Energy and ETa data come as a group of daily (csv) files.
-
parsing_input_files.py flattens this data into a single file (hundreds of MiB).
-
eta_data_analysis.py prepares ETa data for visualization.
-
power_data_analysis.py prepares power data for visualization.
The last two files have utilities for indexing, parsing time, aggregating power usage or ETa values, selecting data based on crop type, location, or power usage type.
- visualization.py combines Pandas data frames produced with the previous files and plots them.
- Methods for GMM, K-means (gmm_clustering.py), and extended K-means with Mahalanobis distance clustering (mahalanobis_kmeans.py).
- Methods for parsing (filter_clusters.py) and visualizing (cluster_map_viz.py) the results.