Update predetermined info handling

README.md

@@ -5,7 +5,7 @@
 <a><img alt="Coverage" src="https://raw.githubusercontent.com/STRONGAYA/v6-tools-general/main/tests/coverage-badge.svg"></a>
 <a href="https://www.python.org/downloads/"><img alt="Python 3.10+" src="https://img.shields.io/badge/python-3.10+-blue.svg"></a>
 <a href="https://opensource.org/licenses/Apache-2.0"><img alt="Licence: Apache 2.0" src="https://img.shields.io/badge/Licence-Apache%202.0-blue.svg"></a>
-<a href="https://strongaya.eu/wp-content/uploads/2025/07/algorithm_review_guidelines.pdf"><img alt="STRONG AYA Algorithm Guideline Conformity: v1.0.2 Pending" src="https://img.shields.io/badge/STRONG%20AYA%20Algorithm%20Guideline%20Conformity-v1.0.2%20pending-yellow"></a>
+<a href="https://strongaya.eu/wp-content/uploads/2025/07/algorithm_review_guidelines.pdf"><img alt="STRONG AYA Algorithm Guideline Conformity: v1.0.3 Pending" src="https://img.shields.io/badge/STRONG%20AYA%20Algorithm%20Guideline%20Conformity-v1.0.3%20pending-yellow"></a>
 <br>
 <a href="https://github.com/psf/black"><img alt="Code style: black" src="https://img.shields.io/badge/code%20style-black-000000.svg"></a>
 <a href="https://flake8.pycqa.org/"><img alt="Linting: flake8" src="https://img.shields.io/badge/linting-flake8-informational"></a>
@@ -16,7 +16,7 @@
 
 <!--
 To show the approved badge instead, use:
-<a href="https://strongaya.eu/wp-content/uploads/2025/07/algorithm_review_guidelines.pdf"><img alt="STRONG AYA Algorithm Guideline Conformity: v1.0.2 Approved" src="https://img.shields.io/badge/STRONG%20AYA%20Algorithm%20Guideline%20Conformity-v1.0.2%20approved-brightgreen">
+<a href="https://strongaya.eu/wp-content/uploads/2025/07/algorithm_review_guidelines.pdf"><img alt="STRONG AYA Algorithm Guideline Conformity: v1.0.3 Approved" src="https://img.shields.io/badge/STRONG%20AYA%20Algorithm%20Guideline%20Conformity-v1.0.3%20approved-brightgreen">
 -->
 
 # Purpose of this repository
@@ -51,13 +51,13 @@ algorithm.
 For the `requirements.txt` file, you can add the following line to the file:
 
 ```
-git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.2
+git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.3
 ```
 
 For the `setup.py` file, you can add the following line to the `install_requires` list:
 
 ```python
-        "vantage6-strongaya-general @ git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.2",
+        "vantage6-strongaya-general @ git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.3",
 ```
 
 The algorithm's `setup.py`, particularly the `install_requirements`, section file should then look something like this:
@@ -84,7 +84,7 @@ setup(
         'vantage6-algorithm-tools',
         'numpy',
         'pandas',
-        "vantage6-strongaya-general @ git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.2"
+        "vantage6-strongaya-general @ git+https://github.com/STRONGAYA/v6-tools-general.git@v1.0.3"
         # other dependencies
     ]
 )

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "vantage6-strongaya-general"
-version = "1.0.2"
+version = "1.0.3"
 description = "A small library with various general tools for Vantage6 algorithms developed for the STRONG AYA Project."
 authors = [
     {name = "Joshi Hogenboom (@Jhogenboom)", email = "joshi.hogenboom@maastrichtuniversity.nl"},

src/vantage6_strongaya_general/__init__.py

@@ -10,6 +10,7 @@
     check_partial_result_presence,
     apply_data_stratification,
     set_datatypes,
+    convert_to_json_serialisable,
 )
 
