vantage6-algorithm-tools 5.0.2rc2__tar.gz → 5.0.3rc5__tar.gz

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: vantage6-algorithm-tools
-Version: 5.0.2rc2
+Version: 5.0.3rc5
 Summary: Vantage6 algorithm tools
 Author: Vantage6 Team
 Maintainer-email: Frank Martin <f.martin@iknl.nl>, Bart van Beusekom <b.vanbeusekom@iknl.nl>
@@ -14,7 +14,7 @@ Requires-Dist: pyfiglet==1.0.4
 Requires-Dist: pyjwt==2.13.0
 Requires-Dist: sparqlwrapper>=2.0.0
 Requires-Dist: sqlalchemy>=1.4.46
-Requires-Dist: vantage6-common==5.0.2rc2
+Requires-Dist: vantage6-common==5.0.3rc5
 Provides-Extra: dev
 Requires-Dist: black; extra == 'dev'
 Requires-Dist: coverage==7.10.2; extra == 'dev'

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "vantage6-algorithm-tools"
-version = "5.0.2rc2"
+version = "5.0.3rc5"
 description = "Vantage6 algorithm tools"
 readme = "README.md"
 license = {text = "MIT"}
@@ -27,7 +27,7 @@ dependencies = [
     "pyfiglet==1.0.4",
     "SPARQLWrapper>=2.0.0",
     "sqlalchemy>=1.4.46",
-    "vantage6-common==5.0.2rc2",
+    "vantage6-common==5.0.3rc5",
 ]
 
 [project.optional-dependencies]

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/tests/_test_preprocessing.py

@@ -6,7 +6,7 @@ python -m unittest vantage6-algorithm-tools.tests.test_preprocessing
 """
 
 import unittest
-from datetime import datetime, timedelta
+from datetime import UTC, datetime, timedelta
 
 import numpy as np
 import pandas as pd
@@ -16,7 +16,7 @@ from vantage6.algorithm.preprocessing.filtering import select_rows
 
 
 def random_date(
-    start: datetime, end: datetime, fmt: str = "%Y-%m-%d", seed: int = None
+    start: datetime, end: datetime, fmt: str = "%Y-%m-%d", seed: int | None = None
 ) -> str:
     """
     Generate a random date between start and end.
@@ -537,8 +537,8 @@ class TestPreprocessing(unittest.TestCase):
         df = get_test_dataframe()
 
         # Set start and end dates for random date generation
-        start_date = datetime(2020, 1, 1)
-        end_date = datetime(2022, 12, 31)
+        start_date = datetime(2020, 1, 1, tzinfo=UTC)
+        end_date = datetime(2022, 12, 31, tzinfo=UTC)
 
         # Generate a new column with random dates in string format
         magic_fmt = "(%d)+(%m)=(%Y)"
@@ -637,7 +637,7 @@ class TestPreprocessing(unittest.TestCase):
             '{"age":{"171":23,"342":23},"income":{"171":62026,"342":44074},'
             '"education":{"171":"Master","342":"Master"},"color_preference":'
             '{"171":"Green","342":"Green"},"purchased_product":{"171":1,"342":'
-            '0},"magic_date":{"171":"2022-11-12","342":"2020-01-20"},"income\/'
+            r'0},"magic_date":{"171":"2022-11-12","342":"2020-01-20"},"income\/'
             'age":{"171":0.9737126326,"342":0.0147479299},"age_days":{"171":'
             '8395,"342":8395},"age_days_td":{"171":"8395 days","342":"8395 '
             'days"}}'

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/tests/algorithm/test___init__.py

@@ -88,11 +88,7 @@ class TestAlgorithmClient(unittest.TestCase):
         results = self.client.result.from_task(task_id=1)
         self.assertEqual(results[0], {"foo": "bar"})
 
