Course Code: 20CSST10 R20 PRAGATI ENGINEERING COLL (AUTONOMOUS) 111 B.Tech 1 Semester Supplementary Examinations, May - 2023 DATA WAREHOUSING AND DATA MINING (Computer Science and Engineering) Time: 3 hours Max. Marks: 70 M SURAMPALEM Answer ONE Question from each Unit All Questions Carry Equal Marks Q.No. Questions BTL | CO | Marks Explain the Star, Snowflake Tae tellati lL fa) ‘xplain the Star, Snov e, and Fact Constellation » schemas for Multidimensional Data Models k2_|col| ™ }) _| Explain the Data Warehouse Design Process K2_ [col] 7™M OR 2. |a) | Explain the steps of knowledge discovery process with neat sketch K2 |CO1l| 7M b) | Explain the major challenges of mining a huge amount of data in comparison with mining a small amount of data K2 |CO1| 7M UNIT - II 3. |a) | Explain the Major Tasks in Data Pre-processing K2 |CO2| 7M b) _| Discuss the issues during data integration. K2 |CO2| 7M OR 4. ]a) | Explain the four methods for the generation of concept hierarchies for nominal data Kz |co2| 7 b) _| Explain the different Data Transformation Strategies K2 |CO2| 7M UNIT - III 3. ]Explain Decision tree induction algorithm for classification. | ] cos) 14M Discuss the usage of information gain. | OR | 6. ]a) | Why is tree pruning useful in decision tree induction? What is a drawback of using a separate set of tuples to evaluate k2 |CO3| 7M pruning | b) _| Discuss the Visual Mining for Decision Tree Induction K2 | co3| 7M UNIT-IV 7. ]a) | How is association rules generated from frequent itemsets? Explain K2 |CO4| 7M b) [Explain the limitations of apriori algorithm K2 |co4] 7M Page 1 of 2OR, ‘8. | Find the frequent itemsets and strong association rules for the | following transactional database table using Aprion algorithm. = 40%. Consider the thresholds as PP = 30% and confidence = 40% He fina. [2 ]12.i5i7.i9 | [3 [113.1517] [suid | pesca Pur fieazaoi | [12] UNIT — Vv (9. | Explain different types of Clustering methods. OR How to Handling Empty Explain Write Bisecting K-means al example of four clusters Kg,Peet ti code: I9CSSTI2 {ms PRAGATI ENGINEERING COLLEGE: SURAMPALEM (AUTONOMOUS) III B.Tech I Semester Regular Examinations, February-2022 DATA WAREHOUSING AND DATA MINING (Comman to CSE & IT) ime: 3 HOUTS Max. Marks: 70 Answer ONE Question from each Unit All Questions Carry Equal Marks No. Questions BIL | CO | Marks ee UNIT-1 2) | Whatis the significance of OLAP in data warehouse? ™ Describe OLAP operations with necessary k2 |COl diagram/example 1) _| Explain about the three — tier data warehouse architecture | x1 |COl ™ 7 OR a) | Differentiate Multidimensional and Multi-relationaLOLAP. | yx Col | 7M 7) [Gist different schemas and explain star schema and fact cor |7™ constellation schemas. Kl UNIT-0 @) _ | Deseribe Discretization and concept hierarchy generation | y, |CO2|7™M for numerical data? “How can the data cube be efficiently ‘constructed for C02 | 7M b) | discovery-driven Exploration? Explain various operations | KI ofa Data Cube. OR a) | Describe Datamining Task primitives. Kl C02 | 7M b) | Describe data mining as a step process of knowledge 2 C02 | 7M discovery. Mention the Functionalities of Data mining. L UNIT-U a) _| Explain decision tree induction algorithm for classifying KI C03 | 7M data tuples and discuss suitable example | b) | Discuss the methods that are commonly used to evaluate the K2 C03 | 7M + formance of a classifier OR. a lain the | approach to solving a classificati | ) ee. general app! ig ion x1 | co3| ™ b) | Explain Navie Bayesian Classification ™ KI | CO3 Page 1 of 2a) How can we mine multilevel} Association rules cfficiently using concept hicrarchies? Nhustrate Apriori Algorithm with an-example OR Explain FP-growth algorithm for frequent