"estimator, check",
[
pytest.param(estimator, check, id=f"{estimator}:{check.__name__}")
for estimator in list(get_all_estimators()) + [
feature_extraction.TFIDF(),
linear_model.LogisticRegression(),
preprocessing.StandardScaler() | linear_model.LinearRegression(),
preprocessing.StandardScaler() | linear_model.PAClassifier(),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(
linear_model.LogisticRegression())),
(preprocessing.StandardScaler()
| multiclass.OneVsRestClassifier(linear_model.PAClassifier())),
naive_bayes.GaussianNB(),
preprocessing.StandardScaler(),
cluster.KMeans(n_clusters=5, seed=42),
preprocessing.MinMaxScaler(),
preprocessing.MinMaxScaler() + preprocessing.StandardScaler(),
feature_extraction.PolynomialExtender(),
(feature_extraction.PolynomialExtender()
| preprocessing.StandardScaler()
| linear_model.LinearRegression()),
feature_selection.VarianceThreshold(),
feature_selection.SelectKBest(similarity=stats.PearsonCorr()),
] for check in utils.estimator_checks.yield_checks(estimator)
if check.__name__ not in estimator._unit_test_skips()
],
)
def test_check_estimator(estimator, check):
check(copy.deepcopy(estimator))
def _unit_test_params(cls):
return {"similarity": stats.PearsonCorr()}
def _default_params(cls):
return {'similarity': stats.PearsonCorr()}
n = stat.window_size
X = [random.random() for _ in range(30)]
for i, x in enumerate(X):
stat.update(x)
if i >= 1:
assert math.isclose(stat.get(),
func(tail(X[:i + 1], n)),
abs_tol=1e-10)
@pytest.mark.parametrize(
'stat, func',
[(stats.Cov(), lambda x, y: np.cov(x, y)[0, 1]),
(stats.PearsonCorr(), lambda x, y: sp_stats.pearsonr(x, y)[0])])
def test_bivariate(stat, func):
# Shhh
np.warnings.filterwarnings('ignore')
X = [random.random() for _ in range(30)]
Y = [random.random() * x for x in X]
for i, (x, y) in enumerate(zip(X, Y)):
stat.update(x, y)
if i >= 1:
assert math.isclose(stat.get(),
func(X[:i + 1], Y[:i + 1]),
abs_tol=1e-10)
def _unit_test_params(cls):
yield {"similarity": stats.PearsonCorr()}