-    @patch("vantage6.algorithm.client.AlgorithmClient._multi_page_request")
-    @patch("vantage6.common.client.client_base.ClientBase._download_run_data_from_hq")
-    def test_result_from_task_azure(
-        self, mock_download_run_data, mock_multi_page_request
-    ):
+    def test_result_from_task_azure(self):
         with (
             patch.object(
                 self.client.result.parent, "_multi_page_request"

vantage6_algorithm_tools-5.0.3rc5/tests/tools/test_error_handling.py

@@ -0,0 +1,36 @@
+import traceback
+import unittest
+
+from vantage6.algorithm.tools.error_handling import handle_data_errors
+from vantage6.algorithm.tools.exceptions import AlgorithmRuntimeError, UserInputError
+
+
+class TestHandleDataErrors(unittest.TestCase):
+    def test_non_pandas_error_is_sanitized(self):
+        """Errors that are not raised by vantage6 should not leak any details."""
+
+        @handle_data_errors
+        def func():
+            raise ValueError("could not convert string to float: 'secret_42'")
+
+        with self.assertRaises(AlgorithmRuntimeError) as ctx:
+            func()
+
+        self.assertNotIn("secret_42", str(ctx.exception))
+        # the original error should not be printed when the traceback is logged
+        traceback_ = "".join(traceback.format_exception(ctx.exception))
+        self.assertNotIn("secret_42", traceback_)
+
+    def test_algorithm_errors_pass_through(self):
+        """Vantage6 errors are meant for the user and should not be replaced."""
+
+        @handle_data_errors
+        def func():
+            raise UserInputError("old_names and new_names must have the same length")
+
+        with self.assertRaises(UserInputError):
+            func()
+
+
+if __name__ == "__main__":
+    unittest.main()

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/client/__init__.py

@@ -136,7 +136,7 @@ class AlgorithmClient(ClientBase):
 
         return self.result.from_task(task_id)
 
-    def _multi_page_request(self, endpoint: str, params: dict = None) -> dict:
+    def _multi_page_request(self, endpoint: str, params: dict | None = None) -> dict:
         """
         Make multiple requests to HQ to get all pages of a list of results.
 
@@ -247,9 +247,8 @@ class AlgorithmClient(ClientBase):
                     result = json.loads(
                         base64s_to_bytes(response.get("result")).decode()
                     )
-                except Exception as e:
-                    self.parent.log.error("Unable to load results")
-                    self.parent.log.exception(e)
+                except Exception:
+                    self.parent.log.exception("Unable to load results")
             return result
 
         def from_task(self, task_id: int) -> list[Any]:
@@ -288,7 +287,7 @@ class AlgorithmClient(ClientBase):
                         return json.loads(run_data.decode(STRING_ENCODING))
                     else:
                         return json.loads(base64s_to_bytes(result_data).decode())
-                except Exception as e:
+                except Exception as e:  # noqa: BLE001
                     self.parent.log.error(
                         f"Unable to load results for task {task_id}: {e}"
                     )
@@ -328,9 +327,9 @@ class AlgorithmClient(ClientBase):
             self,
             method: str,
             arguments: dict | None = None,
-            organizations: list[int] = None,
+            organizations: list[int] | None = None,
             name: str = "subtask",
-            description: str = None,
+            description: str | None = None,
         ) -> dict:
             """
             Create a new (child) task at HQ.

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/data_extraction/__init__.py

@@ -7,7 +7,7 @@ from sqlalchemy import create_engine
 
 from vantage6.common import error, info
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 from vantage6.algorithm.tools.exceptions import DataReadError
 
 from vantage6.algorithm.decorator.action import data_extraction
@@ -15,7 +15,7 @@ from vantage6.algorithm.decorator.action import data_extraction
 _SPARQL_RETURN_FORMAT = CSV
 
 
-@handle_pandas_errors
+@handle_data_errors
 @data_extraction
 def read_csv(connection_details: dict) -> pd.DataFrame:
     """
@@ -48,14 +48,14 @@ def _read_csv(connection_details: dict) -> pd.DataFrame:
         error(f"File not found: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"File not found: {e}")
-    except Exception as e:
+    except Exception as e:  # noqa: BLE001
         error(f"Error reading CSV file: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"Error reading CSV file: {e}")
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @data_extraction
 def read_parquet(connection_details: dict) -> pd.DataFrame:
     """
@@ -87,14 +87,14 @@ def _read_parquet(connection_details: dict) -> pd.DataFrame:
         error(f"File not found: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"File not found: {e}")
-    except Exception as e:
+    except Exception as e:  # noqa: BLE001
         error(f"Error reading Parquet file: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"Error reading Parquet file: {e}")
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @data_extraction
 def read_excel(connection_details: dict, sheet_name: str | None = None) -> pd.DataFrame:
     """
@@ -137,14 +137,14 @@ def _read_excel(
         error(f"File not found: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"File not found: {e}")
-    except Exception as e:
+    except Exception as e:  # noqa: BLE001
         error(f"Error reading Excel file: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"Error reading Excel file: {e}")
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @data_extraction
 def read_sparql_database(connection_details: dict, query: str) -> pd.DataFrame:
     """
@@ -180,7 +180,7 @@ def _read_sparql_database(connection_details: dict, query: str) -> pd.DataFrame:
 
