CENG-303/503-Wk-5-LAB -Classification and Clustering

This session, a part of a Data Science & Analytics course features a live, hands-on JupyterLab session focused on Classification and Clustering. In this practical lab, we use Python and machine learning techniques to analyze data, predict categories, and discover meaningful patterns within datasets. The classification portion introduces supervised learning workflows, including preparing features and target labels, splitting data into training and testing sets, building classification models, generating predictions, and evaluating performance using accuracy, precision, recall, F1-score, confusion matrices, and other classification metrics. The clustering portion explores unsupervised learning, where algorithms identify natural groups within unlabeled data. We examine concepts such as data scaling, cluster formation, similarity, K-means clustering, selecting the number of clusters, and interpreting customer or data segments. This live JupyterLab demonstration connects machine learning theory with practical implementation using Python, Pandas, NumPy, Matplotlib, Seaborn, and Scikit-learn. The session helps students understand how classification and clustering are applied in customer segmentation, fraud detection, medical diagnosis, image recognition, recommendation systems, and predictive analytics. #DataScience #DataAnalytics #Classification #Clustering #MachineLearning #Python #JupyterLab #ScikitLearn #SupervisedLearning #UnsupervisedLearning #KMeans #LogisticRegression #DecisionTrees #ConfusionMatrix #CustomerSegmentation #PredictiveAnalytics #ArtificialIntelligence