update apply_classification task and tests

ci/envs/py3.10-ecoscope1.8.3.yml

@@ -8,4 +8,4 @@ dependencies:
   - numpy<2
   - pip
   - pip:
-    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@e0f77e7
+    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@510771e

ci/envs/py3.11-ecoscope1.8.3.yml

@@ -8,4 +8,4 @@ dependencies:
   - numpy<2
   - pip
   - pip:
-    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@e0f77e7
+    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@510771e

ci/envs/py3.12-ecoscope1.8.3.yml

@@ -8,4 +8,4 @@ dependencies:
   - numpy<2
   - pip
   - pip:
-    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@e0f77e7
+    - ecoscope[analysis,mapping,plotting] @ git+https://github.com/wildlife-dynamics/ecoscope@510771e

ecoscope_workflows/tasks/transformation/_classification.py

@@ -27,6 +27,20 @@ class NaturalBreaksArgs(SharedArgs):
     initial: int = 10
 
 
+class LabelOptions(BaseModel):
+    label_prefix: str = ""
+    label_suffix: str = ""
+
+
+class CustomLabels(LabelOptions):
+    labels: list[str]
+
+
+class DefaultLabels(LabelOptions):
+    label_ranges: bool = False
+    label_decimals: int = 1
+
+
 @task
 def apply_classification(
     df: Annotated[
@@ -42,12 +56,12 @@ def apply_classification(
             description="The dataframe column that will contain the classification values."
         ),
     ] = None,
-    labels: Annotated[
-        list[str] | SkipJsonSchema[None],
+    label_options: Annotated[
+        DefaultLabels | CustomLabels | SkipJsonSchema[None],
         Field(
-            description="Labels of classification bins, uses bin edges if not provied."
+            description="Optional specification or formatting of classification values."
         ),
-    ] = None,
+    ] = DefaultLabels(),
     scheme: Annotated[
         Literal[
             "equal_interval",
@@ -76,7 +90,7 @@ def apply_classification(
         input_column_name (str): The dataframe column to classify.
         output_column_name (str): The dataframe column that will contain the classification.
             Defaults to "<input_column_name>_classified"
-        labels (list[str]): labels of bins, use bin edges if labels==None.
+        label_options (DefaultLabels | CustomLabels): Optional specification or formatting of classification values.
         scheme (str): Classification scheme to use [equal_interval, natural_breaks, quantile, std_mean, max_breaks,
         fisher_jenks]
 
@@ -110,8 +124,8 @@ def apply_classification(
         df,
         input_column_name=input_column_name,
         output_column_name=output_column_name,
-        labels=labels,
         scheme=scheme,
+        **label_options.model_dump(exclude_none=True),
         **classification_options.model_dump(exclude_none=True),
     )
 

tests/tasks/test_classification.py

@@ -9,6 +9,8 @@
     MaxBreaksArgs,
     StdMeanArgs,
     NaturalBreaksArgs,
+    CustomLabels,
+    DefaultLabels,
 )
 
 
@@ -36,21 +38,34 @@ def test_color_map():
 
 
 @pytest.mark.parametrize(
-    "scheme, args",
+    "scheme, classification_args, label_args",
     [
-        ("equal_interval", SharedArgs(k=3)),
-        ("max_breaks", MaxBreaksArgs(k=4, min_diff=20)),
-        ("natural_breaks", NaturalBreaksArgs(k=4, initial=3)),
-        ("std_mean", StdMeanArgs(multiples=[-1, 1], anchor=False)),
+        (
+            "equal_interval",
+            SharedArgs(k=3),
+            DefaultLabels(label_ranges=True, label_decimals=0),
+        ),
+        (
+            "max_breaks",
+            MaxBreaksArgs(k=4, min_diff=20),
+            DefaultLabels(label_prefix="_", label_suffix="_"),
+        ),
+        (
+            "natural_breaks",
+            NaturalBreaksArgs(k=4, initial=3),
+            CustomLabels(labels=["One", "Two", "Three", "Four"]),
+        ),
+        ("std_mean", StdMeanArgs(multiples=[-1, 1], anchor=False), DefaultLabels()),
     ],
 )
-def test_apply_classification_equal_interval(test_df, scheme, args):
+def test_apply_classification(test_df, scheme, classification_args, label_args):
     result = apply_classification(
         df=test_df,
         input_column_name="column_name",
         scheme=scheme,
         output_column_name="classified",
-        classification_options=args,
+        label_options=label_args,
+        classification_options=classification_args,
     )
 
     assert "classified" in result.columns