     try:
         df = pd.read_csv(io.StringIO(result))
-    except Exception as e:
+    except Exception as e:  # noqa: BLE001
         error(f"Error reading SPARQL data: {e}")
         # pylint: disable=raise-missing-from
         raise DataReadError(f"Error reading SPARQL data: {e}")
@@ -230,7 +230,7 @@ def _sqldb_uri_preprocess(database_uri: str) -> str:
         return database_uri
 
 
-@handle_pandas_errors
+@handle_data_errors
 @data_extraction
 def read_sql_database(connection_details: dict, query: str) -> pd.DataFrame:
     """

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/data_extraction/mock_extract.py

@@ -1,3 +1,4 @@
+import sys
 from collections.abc import Callable
 
 import pandas as pd
@@ -70,7 +71,7 @@ def load_mock_data(
             " Please check the node configuration."
         )
         info(f"Available mock database types: {', '.join(MockDatabaseType.list())}")
-        exit(1)
+        sys.exit(1)
 
     connection_details = {
         "uri": database_uri,
@@ -84,7 +85,7 @@ def load_mock_data(
     ):
         if not query:
             error(f"Query is required for {database_type} databases.")
-            exit(1)
+            sys.exit(1)
         return loader(connection_details, query)
     else:
         return loader(connection_details)

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/decorator/action.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from collections.abc import Callable
 from functools import wraps
 from typing import Any
@@ -181,10 +182,10 @@ def data_extraction(func: Callable) -> Callable:
         type_ = get_env_var(ContainerEnvNames.DATABASE_TYPE.value, mock_type)
         if not uri:
             error("No database URI provided. Exiting...")
-            exit(1)
+            sys.exit(1)
         if not type_:
             error("No database type provided. Exiting...")
-            exit(1)
+            sys.exit(1)
 
         connection_details["uri"] = uri
         connection_details["type"] = type_

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/decorator/algorithm_client.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from collections.abc import Callable
 from functools import wraps
 from typing import TYPE_CHECKING, Optional
@@ -69,7 +70,7 @@ def _algorithm_client() -> Callable:
                     "Token not found. Is the method you called started as a "
                     "compute container? Exiting..."
                 )
-                exit(1)
+                sys.exit(1)
 
             # read HQ address from the environment
             host = os.environ[ContainerEnvNames.HOST.value]

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/decorator/data.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from collections.abc import Callable
 from functools import wraps
 
@@ -90,7 +91,7 @@ def _validate_user_provided_dataframes(
             f"but only {len(dataframes_grouped)} were provided. "
             "Exiting..."
         )
-        exit(1)
+        sys.exit(1)
     elif len(dataframes_grouped) > number_of_expected_arguments:
         warn(
             f"Algorithm requires only {number_of_expected_arguments} databases"
@@ -143,7 +144,7 @@ def _read_dataframes_from_disk(
                     "for preprocessing functions. Use @preprocessing instead. "
                     "Exiting..."
                 )
-                exit(1)
+                sys.exit(1)
             requested_dataframes = dataframes_grouped[idx_dataframes]
             data_ = {
                 df_name: _read_df_from_disk(df_name) for df_name in requested_dataframes
@@ -243,13 +244,13 @@ def dataframe(*sources: str | int) -> Callable:
                     "The @dataframe decorator cannot be used for data extraction "
                     "functions. Exiting..."
                 )
-                exit(1)
+                sys.exit(1)
 
             if getattr(func, "vantage6_dataframe_decorated", False):
                 error(
                     "The @dataframe decorator cannot be used multiple times. Exiting..."
                 )
-                exit(1)
+                sys.exit(1)
 
