def test_gpipeline_regression():
gpipeline = GraphPipeline({
"PT": PassThrough(),
"Ridge": Ridge()
}, [("PT", "Ridge")])
X = dfX.loc[:, ["num1", "num2", "num3"]]
gpipeline.fit(X, y)
yhat = gpipeline.predict(X)
yhat2 = gpipeline.models["Ridge"].predict(X)
assert yhat.shape == y.shape
assert (yhat == yhat2).all()
with pytest.raises(AttributeError):
gpipeline.predict_proba(X)
with pytest.raises(AttributeError):
gpipeline.predict_log_proba(X)
assert gpipeline.get_feature_names_at_node("PT") == list(X.columns)
assert gpipeline.get_input_features_at_node("PT") == list(X.columns)
assert gpipeline.get_input_features_at_node("Ridge") == list(X.columns)
with pytest.raises(ValueError):
assert gpipeline.get_feature_names_at_node("DONTEXIST")
def test_graphpipeline_merging_node():
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"Pt": DebugPassThrough(debug=True),
},
edges=[("ColNum", "Pt"), ("ColCat", "Pt")],
)
gpipeline.fit(dfX, y)
pt = gpipeline.models["Pt"]
assert pt._expected_columns == ["num1", "num2", "num3", "cat1", "cat2"]
assert pt._expected_type == DataTypes.DataFrame
assert pt._expected_nbcols == 5
dfX_transformed = gpipeline.transform(dfX)
assert (dfX_transformed == dfX.loc[:, ["num1", "num2", "num3", "cat1", "cat2"]]).all().all()
assert gpipeline.get_feature_names() == ["num1", "num2", "num3", "cat1", "cat2"]
assert gpipeline.get_feature_names_at_node("Pt") == ["num1", "num2", "num3", "cat1", "cat2"]
assert gpipeline.get_feature_names_at_node("ColNum") == ["num1", "num2", "num3"]
assert gpipeline.get_feature_names_at_node("ColCat") == ["cat1", "cat2"]
assert gpipeline.get_input_features_at_node("ColNum") == list(dfX.columns)
assert gpipeline.get_input_features_at_node("ColCat") == list(dfX.columns)
assert gpipeline.get_input_features_at_node("Pt") == ["num1", "num2", "num3", "cat1", "cat2"]
# concatenation in the other oreder
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"Pt": DebugPassThrough(debug=True),
},
edges=[("ColCat", "Pt"), ("ColNum", "Pt")],
)
gpipeline.fit(dfX, y)
pt = gpipeline.models["Pt"]
assert pt._expected_columns == ["cat1", "cat2", "num1", "num2", "num3"] # Concanteation in the order of the edges
assert pt._expected_type == DataTypes.DataFrame
assert pt._expected_nbcols == 5
assert gpipeline.get_feature_names() == ["cat1", "cat2", "num1", "num2", "num3"]
assert gpipeline.get_feature_names_at_node("Pt") == ["cat1", "cat2", "num1", "num2", "num3"]
assert gpipeline.get_feature_names_at_node("ColNum") == ["num1", "num2", "num3"]
assert gpipeline.get_feature_names_at_node("ColCat") == ["cat1", "cat2"]
assert gpipeline.get_input_features_at_node("ColNum") == list(dfX.columns)
assert gpipeline.get_input_features_at_node("ColCat") == list(dfX.columns)
assert gpipeline.get_input_features_at_node("Pt") == ["cat1", "cat2", "num1", "num2", "num3"]
dfX_transformed = gpipeline.transform(dfX)
assert (dfX_transformed == dfX.loc[:, ["cat1", "cat2", "num1", "num2", "num3"]]).all().all()
def test_graphpipeline_get_features_names_with_input_features():
xx = np.random.randn(10, 5)
df = pd.DataFrame(xx, columns=["COL_%d" % j for j in range(xx.shape[1])])
model = GraphPipeline(
{"pt1": PassThroughtWithFeatures(prefix="PT1"), "pt2": PassThroughtWithFeatures(prefix="PT2")},
edges=[("pt1", "pt2")],
)
model.fit(df)
### Test 1 : without input_features ###
assert model.get_feature_names() == [
"PT2__PT1__COL_0",
"PT2__PT1__COL_1",
"PT2__PT1__COL_2",
"PT2__PT1__COL_3",
"PT2__PT1__COL_4",
]
assert model.get_feature_names_at_node("pt2") == [
"PT2__PT1__COL_0",
"PT2__PT1__COL_1",
"PT2__PT1__COL_2",
"PT2__PT1__COL_3",
"PT2__PT1__COL_4",
]
assert model.get_feature_names_at_node("pt1") == [
"PT1__COL_0",
"PT1__COL_1",
"PT1__COL_2",
"PT1__COL_3",
"PT1__COL_4",
]
assert model.get_input_features_at_node("pt2") == [
"PT1__COL_0",
"PT1__COL_1",
"PT1__COL_2",
"PT1__COL_3",
"PT1__COL_4",
]
assert model.get_input_features_at_node("pt1") == ["COL_0", "COL_1", "COL_2", "COL_3", "COL_4"]
### Test 2 : with input feautres ###
assert model.get_feature_names(input_features=["a", "b", "c", "d", "e"]) == [
"PT2__PT1__a",
"PT2__PT1__b",
"PT2__PT1__c",
"PT2__PT1__d",
"PT2__PT1__e",
]
assert model.get_feature_names_at_node("pt2", input_features=["a", "b", "c", "d", "e"]) == [
"PT2__PT1__a",
"PT2__PT1__b",
