Course Code: 20CS1101 R20

SIDDHARTH INSTITUTE OF ENGINEERING & TECHNOLOGY:: PUTTUR

(AUTONOMOUS)
Siddharth Nagar, Narayanavanam Road – 517583

QUESTION BANK (DESCRIPTIVE)

Subject with Code: (20CS1101) INTRODUCTION TO DATA SCIENCE

Course & Branch: B.Tech – CSE(CAD) Regulation: R20
UNIT –I
INTRODUCTION TO DATA SCIENCE

1 a Define Data Science and discuss Benefits and uses of data science. [L1][CO1] [6M]

b Discuss the Various Processing Steps in Data Science [L2][CO1] [6M]

2 Explain in Details various data types used in Data science and Big data [L2][CO1] [12M]

3 a Analyze the term: Distributed file systems [L4][CO1] [6M]

b How will you creating research goals in a project charter [L1][CO1] [6M]

4 Classify the term big data ecosystem [L4][CO1] [12M]

5 How will you retrieve the required data from data science [L1][CO5] [12M]
6 Discuss in detailed Data Cleaning operation in data science [L2][CO1] [12M]

7 a What are various steps involved in integrating phase [L1][CO1] [6M]

b What is meant by exploratory data analysis [L1][CO1] [6M]

8 Examine the term: Transforming data in Data science [L3][CO1] [12M]

9 a Show the various components of model building. [L2][CO1] [6M]

b What are the ways analyzed the data and built a well-performing model [L2][CO1] [6M]

10 a How will you handling missing data in data science [L2][CO1] [6M]
b Examine K-nearest neighbor techniques look at the k-nearest point to make [L4][CO1] [6M]
a prediction
Course Code: 20CS1101 R20

UNIT –II
STATISTICAL METHODS FOR EVALUATION&ASSOCIATION RULES

1 a Define Hypothesis Testing [L1][CO2] [6M]

b How will you mathematically define Confidence [L1][CO2] [6M]
2 a Differentiate Null Hypotheses and Alternative Hypotheses [L4][CO2] [6M]
b Examine the application property of Wilcoxon rank-sum test [L3][CO2] [6M]
3 Discriminate about Difference of Means [L5][CO2] [12M]
4 Explain the differences between Bl and Data Science. [L2][CO2] [12M]
5 Explain the following [L2][CO2] [12M]
a) Student’s t-test
b) Welch’s t-test
6 a What are the three characteristics of Big Data, and what are the main [L1][CO2] [6M]
considerations in processing Big Data?
b How evaluation of Candidate Rules is done? [L2][CO2] [6M]
7 a What is a type I error? What is a type II error? Is one always more serious [L1][CO2] [6M]
than the other? Why?
b Give the difference between Validation and Testing [L4][CO2] [6M]
8 a State Apriori Algorithm [L1][CO2] [4M]
b Explain Apriori Algorithm with example [L2][CO2] [8M]
9 a List and discuss the four measures of significance of Association rules [L1][CO2] [6M]
b Give the Applications of Association Rules [L1][CO2] [6M]
10 Illustrate any five approaches to improve Apriori’s efficiency when the [L3][CO2] [12M]
dataset is large.
Course Code: 20CS1101 R20

UNIT –III
REGRESSION& CLASSIFICATION

1 a Which two basic measures does the entropy methods select the most informative [L1][CO3] [6M]
attribute?
b Define confusion matrix [L1][CO3] [6M]
2 Explain the analytical technique Linear Regression with its model description. [L2][CO3] [12M]
3 Discuss the following with respect to linear regression [L2][CO3] [12M]
a) Categorical Variables
b) Confidence Intervals on the Parameters
c) Confidence Interval on the Expected Outcome
d) Prediction Interval on a Particular Outcome
4 a Justify the usage of linear regression and logistic regression. [L6][CO3] [4M]
b Illustrate Logistic Regression Model. [L3][CO3] [8M]
5 a Describe Decision Trees in detail with example. [L2][CO3] [6M]
b Difference between Alternative hypothesis and null hypothesis [L2][CO4] [6M]
6 Intercept the decision trees algorithms [L4][CO4] [12M]
7 a State Bayes’ Theorem [L1][CO4] [4M]
b Discuss Naïve Bayes classification method considering an example [L2][CO4] [8M]
8 How does one pick the mostsuitable method for a given classification problem? [L2][CO4] [12M]
9 a Compare the C4.5 and CART algorithm of decision tree. [L4][CO4] [4M]
b Discriminate the way show the evaluation of decision tree is done [L5][CO4] [4M]
c Give the two approaches that help avoid over fitting in decision tree learning. [L2][CO4] [4M]
10 Discuss the following term: [L4][CO4] [12M]
a) Accuracy
b) TPR
c) FPR
d) FNR
e) Precision
Course Code: 20CS1101 R20
UNIT –IV
CLUSTERING & TIME SERIES ANALYSIS

1 a What is clustering? [L1][CO5] [6M]

b State the advantage of using PAM. [L1][CO5] [6M]
2 Illustrate the method to find k clusters from a collection of M objects with n [L3][CO5] [12M]
attributes.
3 a Explain any one case study for time series analysis [L2][CO5] [6M]

b What is forecasting in association with time series. Explain [L1][CO6] [6M]

4 a Indicate when the time series ytfor t=1,2,3,…. is said to be stationary time series. [L2][CO6] [6M]
b Express the stationary time series conditions in detail. [L6][CO6] [6M]
5 Discussion detail each part of the ARIMA model [L2][CO5] [12M]
6 a List and explain time series components [L1][CO6] [6M]
b Discriminate the steps involved in Box-Jenkins Methodology [L5][CO6] [6M]
7 a What is meant by k-means [L1][CO5] [4M]
b Describe k-means algorithm to find k clusters [L2][CO5] [8M]
8 Correlate ARMA and ARIMA Models [L4][CO6] [12M]
9 Express the following [L2][CO6] [12M]
a) Autocorrelation Function
b) Autoregressive Models
10 List and describe Additional time series methods [L2][CO6] [12M]
Course Code: (20CS1101 R20

UNIT –V TEXT ANALYSIS

1 a Define Porter’s stemming algorithm. [L1][CO6] [6M]

b What is Topic modeling? [L1][CO6] [6M]
2 Explain the three important steps of the text analysis [L2][CO6] [12M]
3 a Sketch the flow diagram of Text analysis process [L5][CO6] [6M]
b Illustrate in detail the steps involved in the process of Text Analysis done by [L3][CO6] [6M]
organizations
4 a Define TFIDF. [L1][CO6] [4M]
b Describe the usage of TFIDF to compute the usefulness of each word in the [L2][CO6] [8M]
texts.
5 Explain how the data science team will categorize the reviews by topics [L2][CO6] [12M]
6 Illustrate the main challenges of text analysis [L3][CO6] [12M]
7 a Define Topic model. Describe LDA. [L2][CO6] [6M]
b Justify the process of topic modeling simplification. [L6][CO6] [6M]
8 Explain the following [L3][CO6] [12M]
a) Tokenization
b) Case folding
9 a Explain how categorizing documents by topics is done. [L2][CO6] [6M]
b Interpret the procedure used in data science to gain insights into customer [L3][CO6] [6M]
opinions
10 a What is meant by sentiment analysis [L1][CO6] [4M]
b Discriminate the methods used for sentiment analysis [L5][CO6] [8M]

Preparedby:
Mr.G.Prasad Babu
Associate Professor

INTRODUCTION TO DATA SCIENCE (R20)