             # read the data from the database(s)
             dataframes = _read_dataframes_from_disk(dataframes_grouped, sources, action)

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/decorator/ohdsi.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from collections.abc import Callable
 from dataclasses import dataclass
 from functools import wraps
@@ -126,13 +127,13 @@ def _create_omop_database_connection(connection_details: dict) -> Callable:
     if not OHDSI_AVAILABLE:
         error("OHDSI/DatabaseConnector is not available.")
         error("Did you use 'algorithm-ohdsi-base' image to build this algorithm?")
-        exit(1)
+        sys.exit(1)
 
     expected_keys = ["dbms", "uri", "user", "password"]
     if not set(expected_keys).issubset(connection_details):
         missing_keys = set(expected_keys) - set(connection_details)
         error(f"Missing connection details: {missing_keys}. Exiting...")
-        exit(1)
+        sys.exit(1)
 
     info("Creating OHDSI database connection")
     dbms = connection_details["dbms"]
@@ -176,7 +177,7 @@ def _get_ohdsi_metadata(connection_details: dict) -> OHDSIMetaData:
         missing_env_vars = expected_env_vars - connection_details
         error(f"Missing connection details: {missing_env_vars}")
         error("Exiting...")
-        exit(1)
+        sys.exit(1)
 
     tmp = Path(os.environ[ContainerEnvNames.SESSION_FOLDER.value])
     metadata = OHDSIMetaData(

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/mock/client.py

@@ -1,4 +1,5 @@
 import json
+import sys
 import traceback
 from typing import TYPE_CHECKING, Any
 
@@ -29,49 +30,47 @@ class MockBaseClient:
         # Which organization do I belong to?
         self.organization_id = 0
         # Store missing attributes in a set for __getattr__ to check
-        self._missing_attributes = set(
-            [
-                "_access_token",
-                "_ClientBase__auth_url",
-                "_ClientBase__check_algorithm_store_valid",
-                "_ClientBase__hq_url",
-                "_decrypt_run_data",
-                "_decrypt_field",
-                "_download_run_data_from_hq",
-                "_fetch_and_decrypt_run_data",
-                "_multi_page_request",
-                "_refresh_token",
-                "_upload_run_data_to_hq",
-                "auth_url",
-                "authenticate",
-                "check_if_blob_store_enabled",
-                "collaboration_id",
-                "cryptor",
-                "databases",
-                "generate_path_to",
-                "headers",
-                "image",
-                "log",
-                "name",
-                "node_id",
-                "obtain_new_token",
-                "request",
-                "hq_url",
-                "session_id",
-                "setup_encryption",
-                "store_id",
-                "study_id",
-                "token",
-                "wait_for_task_completion",
-                "whoami",
-            ]
-        )
+        self._missing_attributes = {
+            "_access_token",
+            "_ClientBase__auth_url",
+            "_ClientBase__check_algorithm_store_valid",
+            "_ClientBase__hq_url",
+            "_decrypt_run_data",
+            "_decrypt_field",
+            "_download_run_data_from_hq",
+            "_fetch_and_decrypt_run_data",
+            "_multi_page_request",
+            "_refresh_token",
+            "_upload_run_data_to_hq",
+            "auth_url",
+            "authenticate",
+            "check_if_blob_store_enabled",
+            "collaboration_id",
+            "cryptor",
+            "databases",
+            "generate_path_to",
+            "headers",
+            "image",
+            "log",
+            "name",
+            "node_id",
+            "obtain_new_token",
+            "request",
+            "hq_url",
+            "session_id",
+            "setup_encryption",
+            "store_id",
+            "study_id",
+            "token",
+            "wait_for_task_completion",
+            "whoami",
+        }
 
     def __getattr__(self, name: str):
         """Handle access to missing attributes."""
         if hasattr(self, "_missing_attributes") and name in self._missing_attributes:
             warn(f"The attribute {name} is not available in the mock client.")
-            return None
+            return
         raise AttributeError(
             f"'{self.__class__.__name__}' object has no attribute '{name}'"
         )
@@ -113,7 +112,6 @@ class MockBaseClient:
 
