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 criteria assesses how well the engineer uses Kedro's pipeline construction and composition capabilities to build a data processing pipeline. The focus is on proper usage of Kedro's node and pipeline APIs to create modular, composable workflows with automatic dependency resolution.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Node factory usage",
"description": "Uses the kedro.pipeline.node() factory function or node() imported from kedro.pipeline to create individual processing nodes with correct function, inputs, and outputs parameters",
"max_score": 25
},
{
"name": "Pipeline factory usage",
"description": "Uses the kedro.pipeline.pipeline() factory function or pipeline() imported from kedro.pipeline to create pipeline instances from collections of nodes",
"max_score": 20
},
{
"name": "Dependency resolution",
"description": "Correctly specifies inputs and outputs for each node using strings (e.g., 'raw_orders', 'cleaned_orders') to enable automatic dependency resolution between nodes based on dataset names",
"max_score": 20
},
{
"name": "Pipeline composition",
"description": "Demonstrates pipeline composition by combining multiple pipeline instances using operators (+ or |) or by passing multiple pipelines to pipeline() factory to create a single unified pipeline",
"max_score": 20
},
{
"name": "Input/output format",
"description": "Uses appropriate input/output formats: strings for single datasets, lists for multiple ordered datasets, or dicts for named parameter mapping as per Kedro conventions",
"max_score": 15
}
]
}