B.Sc. (Computer Science) Sem 6 Data Science 2022-23 Question Paper - Mumbai University | munotes

Questions asked in this paper

• 2) Figures to the right indicate marks

1. Q3 Illustrations, in-depth answers and diagrams will be appreciated
2. Q4 Mixing of sub-questions is not allowed
3. Q1 Attempt All
   • (a) Select the correct alternative from the options given: (10M)
   • (i) Exploratory Data Analysis represents data in format
   • (a) Numerical (b) Character
   • (c) String (d) Graphical
   • (ii) interviews are conducted by a trained interviewer in a non-structured and natural way with a small group
   • (c) formal (d) informal
   • (iii) Imputation or removal of data are used during handling of data
   • (a) collected (b) Missing
   • (c) table (d) Duplicate
   • (iv) is a query language used for traversing through an XML document
   • (a) XML (b)
   • (v) data have semantic tags
   • (a) structured (b) unstructured
   • (vi) In version control is a mainline or unique line of the development which is not actually a branch
   • (c) path (d) root
   • (vii) service of cloud support services such as storage and network connectivity on demand
   • (c) SaaS (d) SaaN
   • (viii) _ AIC is suited over BIC when the model is
   • (a) simple (b) complex
   • (c) large (d) Small
   • (ix) Lasso regression was introduced in order to improve the prediction
   • (a) accuracy (b) values
   • (c) result (d) set
   • (x) is the process of making prediction of the future based on present and past data
   • (a) Trend (b) Seasonality
   • (c) forecasting (d) classification
   • (b) Fill in the blanks by selecting from the pool of options: (5M)
   • (i) Apriori, K-means and K-medoids are the example of learning
   • (ii) deals with removal of noise from data
   • (iii) data are not organized into special repositories
   • (iv) In observation the person who is being observed is unaware that he is
   • (v) Height and weight are the example of data
4. Q2 Attempt the following (Any THREE) (15M)
   • (a) What is data? Explain types of data
   • (b) What is EDA? Explain methods to visualize data
   • (c) What is data normalization? Illustrate any one type of data normalization technique with an example
   • (d) Explain the difference between data and information
   • (e) Describe any two types of observational methods used in data collection
   • (f) Write a short note on data cleaning and data extraction
5. Q3 Attempt the following (Any THREE) (15M)
   • (a) Discuss the 5 V’s of data
   • (b) What is MongoDB? State its features
   • (c) How to create indexes in MongoDB? Give example
   • (d) What is NoSQL? What are its features?
   • (e) Explain how you can read JSON file in R with the help of an example
   • (f) Write a short note on AWS
6. Q4 Attempt the following (Any THREE) 15 marks
   • (a) What are AIC, BIC? State their mathematical formula
   • (b) Explain Forecasting. List the steps in forecasting
   • (c) Write a short note on SVM
   • (d) What is K-NN? Explain with the help of an example
   • (e) Explain the filter method and forward selection method of data selection
   • (f) Discuss the steps involved in implementing PCA on a 2-D Dataset
7. Q5 Attempt the following (Any FIVE) 15 marks
   • (a) Explain the terms data, information and knowledge
   • (b) Write a short note on Smoothing by means technique
   • (c) How can you see data stored in MongoDB? Explain any two methods with
   • (d) Explain any 3 ways to do web scraping
   • (e) Discuss the important characteristics of HBase
   • (f) Give the formula for Information Gain and Entropy
   • (g) Discuss Model, Train Data and Test Data
   • (h) Discuss the Advantages of Dimensionality reduction

Read from the scan above, so a character or two may differ. The scan is the original.