def test_lr(nps_app_inst: ArrayApplication):
num_samples, num_features = 1000, 10
rs = np.random.RandomState(1337)
real_theta = rs.random_sample(num_features)
real_X, real_y = BimodalGaussian.get_dataset(233, num_features, theta=real_theta)
X = nps_app_inst.array(real_X, block_shape=(100, 3))
y = nps_app_inst.array(real_y, block_shape=(100,))
param_set = [
{"solver": "gd", "lr": 1e-6, "tol": 1e-8, "max_iter": 100},
{"solver": "newton", "tol": 1e-8, "max_iter": 10},
]
for kwargs in param_set:
runtime = time.time()
model: LinearRegression = LinearRegression(**kwargs)
model.fit(X, y)
assert model._beta.shape == real_theta.shape and model._beta0.shape == ()
runtime = time.time() - runtime
y_pred = model.predict(X).get()
print("opt", kwargs["solver"])
print("runtime", runtime)
print("norm", model.grad_norm_sq(X, y).get())
print("objective", model.objective(X, y).get())
print("error", np.sum((y.get() - y_pred) ** 2) / num_samples)
print("D^2", model.deviance_sqr(X, y).get())
# Test if integer array arguments will converge properly.
X = nps_app_inst.array([[1, 2], [3, 5], [1, 5]], block_shape=(2, 2))
y = nps_app_inst.array([1, 2, 3], block_shape=(2,))
model: LinearRegression = LinearRegression()
model.fit(X, y)
try:
pred = model.predict([1, 2]).get()
assert 0.9 < pred < 1.1
except OverflowError:
assert False, "LinearRegression overflows with integer array arguments."
def test_sklearn_linear_regression(nps_app_inst: ArrayApplication):
from sklearn.linear_model import LinearRegression as SKLinearRegression
_, num_features = 1000, 10
rs = np.random.RandomState(1337)
real_theta = rs.random_sample(num_features)
real_X, real_y = BimodalGaussian.get_dataset(233,
num_features,
theta=real_theta)
X = nps_app_inst.array(real_X, block_shape=(100, 3))
y = nps_app_inst.array(real_y, block_shape=(100, ))
param_set = [
{
"solver": "newton-cg",
"tol": 1e-8,
"max_iter": 10
},
]
for kwargs in param_set:
lr_model: LinearRegression = LinearRegression(**kwargs)
lr_model.fit(X, y)
y_pred = lr_model.predict(X).get()
sk_lr_model = SKLinearRegression()
sk_lr_model.fit(real_X, real_y)
sk_y_pred = sk_lr_model.predict(real_X)
np.allclose(sk_y_pred, y_pred)
def test_lr(nps_app_inst: ArrayApplication):
num_samples, num_features = 1000, 10
rs = np.random.RandomState(1337)
real_theta = rs.random_sample(num_features)
real_X, real_y = BimodalGaussian.get_dataset(233,
num_features,
theta=real_theta)
X = nps_app_inst.array(real_X, block_shape=(100, 3))
y = nps_app_inst.array(real_y, block_shape=(100, ))
param_set = [{
"solver": "gd",
"lr": 1e-6,
"tol": 1e-8,
"max_iter": 100
}, {
"solver": "newton",
"tol": 1e-8,
"max_iter": 10
}]
for kwargs in param_set:
runtime = time.time()
model: LinearRegression = LinearRegression(**kwargs)
model.fit(X, y)
assert model._beta.shape == real_theta.shape and model._beta0.shape == (
)
runtime = time.time() - runtime
y_pred = model.predict(X).get()
print("opt", kwargs["solver"])
print("runtime", runtime)
print("norm", model.grad_norm_sq(X, y).get())
print("objective", model.objective(X, y).get())
print("error", np.sum((y.get() - y_pred)**2) / num_samples)
print("D^2", model.deviance_sqr(X, y).get())