Abstract: Parallel coordinates plot (PCP) is an excellent tool for multivariate visualization and analysis, but it may fail to reveal inherent structures for complex and large datasets. Therefore, polyline clustering and coordinate sorting are inevitable for the accurate data exploration and analysis. In this paper, we propose a suite of novel clustering and dimension sorting techniques in PCP, to reveal and highlight hidden trend and correlation information of polylines. Spectrum theory is first introduced to specifically design clustering and sorting techniques for a clear view of clusters in PCP. We also provide an efficient correlation based sorting technique to optimize the ordering of coordinates to reveal correlated relations, and show how our view-range metrics, generated based on the aggregation constraints, can be used to make a clear view for easy data perception and analysis. Experimental results generated using our framework visually represent meaningful structures to guide the user, and improve the efficiency of the analysis, especially for the complex and noisy data.