i m try to apply k-means with Python 3 to my dataset (Amazon review) for classify similar user (from review). I just have a TF and TF-IDF matrix (and i have a row and columns value, row is user and columns is word of review ) and i wish cluster the user. I m starting with sklearn from this sketch https://scikit-learn.org/stable/auto_examples/text/plot_document_clustering.html#sphx-glr-auto-examples-text-plot-document-clustering-py but in my case i don't have label or category. For now i apply k-means and make some analysis on the cluster and on the variance. After i wish calculate a centroid and make a plot of this clustering, but i can't, because i don't have a label like in example: labels = dataset.target In this example , maybe the label will be compute before. I m finding this example too: https://medium.com/@roberto.sannazzaro/unsupervised-learning-come-catalogare-un-dataset-senza-labels-52bf9b6a3073 but don't help me so much. So, the question is: Can i apply k-means without label? I m very lost, because i m new in this word.