add loaders

README.md

@@ -1,6 +1,6 @@
 # ZedProfiler
 
-[![Coverage](https://img.shields.io/badge/coverage-87%25-green)](#quality-gates)
+[![Coverage](https://img.shields.io/badge/coverage-90%25-brightgreen)](#quality-gates)
 
 CPU-first 3D image feature extraction toolkit for high-content and high-throughput image-based profiling.
 

src/zedprofiler/IO/__init__.py

@@ -0,0 +1,23 @@
+from .feature_writing_utils import (
+    FeatureMetadata,
+    format_morphology_feature_name,
+    remove_underscores_from_string,
+    save_features_as_parquet,
+)
+from .loading_classes import (
+    ImageSetConfig,
+    ImageSetLoader,
+    ObjectLoader,
+    TwoObjectLoader,
+)
+
+__all__ = [
+    "FeatureMetadata",
+    "ImageSetConfig",
+    "ImageSetLoader",
+    "ObjectLoader",
+    "TwoObjectLoader",
+    "format_morphology_feature_name",
+    "remove_underscores_from_string",
+    "save_features_as_parquet",
+]

src/zedprofiler/IO/feature_writing_utils.py

@@ -0,0 +1,124 @@
+"""Functions for formatting morphology feature names in a consistent way.
+
+Formats morphology feature names and saves features as parquet files.
+"""
+
+from __future__ import annotations
+
+import dataclasses
+import pathlib
+
+import pandas
+
+
+def remove_underscores_from_string(string: str) -> str:
+    """
+    Remove unwanted delimiters from a string and replace them with hyphens.
+
+    Parameters
+    ----------
+    string : str
+        The string to remove unwanted delimiters from.
+
+    Returns
+    -------
+    str
+        The string with unwanted delimiters removed and replaced with hyphens.
+    """
+    if not isinstance(string, str):
+        try:
+            string = str(string)
+        except Exception as e:
+            msg = (
+                f"Input string must be a string or convertible to a string. "
+                f"Received input: {string} of type {type(string)}"
+            )
+            raise ValueError(msg) from e
+    string = string.translate(
+        str.maketrans(
+            {
+                "_": "-",
+                ".": "-",
+                " ": "-",
+                "/": "-",
+            }
+        )
+    )
+
+    return string
+
+
+def format_morphology_feature_name(
+    compartment: str, channel: str, feature_type: str, measurement: str
+) -> str:
+    """
+    Format a morphology feature name in a consistent way 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
+
+    Parameters
+    ----------
+    compartment : str
+        The compartment name.
+    channel : str
+        The channel name.
+    feature_type : str
+        The feature type.
+    measurement : str
+        The measurement name.
+
+    Returns
+    -------
+    str
+        The formatted feature name.
+    """
+
+    compartment = remove_underscores_from_string(compartment)
+    channel = remove_underscores_from_string(channel)
+    feature_type = remove_underscores_from_string(feature_type)
+    measurement = remove_underscores_from_string(measurement)
+
+    return f"{compartment}_{channel}_{feature_type}_{measurement}"
+
+
+@dataclasses.dataclass
+class FeatureMetadata:
+    """Metadata for feature output."""
+
+    compartment: str
+    channel: str
+    feature_type: str
+    cpu_or_gpu: str
+
+
+def save_features_as_parquet(
+    parent_path: pathlib.Path,
+    df: pandas.DataFrame,
+    metadata: FeatureMetadata,
+) -> pathlib.Path:
+    """Save features as parquet files in a consistent way.
+
+    Saves features as parquet files with consistent naming across morphology
+    features.
+
+    Parameters
+    ----------
+    parent_path : pathlib.Path
+        The parent path to save the features to.
+    df : pandas.DataFrame
+        The dataframe containing the features to save.
+    metadata : FeatureMetadata
+        Metadata for the feature output (compartment, channel, feature_type,
+        cpu_or_gpu).
+
+    Returns
+    -------
+    pathlib.Path
+    """
+    save_path = (
+        parent_path
+        / f"{metadata.compartment}_{metadata.channel}_{metadata.feature_type}_"
+        f"{metadata.cpu_or_gpu}_features.parquet"
+    )
+    df.to_parquet(save_path, index=False)
+    return save_path