def test_get_normalized_scores(header):
train = pd.DataFrame({
header["col_user"]: [1, 1, 1, 1, 2, 2, 2, 2],
header["col_item"]: [1, 2, 3, 4, 1, 5, 6, 7],
header["col_rating"]: [3.0, 4.0, 5.0, 4.0, 3.0, 2.0, 1.0, 5.0],
header["col_timestamp"]: [1, 20, 30, 400, 50, 60, 70, 800],
})
test = pd.DataFrame({
header["col_user"]: [1, 1, 1, 2, 2, 2],
header["col_item"]: [5, 6, 7, 2, 3, 4],
header["col_rating"]: [2.0, 1.0, 5.0, 3.0, 4.0, 5.0],
})
model = SARSingleNode(**header, timedecay_formula=True, normalize=True)
model.fit(train)
actual = model.score(test, remove_seen=True, normalize=True)
expected = np.array([
[-np.inf, -np.inf, -np.inf, -np.inf, 3.0, 3.0, 3.0],
[-np.inf, 3.0, 3.0, 3.0, -np.inf, -np.inf, -np.inf],
])
assert actual.shape == (2, 7)
assert isinstance(actual, np.ndarray)
assert np.isclose(expected, actual).all()
actual = model.score(test, normalize=True)
expected = np.array([
[3.80000633, 4.14285448, 4.14285448, 4.14285448, 3.0, 3.0, 3.0],
[2.8000859, 3.0, 3.0, 3.0, 2.71441353, 2.71441353, 2.71441353],
])
assert actual.shape == (2, 7)
assert isinstance(actual, np.ndarray)
assert np.isclose(expected, actual).all()
def test_get_normalized_scores(header):
train = pd.DataFrame(
{
header["col_user"]: [1, 1, 1, 1, 2, 2, 2, 2],
header["col_item"]: [1, 2, 3, 4, 1, 5, 6, 7],
header["col_rating"]: [3.0, 4.0, 5.0, 4.0, 3.0, 2.0, 1.0, 5.0],
header["col_timestamp"]: [1, 20, 30, 400, 50, 60, 70, 800],
}
)
test = pd.DataFrame(
{
header["col_user"]: [1, 1, 1, 2, 2, 2],
header["col_item"]: [5, 6, 7, 2, 3, 4],
header["col_rating"]: [2.0, 1.0, 5.0, 3.0, 4.0, 5.0],
}
)
model = SARSingleNode(**header, timedecay_formula=True, normalize=True)
model.fit(train)
actual = model.score(test, remove_seen=True)
expected = np.array(
[
[-np.inf, -np.inf, -np.inf, -np.inf, 1.23512374, 1.23512374, 1.23512374],
[-np.inf, 1.23512374, 1.23512374, 1.23512374, -np.inf, -np.inf, -np.inf],
]
)
assert actual.shape == (2, 7)
assert isinstance(actual, np.ndarray)
assert np.isclose(expected, np.asarray(actual)).all()
actual = model.score(test)
expected = np.array(
[
[
3.11754872,
4.29408577,
4.29408577,
4.29408577,
1.23512374,
1.23512374,
1.23512374,
],
[
2.5293308,
1.23511758,
1.23511758,
1.23511758,
3.11767458,
3.11767458,
3.11767458,
],
]
)
assert actual.shape == (2, 7)
assert isinstance(actual, np.ndarray)
assert np.isclose(expected, np.asarray(actual)).all()