Clustering
Download as PPTX, PDF0 likes1,020 views
This document presents an overview of clustering algorithms including K-means clustering and canopy clustering. It discusses how K-means aims to minimize error across clusters and describes the canopy clustering approach of using an initial rough clustering followed by more rigorous clustering within canopies. It also provides examples of applying K-means clustering in Mathematica, R, and Excel and canopy clustering in Excel. Finally, it discusses complexity analysis and outlines future work involving Hadoop and parallelizing K-means.
![
Source: Ref [2]](https://image.slidesharecdn.com/clustering-130226065530-phpapp01/85/Clustering-18-320.jpg)
Clustering
- 1. Presented By, Manasi C. Kadam Sharmishtha P. Alwekar Ganesh H. Satpute Deepak D. Ambegaonkar Rajesh V. Dulhani Under the guidance Prof. G. A. Patil Mr. Varad Meru
- 2. Agenda Introduction Clustering K-means clustering algorithm Canopy clustering algorithm Complexity Evaluation Conclusion Future Enhancement References
- 3. Introduction Tedious task to maintain large Data Types 1. Structured 2. Unstructured
- 4. Introduction to Data analysis Extracting information out of data Two types 1. Exploratory or descriptive 2. Confirmative or inferential
- 5. Clustering (Aka Unsupervised Learning) Goal is to discover the natural grouping(s) between objects Given n objects find K groups on measure of “similarity” Organizing data into clusters such that there is • high intra-cluster similarity • low inter-cluster similarity Ideal cluster - set of points that is compact and isolated Ex. K-means algorithm, k-medoids etc.
- 6.
- 7. Problems in clustering Cluster can differ in size, shape & density Presence of noise Cluster is a subjective entity Automation
- 8. Clustering Algorithm Types of Clustering Algorithm 1. Hierarchical 2. Partitional Hierarchical – recursively finds nested clusters Types 1. Agglomerative 2. Divisive Partitional - finds all the clusters simultaneously ex. K-means
- 9. K-means algorithm
- 10. K-means Algorithm (contd.) Goal of K-means is to minimize the sum of the squared error over all K clusters
- 11. Flowchart
- 12. Class Diagram of K-means
- 13. Parameter for K-means Most critical choice is K Typically algorithm is run for various values of K and most appropriate output is selected Different initialization can lead to different output
- 14. Canopy Clustering Traditional clustering algorithm works well when dataset has either property. Large number of clusters A high feature dimensionality Large number of data points. When dataset has all three property at once computation becomes expensive. This necessitates need of new technique, thus canopy clustering
- 15. Canopy Clustering (contd.) Performs clustering in two stages 1. Rough and quick stage 2. Rigorous stage
- 16. Canopy Clustering (contd.) Rough and quick stage Uses extremely inexpensive method divides the data into overlapping subsets called “canopies” Rigorous stage Uses rigorous and expensive metric Clustering is applied only on canopy
- 17. Flowchart of Canopy Clustering
- 19. Output of K-means on Mathematica on Same Dataset
- 20. Output of K-means on R on Same Dataset
- 22. Output of K-means on Microsoft Excel on Same Dataset
- 24. Output of canopy on Excel on Same Dataset
- 25. Complexity Complexity of K-means is O(nk), where n is number of objects and k is number of centroids Canopy based K-means changes to O(nkf2/c) c is no of canopies f is average no of canopies that each data point falls into As f is very small number and c is comparatively big, the complexity is reduced
- 26. Conclusion Implemented K-means Algorithm Verified Result on Mathematica, R Implemented Canopy Clustering Verified Result on Excel
- 27. Future Enhancement Learning Hadoop and MapReduce Parallelizing K-Means based on MapReduce and comparing the implementation Running All the of K-means on standard dataset
- 28. References Anil K. Jain, “Data Clustering: 50 Years Beyond K- Means” Andrew McCallum et al., “Efficient Clustering of High Dimensional Data Sets with Application to Reference Matching”
- 29. Thank You