item set gencration Kl What is the goal of clustering? How does Partitioning ™ around medoids algorithm aachieve this goal? Cos 7a _- OR Explain the categories of major clustering methods?Course Code. 20085710 L n20 | PRAGATI ENGINEERING COLLEG (AUTONOMOUS) MIT B.Tech | Semester Regular Examinations, December - 2022 DATA WAREHOUSING AND DATA MINING (Computer Science and Engineering) : SURAMPALEM Time: 3 hours Max. Marks: 70 M Answer ONE Question from each Unit All Questions Carry Equal Marks Q.No. ‘Questions BTL | CO | Marks | UNIT-1 | 1. Ja) Compare and Contrast the following: ; information x3 |co1| 14M | processing, analytical processing, and data mining | OR \ 2. a) | Explain the difference and similarity between discrimination and classification, between characterization and clustering,| K2 |COl| 7M \ and between classification and regression b) | How is a data warehouse different from a database? How are they similar? Explain eee UNIT -II a) In real-world data, tuples with missing values for some attributes are a common occurrence. Describe various K2 |CO2| 7M methods for handling this problem b) _| Explain the Binning methods for data smoothing K2_|CO2| 7M OR a) | Explain the Greedy (heuristic) methods for attribute subset selection Hoa b)_[ Explain the Data Cube Aggregation with example k2_|[coz[_7M UNIT - II a) | Explain the data classification process with example K2 |co3| 7M b) | Write Basic algorithm for inducing a decision tree from training tuples K2 |co3| 7M OR a) | Define information gain and explain its importance in decision tree induction K2 |CO3| 7M b) _| Explain the two common approaches to tree pruning K2 |cO3| 7M UNIT -IV a) _| Explain Rule Generation in Apriori Algorithm k2 |co4] 7M b) __| Explain the maximal frequent itemset with example k2 |co4] 7M OR a) | Apply FP-Growth algorithm to the following transactional data to find frequent itemsets. List all frequent itemsets with their support count K3 |CO4| 14M L —. Page 1 of 2Cou 17,18,i6,i1 18,i5,13,i2 11,13,14,i6 OR Compare and Contrast Exclusive versus Overlapping versus Fuzzy clustering Discuss about key issues in Hierarchical clusteringCourse Code: 20CS5T10 a PRAGATI ENGINEERING COLLEGE: SURAMPALEM (AUTONOMOUS) NIB. Tech I Semester Regular/Supplementary Examinations, November - 2023 DATA WAREHOUSING AND DATA MINING (Computer Science and Engineering) Time: 3 hours p 7 8 . Max. Marks: 70 M Answer ONE Question from each Unit All Questions Carry Equal Marks Q. No. Questions BTL | CO | Marks UNIT-1 1, | a) | Mhustrate Multidimensional data model and List the names of x2 |co1| 7M warehouse schemas.? b) What is descriptive and predictive data mining? KI COl| 7M OR 2. a) Illustrate indexing methods used for OLAP data. K2 |COl mM b) Explain data cube computation. What is the need for partial K2 col ™M materialization? a UNIT - II 3. a) Compare data discretization and concept hierarchy co2 generation. iad ™ b) | Explain the preprocessing techniques available in data cO2 mining, K2 ™M OR 4. | a) | Explain data transformation techniques. K2 [©] 744 b) Suppose a group of 12 sales price records has been sorted as follows: 5,10,11,13,15,35,50,55,72,92,204,215. Partition them into three bins by each of the following methods: (i)| K4 |CO2] 74 equal-frequency (equal-depth) partitioning (ii) equal-width partitioning (iii) clustering UNIT - 11 5. | a) | Explain about decision tree induction. K2 | CO3 ™ b) | Construct Decision tree by using information gain. K3 | CO3 a OR 6. a) Discuss general approach for solving a Classification CO3 problem in detail. K2 7M b What are the characteristics of K-Nearest nei, bor ; algorithm? 