Spaces:
Running
Running
File size: 2,633 Bytes
1b19efc 3f21703 1b19efc | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | import numpy as np
import pytest
from sgd_classifier import SUPPORTED_LOSSES, SGDClassifier
def dataset(seed=4, samples=61, features=8):
rng = np.random.default_rng(seed)
X = rng.normal(size=(samples, features))
y = np.where(X[:, 0] - 0.5 * X[:, 1] > 0, "positive", "negative")
return X, y
@pytest.mark.parametrize("loss", SUPPORTED_LOSSES)
@pytest.mark.parametrize("selection", ["random", "permutation"])
def test_every_loss_and_selection_mode_trains(loss, selection):
X, y = dataset()
model = SGDClassifier(
loss=loss, batch_size=13, batch_selection=selection, max_epochs=2,
random_state=7,
).fit(X, y)
assert model.predict(X).shape == (61,)
assert model.n_updates_ == 10
def test_train_step_updates_and_returns_model():
X, y = dataset(samples=20)
model = SGDClassifier(loss="log_loss", learning_rate=0.1)
returned = model.train_step(X, y)
assert returned is model
assert model.n_updates_ == 1
assert np.any(model.coef_ != 0)
def test_get_update_previews_without_applying_it():
X, y = dataset(samples=20)
model = SGDClassifier(loss="log_loss", learning_rate=0.1)
coef_update, intercept_update = model.get_update(X, y)
np.testing.assert_array_equal(model.coef_, np.zeros_like(model.coef_))
np.testing.assert_array_equal(model.intercept_, np.zeros_like(model.intercept_))
assert model.n_updates_ == 0
model.train_step(X, y)
np.testing.assert_allclose(model.coef_, coef_update)
np.testing.assert_allclose(model.intercept_, intercept_update)
def test_evaluate_returns_dataset_loss_and_accuracy():
X, y = dataset(samples=30)
model = SGDClassifier(loss="log_loss").fit(X, y)
metrics = model.evaluate(X, y)
assert metrics["loss"] >= 0
assert 0 <= metrics["accuracy"] <= 1
def test_train_step_can_declare_classes_missing_from_batch():
model = SGDClassifier()
model.train_step([[1.0, 2.0]], ["a"], classes=["a", "b"])
assert model.classes_.tolist() == ["a", "b"]
def test_permutation_batches_cover_each_example_once():
model = SGDClassifier(batch_size=4, batch_selection="permutation")
batches = list(model._batches(11, np.random.default_rng(1)))
assert sorted(np.concatenate(batches).tolist()) == list(range(11))
assert [len(batch) for batch in batches] == [4, 4, 3]
def test_seed_is_reproducible():
X, y = dataset(samples=50)
options = dict(batch_selection="random", max_epochs=3, random_state=9)
first = SGDClassifier(**options).fit(X, y)
second = SGDClassifier(**options).fit(X, y)
np.testing.assert_array_equal(first.coef_, second.coef_)
|