讲解 BUSN9165 – Big Data Analytics and Visualisation辅导 Python语言

BUSN9165 - Big Data Analytics and Visualisation

Individual project instruction

1. Assessment structure

The individual project accounts for 80% of the module grade. Please choose one data set in the list below for your project. The length of the report should be of 3000 words, excluding references. All the relevant literature and resources for your project should be properly cited in the Harvard referencing style (you will find this website helpful). For your convenience, a template is provided here. Previous exemplars are available here.

Marks allocated to criteria:	Criteria
20%	1. Introduction to data and research question (~1000 words) Please introduce the data set used and its background. The relevant literature (e.g., academic journal articles and textbooks) should be surveyed and properly cited with Harvard referencing style. More importantly, please identify a problem to be addressed with this data set (i.e., the research question). Please note that the problem should be specific (i.e., relevant in the application domain and linked to the variables available from the data set).
15%	2. Data processing and exploration (~500 words) Please explain: Which variables are available from the data set? Which variables have been selected for the analysis and why? Any data transformations have been done and why?
25%	3. Data visualisation and interpretation (~800 words) Please provide at least three data visualisations as descriptive analytical results (e.g., properties of the variables selected) and advanced analytical results (e.g., relationships between the variables selected, machine learning results). Please follow best practices taught in the module regarding data visualization. Importantly, please interpret the results and findings with details. Note that the data visualisations should be nontrivial representations of information, yet easy to interpret.
20%	4. Data insights and conclusions (~700 words) Please provide the insights drawn from the analytics and summarise the findings. In particular, is the problem (i.e., research question) identified at the beginning addressed by the analytics? How?

20%

5. Writing, styling and references

The clarity, logic and presentation of the report, including spelling,

grammar and punctuation. The general styling and references should be clear and consistent.

2. Recommended data sets

NOTICE: Before starting the individual project, you will need to confirm your choice of data set with this link on Moodle . The link will be available from Wednesday, February 19th 2025, 12:00 pm. Any submissions without data choice confirmation will have the marks reduced accordingly.

While the use of generative AI technologies such as ChatGPT could be helpful for learning Python programming, it is important to note that employing it to produce any portion of a written report is strictly prohibited.

Please find a list of recommended data sets below, which can be downloaded from https://amazon-reviews-2023.github.io/ or directly loaded to Colab from Hugging Face. All of them have significant textual content (i.e., Amazon reviews). Therefore, text analytics tools should be employed. Please note that each dataset includes reviews (ratings, text, helpfulness votes) as well as product metadata (descriptions, category information, price, brand, and image features), which are linked by product parent_asin number.