Midterm Exam_Tableau
1. Please download the dataset “bikerental_hour.xlsx” and complete the task. (10%).
Please refer to the following table to learn about the variables in this dataset. It is very important to
note that this dataset consists of hourly observations, with each row representing a specific hour on a
particular day.
Variable Role Type Description
Name
instant ID Integer record index
dteday Feature Date date
season Feature Categorical
winter, spring, summer, and fall
yr Feature Categorical
year (0: 2011, 1: 2012)
mnth Feature Categorical
month (1 to 12)
hr Feature Categorical
hour (0 to 23)
holiday Feature Binary weather day is holiday or
weekday Feature Categorical
day of the week
workingday Feature Binary if day is neither weekend nor holiday is 1, otherwise is 0
weathersit Feature Categorical
- 1: Clear, Few clouds, Partly cloudy, Partly cloudy
temp Feature Continuous
Normalized temperature in Celsius. The values are derived via
(t-t_min)/(t_max-t_min), t_min=-8, t_max=+39 (only in hourly scale)
atemp Feature Continuous Normalized feeling temperature in Celsius. The values are derived via (t-
t_min)/(t_max-t_min), t_min=-16, t_max=+50 (only in hourly scale)
hum Feature Continuous Normalized humidity. The values are divided to 100 (max)
windspeed Feature Continuous Normalized wind speed. The values are divided to 67 (max)
casual Other Integer count of casual users
registered Other Integer count of registered users
cnt Target Integer count of total rental bikes including both casual and registered
Please create a pie chart to display the average hourly bike rentals (cnt) across the four seasons. Show
the name of the season and the average daily bike rentals next to each pie.
Change the title of the figure from "sheet xxx" to your netID, take a screenshot of the figure, and
paste it here.
Solution:
2. Based on the observation from task 1, please identify the season with the highest hourly bike rentals.
(5%).
Solution: Summer
3. Now we want to show the percentages of total bike rentals across the four seasons.
To make the label show percentages, you may follow the steps: (1) right-click the quantity you need to
convert into percentages, for example, the SUM(Cnt) you are currently using as the label in the pie
chart; (2) go to “Quick Table Calculation”, and then “Percentage of Total”.
Change the title of the figure from "sheet xxx" to your netID, take a screenshot of the figure, and
paste it here. (10%)
Solution:
4. Please create a scatter plot showing the relationship between the daily average temperature and the
daily total bike rentals.
Note that both axes start at 0, causing the figure to appear off-center. Please adjust the axis limits to
center the figure within the coordinate system. To adjust the axis limit, right-click the axis, then go to
“Edit Axis”. Use the custom range settings to bring the cluster of points to the center of the coordinate
system. See below.
To clearly identify the relationship between temperature and bike rentals, we need to add a trend line.
To add a trend line, right-click the plot, go to “Trend Lines”, and then “Show Trend Lines”. See
below.
Change the title of the figure from "sheet xxx" to your netID, take a screenshot of the figure, and
paste it here. (20%)
Solution:
5. Based on the visualization you get in task 4, please comment on the relationship between daily average
temperature and daily total bike rentals.
Solution: the higher the temperature, the lower the bike rentals.