+1(978)310-4246 credencewriters@gmail.com


Detailed specification
You are to carry out a data exploration for ChrisCo, the fictional company whose sales and website
data we have been analysing throughout the course, using a Python Notebook (in Colab or Jupyter)
and producing visualisations of store / customer data.
The dataset concerns the company’s 40 stores, each identified by a unique 3 letter code (e.g. ABC,
XYZ, etc). However, each student on the course has their own, randomised dataset to explore, and
the codes are randomised so that a store code in one student’s dataset is very unlikely to represent
the same store in another student’s.
You will find your data in the following csv files, where BannerID is your student ID number (e.g.
• https://tinyurl.com/ChrisCoDV/BannerID/DailyCustomers.csv
listing the daily number of customer visits to the company’s 40 stores
• https://tinyurl.com/ChrisCoDV/BannerID/StoreMarketing.csv
the total annual spend on local marketing for each store
• https://tinyurl.com/ChrisCoDV/BannerID/StoreOverheads.csv
the total annual cost of overheads for each store
• https://tinyurl.com/ChrisCoDV/BannerID/StoreSize.csv
the store size (floor space) in metres squared for each store
• https://tinyurl.com/ChrisCoDV/BannerID/StoreStaff.csv
the total number of full-time staff employed at each store
Please contact your tutor if you cannot find your data files.
You should compile your data into two dataframes: one containing daily customer data (one row for
each date); the other compiled from all of the .csv files into a dataframe of summary data (with a
row for each store).
Your task is to investigate the data visually and present some conclusions about any characteristics
you discover, including correlations, seasonal behaviour, outliers, etc., together with a suggestion
about how the data might be best segmented.
The company is most interested in the large and medium sized stores but would like a summary of
the small stores plus any anomalies you identify in the data. You should also identify new stores that
have been opened during the year or stores that the company has closed during the year.
You should present your findings in the form of a pdf report for the company, i.e. based on the
assumption that the reader knows nothing about data visualisation. The report should include:
• A brief introduction to data visualisation (no more than ½ a page).
• A discussion of your findings, including a total of 8 visualisations (no more, no less). Each
visualisation should be accompanied by two paragraphs of text in which you should present:
o a justification for including that particular visualisation:
o a description of what the visualisation reveals about the data – do not assume that
the reader will recognise and understand correlations, seasonality and anomalies.
• A critical review of your work, with a discussion of how best practices were demonstrated
and applied (about ½ a page).
• A summary of the conclusions you have made about the data points (no more than ½ a
page). You are not required to make any business recommendations and the summary may
contain conclusions as bullet.
For the 8 visualisations you include, you should choose your most illuminating charts / plots and
paste in a screenshot. It is strongly recommended to use Insert > Screenshot in Word or the
Windows snipping tool (or similar) and to carefully crop each screenshot so that it shows only the
visualisation. Also do not distort the images when you resize them – if you do change the size make
sure you maintain the aspect ratio.
Each visualisation should be carefully numbered and labelled, with a self-explanatory title and
legend (if appropriate) and should be referred to in the text (e.g. “Figure 1 shows that …”). Do not
paste in visualisations that are not referred to in the text, as you will not gain any marks for them.
The order of the visualisations should be carefully considered, leading the reader through the data
exploration step by step and ideally with each visualisation leading on to the next one.
Your Python Colab / Jupyter notebook should contain the details of your data exploration and
support the report. The markdown should indicate the purpose of each preceding / following code
section but you do not have to present your findings here.
The code should be written efficiently, so that you do not repeat unnecessary code in each section.
At least 2 of the visualisations in the notebook should be interactive and provide functionality to
explore the data in more detail. The markdown for these must include a clear description of
available user interactions.
You must upload a single zip file containing:
• The pdf report containing your 8 chosen visualisations
• A supporting Python notebook (.ipynb) containing your data exploration
Marking scheme
The report will be marked on the discussion and analysis, together with both the quality and impact
of the visualisations.
The notebook will be marked on its organisation, presentation and efficiency of coding. There are
also marks for the interactive visualisations.
Report text (50%)
Introduction to data visualisation
Discussion – justification of visualisations chosen
Discussion – description of findings
Critical review
Data conclusions
Report visualisations (20%)
Presentation quality (labelling, legends, etc)
Impact (as part of the exploration)
Notebook (30%)
Organisation and presentation
Code efficiency (non-duplication)
Interactive visualisations – functionality
Interactive visualisations – description
/ 5
/ 5
Grading criteria
All requirements completed to an excellent standard
All requirements completed. However, there are a number of minor deficiencies in
significant areas.
All requirements completed. However, significant improvements could be made in
many areas.
All requirements completed. However, significant improvements could be made in
all areas.
All requirements attempted but the overall level of understanding and performance
is poor.
There are requirements missing or completed to a very inadequate standard which
indicates a very poor or non-existent level of understanding.
The report should be succinct and so must not contain more than 8 visualisations, although you
may use the technique of facetting (i.e. a number of subplots in a single figure). Reports with 9-10
visualisations will be capped at 60% and those with 11 or more visualisations will be capped at 30%.
However, your notebook may contain as many visualisations as you need to carry out the

Purchase answer to see full

error: Content is protected !!