The dataset contains sales data from a supermarket chain. Your boss wants to know the general sales status. As part of the report, you need to generate the following statistics. (The questions are not systematic in terms of a report. They are to help you practice certain techniques.)
1. Generate descriptive statistics on “Children,” “Units sold,” and “Revenue” respectively. Change the worksheet name to Q1. Based on the statistics, write a couple of lines to summarize the basic characteristics of “Units sold per transaction” in your company.
2. Draw a histogram on “Units sold.” Change the worksheet name to Q2. Write a couple of lines to further discuss the characteristics of Units sold per transaction.
Hint: You need to specify the bins for the histogram
3. Calculate the number of transactions for each gender and draw a pie chart on this gender-based statistics. Change the worksheet name to Q3.
Hint: Use COUNTIF
4. Make pivot tables based on gender and state and report the sum of revenues for each cell. Draw a column chart based on this pivot table. Change the worksheet name to Q4. Based on question 3 and 4 write a couple of lines to explain different gender’s transactions in your company’s all transaction.
Hint: The two dimensions of the pivot table are “gender” and “state. The statistics is “sum” on “revenue.”
5. Make pivot tables base on purchase date and state. Group purchase date to month level and report the maxim transaction revenue per month. Draw a line chart based on this pivot table (x axis is year-month).
Hint: The two dimensions of the pivot table are “date” and “state. Then, you need to group the purchase date dimension. Please note that you need to select both year and month to differentiate different years’ data.