Problem 3 (50 Points): k-Anonymous Algorithm Implementation Design and implement a heuristic algorithm to ensure k-anonymity for the Adult dataset in UCI Machine Learning Repository: https://archive.ics.uci.edu/ml/datasets/Adult. - To simplify the problem, you only need to consider 4 attributes as quasi-identifiers (QIs) to implement the generalization and/or suppression: 1. age: continuous 2. education: Bachelors, Some-college, 11th, HS-grad, Prof-school, Assoc- acdm, Assoc-voc, 9th, 7th-8th, 12th, Masters, 1st-4th, 10th, Doctorate, 5th-6th, Preschool. 3. Marital-Status: Married-civ-spouse, Divorced, Never-married, Separated, Widowed, Married-spouseabsent, Married-AF-spouse. 4. Race: White, Asian-Pac-Islander, Amer-Indian-Eskimo, Other, Black. The full dataset description is available at: https://archive.ics.uci.edu/ml/machine- learning-databases/adult/old.adult.names - Note that the dataset has missing values. If so, it is considered as "Generalized to the top of the hierarchy". - Each record can specify a different k. In the output, the cardinality of each equivalence class (a group of records with identical QI values) should be no less than all the k values in the group. The implementation tasks include: - 10 Points. Define a generalization hierarchy for each of the 4 attributes. - 30 Points. Write a program for the heuristic algorithm (which generalizes/suppresses the data while minimizing the utility loss). You can use any programming language you feel comfortable. - 10 Points. Calculate the distortion and precision of your algorithm. Submission should include: input dataset, output dataset, source code files, hierarchies, and the distortion/precision results