2017 01 30

Pagina 1

Politecnico di Milano School of Industrial and Information Engineering Data Mining and Text Mining Prof. Pier Luca Lanzi & Ing. Daniele Loiacono January 30, 2017 NAME CODICE PERSONA/ID • Answers must be clearly written inside the problem box. All the answers must be adequately motivated. • Pencils are not allowed. The midterm consists of 4 sheets of paper. It must be returned with all the 4 sheets. No any other sheet can be added. No sheet can be removed. • This is a closed-book/closed-notes exam. • Only non-programmable calculators are allowed. • Notes/books/mobile phones are not allowed. • If you are caught using forbidden material, the exam will immediately end and an RP grade will be recorded; then, your Data Mining exam will consist of an oral examination from then on. • Scoring o A problem left unsolved will amount to zero points. o A completely wrong solution will amount to -3 points Grades Problem 1. (7 points) Suppose we created the model and want to assess how well it predicted. The model has the following confusion matrix, PREDICTED CLASS YES NO ACTUAL CLASS YES 94 23 NO 24 100 Define and compute accuracy Define and compute recall Define and compute precision Define and compute F1 measure Problem 2. (7pts) Consider the following dataset, Assuming that stop words have been eliminated, stemming has also being applied and city names like “San Francisco” count as single words. Compute the Naïve Bayes model and then classify the following examples: “andrea: milano, new york, chicago, paris, milano” “marco: san francisco, chicago, new york, san francisco" Note that passengers names are not used for classification purposes. Problem 3 (7pts). Given the data set below and a min support of 3/8 (1) extract all the frequent itemsets using the Eclat algorithm and (2)…