Data analysis and visualization for bike renting company
This data set includes information about individual rides made in a bike-sharing system covering the greater San Francisco Bay area
The file taken from the classroom has only data for February, 2019.
After doing some research I found thatFord GoBikecompany name has changed. The following quoted from Wikipedia:
Tracing the new company name, I found the rest of the data for the whole year of 2019. download link
The twelve months datasets are uploaded in the folder\Data
- Trips increase at rush hours (8 and 17 o'clock)
- Examining the weekday we can see that trips is reduced during the weekends but they take longer time.
- Trips are more in spring and summer more than the rest of the year.
- Bike traffic is more at day than at night. Still at 3 o'clock the average duration tends to be high.
- Customers only represent 20% of the trip count but they tend to rider longer.
- Around 1/3 of the system's total bikes makes less than 100 trips per year.
- Top start stations and top end stations are the almost the same. This means that bikes are usually looping between such stations.
For the presentation, I focused on the relationship between trip duration and time aspects. I tried to clearly represent the instances where
moretrips does not meanlongertrips. I indicated the above in theuser_type,weekday,hour