Hello, if you have any need, please feel free to consult us, this is my wechat: wx91due
GEOG5405M Urban Data Science Project
Data Science Notebook and Practical Briefing
Coursework Brief 2024
A dissertation is a major piece of independent study and takes the form of a research project that you manage and undertake over the last semester of your studies. It represents an opportunity to develop research in any area of urban data science. You may decide to expand on work undertaken as part of your course, to study a problem that has interested you for some time, or research a topic that is relevant to your workplace. We would highly recommend that you align your project with modules you have studied rather than to branch off into new techniques. Whatever you choose, it is vital that you develop a robust project/research design that is appropriate for the research question/problem that you are tackling. Although you will liaise with a project supervisor, and potentially an industrial partner, you should take the initiative and develop your own research ideas, techniques, and types of analysis.
1. Practical Briefing (50%) – a 5000-word written description that focuses on context, implications, and discussion. Generally, it should include a) a description of the urban context or challenge, b) details of prior work and initiatives around this theme (i.e. a literature review), c) a brief description of your analysis (which will be elaborated in the notebook), and d) a discussion of the findings in the context of informing urban policy or practice, including the inherent limitations and biases. You should refer to elements of the code notebook from your report to justify your discussion. The policy briefing should be prepared in Word, Latex, or similar software. The practical briefing is not a technical document; its purpose is clearly communicating the implications of your findings to a lay (non-technical) audience.
The practical briefing should open with the following elements:
Title Page: Your project briefing should include an initial page, giving its title, your full name as registered, the date (month/year) of submission and the words "A dissertation submitted in partial fulfillment of the requirements of the Masters Degree in Urban Data Science and Analytics of the University of Leeds".
Abstract: This should follow the title page, summarising in no more than 200 words the aims of your project and outlining the key aspects of your approach, the main findings and the conclusion. This should be followed by a statement of ‘Acknowledgements’ to any individual or organisations whose assistance you may have received in undertaking your work. This may include acknowledgement of the support of friends, family, partners, etc.
Contents Page and Lists of Tables and Figures: You should provide a full listing of all chapter titles, headings and sub-headings and associated page numbers used to structure the manuscript. You should also list any appendices included. The contents page should then be followed by a list of all tables and figures.
The main body of the practical briefing may include the following, which should be considered to be suggestions and not prescriptive as different structures and detail will apply in different circumstances:
Introduction: Briefly introduce your chosen urban data topic and give an overview of your project.
Background and context: Include a critical review of relevant literature and issues provides the context for your work. You might wish to organise the review by the key themes that you have identified during your reading. This section should also identify the gap in the literature, policy, and practice that you wish to fill with this research.
Justification on the need for the research: Provide a clear rationale for the need for this specific project, linking to the gap identified in the literature above, and the research questions below. Outline how your work is relevant to urban policy/practice.
Overview of research: List the research questions/hypotheses, and how your research addressed them. You may include separate sub-headings for each aspect of the project. You should clearly describe, in lay terms (i.e, for a non-specialist audience) what the main stages of the analysis did, and why. Remember to describe your data, and how it was implemented to answer your research questions.
Discussion of key findings: Analyse the results, emphasising the key findings and their relevance to urban environments. Describe the impact of the work, and how it relates to, and complements, previous work in the field. Identify any future areas for development.
Implications for policy/practice: Summarise the main ‘takeaways’ of your project, and how your findings could be implemented in a practical setting. Make clear recommendations for policy and practice, based on your work.
References: At the end of your briefing, there should be a list of references in alphabetical order by first author, giving all the works you have referred to in the body of the briefing. There should be appropriate citations of each of these references using the Harvard Referencing System (i.e. author's name and date of publication) within the main body of the text.
2. Code Notebook (50%) – a clearly structured Jupyter Notebook that shows the complete data analysis workflow. The focus of this document is on the technical process and critique. This is expected to include library loading, stages of data exploration, data wrangling and cleaning, and the data analysis process (e.g. results, visualisations, tests, etc.). You should accompany the methodology and analysis results with text, which aid navigation and reading of the process. The full interpretation of the results as a whole should be kept within the report section. Important – see note below about requirements for your notebook submission.
