def test_linear_regression(self):
np.random.seed(55)
X = np.random.rand(1000, 3)
w = [0.5, 1.3, -2.5]
b = 12.5
y = X[:, 0] * w[0] + X[:, 1] * w[1] + X[:, 2] * w[2] + b
# should convert to the exact solution with only a little regularization
lr = LinearRegression(lam=0.001)
lr.fit(X, y)
ypred = lr.predict(X)
self.assertTrue(pearsonr_weighted(y, ypred) > 0.99)
# try weighted
weights = np.random.rand(1000)
lr = LinearRegression(lam=0.001)
lr.fit(X, y, weights=weights)
ypred = lr.predict(X)
self.assertTrue(pearsonr_weighted(y, ypred, weights))
def test_pearson_weighted(self):
from scipy.stats import pearsonr
x = np.array([1, 2, 3, 4, 5])
y = np.array([1.0, 1.5, -0.5, 3.4, 2.9])
weights = np.array([1, 0, 0.5, 2, 1.5])
r_no_wgt = pearsonr(x, y)[0]
r_no_wgt_test = evaluation.pearsonr_weighted(x, y)
r_ones_wgt = evaluation.pearsonr_weighted(x, y, np.ones(x.shape))
self.assertTrue(abs(r_no_wgt - r_no_wgt_test) < 1e-12)
self.assertTrue(abs(r_no_wgt - r_ones_wgt) < 1e-12)
xm = mean_std_weighted(x, weights)
ym = mean_std_weighted(y, weights)
r_wgt = np.sum(
(x - xm['mean']) * (y - ym['mean']) * weights) / np.sum(weights)
self.assertTrue(
(evaluation.pearsonr_weighted(x, y, weights) - r_wgt) < 1e-12)
