Driver¶
ContinuousMonitor orchestrates the monitoring loop: evaluate batches, check
drift at intervals, dispatch continual learning on drift.
Continuous drift monitoring system.
This module implements a continuous monitoring architecture that: - Maintains detector state across data stream updates - Processes batches continuously until drift is detected - Pauses for learning when drift is detected - Resumes monitoring with updated model weights - Automatically extends the data stream when exhausted
- class apeiron.driver.continuous_monitor.ContinuousMonitor[source]¶
Bases:
objectContinuous drift monitoring system.
This class manages the continuous monitoring of a data stream, detecting drift and dispatching learning modules as needed.
- cfg¶
Configuration object
- modelHarness¶
Model harness containing model and data loaders
- logger¶
Logger for metrics
- detector¶
Persistent drift detector instance
- metric_idx¶
Index of metric to monitor
- detection_interval¶
Number of batches between drift checks
- max_stream_updates¶
Maximum number of stream extensions
- stream_update_count¶
Number of times stream has been extended
- batch_count¶
Total number of batches processed
- metric_buffer¶
Buffer for accumulating metrics between checks
- __init__(cfg, modelHarness)[source]¶
Initialize continuous monitor.
- Parameters:
cfg (Config) – Configuration object
modelHarness (BaseModelHarness) – Model harness containing model and data loaders
logger – Logger for metrics