         def missing_method(self, method: str):
             warn(f"The method {method} is not available in the mock client.")
-            return
 
     def wait_for_results(self, task_id: int, interval: float = 1) -> list:
         """
@@ -135,7 +133,7 @@ class MockBaseClient:
         return self.result.from_task(task_id)
 
     class Study(SubClient):
-        """ """
+        """Study subclient for the MockAlgorithmClient"""
 
         def __init__(self, parent) -> None:
             super().__init__(parent)
@@ -261,20 +259,20 @@ class MockBaseClient:
                         "sure that the method is available in the top level of your "
                         "algorithm module?"
                     )
-                    exit(1)
+                    sys.exit(1)
                 except SessionActionMismatchError:
                     error(
                         f"The {method} method is not a computation task, are you sure "
                         "you specified the correct method?"
                     )
-                    exit(1)
+                    sys.exit(1)
                 except DataFrameNotFound as e:
                     error(f"A dataframe you specified does not exist: {e}")
-                    exit(1)
-                except Exception as e:
+                    sys.exit(1)
+                except Exception as e:  # noqa: BLE001
                     error(f"Error simulating task run for organization {org_id}: {e}")
                     traceback.print_exc()
-                    exit(1)
+                    sys.exit(1)
 
                 result_response = self.parent.network.hq.save_result(result, task["id"])
                 self.parent.network.hq.save_run(
@@ -582,15 +580,15 @@ class MockUserClient(MockBaseClient):
                 except SessionActionMismatchError:
                     error(f"The function {method} is not a data extraction method.")
                     error("Exiting...")
-                    exit(1)
-                except Exception as e:
+                    sys.exit(1)
+                except Exception as e:  # noqa: BLE001
                     error(
                         "Error simulating dataframe creation for organization "
                         f"{org_id}: {e}"
                     )
                     error("Exiting...")
                     traceback.print_exc()
-                    exit(1)
+                    sys.exit(1)
 
                 dataframes.append(df_response)
 
@@ -612,7 +610,10 @@ class MockUserClient(MockBaseClient):
         def preprocess(
             self, id_: int, image: str, method: str, arguments: dict
         ) -> dict:
-            """ """
+            """
+            Preprocess a dataframe by creating a task that runs the preprocessing
+            method.
+            """
             dataframe = self.parent.network.hq.get_dataframe(id_)
             data_frame_name = dataframe.get("name")
             if not dataframe or not data_frame_name:
@@ -635,15 +636,15 @@ class MockUserClient(MockBaseClient):
                 except SessionActionMismatchError:
                     error(f"The function {method} is not a preprocessing method.")
                     error("Exiting...")
-                    exit(1)
-                except Exception as e:
+                    sys.exit(1)
+                except Exception as e:  # noqa: BLE001
                     error(
                         "Error simulating dataframe preprocessing for organization "
                         f"{org_id}: {e}"
                     )
                     error("Exiting...")
                     traceback.print_exc()
-                    exit(1)
+                    sys.exit(1)
                 dataframes.append(df)
 
                 result_response = self.parent.network.hq.save_result({}, task["id"])
@@ -687,7 +688,7 @@ class MockAlgorithmClient(MockBaseClient):
                     "parent task."
                 )
                 error("Exiting...")
-                exit(1)
+                sys.exit(1)
 
             # inject the mock data into the arguments
             kwargs["databases"] = self.parent.databases

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/mock/hq.py

@@ -1,5 +1,5 @@
 import json
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from typing import TYPE_CHECKING, Any
 
 import pandas as pd
@@ -113,9 +113,9 @@ class MockHQ:
         last_run_id = len(self.runs) + 1
         run = {
             "id": last_run_id,
-            "started_at": datetime.now(timezone.utc).isoformat(),
-            "assigned_at": datetime.now(timezone.utc).isoformat(),
-            "finished_at": datetime.now(timezone.utc).isoformat(),
+            "started_at": datetime.now(UTC).isoformat(),
+            "assigned_at": datetime.now(UTC).isoformat(),
+            "finished_at": datetime.now(UTC).isoformat(),
             "log": "mock_log",
             "ports": [],
             "status": "completed",

