COMP5121_Assignment_1_05467424g(HuJiaRong)

October 2, 2006 @ 22:59, Robin Hoo

The Hong Kong Polytechnic University
Department of Computing
Data Mining and Data Warehousing
Assignment 1
Due: October 3, 2006

Section A: Regular Questions
1.
a)

C1:ITEM SET       SUP.   
=========================
{DryFruit}     6  20.00%
{Nut}         11  36.67%
{Noodle}      17  56.67%
{Shampoo}      5  16.67%*
{Diaper}       7  23.33%
{Beer}        15  50.00%
{Milk}        11  36.67%
=========================

L1:ITEM SET       SUP.   
=========================
{DryFruit}     6  20.00%
{Diaper}       7  23.33%
{Milk}        11  36.67%
{Nut}         11  36.67%
{Beer}        15  50.00%
{Noodle}      17  56.67%
=========================

C2:ITEM SET              SUP.   
================================
{Beer,Diaper}         1   3.33%*
{Beer,DryFruit}       1   3.33%*
{Beer,Milk}           2   6.67%*
{Beer,Noodle}        12  40.00%
{Beer,Nut}           10  33.33%
{Diaper,DryFruit}     5  16.67%*
{Diaper,Milk}         7  23.33%
{Diaper,Noodle}       1   3.33%*
{Diaper,Nut}          1   3.33%*
{DryFruit,Milk}       6  20.00%
{DryFruit,Noodle}     2   6.67%*
{DryFruit,Nut}        1   3.33%*
{Milk,Noodle}         5  16.67%*
{Milk,Nut}            2   6.67%*
{Noodle,Nut}          8  26.67%
================================

L2:ITEM SET            SUP.   
==============================
{DryFruit,Milk}     6  20.00%
{Diaper,Milk}       7  23.33%
{Noodle,Nut}        8  26.67%
{Beer,Nut}         10  33.33%
{Beer,Noodle}      12  40.00%
==============================

C3:ITEM SET             SUP.   
===============================
{Beer,Noodle,Nut}    7  23.33%
===============================

L3:ITEM SET             SUP.   
===============================
{Beer,Noodle,Nut}    7  23.33%
===============================

Seek Rules
      LHS            RHS    Exp Conf(%) Conf (%)  Life  Supp(%)
===============================================================
1 Beer        -> Noodle,Nut      26.67%   46.67%    1.75  23.33%
2 Noodle      -> Beer,Nut        33.33%   41.18%    1.24  23.33%
3 Nut         -> Beer,Noodle     40.00%   63.64%    1.59  23.33%
4 Beer,Noodle -> Nut             36.67%   58.33%    1.59  23.33%
5 Beer,Nut    -> Noodle          56.67%   70.00%    1.24  23.33%*
6 Noodle,Nut  -> Beer            50.00%   87.50%    1.75  23.33%*
===============================================================

     LHS           RHS    Exp Conf(%) Conf (%)  Life  Supp(%)
=============================================================
1 Beer,Nut   -> Noodle         56.67%   70.00%    1.24  23.33%*
2 Noodle,Nut -> Beer           50.00%   87.50%    1.75  23.33%*
=============================================================

 No interesting items.

c)
i)

=== Run information ===

Scheme:       weka.associations.Apriori -I -N 10 -T 0 -C 0.7 -D 0.15 -U 1.0 -M 0.1 -S -1.0 -V
Relation:     data2006
Instances:    1080
Attributes:   7
              Dry Fruit
              Nut
              Noodle
              Shampoo
              Diaper
              Beer
              Milk
=== Associator model (full training set) ===


Apriori
=======

Minimum support: 0.1 (108 instances)
Minimum metric : 0.7
Number of cycles performed: 6

Generated sets of large itemsets:

Size of set of large itemsets L(1): 7

Large Itemsets L(1):
Dry Fruit=T 391
Nut=T 221
Noodle=T 507
Shampoo=T 250
Diaper=T 182
Beer=T 400
Milk=T 536

Size of set of large itemsets L(2): 6

Large Itemsets L(2):
Dry Fruit=T Noodle=T 247
Dry Fruit=T Milk=T 356
Nut=T Shampoo=T 175
Nut=T Beer=T 220
Noodle=T Milk=T 390
Shampoo=T Beer=T 245

Size of set of large itemsets L(3): 2

Large Itemsets L(3):
Dry Fruit=T Noodle=T Milk=T 212
Nut=T Shampoo=T Beer=T 175

Best rules found:

 1. Nut=T Shampoo=T 175 ==> Beer=T 175    conf:(1)
 2. Nut=T 221 ==> Beer=T 220    conf:(1)
 3. Shampoo=T 250 ==> Beer=T 245    conf:(0.98)
 4. Dry Fruit=T 391 ==> Milk=T 356    conf:(0.91)
 5. Dry Fruit=T Noodle=T 247 ==> Milk=T 212    conf:(0.86)
 6. Nut=T Beer=T 220 ==> Shampoo=T 175    conf:(0.8)
 7. Nut=T 221 ==> Shampoo=T Beer=T 175    conf:(0.79)
 8. Nut=T 221 ==> Shampoo=T 175    conf:(0.79)
 9. Noodle=T 507 ==> Milk=T 390    conf:(0.77)
10. Milk=T 536 ==> Noodle=T 390    conf:(0.73)

ii)

* According to rules 1,2,3,6,7,8 put Nut, Shampoo and Beer closer; 
  put Nut and Beer together or in packages.
* Put Dry Fruit, Noodle and Milk closer or together according to 
  rules 4,5,9,10.

iii)