The advent of big data era elicits the importance of visualization. As an import data analysis method, visual analytics explores the cognitive ability and advantages of human beings, integrates the abilities of human and computer, and gains insights into big data with human-computer interaction. In view of the characteristics of large amount of data, high dimension, multi-source and multi-form, the visualization method of large scale data was discussed firstly: 1) divide and rule principle was used to divide big problem into a number of smaller tasks, and parallel processing was used to improve the processing speed; 2) the means of aggregation, sampling and multi-resolution express were used to reduce data; 3) multi-view was used to present high dimensional data. Then, the visualization process of flow data was discussed for the two types of flow data, which were monitoring and superposition. Finally, the visualization of unstructured data and heterogeneous data was described. In a word, the visualization could make up for the disadvantages and shortcomings of computer automatic analysis, integrate computer analysis ability and human perception of information, and find the information and wisdom behind big data effectively. However, the research results of this theory are very limited, and it is faced with the challenge of large scale, dynamic change, high dimension and multi-source heterogeneity, which are becoming the hot spot and direction of large data visualization research in the future.