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/mock/network.py

@@ -1,3 +1,5 @@
+import sys
+
 import pandas as pd
 
 from vantage6.common import info
@@ -148,7 +150,7 @@ class MockNetwork:
                     "install your algorithm package in this environment?"
                 )
                 error("Exiting...")
-                exit(1)
+                sys.exit(1)
 
         # In the case the user provides a pandas DataFrame we need to create a dataframe
         # record in HQ.

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/mock/node.py

@@ -238,7 +238,9 @@ class MockNode:
         self.dataframes[dataframe_name] = df
         return df
 
-    def run(self, method_fn: Callable, arguments: dict, task_env_vars: dict = {}):
+    def run(
+        self, method_fn: Callable, arguments: dict, task_env_vars: dict | None = None
+    ):
         """
         Run a method with the given arguments and task environment variables.
 
@@ -256,6 +258,8 @@ class MockNode:
         Any
             The result of the method run.
         """
+        if task_env_vars is None:
+            task_env_vars = {}
         with env_vars(**task_env_vars):
             return method_fn(**arguments)
 

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/preprocessing/aggregation.py

@@ -7,13 +7,13 @@ DataFrame with statistical information based on a given grouping.
 
 import pandas as pd
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 from vantage6.algorithm.tools.exceptions import UserInputError
 
 from vantage6.algorithm.decorator.action import preprocessing
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def collapse(
     df: pd.DataFrame,
@@ -160,7 +160,7 @@ def collapse(
     return agg_df.reset_index()
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def group_statistics(
     df: pd.DataFrame,

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/preprocessing/column.py

@@ -6,13 +6,13 @@ expressions.
 
 import pandas as pd
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 from vantage6.algorithm.tools.exceptions import UserInputError
 
 from vantage6.algorithm.decorator.action import preprocessing
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def rename_columns(
     df: pd.DataFrame, old_names: list[str], new_names: list[str], strict: bool = False
@@ -55,7 +55,7 @@ def rename_columns(
     )
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def assign_column(df: pd.DataFrame, column_name: str, expression: str) -> pd.DataFrame:
     """
@@ -96,7 +96,7 @@ def assign_column(df: pd.DataFrame, column_name: str, expression: str) -> pd.Dat
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def redefine_column(
     df: pd.DataFrame, column_name: str, expression: str
@@ -140,7 +140,7 @@ def redefine_column(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def change_column_type(
     df: pd.DataFrame, columns: list[str], target_type: str

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/preprocessing/datetime.py

@@ -5,17 +5,17 @@ for converting strings to datetime, adding fixed or variable timedeltas, and
 calculating ages from birthdate columns.
 """
 
-from datetime import date
+import datetime
 
 import pandas as pd
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 from vantage6.algorithm.tools.exceptions import DataError, UserInputError
 
 from vantage6.algorithm.decorator.action import preprocessing
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def to_datetime(
     df: pd.DataFrame,
@@ -81,7 +81,7 @@ def to_datetime(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def to_timedelta(
     df: pd.DataFrame,
@@ -179,7 +179,7 @@ def to_timedelta(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def timedelta(
     df: pd.DataFrame,
@@ -268,7 +268,7 @@ def timedelta(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def calculate_age(
     df: pd.DataFrame,
@@ -316,7 +316,7 @@ def calculate_age(
     1  1980-05-15   44
     """
     if reference_date is None:
-        reference_date = date.today()
+        reference_date = datetime.datetime.now(datetime.UTC).date()
     else:
         try:
             reference_date = pd.to_datetime(reference_date)

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/preprocessing/encoding.py

@@ -9,13 +9,13 @@ standard deviations for scaling operations.
 
 import pandas as pd
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 from vantage6.algorithm.tools.exceptions import UserInputError
 
 from vantage6.algorithm.decorator.action import preprocessing
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def min_max_scale(
     df: pd.DataFrame,
@@ -89,7 +89,7 @@ def min_max_scale(
     return df_scaled
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def standard_scale(
     df: pd.DataFrame,
@@ -163,7 +163,7 @@ def standard_scale(
     return df_scaled
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def one_hot_encode(
     df: pd.DataFrame,
@@ -251,7 +251,7 @@ def one_hot_encode(
     return df_out
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def encode(
     df: pd.DataFrame,
@@ -335,7 +335,7 @@ def encode(
     return encoded_df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def discretize_column(
     df: pd.DataFrame,
@@ -401,7 +401,7 @@ def discretize_column(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def extract_from_string(
     df: pd.DataFrame,
@@ -457,7 +457,7 @@ def extract_from_string(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def impute(
     df: pd.DataFrame,

