[Solved] ITE4005 Assignment 1-Apriori algorithm

1. Environment l OS: Windows, Mac OS, or Linux
   • Languages: C++, Java, or Python (any version is ok)

2. Goal: find association rules using the Apriori algorithm

3. Requirements

The program must meet the following requirements:

• Execution file name: apriori.exe
• Execute the program with three arguments: minimum support, input file name, output file name n Example:
• Minimum support = 5%, input file name = input.txt, output file name = output.txt
• If you python, you are allowed to use apriori.py file instead of apripri.exe

• Input file format (.txt)

[item_id]t[item_id]

[item_id]t[item_id]t[item_id]t[item_id]t[item_id]

[item_id]t[item_id]t[item_id]t[item_id]
n Row: transaction n item_id is a numerical value

• There is no duplication of items in each transaction n Example:
• Output file format Figure 1. Input file example (.txt)

[item_set]t[associative_item_set]t[support(%)]t[confidence(%)]

[item_set]t[associative_item_set]t[support(%)]t[confidence(%)]
n [item_set]t[associative_item_set]: association rules with minimum support

• [item_set][associative_item_set]
• Use braces to represent item sets: {[item_id],[item_id],} (Important!!) l g., {0}, {0,4}, {0,3,1}

• Support: probability that a transaction contains [item_set] [associative_item_set]
• Confidence: conditional probability that a transaction having [item_set] also contains [associative_item_set] n The order of output is unimportant.
• The value of support and confidence should be rounded to two decimal places.

e.g., 24.631 rounded to two decimal places should become 24.63.

• An additional penalty will be imposed if you dont keep the output file format. n Example:

• Note: Please make sure to match the output format!

If the format is not correct, you cant get any score.