d43f08d272
Enhance README and Implement Drift Detection and Metrics Workflows - Added new sections in README for Drift Workflow and Simple Metrics Workflow, detailing their execution flows and functionalities. - Introduced `drift.py` for data drift detection, comparing current data against reference datasets. - Added `simple_metrics.py` for calculating regression metrics (RMSE, MSE, MAE, R²). - Updated `values.yaml` to include configuration for MinIO retention hours and offload threshold. - Refactored `minio_dataframe_payload.py` to use the new offload threshold environment variable. - Adjusted tests to reflect changes in environment variable handling for MinIO offload threshold.
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
import os
|
|
import sys
|
|
from unittest.mock import MagicMock
|
|
|
|
# The production code converts SIENTIA_MINIO_OFFLOAD_THRESHOLD_MEGABYTES to int at import-time.
|
|
# Tests must set it to a valid integer string to avoid import errors.
|
|
os.environ.setdefault('SIENTIA_MINIO_OFFLOAD_THRESHOLD_MEGABYTES', '1')
|
|
|
|
|
|
class DummyMinioDataFramePayload:
|
|
"""
|
|
Minimal payload double used by unit tests.
|
|
|
|
The production workflow/gates expect a MinioDataFramePayload-like object with:
|
|
- async retrieve(minio_repo, workflow_metadata) -> DataFrame | dict
|
|
- has_data() -> bool
|
|
- cleanup_prefix() -> str | None
|
|
- last_timestamp: attribute
|
|
- status: attribute
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*,
|
|
retrieve_return=None,
|
|
has_data: bool = True,
|
|
cleanup_prefix: str | None = None,
|
|
last_timestamp: str = '2024-01-01',
|
|
status: dict | None = None,
|
|
):
|
|
self._retrieve_return = retrieve_return
|
|
self._has_data = has_data
|
|
self._cleanup_prefix = cleanup_prefix
|
|
self.last_timestamp = last_timestamp
|
|
self.status = status
|
|
|
|
async def retrieve(self, _minio_repo, _workflow_metadata=None):
|
|
return self._retrieve_return
|
|
|
|
def has_data(self) -> bool:
|
|
return self._has_data
|
|
|
|
def cleanup_prefix(self) -> str | None:
|
|
return self._cleanup_prefix
|
|
|
|
|
|
"""
|
|
Pytest configuration file with global mocks for external dependencies.
|
|
|
|
This module mocks the 'sientia' module to avoid requiring its installation
|
|
during unit tests. The mock is registered in sys.modules before any test
|
|
imports are executed.
|
|
"""
|
|
|
|
# Mock sientia module
|
|
sientia_mock = MagicMock()
|
|
sientia_mock.ModelAnalysis = MagicMock
|
|
sys.modules['sientia'] = sientia_mock
|
|
sys.modules['sientia.ModelAnalysis'] = MagicMock()
|