The dataset being used for this project is the Ford GoBike System Dataset, provided by Udacity. This dataset contains information of a bike-sharing system of approximately 183,412 rides and 16 features. The data covered the greater San Francisco Bay area in 2019. Most variables are qualitative and some are categorical in nature. The dataset can be found here Link to Google
For this exploratory analysis, my area of interest was on hours of the day, gender, bike share and customer type.
. In the course of exploring the variables considered in this analysis, from the beginning some basic insights were dicovered. One of these is that there are more suscriber type of user and the population of users in the data was dominated by the male gender with 74.3% of the total population. While exploring with one variable it was also dicovered that trips with this means were mostly embaked on during working days with significant reduction on weekends and also this trips peaked in the morning and evening.
In futher investigation using two variables to gather more enlightening insights from the data, we could see a trend of having outliers while checking the relationship between the age of users and the type of users. From the exploration of these two variables it was discovered riders under the customer type have younger age distribution compared to the subscriber type though there was no significant difference in the age distribution average. Also while exploring the age and gender variables it was shown that the female gender have a younger age distribution average than the rest of the genders.
Finally in exploration of this data a three variable analysis was carried out on time_of_day, duration_min and bike_share_for_all_trip. This visualization showed that morning hours of the day which is the time in which employees and students to go to thier companies and school, the bike share and duration of the trip increases. And in afternoon which is the main time students finish from school for the day also the distance of the trip increase.
The high frequency in rides in the morning and evening can be linked to rush hours where employees and students leave for work and school and come back later in the evening
The population of riders is dominated by the male gender, while the female riders have a lower average age distribution compared to other genders.
The subscribers constitue a large proportion of the type of users database