address issues

README.md

@@ -1,4 +1,4 @@
-# ZEDprofiler [![Documentation](https://img.shields.io/badge/documentation-available-brightgreen)](https://zedprofiler.readthedocs.io/en/latest/) ![License](https://img.shields.io/badge/license-BSD%203--Clause-blue)[![Coverage](https://img.shields.io/badge/coverage-92%25-brightgreen)](#quality-gates)
+# ZEDprofiler [![Documentation](https://img.shields.io/badge/documentation-available-brightgreen)](https://zedprofiler.readthedocs.io/en/latest/) ![License](https://img.shields.io/badge/license-BSD%203--Clause-blue)[![Coverage](https://img.shields.io/badge/coverage-91%25-brightgreen)](#quality-gates)
 
 [![ZEDprofiler](https://github.com/WayScience/ZEDprofiler/raw/main/logo/with-text-for-dark-bg.png)](https://github.com/WayScience/ZEDprofiler)
 

pyproject.toml

@@ -37,6 +37,7 @@ dependencies = [
   "pyarrow>=23.0.1",
   "pydantic>=2.10",
   "scikit-image>=0.26",
+  "scipy>=1.14",
   "tomli>=2.4.1",
 ]
 urls.Homepage = "https://zedprofiler.readthedocs.io"
@@ -111,6 +112,10 @@ ignore-words-list = "inout"
 paths = [ "src/zedprofiler", "tests" ]
 min_confidence = 90
 
+[tool.mypy]
+ignore_missing_imports = true
+python_version = "3.11"
+
 [tool.pytest]
 ini_options.pythonpath = [ "." ]
 

src/zedprofiler/IO/feature_writing_utils.py

@@ -12,28 +12,22 @@
 import pandera.pandas as pa
 from beartype import beartype
 
-FEATURE_NAME_COMPONENT_COLUMNS = (
-    "compartment",
-    "channel",
-    "feature_type",
-    "measurement",
-)
-
 
 def _coerce_dataframe_column_names_to_strings(
     dataframe: pandas.DataFrame,
 ) -> pandas.DataFrame:
-    """
-    Ensure DataFrame column labels are string-typed before writing.
+    """Ensure DataFrame column labels are string-typed before writing.
 
     Parameters
     ----------
     dataframe : pandas.DataFrame
         The DataFrame whose column names should be coerced to strings.
+
     Returns
     -------
     pandas.DataFrame
         A copy of the input DataFrame with all column names coerced to strings.
+
     """
     parsed_dataframe = dataframe.copy()
     parsed_dataframe.columns = [str(column) for column in parsed_dataframe.columns]
@@ -42,8 +36,7 @@ def _coerce_dataframe_column_names_to_strings(
 
 @beartype
 def remove_underscores_from_string(string: object) -> str:
-    """
-    Remove unwanted delimiters from a string and replace them with hyphens.
+    """Remove unwanted delimiters from a string and replace them with hyphens.
 
     Parameters
     ----------
@@ -54,6 +47,7 @@ def remove_underscores_from_string(string: object) -> str:
     -------
     str
         The string with unwanted delimiters removed and replaced with hyphens.
+
     """
     if not isinstance(string, str):
         try:
@@ -64,42 +58,34 @@ def remove_underscores_from_string(string: object) -> str:
                 f"Received input: {string!r} of type {type(string)}"
             )
             raise ValueError(msg) from e
-    string = string.translate(
-        str.maketrans(
-            {
-                "_": "-",
-                ".": "-",
-                " ": "-",
-                "/": "-",
-            }
-        )
-    )
+    string = string.translate(str.maketrans("_. /", "----"))
 
     return string
 
 
 def _coerce_feature_name_components(
     dataframe: pandas.DataFrame,
 ) -> pandas.DataFrame:
-    """
-    Normalize feature-name components using shared delimiter cleanup.
+    """Normalize feature-name components using shared delimiter cleanup.
 
     Parameters
     ----------
     dataframe : pandas.DataFrame
         The DataFrame containing feature name components to be normalized.
         Expected to have columns corresponding to FEATURE NAME COMPONENT COLUMNS.
+
     Returns
     -------
     pandas.DataFrame
         A copy of the input DataFrame with feature name components normalized by
         removing unwanted delimiters and replacing them with hyphens.
+
     """
     parsed_dataframe = dataframe.copy()
     for column in FEATURE_NAME_COMPONENT_COLUMNS:
         if column in parsed_dataframe.columns:
             parsed_dataframe[column] = parsed_dataframe[column].map(
-                remove_underscores_from_string
+                remove_underscores_from_string,
             )
     return parsed_dataframe
 
@@ -135,10 +121,12 @@ def _coerce_feature_name_components(
 
 @beartype
 def format_morphology_feature_name(
-    compartment: object, channel: object, feature_type: object, measurement: object
+    compartment: object,
+    channel: object,
+    feature_type: object,
+    measurement: object,
 ) -> str:
-    """
-    Format a morphology feature name in a consistent way across all morphology features.
+    """Format a morphology feature name consistently across all morphology features.
     This format follows specification for the following:
     https://github.com/WayScience/NF1_3D_organoid_profiling_pipeline/blob/main/docs/RFC-2119-Feature-Naming-Convention.md
 
@@ -157,17 +145,17 @@ def format_morphology_feature_name(
     -------
     str
         The formatted feature name.
-    """
 
+    """
     component_frame = pandas.DataFrame(
         [
             {
                 "compartment": compartment,
                 "channel": channel,
                 "feature_type": feature_type,
                 "measurement": measurement,
-            }
-        ]
+            },
+        ],
     )
     coerced_components = FEATURE_NAME_COMPONENT_SCHEMA.validate(component_frame)
     parsed_row = coerced_components.iloc[0]
@@ -212,6 +200,7 @@ def save_features_as_parquet(
     Returns
     -------
     pathlib.Path
+
     """
     validated_df = FEATURE_OUTPUT_SCHEMA.validate(df)
     output_prefix = format_morphology_feature_name(