.score(filter_(X_diabetes), y_diabetes)
assert score >= score2
def _test_multi_ridge_diabetes(filter_):
# simulate several responses
Y = np.vstack((y_diabetes, y_diabetes)).T
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), Y)
Y_pred = ridge.predict(filter_(X_diabetes))
ridge.fit(filter_(X_diabetes), y_diabetes)
y_pred = ridge.predict(filter_(X_diabetes))
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred, decimal=3)
def _test_multi_ridge_diabetes(filter_):
# simulate several responses
Y = np.vstack((y_diabetes, y_diabetes)).T
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), Y)
Y_pred = ridge.predict(filter_(X_diabetes))
ridge.fit(filter_(X_diabetes), y_diabetes)
y_pred = ridge.predict(filter_(X_diabetes))
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred)
def _test_multi_ridge_diabetes(filter_):
# simulate several responses
Y = np.vstack((y_diabetes,y_diabetes)).T
n_features = X_diabetes.shape[1]
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), Y)
assert_equal(ridge.coef_.shape, (2, n_features))
Y_pred = ridge.predict(filter_(X_diabetes))
ridge.fit(filter_(X_diabetes), y_diabetes)
y_pred = ridge.predict(filter_(X_diabetes))
assert_array_almost_equal(np.vstack((y_pred,y_pred)).T,
Y_pred, decimal=3)
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert_equal(ridge.coef_.shape, (X.shape[1], ))
assert ridge.score(X, y) > 0.5
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.5
# With more features than samples
n_samples, n_features = 5, 10
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert ridge.score(X, y) > .9
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.9
def test_ridge():
"""Ridge regression convergence test using score
TODO: for this test to be robust, we should use a dataset instead
of np.random.
"""
alpha = 1.0
# With more samples than features
n_samples, n_features = 6, 5
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert ridge.score(X, y) > 0.5
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.5
# With more features than samples
n_samples, n_features = 5, 10
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=alpha)
ridge.fit(X, y)
assert ridge.score(X, y) > .9
ridge.fit(X, y, sample_weight=np.ones(n_samples))
assert ridge.score(X, y) > 0.9
def test_ridge_vs_lstsq():
"""On alpha=0., Ridge and OLS yield the same solution."""
# we need more samples than features
n_samples, n_features = 5, 4
np.random.seed(0)
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=0.)
ols = LinearRegression()
ridge.fit(X, y)
ols.fit (X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
ridge.fit(X, y, fit_intercept=False)
ols.fit (X, y, fit_intercept=False)
assert_almost_equal(ridge.coef_, ols.coef_)
def test_ridge_vs_lstsq():
"""On alpha=0., Ridge and OLS yield the same solution."""
# we need more samples than features
n_samples, n_features = 5, 4
np.random.seed(0)
y = np.random.randn(n_samples)
X = np.random.randn(n_samples, n_features)
ridge = Ridge(alpha=0.)
ols = LinearRegression()
ridge.fit(X, y)
ols.fit(X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
ridge.fit(X, y, fit_intercept=False)
ols.fit(X, y, fit_intercept=False)
assert_almost_equal(ridge.coef_, ols.coef_)
def test_toy_ridge_object():
"""Test BayesianRegression ridge classifier
TODO: test also n_samples > n_features
"""
X = np.array([[1], [2]])
Y = np.array([1, 2])
clf = Ridge(alpha=0.0)
clf.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert_almost_equal(clf.predict(X_test), [1., 2, 3, 4])
assert_equal(len(clf.coef_.shape), 1)
assert_equal(type(clf.intercept_), np.float64)
Y = np.vstack((Y,Y)).T
clf.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert_equal(len(clf.coef_.shape), 2)
assert_equal(type(clf.intercept_), np.ndarray)
def test_toy_ridge_object():
"""Test BayesianRegression ridge classifier
TODO: test also n_samples > n_features
"""
X = np.array([[1], [2]])
Y = np.array([1, 2])
clf = Ridge(alpha=0.0)
clf.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert_almost_equal(clf.predict(X_test), [1., 2, 3, 4])
assert_equal(len(clf.coef_.shape), 1)
assert_equal(type(clf.intercept_), np.float64)
Y = np.vstack((Y, Y)).T
clf.fit(X, Y)
X_test = [[1], [2], [3], [4]]
assert_equal(len(clf.coef_.shape), 2)
assert_equal(type(clf.intercept_), np.ndarray)
def _test_ridge_diabetes(filter_):
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
return np.round(ridge.score(filter_(X_diabetes), y_diabetes), 5)
def _test_ridge_diabetes(filter_):
ridge = Ridge(fit_intercept=False)
ridge.fit(filter_(X_diabetes), y_diabetes)
return np.round(ridge.score(filter_(X_diabetes), y_diabetes), 5)