首页 >
> 详细

School of Computer Science

Uwe Roehm

DATA2001/DATA2901: Data Science, Big Data, and Data Diversity 1.Sem./2020

Practical Assignment: Viral Vulnerability Analysis

Group Assignment (20%) 06.05.2020

Introduction

In this practical assignment of DATA2001/DATA2901 you are asked to gather and integrate several

datasets to perform a data analysis of the viral vulnerability of different neighbourhoods in Sydney.

You find links to online documentation, data, and hints on tools and schema needed for this

assignment in the ’Assignments’ section in Canvas.

Disclaimer: This assignment is mainly about data integration. Note that the age and varying

quality of the provided data do not allow to reliably assess the actual COVID19 risk.

Data Set Description and Preparation

Your task in this assignment is to calculate a vulnerability score with regard to infectious diseases for

different neighbourhoods in Sydney. The neighbourhood ’vulnerability’ is expressed as a measure

of several factors which we assume to affect the spread of a virus within a community — population

density, age distribution, pre-existing health conditions, and access to healthcare services.

In order to calculate this score, you will need to integrate different data sources. As a starting

point, we provide you with a few census-based datasets which give you input on at least three

factors: population density, age distribution, and locations of health services (hospitals and GPs).

We leave it up-to you to integrate further data and to refine the suggested vulnerability score.

Some ideas would be percentage of population with pre-existing health conditions such as asthma

or diabetes, presence of meeting hotspots such as large shopping centres or sports venues, intensity

of international travel (either by locals there or by tourists in an area), or public transport usage.

Based on your computed vulnerability scores, perform then a correlation analysis with the offi-

cial COVID-19 data per neighbourhood as provided by NSW Health (also provided, resp. linked).

Your submission should consist of your Jupyter notebook that you used for integrating the data

sets and for performing and visualising your analysis.

Milestone 1: Load and integrate the provided datasets into postgres by the tutorials in Week 11.

Provided datasets: We provide in Canvas several CSV files with Statistical Area 2 (SA2) data

from the Australian Bureau of Statistics (ABS), as well as some health service location data from

Sydney (keep checking Canvas for any later additions or updates):

StatisticalAreas.csv: area id, area name, parent area id

Neighbourhoods.csv: area id, area name, land area, population, dwellings, businesses, median income, avg monthly rent, bounding box

PopulationStats2016.csv:area id, area name, age distribution, total persons, females, males

HealthServices.csv: id, name, category, num beds, address, ..., longitude, latitude, comment

NSW Postcodes.csv id, postcode, locality, longitude, latitude

COVID-19 Statistics recent daily data can be accessed from data.gov.au

e.g.: https://data.gov.au/dataset/ds-nsw-5424aa3b-550d-4637-ae50-7f458ce327f4

1

Task 1: Data Integration and Database Generation

Build a database using PostgreSQL that integrates data from the following sources:

1. Sydney neighbourhood dataset (based on provided CSV files with SA2-data from ABS).

2. Census data for the given neighbourhoods including population count and age distributions.

3. Health services in NSW; Todo: spatial join with neighbourhoods.

4. You are encouraged to extend and refine both scoring function and source data. For

full points when integrating at least one additional data set.

Milestone 1: Load and integrate the provided datasets into PostgreSQL by the tutorials in Week 11.

Task 2: Viral Vulnerability Analysis

1. Compute the vulnerability score for all given neighbourhoods according to the following formula

and definitions (adjust as needed if you integrated any additional datasets):

vulnerability = S(z(population density)+z(population age)−z(healthservice density)−z(hospitalbed density))

With S being the logistic function (sigmoid function), and z the z-score (”standard score”) of a

measure - the number of standard deviations from the mean (assuming a normal distribution):

z(measure, x) = x − avgmeasure

stddevmeasure

Measure Definition Risk Data Source

population density population divided by neighbourhood’s land area + nNeighbourhoods.csv

population age percentage of a neighbourhood’s population age 70+ + PopulationStats2016.csv

healthservice density number of health services per suburb per 1000 people – HealthServices.csv

hospitalbed density number of hospital beds per suburb per 1000 people – HealthServices.csv

2. Store the computed measures and scores of each neighbourhood in your database. Create

at least one index which is helpful for data integration or the vulnerability score computation.

3. Determine whether there is a correlation between your viral vulnerability score and the number

of COVID-19 tests or COVID-19 cases (positive tests) per neighbourhood.

Task 3: Documentation of your Viral Vulnerability Analysis

Write a document (Jupyter notebook or Word document or PDF file, no more than 5 pages plus

optional Appendix) in which you document your data integration steps and the main outcomes of

your vulnerability data analysis, including the correlation study with the COVID-19 statistics. Your

document should contain the following:

1. Dataset Description

What are your data sources and how did you obtain and pre-process the data?

