def test_n_directions_auto_heuristic():
X, y = datasets.make_exponential(random_state=123)
sir = SlicedInverseRegression(n_directions='auto').fit(X, y)
assert sir.n_directions_ == 2
X_sir = sir.transform(X)
assert X_sir.shape == (500, 2)
def test_regression():
"""NOTE: subsequent calls may flip the direction of eigenvectors
(mulitply by -1), so we can only compare absolute values.
This was not a problem for svds.. investigate if we can get
deterministic behavior back.
"""
X, y = datasets.make_cubic(random_state=123)
for n_dir in range(1, X.shape[1]):
sir = SlicedInverseRegression(n_directions=n_dir)
# take shape is correct
X_sir = sir.fit(X, y).transform(X)
np.testing.assert_equal(X_sir.shape[1], n_dir)
# should match fit_transform
X_sir2 = sir.fit_transform(X, y)
np.testing.assert_allclose(np.abs(X_sir), np.abs(X_sir2))
# call transform again and check if things are okay
X_sir = sir.transform(X)
X_sir2 = sir.fit_transform(X, y)
np.testing.assert_allclose(np.abs(X_sir), np.abs(X_sir2))
# there is one true angle it should fine
true_beta = (1 / np.sqrt(2)) * np.hstack((np.ones(2), np.zeros(8)))
angle = np.dot(true_beta, sir.directions_[0, :])
np.testing.assert_allclose(np.abs(angle), 1, rtol=1e-1)
def test_classification():
"""SIR is LDA for classification so lets test some predictions."""
# Data is just 6 separable points in the plane
X = np.array([[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]],
dtype=np.float64)
y = np.array([1, 1, 1, 0, 0, 0])
sir = SlicedInverseRegression(n_directions=1, n_slices=2).fit(X, y)
lda = LinearDiscriminantAnalysis(solver='eigen').fit(X, y)
y_pred = sir.transform(X) > 0
np.testing.assert_equal(y, y_pred.ravel())
np.testing.assert_equal(lda.predict(X), y_pred.ravel())
"""
=======================
Binary Targets with SIR
=======================
Sliced Inverse Regression is able to find a one-dimensional subspace
that seperates cases in the famous breast cancer dataset.
"""
import matplotlib.pyplot as plt
from sklearn.datasets import load_breast_cancer
from sliced import SlicedInverseRegression
X, y = load_breast_cancer(return_X_y=True)
sir = SlicedInverseRegression(n_directions=2).fit(X, y)
X_sir = sir.transform(X)
plt.scatter(X_sir[:, 0], X_sir[:, 1], c=y, alpha=0.8, edgecolor='k')
plt.xlabel("$X\hat{\\beta}_{1}$")
plt.ylabel("$X\hat{\\beta}_{2}$")
plt.title("Breast Cancer Data")
plt.show()