def test_gpipeline_graphviz():
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"Pt": PassThrough(),
},
edges=[("ColNum", "Pt"), ("ColCat", "Pt")],
)
gpipeline.fit(dfX, y)
assert isinstance(gpipeline.graphviz, graphviz.dot.Digraph)
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"Pt": PassThrough(),
},
edges=[("ColCat", "Pt"), ("ColNum", "Pt")],
)
assert isinstance(
gpipeline.graphviz,
graphviz.dot.Digraph) # graphviz even before fit is called
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_edge_not_in_models():
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"PtNum": PassThrough(),
"PtCat": PassThrough(),
},
edges=[("ColNum", "PtNummm"), ("ColCat", "PtCat")],
)
with pytest.raises(ValueError):
gpipeline.fit(dfX, y) # ValueError "the node 'PtNummm' isn't in the dictionnary of models"
def test_graphpipeline_more_than_one_terminal_node():
gpipeline = GraphPipeline(
{
"ColNum": ColumnsSelector(columns_to_use=["num1", "num2", "num3"]),
"ColCat": ColumnsSelector(columns_to_use=["cat1", "cat2"]),
"PtNum": PassThrough(),
"PtCat": PassThrough(),
},
edges=[("ColNum", "PtNum"), ("ColCat", "PtCat")],
)
with pytest.raises(ValueError):
gpipeline.fit(dfX, y) # ValueError the graph should have only one terminal node, instead i got 2
def test_graphpipeline_concat_names():
df = get_sample_df(size=100, seed=123)
gpipeline = GraphPipeline(
models={
"sel": ColumnsSelector(columns_to_use=["float_col", "int_col"]),
"vec": CountVectorizerWrapper(columns_to_use=["text_col"]),
"pt": PassThrough(),
},
edges=[("sel", "pt"), ("vec", "pt")],
)
gpipeline.fit(df)
df_res = gpipeline.transform(df)
assert list(df_res.columns) == [
"float_col",
"int_col",
"text_col__BAG__aaa",
"text_col__BAG__bbb",
"text_col__BAG__ccc",
"text_col__BAG__ddd",
"text_col__BAG__eee",
"text_col__BAG__fff",
"text_col__BAG__jjj",
]
assert gpipeline.get_feature_names() == list(df_res.columns)
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"]