Scribd Logo
Upload

Welcome to Scribd!

  • 10 views

    Data Mining - Sem 3 - Assignment - 2

    Uploaded by

    132komalprasad
    The document provides instructions for a data mining assignment with 5 questions. It asks students to perform frequent itemset mining, naive bayes classification, k-means clustering, kNN classification and decision tree concepts like information gain and gini index on sample datasets.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Data Mining - Sem 3 - Assignment - 2

    Uploaded by

    132komalprasad
    10 views5 pages
    The document provides instructions for a data mining assignment with 5 questions. It asks students to perform frequent itemset mining, naive bayes classification, k-means clustering, kNN classification and decision tree concepts like information gain and gini index on sample datasets.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document provides instructions for a data mining assignment with 5 questions. It asks students to perform frequent itemset mining, naive bayes classification, k-means clustering, kNN classification and decision tree concepts like information gain and gini index on sample datasets.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    10 views5 pages

    Data Mining - Sem 3 - Assignment - 2

    Uploaded by

    132komalprasad
    The document provides instructions for a data mining assignment with 5 questions. It asks students to perform frequent itemset mining, naive bayes classification, k-means clustering, kNN classification and decision tree concepts like information gain and gini index on sample datasets.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 5

    Data Mining - I

    Assignment - 2

    20.11.2023

    Discipline Specific Core


    3rd Semester
    Lakshmibai College, University of Delhi
    INSTRUCTIONS

    ● Write answers on sheets.


    ● If any assignment (even a single question) is found to be copied from anywhere, no marks
    will be awarded at all for the assignment. (For both the students in case one/two students
    copy from each other)
    ● Studying in groups is encouraged. However, while writing your final assignment, all
    students must do them separately on their own.
    ● This assignment will contribute 40% to your final Internal Assessment score.
    ● Deadline for submission is 8 December 2023 by 09:00 AM. It’s a hard deadline.
    Assignments submitted after the deadline will not be graded.
    ● A scanned copy of the answers should be submitted at [email protected] with
    subject line: Data Mining Assignment 2.

    1
    ASSIGNMENT - 2

    Questions 50 Marks

    Q1) Consider the market basket transactions shown in the following table. Use Apriori
    algorithm to answer the questions that follow.
    TID Item Bought
    1 oregano, chocolate, milk, cheese, french fries
    2 milk, french fries, cheese, ketchup
    3 chocolate, cheese, oregano, ketchup
    4 chocolate, cheese, french fries
    5 french fries, cheese, oregano, chocolate
    6 chocolate, ketchup
    7 oregano, french fries, ketchup
    8 oregano, french fries, chocolate
    9 ketchup, oregano, milk
    10 french fries, chocolate

    • Assuming the minimum support threshold is fixed at 40%, list the set of frequent 1-itemsets
    (L1) and with their respective supports.
    • List the itemsets in the set of candidate 2-itemsets (C2) and calculate their supports.
    • Generate all association rules from the itemsets in L2 and also compute the confidence of
    these rules.

    Q2) Consider the dataset given below:


    Age Income Employed Credit-rating Buys Car
    Young High Yes Fair Yes
    Young High No Good No
    Middle High No Fair Yes
    Old Medium No Fair Yes
    Old Medium No Fair Yes
    Old Low Yes Good No
    Old Medium No Good No
    Middle High Yes Fair Yes

    Compute all class conditional and class prior probabilities. Use Naive Bayes classifier to
    predict the class of the following tuple:
    X = (age = young, income = medium, employed = yes, credit rating = good)
    Q3) Consider the following set of points:
    {44, 28, 48, 26, 32, 14, 52, 50}

    2
    Assuming that k=2, and initial cluster centres for k-means clustering are 5 and 38, compute
    the sum of squared errors (SSE) and cluster assignment for each iteration.
    Q4) Consider the following dataset with points in a two-dimensional space:
    Point Coordinates Class
    A 2, 3 1
    B 4, 5 1
    C 6, 1 2
    D 8, 4 2
    E 3, 6 1
    F 1, 1 1
    G 5, 2 2
    H 7, 3 2
    I 9, 5 2
    J 4, 3 1

    You are given a test point P: (5, 3) for which you need to determine the class using the k-
    nearest neighbors (KNN) algorithm.

    • For k = 3, calculate the Euclidean distance between point P and all other points in the
    dataset. Identify the k nearest neighbors of point P.
    • Determine the class of point P.
    • Discuss how the choice of k might impact the classification result.

    Q5) Consider the training examples shown in the following table for a classification problem.
    Student ID Admission Admission Gender Predicted Actual
    Category List Class Class
    1 Sports First M 0 0
    2 Arts Second F 0 1
    3 Arts Third F 0 0
    4 Sports Fourth M 0 1
    5 Academics First F 0 0
    6 Arts Second F 1 1
    7 Arts Third M 1 1
    8 Sports Fourth M 1 0
    9 Sports Third F 1 1
    10 Arts First F 1 0
    11 Sports Third M 1 1
    12 Sports Second F 1 1
    13 Sports First M 1 0

    • Compute the Information Gain for the Student ID attribute.


    • Compute the Gini Index for the Admission Category Attribute and Admission List attribute

    3
    • Which is a better attribute for split based on the Gini Index: Admission Category or
    Admission List? Why?
    • Create a confusion matrix for the above data set and compute False positive rate,accuracy,
    recall and precision.

    You might also like