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_usecase():
clf = InteractiveClassifier.from_json(
"tests/test_classification/demo-data.json")
pipe = Pipeline([
("id", PipeTransformer(identity)),
("mod", clf),
])
grid = GridSearchCV(pipe, cv=5, param_grid={})
df = load_penguins(as_frame=True).dropna()
X, y = df.drop(columns=["species", "island", "sex"]), df["species"]
preds = grid.fit(X, y).predict_proba(X)
assert preds.shape[0] == df.shape[0]
assert preds.shape[1] == 3
def test_grid_predict_usecase():
tfm = InteractivePreprocessor.from_json(
"tests/test_classification/demo-data.json")
pipe = Pipeline([
(
"features",
FeatureUnion([("original", PipeTransformer(identity)),
("new_feats", tfm)]),
),
])
df = load_penguins(as_frame=True).dropna()
X, y = df.drop(columns=["species", "island", "sex"]), df["species"]
preds = pipe.fit(X, y).transform(X)
assert preds.shape[0] == df.shape[0]
assert preds.shape[1] == X.shape[1] + 3
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]
def test_penguin2():
df = load_penguins(as_frame=True)
assert df.shape == (344, 7)
def test_penguin1():
X, y = load_penguins(return_X_y=True)
assert X.shape == (344, 6)
assert y.shape[0] == 344
def penguins_df():
df = load_penguins(as_frame=True).dropna()
X = df.drop(columns='species')
return X
