def test_without_target():
df = pd.DataFrame({"a": [2], "b": [3]})
conv = DFtoVW(
df=df, namespaces=Namespace([Feature(Col("a")), Feature(Col("b"))])
)
first_line = conv.process_df()[0]
assert first_line == "| 2 3"
def test_multilabel_list_of_len_1():
df = pd.DataFrame({"y": [1], "x": [2]})
conv1 = DFtoVW(
df=df, label=MultiLabel(["y"]), features=Feature("x")
)
conv2 = DFtoVW(
df=df, label=MultiLabel("y"), features=Feature("x")
)
assert conv1.convert_df()[0] == conv2.convert_df()[0]
def test_multiple_namespaces():
df = pd.DataFrame({"y": [1], "a": [2], "b": [3]})
conv = DFtoVW(
df=df,
label=SimpleLabel(Col("y")),
namespaces=[
Namespace(name="FirstNameSpace", features=Feature(Col("a"))),
Namespace(name="DoubleIt", value=2, features=Feature(Col("b"))),
],
)
first_line = conv.process_df()[0]
assert first_line == "1 |FirstNameSpace 2 |DoubleIt:2 3"
def test_absent_col_error():
with pytest.raises(ValueError) as value_error:
df = pd.DataFrame({"a": [1]})
conv = DFtoVW(
df=df,
label=SimpleLabel(Col("a")),
namespaces=Namespace(
[Feature(Col("a")), Feature(Col("c")), Feature("d")]
),
)
expected = "In argument 'features', column(s) 'c' not found in dataframe"
assert expected == str(value_error.value)
def test_multiclasslabel():
df = pd.DataFrame({"a": [1], "b": [0.5], "c": ["x"]})
conv = DFtoVW(
df=df, label=MulticlassLabel(name="a", weight="b"), features=Feature("c")
)
first_line = conv.convert_df()[0]
assert first_line == "1 0.5 | x"
def test_multilabel():
df = pd.DataFrame({"y1": [1], "y2": [2], "x": [3]})
conv = DFtoVW(
df=df, label=MultiLabel(["y1", "y2"]), features=Feature("x")
)
first_line = conv.convert_df()[0]
assert first_line == "1,2 | 3"
def test_multiple_lines():
df = pd.DataFrame({"y": [1, -1], "x": [1, 2]})
conv = DFtoVW(
label=SimpleLabel("y"),
features=Feature(value="x"),
df=df,
)
lines_list = conv.convert_df()
assert lines_list == ["1 | 1", "-1 | 2"]
def test_feature_variable_column_name():
df = pd.DataFrame({"y": [1], "x": [2], "a": ["col_x"]})
conv = DFtoVW(
label=SimpleLabel(Col("y")),
namespaces=Namespace(Feature(name=Col("a"), value=Col("x"))),
df=df,
)
first_line = conv.process_df()[0]
assert first_line == "1 | col_x:2"
def test_multiple_lines_conversion():
df = pd.DataFrame({"y": [1, -1], "x": [1, 2]})
conv = DFtoVW(
label=SimpleLabel(Col("y")),
namespaces=Namespace(Feature(value=Col("x"))),
df=df,
)
lines_list = conv.process_df()
assert lines_list == ["1 | 1", "-1 | 2"]
def test_variable_feature_name():
df = pd.DataFrame({"y": [1], "x": [2], "a": ["col_x"]})
conv = DFtoVW(
label=SimpleLabel("y"),
features=Feature(name="a", value="x", name_from_df=True),
df=df,
)
first_line = conv.convert_df()[0]
assert first_line == "1 | col_x:2"
def test_multilabel_non_positive_name_error():
df = pd.DataFrame({"y": [0], "b": [1]})
with pytest.raises(ValueError) as value_error:
DFtoVW(
df=df,
label=MultiLabel(name="y"),
features=Feature("b"),
)
expected = "In argument 'name' of 'MultiLabel', column 'y' must be >= 1."
assert expected == str(value_error.value)
def test_multiclasslabel_non_positive_name_error():
df = pd.DataFrame({"a": [0], "b": [0.5], "c": ["x"]})
with pytest.raises(ValueError) as value_error:
DFtoVW(
df=df,
label=MulticlassLabel(name="a", weight="b"),
features=Feature("c"),
)
expected = "In argument 'name' of 'MulticlassLabel', column 'a' must be >= 1."
