Spatial Epidemiological Analysis of Early COVID-19 in the Municipality of Los Baños, Laguna, Philippines using K-means Clustering

—This paper aims to analyze the spread of COVID-19 in the municipality of Los Baños, Laguna in the Philippines through the use of clustering algorithms. The record of the COVID-19 cases in Los Baños from March 2020 up-to March 2021 was used as dataset which includes susceptible, probable, confirmed, recovered and death cases. Following the clustering technique in data mining, a model was created to further analyzed the patterns of COVID-19. Three famous clustering algorithms were used in this study namely; K-means, K-medoids and mean shift. Furthermore, GeoPandas was used in this study for spatial analysis using cluster data while evaluation metrics for clustering such as Dunn index and Euclidean distance dendrogram were used to inspect clustering capability. Through the use of Dunn index, the study had identified K-Means as an efficient clustering method for COVID-19 cases. Hence, shown in this paper that barangay Tuntungin Putho, Mayondon, San Antonio, and Batong Malake formed a relationship.