roi.py

Filters and labels execution regions for visualization.

This script takes a JSON file of performance metrics, as output by join.py, and generates another JSON, where the execution regions are filtered and labeled for visualization, according to an auxiliary region-of-interest (ROI) specification file (JSON format). The specification file can be a Mako template to parameterize certain parameters, such as the number of clusters in the system. The output JSON can be passed to the visualize.py script for visualization.

Check out test_data/data.json and test_data/spec.json for an example input and specification file which can be fed as input to the tool respectively. The corresponding output is contained in test_data/roi.json.