Materializing Lightning Clustering pipeline
====================================
In my latest post, I perform Exploratory Data Analysis on NOAA's GLM dataset. I create a data pipeline in which I ingest the data and utilize #clustering analysis to create a rough map of lightning clusters .
In the EDA #notebook, I load spatial, latitude and longitude raw data and implement k-means clustering algorithm on the test dataset. I evaluate the perform of the 'k' clusters and create a time lapse of lightning clusters.
I convert the notebook into a Dagster orchestrated #data pipeline composed of materialized assets performing the required data ingestion and clustering analysis.
https://blog.devgenius.io/exploratory-data-analysis-with-lightning-clustering-pipeline-6a2bca17d0d3https://github.com/BayoAdejare/lightning-maphttps://github.com/BayoAdejare/lightning-map/blob/master/notebooks/eda_kmeans.ipynb#machinelearning#analytics#orchestration#data#pipeline#dagster#dataengineering#etl
🎉 1
❤️ 3
🌈 4
o
Odette Harary
05/08/2023, 3:00 PM
Hey Adebayo - We have a dagster community call coming up on June 12th- would you be interested in showcasing this?