This repo has r codes for predictive models along with test and train datasets of bike share demand kaggle competition.
train.csv - contains First 19 days of the month are in training dataset. test.csv - remaining days from 20th to month end are included in test dataset for prediction.
This study will focus on predicting bikes rented per hour based on the test dataset. In this paper I will present my modeling approach to the problem, which has different data mining models such as Random Forest , Neural networks, PCA( Principal Component Analysis) and Conditional trees to predict the user counts which have registered and casual users who travel by bike sharing bicycles.