· Outline for An Exploratory of Public Opinion about Online Shopping During COVID-19 1) Define your data sources and why you are using them. what are the key fields you will be using? 1/4 page 5 marks...

An Exploratory of Public Opinion about Online Shopping During COVID-19
· Data Sources
For performing the exploratory data analysis we first have to collect some real data that we can use for for the purpose. Here we have collected the data from the Kaggle and statista-. Among all the available data we are using some key fields which are as follows: product categories, customer id, state, market, sales, quantity, profit, etc.
· Extracting the data
On the website of Kaggle we have searched for the relevant data to get the analysis of the public opinion about online shopping during covid - Also how online shopping had made a difference in the market during covid- which one (online or offline was more likable by people). Over the platform we got some relevant data. Then we looked for how we can extract this data so that we can do analysis over it. Over the data there is an option to extract or download the data in the csv format. There were two files available for dataset – one is csv file and other is excel data, so we have downloaded the both files – that we can use for further analysis of insights, patterns in online vs offline shopping during covid so that more conclusions can be made over what people are liking and what is their opinion.
· Creating final analytical file
We will create final analytical file using python. First we will read the csv file into the python environment, There we will be doing data cleaning and data pre-processing so that our analysis is perfectly showing outputs based on the good data and not on random and unnecessary stuffs. Although our file have a huge number of columns but we will be using some major key columns to be more precise about the kind of findings we are looking for. The final key columns that we will be using are product categories, customer id, state, market, sales, quantity, profit, etc.
Then we will use seaborn and matplotlib along with pandas for the final analysis.
· Type of analysis
We will run kind of analysis that will help us to understand people’s choice, perspective, behaviours, liking towards online and offline shopping. We will do analysis to detect that when people have shopped more (online or offline). What other factors are there that are influencing people’s shopping behaviour during online and offline scenarios. Also, we will try to look at descriptive statistical analysis of the data to check what kind of data distribution we have in our data.
Other than that we will try to visualize some of the key fields available in the data so derive conclusions. For visualization, python modules like seaborn and matplotlib will...