 from .privacy_measures import (
@@ -33,6 +34,7 @@
     "check_partial_result_presence",
     "apply_data_stratification",
     "set_datatypes",
+    "convert_to_json_serialisable",
     "mask_unnecessary_variables",
     "apply_sample_size_threshold",
     "apply_differential_privacy",
@@ -41,4 +43,4 @@
     "compute_local_general_statistics",
     "compute_local_adjusted_deviation",
 ]
-__version__ = "1.0.2"
+__version__ = "1.0.3"

src/vantage6_strongaya_general/miscellaneous.py

@@ -13,6 +13,7 @@
 import json
 
 import pandas as pd
+import numpy as np
 
 from typing import (
     Any,
@@ -77,7 +78,7 @@ def apply_data_stratification(
 
     Caution: The flexibility provided by this function may facilitate differencing attacks if not implemented carefully.
              Consider including extra privacy-enhancing mechanisms by applying differential privacy post-stratification
-             or restricting the variables on which one can stratify -
+             or restricting the variables on which one can stratify
              e.g. through environment variables or a dedicated database and/or list.
 
     Args:
@@ -431,6 +432,35 @@ def check_partial_result_presence(
         )
 
 
+def convert_to_json_serialisable(obj: Any) -> Any:
+    """
+    Convert numpy/pandas types to native Python types for JSON serialisation.
+
+    Args:
+        obj (Any): The object to convert
+
+    Returns:
+        Any: A JSON-serialisable version of the object
+    """
+    if isinstance(obj, (np.integer, np.int64, np.int32, np.int16, np.int8)):
+        return int(obj)
+    elif isinstance(obj, (np.floating, np.float64, np.float32, np.float16)):
+        return float(obj)
+    elif isinstance(obj, np.bool_):
+        return bool(obj)
+    elif isinstance(obj, np.ndarray):
+        return obj.tolist()
+    elif isinstance(obj, pd.Series):
+        return obj.tolist()
+    elif isinstance(obj, dict):
+        return {key: convert_to_json_serialisable(value) for key, value in obj.items()}
+    elif isinstance(obj, (list, tuple)):
+        return [convert_to_json_serialisable(item) for item in obj]
+    elif pd.isna(obj):
+        return None
+    return obj
+
+
 @pd.api.extensions.register_dataframe_accessor("predetermined_info")
 class PredeterminedInfoAccessor:
     """
@@ -458,7 +488,7 @@ def __init__(self, pandas_obj: pd.DataFrame):
 
     def _check_initialized(self) -> None:
         """
-        Initialize the storage if not already done.
+        Initialise the storage if not already done.
 
         Ensures the DataFrame has the necessary attribute storage structure.
         """
@@ -542,6 +572,9 @@ def calculate_for_df(**kwargs: Any) -> Any:
 
                 value = safe_calculate(calculate_for_df, default_value=None, **kwargs)
 
+        # Convert numpy/pandas types to native Python types
+        value = convert_to_json_serialisable(value)
+
         try:
             json.dumps(value)
         except TypeError:
@@ -566,7 +599,7 @@ def get_stat(self, stat_name: str, column: Optional[str] = None) -> Any:
             Any: The stored statistic value
 
         Raises:
-            KeyError: If statistic not found
+            KeyError: If the statistic is not found
         """
         if stat_name not in self._obj.attrs["stats"]:
             safe_log("error", f"Statistic '{stat_name}' not found")
@@ -599,7 +632,7 @@ def get_column_stats(self, column: str) -> Dict[str, Any]:
             Dict[str, Any]: Dictionary containing all statistics for the column
 
         Raises:
-            KeyError: If column not found in DataFrame
+            KeyError: If the column is not found in DataFrame
         """
         if column not in self._obj.columns:
             safe_log("error", f"Column '{column}' not found in DataFrame")
@@ -646,7 +679,7 @@ def update_stat(self, stat_name: str, **kwargs: Any) -> None:
             **kwargs: Arguments to pass to calculation function
 
         Raises:
-            KeyError: If statistic not found
+            KeyError: If the statistic is not found
         """
         if stat_name not in self._obj.attrs["stats"]:
             safe_log(