tessl install tessl/pypi-kedro@1.1.0Kedro helps you build production-ready data and analytics pipelines
Agent Success
Agent success rate when using this tile
98%
Improvement
Agent success rate improvement when using this tile compared to baseline
1.32x
Baseline
Agent success rate without this tile
74%
{
"context": "This evaluation assesses how well the engineer uses Kedro's plugin system and hooks framework to implement a custom plugin for tracking pipeline execution metrics. The focus is on correct implementation of hook specifications, proper hook lifecycle methods, and appropriate use of Kedro's plugin architecture.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Hook class creation",
"description": "Creates a hook class (e.g., MetricsHook) that implements Kedro's hook specification interface with the necessary lifecycle methods",
"max_score": 15
},
{
"name": "before_node_run implementation",
"description": "Correctly implements the before_node_run(node, catalog, inputs, is_async, session_id) hook method with proper signature to capture start time before each node executes",
"max_score": 25
},
{
"name": "after_node_run implementation",
"description": "Correctly implements the after_node_run(node, catalog, inputs, outputs, is_async, session_id) hook method with proper signature to calculate and record execution duration after each node completes",
"max_score": 25
},
{
"name": "after_pipeline_run implementation",
"description": "Correctly implements the after_pipeline_run(run_params, pipeline, catalog) hook method with proper signature to write collected metrics to JSON file after pipeline completion",
"max_score": 25
},
{
"name": "Data persistence",
"description": "Properly stores execution metrics between hook calls using instance variables or class attributes, and correctly writes the data to execution_metrics.json in the expected format (list of objects with node_name and duration fields)",
"max_score": 10
}
]
}