The code notebook may include the following, which should be considered as suggestions and not prescriptive, as different structures and detail will apply in different circumstances:
Introduction: This sets the scene and should clearly outline the ‘research problem’. It will also outline the context for your project, and flag its relevancy to: urban data science in general, your work place (if relevant), and also the academic literature.
Research Question(s)/Hypothesis: You should outline your research aims, objectives, questions, and research hypotheses as appropriate, as well as indicating the scope and rationale of your project. This will provide the ‘terms of reference’ with which the examiners will assess the project.
Data: Explain what the dataset is, where you obtained it, how is was collected, and how it will help you answer your research question (or test your hypothesis). You must give full details of what secondary data sets were combined and linked together. If you have collected primary data, you will need to describe your sampling strategy and/or sample size calculation.
Statistics and Visualisation: Define the structure of your data, what variables are included, and how they are measured (including units). Use visual, statistical, and written descriptors, to provide an overview of the key variables.
Data wrangling: To prepare your data for analysis, outline all pre-processing, cleaning, or re-organising of the data, to make it useable for your research. If you're using more than one data set, you can join or aggregate them. Explain exactly what you've done and why, demonstrating each step with clearly annotated code.
Data analysis: Provide a detailed description and justification for your chosen research methods. You should fully outline what type of analysis was undertaken (e.g. regression analysis, interrupted time series, etc.), including, and fully explaining, the equations and parameters used. You should also flag any limitations of the methodology that you anticipate from the onset (e.g. bias, out of date data sources, small sample size etc.).
Results: Present your results statistically, visually, and textually, explaining fully what each coefficient/value/plot shows, in the context of your research. Remember to report both values and statistical significance, where appropriate.
Interpretation: It should be clear to the reader what analysis has been undertaken and what you interpret your results to mean. You should attempt to relate your empirical research findings back to your literature review. In particular, you should flag results that differ or are similar to those reported by researchers in other studies. Remember, a project is an examination of some conceptual, theoretical or empirical problem, so your discussion should consider what your results tell us about the concepts, theories or other empirical findings reported in the literature.
Conclusion: Include a critical appraisal of the strengths and weaknesses of your work and its implications for the wider research field within which your study is located, as well as an exploration of the potential for further work. Make sure that your conclusions can be supported by the rest of your project. Be sure to include a self-critique of your research methodology identifying things that worked and other things that did not. In the case of the latter provide appropriate explanations for why things did not work out (e.g. lack of time and resources) and how you might have done things differently with hindsight. Conclusions should provide some restatement of your main findings and arguments in relation to your original aims and objectives.
References: At the end of your notebook, there should be a list of references in alphabetical order by first author, giving all the works you have referred to in the body of your notebook. There should be appropriate citations of each of these references using the Harvard Referencing System (i.e. author's name and date of publication) within the main body of the text.
Both components of the assessment should be submitted via Minerva.
Further Notes and Guidance
Notebook submission requirements
The notebook and data files should be saved in a OneDrive folder, and the link for this shared using the Coursework Coversheet (available on Minerva). Please include the following components in the folder:
· Your Jupyter notebook containing the complete analysis.
· Your data – or if the original dataset is too large, a processed version of it may be submitted, as long as the stage at which the data is exported from your workflow clearly marked.
· A YML file for your Conda environment, detailing the libraries and version numbers used for this analysis. You can export it by running this command from CL/Terminal (replacing ENVNAME as appropriate): conda env export --name ENVNAME > envname.yml
It is your responsibility to ensure that the notebook can run on another machine. Therefore, you should ensure all data are provided with relative directories accessible from the notebook.
Word limit
The word limit for the practical is 5000 words. This limit (+/- 10%) includes EVERYTHING apart from i) the overall title of the piece of work; ii) where appropriate, an opening contents page and abstract; iii) the reference list or bibliography, iv) tables and figures (although captions for figures and tables are part of the word count), and v) any appendices. Tables should not contain lengthy passages of text in an attempt to circumvent the word limit; such cases will be investigated for academic malpractice. Please note that there is no leeway for word length. Marks will be deducted for work which is over the limit as set out in the module handbook.