2. Database Description

Into which database schema did you integrate your data (preferable shown with a diagram)?

Which index(es) did you create, and why?

3. Vulnerability Score Analysis

Show which formula you applied to compute the vulnerability score per neighbourhood, and

give an overview of vulnerability results. This can be done either in text by highlighting some

representative results, or with a graphical representation onto a map (preferred).

4. Correlation Analysis

How well does your score correlate to the number of COVID-19 cases in the given suburbs?

Is there any correlation with the number of COVID-19 tests in the neighbourhoods?

2

Task 4: DATA2901 Task for Advanced Class Only

1. For teams in the advance class, integration of at least one additional data set is compulsory.

2. One of the additional data sources must come from a web source such as be Web Scraping

or using a Web-API, rather than just a downloadable additional CSV data set.

3. Include in the vulnerability analysis some data that was inferred using a machine learning or

natural language processing step. For example, you could retrieve and count named entities

from the scrapped content of a website about international visitors or travel infrastructure in

different neighbourhoods in Sydney, or you could try to train a neighbourhood classifier.

General Coding Requirements

1. Solve this assignment with a Python Jupyter notebook in Python and SQL (Adv: also Unix).

2. Use the provided Jupyter and PostgreSQL servers from the tutorials.

3. If you use any extra libraries which are not installed in the labs, disclose in your documentation

which library and what version.

Deliverables and Submission Details

There are four deliverables:

1. source code of the data integration and analysis tasks,

2. a brief report/documentation (up to 5 pages, as of content description above), and a

3. short demo in the labs of Week 12 with the whole team present.

4. Please also provide access to your database with the schema and the processed data.

All deliverables are due in Week 12, no later than 8pm, Friday 22 May 2020. Late submission

penalty: -20% of the awarded marks per day late. See also the published marking rubric in Canvas.

Please submit the source code and a soft copy of your documentation as a zip or tar file electronically

in Canvas, one per each group. Name your zip archive after your UniKey: abcd1234.zip

Students must retain electronic copies of their submitted assignment files and databases, as the

unit coordinator may request to inspect these files before marking of an assignment is completed. If

these assignment files are not made available to the unit coordinator when requested, the marking

of this assignment may not proceed.

All the best!

Group member participation

This is a group assignment. The mark awarded for your assignment is conditional on you being

able to explain any of your answers to your tutor or the lecturers if asked.

If members of your group do not contribute sufficiently you should alert your tutor as soon as

possible. The tutor has the discretion to scale the group’s mark for each member as follows, based

on the outcome of the group’s demo in Week 12:

Level of contribution Proportion of final grade received

No participation or no demo. 0%

Passive member, but full understanding of the submitted work. 50%

Minor contributor to the group’s submission. 75%

Major contributor to the group’s submission. 100%

联系我们

- QQ：99515681
- 邮箱：99515681@qq.com
- 工作时间：8:00-23:00
- 微信：codinghelp2

- 代写r留学生作业、代做data课程作业、代写r编程语言作业代做r语言编程|调 2020-05-25
- Cosc473作业代做、Systems作业代写、Python编程设计作业调试 2020-05-25
- Data留学生作业代做、R编程设计作业调试、R语言作业代写、Program课 2020-05-25
- Comp 250 Assignment 3 2020-05-24
- Macm 316 – Computing Assignment 7 2020-05-24
- Sta457 Assignment 2020-05-24
- Homework 10 2020-05-24
- Lab 2 Msc: Time Series Prediction With... 2020-05-24
- Comp2011作业代做、Data Analysis作业代写、C++编程语言 2020-05-24
- 代做compsys201作业、Python，Java，C/C++编程语言作业 2020-05-24
- Program留学生作业代做、Python编程设计作业调试、Data作业代写 2020-05-24
- 代写 Practical 3 Covid-19程序作业，代写... 2020-05-23
- 代写comp3059作业、代做programming作业、Java语言作业代 2020-05-23
- Coit12206作业代写、Program课程作业代做、Java、Pytho 2020-05-23
- Data2001作业代做、Data Science作业代做、Sql语言作业代 2020-05-23
- 代写comp2017作业、代写c/C++语言作业、代写data作业、C/C+ 2020-05-23
- Data留学生作业代做、Python编程设计作业调试、代写program课程 2020-05-22
- Mkan1-Uc 5103作业代写、代做analytics作业、Java，P 2020-05-22
- Pols 512作业代写、R编程设计作业调试、Data留学生作业代做、代写r 2020-05-21
- Econ 6070作业代做、Data课程作业代写、代做java，Python 2020-05-21