This project explores the association between the El Niño–Southern Oscillation (ENSO) and regional climate variability across Eurasia. Rather than employing traditional regression-based methods, this study leverages association rule mining to investigate whether specific temperature and precipitation anomaly states co-occur under different ENSO phases. By comparing El Niño and Neutral conditions, we examine variations in rule presence and strength to assess how these co-occurrence patterns evolve across ENSO states.

The objective of this project is to analyze how does the perceptual space of wine quality differ when it is constructed from objective chemical composition versus when subjective quality information is incorporated into the dissimilarity structure by comparing two methods metric and non-metric multidimensional scaling (MDS).

This document represents the unsupervised learning of clustering study, aiming to inform the siting of delivery courier stations, by clustering features from working population and income characteristics combined with geographic location. By comparing 3 mainstream clustering methods(K-means,PAM,DBSCAN), try to find the appropriate clusters with reasonable interpretation.