assert expected == str(value_error.value)
def test_feature_constant_column_with_empty_name():
df = pd.DataFrame({"idx": ["id_1"], "y": [1], "x": [2]})
conv = DFtoVW(
label=SimpleLabel(Col("y")),
tag=Col("idx"),
namespaces=Namespace([Feature(name="", value=2)]),
df=df,
)
first_line = conv.process_df()[0]
assert first_line == "1 id_1| :2"
def test_feature_column_renaming_and_tag():
df = pd.DataFrame({"idx": ["id_1"], "y": [1], "x": [2]})
conv = DFtoVW(
label=SimpleLabel(Col("y")),
tag=Col("idx"),
namespaces=Namespace([Feature(name="col_x", value=Col("x"))]),
df=df,
)
first_line = conv.process_df()[0]
assert first_line == "1 id_1| col_x:2"
def test_absent_col_error():
with pytest.raises(ValueError) as value_error:
df = pd.DataFrame({"a": [1]})
DFtoVW(
df=df,
label=SimpleLabel("a"),
features=[Feature(col) for col in ["a", "c", "d"]],
)
expected = "In 'Feature': column(s) 'c', 'd' not found in dataframe."
assert expected == str(value_error.value)
def test_multiclasslabel_negative_weight_error():
df = pd.DataFrame({"y": [1], "w": [-0.5], "x": [2]})
with pytest.raises(ValueError) as value_error:
DFtoVW(
df=df,
label=MulticlassLabel(name="y", weight="w"),
features=Feature("x"),
)
expected = "In argument 'weight' of 'MulticlassLabel', column 'w' must be >= 0."
assert expected == str(value_error.value)
def test_constant_feature_value_with_empty_name():
df = pd.DataFrame({"idx": ["id_1"], "y": [1], "x": [2]})
conv = DFtoVW(
label=SimpleLabel("y"),
tag="idx",
features=Feature(name="", value=2, value_from_df=False),
df=df,
)
first_line = conv.convert_df()[0]
assert first_line == "1 id_1| :2"
def test_feature_column_renaming_and_tag():
df = pd.DataFrame({"idx": ["id_1"], "y": [1], "x": [2]})
conv = DFtoVW(
label=SimpleLabel("y"),
tag="idx",
features=Feature(name="col_x", value="x"),
df=df,
)
first_line = conv.convert_df()[0]
assert first_line == "1 id_1| col_x:2"
def test_multiclasslabel_constant_label_type_error():
df = pd.DataFrame({"a": [0], "b": [0.5], "c": ["x"]})
with pytest.raises(TypeError) as type_error:
DFtoVW(
df=df,
label=MulticlassLabel(name="a", weight="b", weight_from_df=False),
features=Feature("c"),
)
expected = "In 'MulticlassLabel', when weight_from_df=False, argument 'weight' should be either of the following type(s): 'int', 'float'."
assert expected == str(type_error.value)
def test_multiclasslabel_non_positive_constant_label_error():
df = pd.DataFrame({"a": [0], "b": [0.5], "c": ["x"]})
with pytest.raises(ValueError) as value_error:
DFtoVW(
df=df,
label=MulticlassLabel(name=-1, weight="b", name_from_df=False),
features=Feature("c"),
)
expected = "In 'MulticlassLabel', argument 'name' must be >= 1."
assert expected == str(value_error.value)
def test_non_numerical_simplelabel_error():
df = pd.DataFrame({"y": ["a"], "x": ["featX"]})
with pytest.raises(TypeError) as type_error:
DFtoVW(df=df, label=SimpleLabel(name="y"), features=Feature("x"))
expected = "In argument 'name' of 'SimpleLabel', column 'y' should be either of the following type(s): 'int', 'float'."
assert expected == str(type_error.value)
def test_without_target_multiple_features():
df = pd.DataFrame({"a": [2], "b": [3]})
conv = DFtoVW(df=df, features=[Feature(col) for col in ["a", "b"]])
first_line = conv.convert_df()[0]
assert first_line == "| 2 3"