Humidity forecast using RNN
As the first use case of RNNs, we see how we can train and predict an RNN using the trainr() function. Our purpose is to forecast the humidity of a certain location as a function of the day. The input file contains daily weather observations from multiple Australian weather stations. These observations are obtained from the Australian Commonwealth Bureau of Meteorology and are subsequently processed to create a relatively large sample dataset for illustrating analytics, data mining, and data science using R and the rattle.data package. The weatherAUS dataset is regularly updated and updates of this package usually correspond to updates to this dataset. The data is updated from the Bureau of Meteorology website. The locationsAUS dataset records the location of each weather station. The source dataset is copyrighted by the Australian Commonwealth Bureau of Meteorology and is used with permission.
Note
A CSV version of this dataset is available at the following link...
