need SAS visualisation expert

Data Cleansing The data analyst must clean the data before using any data mining technique. • Missing data must be determined or removed (by deleting the observations (records or rows)) • Categorical variables must be converted to binary (dummy) variables • Erroneous data and outliers must be investigated Unsupervised Data Mining Methods In unsupervised methods of data mining there is no outcome variable to predict; rather, the goal is to use the variable values to identify relationships between observations. In short, these methods are used to discover patterns in data. When observations include continuous variables, Euclidean distance is the most common method to measure similarity between observations. We will cover two unsupervised learning methods: cluster analysis and association rules.