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/preprocessing/filtering.py

@@ -5,12 +5,12 @@ pandas DataFrames, such as selecting and filtering rows and columns.
 
 import pandas as pd
 
-from vantage6.algorithm.tools.error_handling import handle_pandas_errors
+from vantage6.algorithm.tools.error_handling import handle_data_errors
 
 from vantage6.algorithm.decorator.action import preprocessing
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def select_rows(df: pd.DataFrame, query: str) -> pd.DataFrame:
     """
@@ -78,13 +78,13 @@ def select_rows(df: pd.DataFrame, query: str) -> pd.DataFrame:
     return df.query(query)
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def filter_range(
     df: pd.DataFrame,
     column: str,
-    min_value: float = None,
-    max_value: float = None,
+    min_value: float | None = None,
+    max_value: float | None = None,
     include_min: bool = True,
     include_max: bool = True,
 ) -> pd.DataFrame:
@@ -162,7 +162,7 @@ def filter_range(
     return df
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     """
@@ -218,7 +218,7 @@ def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     return df[columns]
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def drop_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     """
@@ -266,7 +266,7 @@ def drop_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     return df.drop(columns, axis=1)
 
 
-@handle_pandas_errors
+@handle_data_errors
 @preprocessing
 def filter_by_date(
     df: pd.DataFrame,

vantage6_algorithm_tools-5.0.3rc5/vantage6/algorithm/tools/error_handling.py

@@ -0,0 +1,48 @@
+import logging
+from collections.abc import Callable
+from functools import wraps
+
+from vantage6.common import logger_name
+
+from vantage6.algorithm.tools.exceptions import AlgorithmError, AlgorithmRuntimeError
+
+module_name = logger_name(__name__)
+log = logging.getLogger(module_name)
+
+
+def handle_data_errors(func: Callable) -> Callable:
+    """
+    Decorator to catch errors from data manipulation in algorithm functions and
+    prevent leaking privacy-sensitive data via error messages or tracebacks.
+
+    Any exception that is not a vantage6 ``AlgorithmError`` is replaced by a generic
+    ``AlgorithmRuntimeError``. This includes non-pandas exceptions such as
+    ``ValueError`` or ``KeyError``, which are commonly raised by pandas operations and
+    tend to contain data values in their message.
+
+    The vantage6 ``AlgorithmError`` exceptions are re-raised unchanged: their messages
+    are written by algorithm developers and are meant to be shown to the user.
+    """
+
+    @wraps(func)
+    def wrapper(*args, **kwargs):
+        try:
+            return func(*args, **kwargs)
+        except AlgorithmError:
+            raise
+        except Exception as e:  # noqa: BLE001
+            msg = (
+                f"An error of type {type(e).__name__} occurred in "
+                f"'{func.__qualname__}'. Details have been omitted to protect privacy."
+            )
+            log.error(msg)
+            # `from None` suppresses the exception context: without it, the original
+            # exception, including its message, is still printed when the traceback
+            # is logged
+            raise AlgorithmRuntimeError(msg) from None
+
+    return wrapper
+
+
+# Backwards-compatible alias
+handle_pandas_errors = handle_data_errors

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/tools/util.py

@@ -160,7 +160,7 @@ def _convert_envvar_to_int(envvar_name: str, envvar_value: str) -> int:
         ) from exc
 
 
-def check_envvar_value_positive(envvar_name: str, envvar_value: int | float) -> None:
+def check_envvar_value_positive(envvar_name: str, envvar_value: float) -> None:
     """
     Check whether an environment variable is a positive integer.
 

