In this chapter, we are going to discuss about various methods to reduce data dimensions in performing analysis. In data mining, traditionally people used to apply principal component analysis (PCA) as a method to reduce the dimensionality in data. Though now in the age of big data, PCA is still valid, however along with that, many other techniques are being used to reduce dimensions. With the growth of data in volumes and variety, the dimension of data has been continuously on the rise. Dimensionality reduction techniques have many applications in different industries, such as in image processing, speech recognition, recommendation engines, text processing, and so on. The main problem in these application areas is not only high dimensional data but also high sparsity. Sparsity means that many columns in the dataset will have missing or blank values.
In this chapter, we will implement dimensionality reduction techniques such as PCA, singular...