Bike Rentals Data - UCI 🚲

Why do we use this data set ?

Existing bicycle rental systems in large cities have an automated system of pick-up and return of the vehicle through a network of stations distributed throughout the metropolis.

Using these systems, people can rent a bike at one location and return it at a different location depending on their needs.

The data generated by these systems are attractive to researchers because of variables such as trip length, departure and destination points, and travel time.

Thus, bike sharing systems function as a network of sensors that are useful for mobility studies. To improve management, one of these companies needs to anticipate the demand that will occur in a certain time range depending on factors such as time zone, type of day (working day or holiday), weather, etc..

Meaning of variables

The variables present in the 2 data sets are:

id - identifier of the time slot (not related to the time order)
year - year (2011 or 2012)
hour - time of day (0 to 23)
season - 1 = winter, 2 =spring, 3 = summer, 4 = autumn
holiday - if the day was a holiday
workingday - if the day was a working day (neither a holiday nor a weekend)
weather - four categories (1 to 4) ranging from best to worst weather
temp - temperature in degrees Celsius
atemp - temperature sensation in degrees Celsius
humidity - relative humidity
windspeed - wind speed (km/h)
count - (only in the training set): total number of rentals in that band