We are applying k-means clustering algorithm on an unlabeled data. Our aim is to at the end, pool a result that shows two possibility. Is it necessary then to carry out k-nn classification after the clustering?
Hey Ajayi Olusola Olajide
Classification and Clustering are different methodological approaches for different learning techniques of data.
Classification is used for supervised learning whereas clustering is used for unsupervised learning.
Both Classification and Clustering is utilized for the categorizing of data points into at least one classes with respect to features. On account of Classification, there are predefined labels relegated to each info as per their properties while in clustering those labels are absent.
So, for unlabeled data points, Clustering would be the appropriate method to be implemented. Or you can even label the data points and implement any classification algorithm.
Classification: Logistic regression, Naive Bayes classifier, Support vector machines, etc.
Clustering: k-means clustering algorithm, Fuzzy c-means clustering algorithm, Gaussian (EM) clustering algorithm, etc.
Thank you.
No, classification is not necessary after clustering. Clustering is the process of grouping similar data points, while classification is correctly labelling data points based on known labels. Clustering can be useful for exploratory data analysis and data segmentation, while classification can be used to make predictions.
I think clustering is one way of classifying. Therefore, after clustering, some additional classification is not required.
As Eugene mentioned, clustering does a kind of classification where labels are not assigned. One need to inspect the clusters to mark labels to them if required.
Sometimes (practically) clusters will contain some outliers and use case may require you to remove them. Several techniques can be used and k-nn could be one of them.
- Badges
- Science topic
- Similar topics
- Mathematics