7 K2 | 7™M UNIT-IV 7. |a) | Discover all frequent item sets with support 50% and confidence 60% using Apriori for a given data K4 |CO4| 7M Page 1of2TI 111213, T2— 1213.14, T3> 1415, T4— 1112.14, TS— 11,12,13,18, T6— 112,13,14 b) | Discover the association rules using Apriori for above transactions, K4 CO4 OR a) b) | What are the advantages of FP-Growth algorithm? What is support and confidence related to association rules. Explain with examples. Kl C04 cos] 7y) UNIT-V a) Illustrate Additional issues occurred Basic Means of Clustering with example 8 COs b) Interpret Bisecting K-means algorithm with example. COS OR 10. a) b) Suppose that the data-mining task is to cluster the following eight points (representing location) into three clusters: Al (2510) ; A2 (2;5) ; A3 (8;4) ; BI (5;8) ; B2 (7;5) ; B3 (6;4) ; Cl (1;2) ; C2 (4;9). The distance function is Euclidean distance. Suppose initially we assign Al, Bl, and Cl as the center of each cluster, respectively. Use the k-means algorithm to determine: the three cluster centers after the first round of execution What are the advantages and disadvantages of k-means | clustering against model-based clusterin 2? K4 Cos cosCourse Code: 20CSST10 ney | PRAGATI ENGINEERING COLLEGE: SURAMPALEM (AUTONOMOUS) 111 B. Tech I Semester Regular/Supplementary Examinations, November - 2023 DATA WAREHOUSING AND DATA MINING (Computer Science and Engineering) Max. Marks: 70M Time: 3 hours Answer ONE Question from cach Unit All Questions Carry Equal Marks Q.No. Questions ~ [ete [CO | Marks UNIT -1 1.- | a) _ | Mlustrate Multidimensional dats mode! and List the names of TI. | warehouse schemas. me col aa [b)_ [What is descriptive and predictive data mining? K1_ [cor] 7M OR 2. ‘a) | Mlustrate indexing methods used for OLAP data. K2 Coll] 7M b) | Explain data cube computation. What is the need for partial K2 COL! any materialization? UNIT-II 3. Ja) [Compare data discretization and concept hierarchy CO2] ay generation. b) | Explain the preprocessing techniques available in data K2 co2 ™M mining. OR 4. ]a) | Explain data transformation techniques. x2 ©] ™ b) | Suppose a group of 12 sales price records has been sorted as follows: 5,10,11,13,15,35,50,55,72,92,204,215. Partition ; them into three bins by each of the following methods: (i) | K4 C02! 9M equal-frequency (equal-depth) partitioning (ii) equal-width partitioning (iii) clustering UNIT - Ill 5. |a) | Explain about decision tree induction. K2 C03 7M b) | Construct Decision tree by using information gain. K3 CO3|} aM OR 6. ]a) | Discuss general approach for solving a Classification K2 C03 ™M problem in detail. Dao b) | What are the characteristics of K-Nearest neighbor Kw C03! aM algorithm? a UNIT -IV a 7. ]a) | Discover all frequent item sets with support 50% and Ka [cod] 7 M confidence 60% using Apriori for a given data | | + — Page 1of2 a[TI 1.123, T25 12.1314, T3 14.5, T4—> 112.14, | TS— 11.12.1315, T6— 11.12,13,14 Discover the association rules using Apriori for above transactions. _ OR What is support and confidence related to association rules. Explain with examples. What are the advantages of FP-Growth algorithm? UNIT-V Illustrate Additional issues occurred Basic Means of Clustering with example Interpret Bisecting K-means algorithm with example. oR ‘Suppose that the data-mining task is to cluster the following eight points (representing location) into three clusters: Al 2510) ; A2 (2;5) ; A3 (8:4) ; B1 (5;8) ; B2 (7;5) ; B3 (6;4) ; Cl (1;2) ; C2 (4;9). The distance function is Euclidean distance. Suppose initially we assign Al, B1, and C1 as the center of each cluster, respectively. Use the k-means algorithm to determine: the three cluster centers after the first round of execution K4 b) What are the advantages and disadvantages of k-means clustering against model-based clustering?