The Ford GoBike data set contains information about individual rides made in a bike-sharing system covering the greater San Francisco Bay area. The dataset is made up of 183412 observations with 16 columns. Nine additional columns were created, bring the total columns in the dataset to 25.
The main feature of interest is the duration_min and how other features contribute to the length of ride. The features that will help to support the main feature of interest are; start_day, end_day, start_hour, end_hour, user_type, member_gender, member_birth_year and bike_share_for_all_trip.
In the univariate exploration, the distribution of both categorical variable and numerical variable were visualised. The Male gender in the gender_member column has the highest frequency follow by female. Majority of bike users are subscribers while only few are customers. The station with the highest frequency of start is Market St at 10th St while the station with the highest frquency of end San Francisco Caltrain Station. The distribution of duration per seconds is right skewed with high number of bike riders at the left side of the chart.
During the bivariate and multivariate visualization, I discovered fascinating relationship that duration of journey has with member gender, bike sharing, and user type. Other genders spend more time on trip than male and female. Customer user type spend longer duration than subscribers. Bike riders that do not share their ride during the journey spend longer duration than those that shared the ride.
For the presentation, I focused on the distribution of the variable of interest (duration of trip) and how the other variable affects it. Although the male gender are the predominant sex in the data set, they do not spend long duration on their trip. The other gender out perform the other two gender. Also, Customer user types tip spend longer time on their trips than Subscriber user types. Sharing ride throughout the journey does not necessarily increase the duration of the trip.