def test_ignore_bad_data():
"""
There might be some "bad data" drawn. For example, when you quickly hit double-click you might
draw a line instead of a poly. Bokeh is "okeh" with it, but our point-in-poly algorithm is not.
"""
data = [
{
"chart_id": "9ec8e755-2",
"x": "bill_length_mm",
"y": "bill_depth_mm",
"polygons": {
"Adelie": {"bill_length_mm": [], "bill_depth_mm": []},
"Gentoo": {"bill_length_mm": [], "bill_depth_mm": []},
"Chinstrap": {"bill_length_mm": [], "bill_depth_mm": []},
},
},
{
"chart_id": "11640372-c",
"x": "flipper_length_mm",
"y": "body_mass_g",
"polygons": {
"Adelie": {
"flipper_length_mm": [[214.43261376806052, 256.2612913545137]],
"body_mass_g": [[3950.9482324534456, 3859.9137496948247]],
},
"Gentoo": {"flipper_length_mm": [], "body_mass_g": []},
"Chinstrap": {"flipper_length_mm": [], "body_mass_g": []},
},
},
]
clf = InteractiveOutlierDetector(json_desc=data)
assert len(list(clf.poly_data)) == 0
def test_estimator_checks(test_fn):
"""
We're skipping a lot of tests here mainly because this model is "bespoke"
it is *not* general. Therefore a lot of assumptions are broken.
"""
clf = InteractiveOutlierDetector.from_json(
"tests/test_classification/demo-data.json")
test_fn(InteractiveOutlierDetector, clf)
def test_base_predict_usecase():
clf = InteractiveOutlierDetector.from_json(
"tests/test_classification/demo-data.json")
df = load_penguins(as_frame=True).dropna()
X, y = df.drop(columns=["species"]), df["species"]
preds = clf.fit(X, y).predict(X)
assert preds.shape[0] == df.shape[0]
def test_grid_predict():
clf = InteractiveOutlierDetector.from_json(
"tests/test_classification/demo-data.json")
pipe = Pipeline([
("id", PipeTransformer(identity)),
("mod", clf),
])
grid = GridSearchCV(
pipe,
cv=5,
param_grid={},
scoring={"acc": make_scorer(accuracy_score)},
refit="acc",
)
df = load_penguins(as_frame=True).dropna()
X = df.drop(columns=["species", "island", "sex"])
y = (np.random.random(df.shape[0]) < 0.1).astype(int)
preds = grid.fit(X, y).predict(X)
assert preds.shape[0] == df.shape[0]