"PT2__PT1__c",
"PT2__PT1__d",
"PT2__PT1__e",
]
assert model.get_feature_names_at_node("pt1", input_features=["a", "b", "c", "d", "e"]) == [
"PT1__a",
"PT1__b",
"PT1__c",
"PT1__d",
"PT1__e",
]
assert model.get_input_features_at_node("pt2", input_features=["a", "b", "c", "d", "e"]) == [
"PT1__a",
"PT1__b",
"PT1__c",
"PT1__d",
"PT1__e",
]
assert model.get_input_features_at_node("pt1", input_features=["a", "b", "c", "d", "e"]) == [
"a",
"b",
"c",
"d",
"e",
]
### Test 3 : with numpy array ###
model = GraphPipeline(
{"pt1": PassThroughtWithFeatures(prefix="PT1"), "pt2": PassThroughtWithFeatures(prefix="PT2")},
edges=[("pt1", "pt2")],
)
model.fit(xx)
assert model.get_feature_names() is None
assert model.get_feature_names_at_node("pt2") is None
assert model.get_feature_names_at_node("pt1") is None
assert model.get_input_features_at_node("pt2") is None
assert model.get_input_features_at_node("pt1") is None
assert model.get_feature_names(input_features=["a", "b", "c", "d", "e"]) == [
"PT2__PT1__a",
"PT2__PT1__b",
"PT2__PT1__c",
"PT2__PT1__d",
"PT2__PT1__e",
]
assert model.get_feature_names_at_node("pt2", input_features=["a", "b", "c", "d", "e"]) == [
"PT2__PT1__a",
"PT2__PT1__b",
"PT2__PT1__c",
"PT2__PT1__d",
"PT2__PT1__e",
]
assert model.get_feature_names_at_node("pt1", input_features=["a", "b", "c", "d", "e"]) == [
"PT1__a",
"PT1__b",
"PT1__c",
"PT1__d",
"PT1__e",
]
assert model.get_input_features_at_node("pt2", input_features=["a", "b", "c", "d", "e"]) == [
"PT1__a",
"PT1__b",
"PT1__c",
"PT1__d",
"PT1__e",
]
assert model.get_input_features_at_node("pt1", input_features=["a", "b", "c", "d", "e"]) == [
"a",
"b",
"c",
"d",
"e",
]
def test_graphpipeline_get_features_names():
dfX = pd.DataFrame(
{
"text1": ["aa bb", "bb bb cc", "dd aa cc", "ee"],
"text2": ["AAA ZZZ", "BBB EEE", "DDD TTT", "AAA BBB CCC"],
"num1": [0, 1, 2, 3],
"num2": [1.1, 1.5, -2, -3.5],
"num3": [-1, 1, 25, 4],
"cat1": ["A", "B", "A", "D"],
"cat2": ["toto", "tata", "truc", "toto"],
}
)
### Test 1 ###
model = GraphPipeline({"sel": ColumnsSelector(["cat1", "cat2"]), "pt": PassThrough()}, edges=[("sel", "pt")])
model.fit(dfX)
assert model.get_feature_names() == ["cat1", "cat2"] # features at ending nodeC
assert model.get_feature_names_at_node("pt") == ["cat1", "cat2"]
assert model.get_feature_names_at_node("sel") == ["cat1", "cat2"]
assert model.get_input_features_at_node("pt") == ["cat1", "cat2"]
assert model.get_input_features_at_node("sel") == ["text1", "text2", "num1", "num2", "num3", "cat1", "cat2"]
### Test 2 ###
model = GraphPipeline(
{"sel1": ColumnsSelector(["cat1", "cat2"]), "sel2": ColumnsSelector(["num1", "num2"]), "pt": PassThrough()},
edges=[("sel1", "pt"), ("sel2", "pt")],
)
model.fit(dfX)
assert model.get_feature_names() == ["cat1", "cat2", "num1", "num2"]
assert model.get_feature_names_at_node("pt") == ["cat1", "cat2", "num1", "num2"]
assert model.get_feature_names_at_node("sel1") == ["cat1", "cat2"]
assert model.get_feature_names_at_node("sel2") == ["num1", "num2"]
assert model.get_input_features_at_node("pt") == ["cat1", "cat2", "num1", "num2"]
assert model.get_input_features_at_node("sel1") == ["text1", "text2", "num1", "num2", "num3", "cat1", "cat2"]
assert model.get_input_features_at_node("sel2") == ["text1", "text2", "num1", "num2", "num3", "cat1", "cat2"]
### Test 3 ###
model = GraphPipeline(
{
"sel1": ColumnsSelector(["cat1", "cat2"]),
"sel2": ColumnsSelector(["num1", "num2"]),
"sel12": ColumnsSelector(["cat1", "num1"]),
"pt": PassThrough(),
},
edges=[("sel1", "sel12", "pt"), ("sel2", "sel12", "pt")],
)
model.fit(dfX)
assert model.get_feature_names() == ["cat1", "num1"]
assert model.get_feature_names_at_node("pt") == ["cat1", "num1"]
assert model.get_feature_names_at_node("sel12") == ["cat1", "num1"]
assert model.get_feature_names_at_node("sel1") == ["cat1", "cat2"]
assert model.get_feature_names_at_node("sel2") == ["num1", "num2"]
assert model.get_input_features_at_node("pt") == ["cat1", "num1"]
assert model.get_input_features_at_node("sel12") == ["cat1", "cat2", "num1", "num2"]
assert model.get_input_features_at_node("sel1") == ["text1", "text2", "num1", "num2", "num3", "cat1", "cat2"]
assert model.get_input_features_at_node("sel2") == ["text1", "text2", "num1", "num2", "num3", "cat1", "cat2"]
