Bike sharing systems are a means of renting bicycles where the process of obtaining membership, rental, and bike return is automated via a network of kiosk locations throughout a city. Using these systems, people are able to rent a bike from one location and return it to a different place on an as-needed basis. Currently, there are over 500 bike-sharing programs around the world. The data generated by these systems makes them attractive for researchers because the duration of travel, departure location, arrival location, and time elapsed is explicitly recorded. Bike sharing systems therefore function as a sensor network, which can be used for studying mobility in a city.
In this project, I have combined historical usage patterns with weather data in order to forecast hourly bike rental demand.
The following files are attached in this repository : 1. train.csv : Use this dataset to train the model. This file contains all the weather related features as well as the target variable “count”. Train dataset is comprised of first 18 months. 2. test.csv : Use the trained model to predict the count of total rentals for each hour during the next 6 months.
Here is the description of all the variables :
1. datetime hourly date + timestamp
2. season Type of season (1 = spring, 2 = summer, 3 = fall, 4 = winter)
3. holiday whether the day is considered a holiday
4. workingday whether the day is neither a weekend nor holiday
5. weather weather
6. temp temperature in Celsius
7. atemp "feels like" temperature in Celsius
8. humidity relative humidity
9. windspeed wind speed
10. casual number of non-registered user rentals initiated
11. registered number of registered user rentals initiated
12. count number of total rentals
Use solution_checker.xlsx to generate score (RMSLE) of predictions. This is an excel sheet where its provided with the timestamp and predictions should have to submitted in the count column.