📗 The lecture is in person, but you can join Zoom: 8:50-9:40 or 11:00-11:50. Zoom recordings can be viewed on Canvas -> Zoom -> Cloud Recordings. They will be moved to Kaltura over the weekends.
📗 The in-class (participation) quizzes should be submitted on TopHat (Code:741565), but you can submit your answers through Form at the end of the lectures too.
📗 The Python notebooks used during the lectures can also be found on: GitHub. They will be updated weekly.
📗 Exams:
➭ Version X: PDF, Solution: PDF.
➭ Version Y: PDF, Solution: PDF.
➭ Clarifications:
(1) Question 2: some versions contain a typo "tr" and "td" are switched in the correct answer, if you noted this in Question 20 as the reason you selected another answer, you got the point for this question.
(2) Question 5: in all versions on Canvas, "&" is displayed as "&", if you noted this in Question 20 as the reason you selected the answer with "," and without the double quotes, you got the point for this question.
(3) Question 7: the meaning of "Device information" could be ambiguous, but "Service provide" and "Location information" are better options, as stated in Lecture 21: Link "Collecting Visitor Information" section, and used in P4.
(4) Question 8: "index/a?x=b" access the function that binds "index/", i.e. "index/a", and is not affected by the query string "?x=b", therefore, "index/a?x=b" will return a page that displays "a", and this can be found in Lecture 21: Link "Binding Multiple Paths" section.
(4) Question 12: "texture (different patterns inside a shape)" can be used for both ordinal or categorical columns, (e.g. ordinal if the same pattern with different densities are used), but the question is asking for which ones are more suitable for ordinal data in general: when texture is used, they represent different categories, as stated in Lecture 23: Link "Visual Encodings" section.
(5) Question 17: box(0, 0, 1, 1) and box(0.5, 0.5, 1.5, 1.5) produces a polygon with 8 vertices and box(0, 0, 1, 1) and box(0, 0, 2, 2) produces a polygon with 4 vertices, both examples appeared in past exams.
(6) Question 19: There are two matches, "123" and "320", in each match, the groups are ordered by the left parentheses, i.e. ("123", "12", "1") and ("320", "32", "3"), and therefore, if the orders are reversed, we have "112123" and "332320", and an example of this can be found in the last "dates and times" example in: Notebook.
📗 Exam Coverage:
➭ 20 multiple choice questions (four choices, only one of them is the "most correct").
➭ Week 7 Monday (Oct 16) to Week 9 Wednesday (Nov 1).
📗 Past Exam:
Ten questions are similar to past exams Link or quiz questions (other questions on these past exams are not covered this semester):
📗 New Questions:
Ten questions are not similar to past exam questions or quiz questions, including on the new topics covered this semester:
➭ - Informed search: GBS, A, A*.
Question 1:
➭ - Multi-armed bandit, UCB.
Question 2:
➭ - Visual encodings, seaborn.
Question 3:
➭ - Curve plotting, Bezier curves.
Question 4:
➭ - Enter a different ID to see a different version of the questions: , and click (or hit the "Enter" key).
➭ To check your answer, click :
***** ***** ***** ***** *****
***** ***** ***** ***** *****
➭ There are no more new questions on these topics other than these four and the ones in the weekly quizzes.
📗 Not on exam:
The following topics are NOT on exam 2:
➭ Chernoff faces.
➭ Dimensionality reduction: PCA (will be on exam 3).
➭ Graph layouts.
➭ Minimum spanning trees.
➭ GET POST methods (not covered this semester).
➭ Text and image preprocessing and features (will be on exam 3).
1,2,3,4q
📗 [1 points] There are infinite number of web pages labeled by (0, 0), (0, 1), (0, 2), ..., (1, 0), (1, 1), ... and page (i, j) contains links to pages (i + 1, j) and (i, j + 1). Suppose we start at page (0, 0) and the goal is to find page (10, 10), which one of the following search heuristic is NOT admissible? h((i, j)) = h((i, j)) = h((i, j)) = h((i, j)) =
📗 [1 points] If the current average click through rates from versions A, B, C of the page are the same, and the numbers of visits to A, B, C are , respectively, which version with the UCB1 (upper confidence bound) algorithm display next?
📗 [1 points] In a DataFrame with columns c1, c2, c3, c4 containing categorical data with categories respectively, how many subplots (axes) will seaborn.relplot(data, x = "c1", y = "c2", col= "c3", row = "c4") make?
📗 [1 points]If the quadratic Bezeir curve matplotlib.patches.FancyArrowPatch((10, 10), (0, 0), connectionstyle=ConnectionStyle.Angle3(x, y) with x = and y = has three control points (10, 10), (a, b), (0, 0), what is the value of (a, b)?