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/tools/wrap.py

@@ -1,6 +1,7 @@
 import importlib
 import json
 import os
+import sys
 import traceback
 from typing import Any
 
@@ -47,7 +48,7 @@ def wrap_algorithm(log_traceback: bool = True) -> None:
             "No PKG_NAME specified! Make sure that the PKG_NAME environment "
             "variable is specified in the Dockerfile. Exiting..."
         )
-        exit(1)
+        sys.exit(1)
     info(f"wrapper for {module}")
 
     # Decode environment variables that are encoded by the node.
@@ -112,7 +113,7 @@ def _run_algorithm_method(
         error(f"Module '{module}' can not be imported! Exiting...")
         if log_traceback:
             error(traceback.print_exc())
-        exit(1)
+        sys.exit(1)
 
     # get algorithm method and attempt to load it
     try:
@@ -121,7 +122,7 @@ def _run_algorithm_method(
         error(f"Method '{method}' not found!\n")
         if log_traceback:
             error(traceback.print_exc())
-        exit(1)
+        sys.exit(1)
 
     # check if the method is decorated with a vantage6 decorator. If it is not,
     # we need to raise an error. It is important to check this, because the decorator
@@ -132,18 +133,18 @@ def _run_algorithm_method(
             "algorithm functions should have a decorator such as @federated, "
             "@central, @preprocessing, @data_extraction, etc."
         )
-        exit(1)
+        sys.exit(1)
 
     # try to run the method
     if not arguments:
         arguments = {}
     try:
         result = method_fn(**arguments)
-    except Exception as exc:
+    except Exception as exc:  # noqa: BLE001
         error(f"Error encountered while calling {method}: {exc}")
         if log_traceback:
             error(traceback.print_exc())
-        exit(1)
+        sys.exit(1)
 
     return result
 

vantage6_algorithm_tools-5.0.2rc2/vantage6/algorithm/tools/error_handling.py

@@ -1,59 +0,0 @@
-import logging
-from collections.abc import Callable
-from functools import wraps
-
-import pandas as pd
-
-from vantage6.common import logger_name
-
-from vantage6.algorithm.tools.exceptions import AlgorithmRuntimeError
-
-module_name = logger_name(__name__)
-log = logging.getLogger(module_name)
-
-
-def _collect_pandas_error_types() -> tuple[type, ...]:
-    """
-    Collect all exception classes exported from pandas.errors.
-
-    Returns a tuple of exception types to be used in an except clause.
-    """
-    exception_types = []
-    errors_module = pd.errors
-    for attr_name in errors_module.__all__:
-        attr = getattr(errors_module, attr_name, None)
-        if isinstance(attr, type) and issubclass(attr, Exception):
-            exception_types.append(attr)
-
-    return tuple(exception_types)
-
-
-PANDAS_ERROR_TYPES = _collect_pandas_error_types()
-
-
-def handle_pandas_errors(func: Callable) -> Callable:
-    """
-    Decorator to catch pandas-related errors from algorithm functions and
-    prevent leaking privacy-sensitive data via tracebacks.
-
-    - Catches pandas-specific exceptions and common data-manipulation errors.
-    - Logs a minimal, non-identifying message (no traceback, no exception str).
-    - Returns a safe, generic error response with 400 Bad Request.
-    - Other unexpected exceptions continue to log with traceback for debugging.
-    """
-
-    @wraps(func)
-    def wrapper(*args, **kwargs):
-        try:
-            return func(*args, **kwargs)
-        except PANDAS_ERROR_TYPES as e:
-            # Avoid logging tracebacks or exception messages that may contain data
-            msg = (
-                f"Pandas-related error of type {type(e).__name__} occurred in "
-                "algorithm function. Details have been omitted to protect privacy."
-            )
-            log.error(msg)
-            # pylint: disable=raise-missing-from
-            raise AlgorithmRuntimeError(msg)
-
-    return wrapper

{vantage6_algorithm_tools-5.0.2rc2 → vantage6_algorithm_tools-5.0.3rc5}/vantage6/algorithm/decorator/__init__.py

@@ -15,13 +15,13 @@ from vantage6.algorithm.decorator.metadata import metadata
 from vantage6.algorithm.decorator.ohdsi import omop_data_extraction
 
 __all__ = [
+    "algorithm_client",
     "central",
     "data_extraction",
-    "federated",
-    "preprocessing",
-    "algorithm_client",
     "dataframe",
     "dataframes",
+    "federated",
     "metadata",
     "omop_data_extraction",
+    "preprocessing",
 ]