COS10022 Data Science Principles Assignment 2 Questions Semester 1 | SUT

Assessable Item: 

• One (1) piece of a written report no more than 10 pages long, with the signed Assignment Cover Sheet.
• One (1) zip file containing your KNIME workflow, the input file, the output file or any intermediate files produced in your workflow execution process.
• The submitted report must pass the Turnitin check on Canvas with no more than 30% similarity, except for the parts from the template or the short answers. 

The submitted report should answer all questions listed in the assignment task section in sequence. 

You must include a digitally signed Assignment Cover Sheet with your submission. Submitting the zip file containing the input/output files and your fully functional KNIME workflow is essential for your submission to be marked. If the submitted zip file cannot execute properly or the execution result differs from what you have in the report, you will not get the mark even if you put in the correct answer. 

Purpose of Assignment 

This assignment aims to evaluate students' achievement of the following unit learning outcomes: 

• Appreciate (and explain) the key concepts, techniques, and tools for handling the data and producing analytic outcomes.
• Experiencing data cleaning and integration for a data science project. 

This is an individual assignment. Refer to the Unit Outline for the late submission penalty policy. You can ignore the high similarity that appears on the cover page, the template wording, and the short answers. You must make sure your submitted report has a similarity lower than 30% in total and less than 6% from a single source. Otherwise, your report will not be marked. 

Key Lessons: 

You are asked to use the specified dataset and then build models in the KNIME analytics platform and explain your design concept. Two source datasets are provided, and you are expected to perform data cleaning and integration to create a combined dataset. Furthermore, you are expected to perform specified analysis with the produced dataset. KNIME must be used to find answers to all questions except the part asking you to observe the data. 

Introduction

Assignment Goal 

This assignment aims to build experiences for students to clean the data before integrating multiple data sources into a combined dataset and explaining the outputs. A small part of the discovery and research component is included in the assignment for expanding the skill set of the students.

Hints and Supplement Materials 

• Here is the list of nodes that require you to research how to use them. You may use them at least once in the workflow to answer all questions in this assignment:
• Here is a YouTube video regarding using the Crosstab node for the Chi-Square Test in KNIME: YouTube
• This assignment involves a heavy part of data cleaning. Observation is the key to completing the assignment correctly. Be careful about the data contained. You may need to do more processing than what was asked in the questions to get the result correct.
• The Chi-Square table is provided below:

Assignment Task 

We have collected two data sets from different sources at different times. Your task is to clean the dataset according to the requirements and observations. The source files are specified in the tasks. The report should be prepared with the template. A table of Contents is not required. 

The data source contains many details of the record. We aim to clean the data sets and then integrate them into one complete dataset before performing data analytics on it. Please follow the steps below to prepare your data after loading it into KNIME. When preparing the zip file, please put all input files under the same path as your KNIME workflow. This will make the marking easier for the tutors. You can keep growing the workflow across multiple steps or start an independent one, depending on your need to complete the tasks. Your submitted workflow must reveal all results corresponding to all questions in the task sheet: 

• Create a KNIME workflow to load the source file "2025_a2_src_d1.csv". Align the column in the order of "Resident ID," "Resident," "DoB," "Current Age," "Education," "Location," and "Income." Observe the content and perform data cleaning processes in KNIME. You may need to go back and forward in this process, as some abnormal cases will not be discovered until data integration.
• Load the second source file entitled "2025_a2_src_d2.csv" in KNIME. Align the column in the order of "Customer ID," "Name," "Birthday," "Age," "Education Level," "City," "Purchase Date," "Shopping List," "Item List," "Item A," "Item B," "Item C," "Item D," "Item E," "Item F," "Item G," "Item H," "Item I," "Item J," "Item K," "Item L," "Item M," "Item N," "Item O," "Item P," "Item Q," "Item R," "Item S," "Item T," "Item U."Observe the content and perform data cleaning processes in KNIME. You may need to go back and forward in this process, as some abnormal cases will not be discovered until data integration. 
• For both data sets, drop the unused columns according to the instructions in the assignment sheet and then integrate them into a complete record.
• Perform the association rule analysis on the part of the data that is suitable for use in the association.