def test_nonunique_output():
with pytest.raises(ValueError, match="ambiguous"):
Pipenet(
{
"deseasonal_residual": {
"model": (
transformer.ClassicSeasonalDecomposition(freq=6)
),
"input": "original",
},
"abs_residual": {
"model": transformer.CustomizedTransformer1D(
transform_func=abs
),
"input": "deseasonal_residual",
},
"iqr_ad": {
"model": detector.InterQuartileRangeAD(c=(None, 3)),
"input": "abs_residual",
},
"sign_check": {
"model": detector.ThresholdAD(high=0.0, low=-float("inf")),
"input": "deseasonal_residual",
},
}
)
def test_transformer_pipe():
s = pd.Series(
[0, 1, 2, 3, 2, 1] * 10,
index=pd.date_range(start="2017-1-1", periods=60, freq="D"),
)
my_pipe = Pipenet(
{
"deseasonal_residual": {
"model": transformer.ClassicSeasonalDecomposition(freq=6),
"input": "original",
},
"abs_residual": {
"model": transformer.CustomizedTransformer1D(
transform_func=abs
),
"input": "deseasonal_residual",
},
}
)
with pytest.raises(RuntimeError, match="`fit_transform`"):
my_pipe.fit_detect(s)
my_pipe.fit(s)
my_pipe.transform(s)
my_pipe.fit_transform(s)
my_pipe = Pipeline(
[
(
"deseasonal_residual",
transformer.ClassicSeasonalDecomposition(freq=6),
),
(
"abs_residual",
transformer.CustomizedTransformer1D(transform_func=abs),
),
]
)
with pytest.raises(RuntimeError, match="`fit_transform`"):
my_pipe.fit_detect(s)
my_pipe.fit(s)
my_pipe.transform(s)
my_pipe.fit_transform(s)
def test_seasonal_transformer_shift():
s_train = pd.Series(
[0, 1, 2, 3, 4] * 8,
index=pd.date_range(start="2017-1-1 00:05:00", periods=40, freq="min"),
)
model = transformer.ClassicSeasonalDecomposition(freq=5, trend=False)
model.fit(s_train)
s_test = pd.Series(
[2, 3, 4.1, 0, 1, 2, 2.9, 4, 0, 1],
index=pd.date_range(start="2017-1-1 00:02:00", periods=10, freq="min"),
)
pd.testing.assert_series_equal(
model.transform(s_test),
pd.Series(
[0, 0, 0.1, 0, 0, 0, -0.1, 0, 0, 0],
index=pd.date_range(
start="2017-1-1 00:02:00", periods=10, freq="min"
),
),
check_dtype=False,
)
s_test = pd.Series(
[2, 3, 4.1, 0, 1, 2, 2.9, 4, 0, 1],
index=pd.date_range(start="2017-1-1 00:52:00", periods=10, freq="min"),
)
pd.testing.assert_series_equal(
model.transform(s_test),
pd.Series(
[0, 0, 0.1, 0, 0, 0, -0.1, 0, 0, 0],
index=pd.date_range(
start="2017-1-1 00:52:00", periods=10, freq="min"
),
),
check_dtype=False,
)
detector.PersistAD(),
detector.LevelShiftAD(),
detector.VolatilityShiftAD(),
detector.AutoregressionAD(),
detector.SeasonalAD(freq=2),
transformer.RollingAggregate(agg="median"),
transformer.RollingAggregate(agg="quantile", agg_params={"q": 0.5}),
transformer.DoubleRollingAggregate(agg="median"),
transformer.DoubleRollingAggregate(
agg="quantile", agg_params={"q": [0.1, 0.5, 0.9]}
),
transformer.DoubleRollingAggregate(
agg="hist", agg_params={"bins": [30, 50, 70]}
),
transformer.StandardScale(),
transformer.ClassicSeasonalDecomposition(freq=2),
]
one2many_models = [
transformer.RollingAggregate(
agg="quantile", agg_params={"q": [0.1, 0.5, 0.9]}
),
transformer.RollingAggregate(
agg="hist", agg_params={"bins": [20, 50, 80]}
),
transformer.Retrospect(n_steps=3),
]
many2one_models = [
detector.MinClusterDetector(KMeans(n_clusters=2)),
detector.OutlierDetector(
def test_pipeline():
s = pd.Series(
[0, 1, 2, 3, 2, 1] * 5 + [0, 1, 2, 4, 2, 1] + [0, 1, 2, 3, 2, 1] * 4,
index=pd.date_range(start="2017-1-1", periods=60, freq="D"),
)
my_pipe = Pipeline(
[
(
"deseasonal_residual",
transformer.ClassicSeasonalDecomposition(freq=6),
),
(
"abs_residual",
transformer.CustomizedTransformer1D(transform_func=abs),
),
("ad", detector.QuantileAD(high=0.99)),
]
)
my_pipe.fit_detect(s)
assert (
my_pipe.score(
s,
pd.Series([0] * 33 + [1] + [0] * 26, index=s.index),
scoring="recall",
)
== 1
)
assert (
my_pipe.score(
s,
pd.Series([0] * 33 + [1] + [0] * 26, index=s.index),
scoring="precision",
)
== 1
)
assert (
my_pipe.score(
s,
pd.Series([0] * 33 + [1] + [0] * 26, index=s.index),
scoring="f1",
)
== 1
)
assert (
my_pipe.score(
s,
pd.Series([0] * 33 + [1] + [0] * 26, index=s.index),
scoring="iou",
)
== 1
)
assert my_pipe.get_params() == {
"deseasonal_residual": {"freq": 6, "trend": False},
"abs_residual": {
"fit_func": None,
"fit_func_params": None,
"transform_func": abs,
"transform_func_params": None,
},
"ad": {"high": 0.99, "low": None},
}