rf2
OpenML dataset with id 41484
Author name not available (Why is that?)
Full work available at URL: https://api.openml.org/data/v1/download/21230441/rf2.arff
Upload date: 14 March 2019
Dataset Characteristics
Number of features: 584 (numeric: 584, symbolic: 0 and in total binary: 0 )
Number of instances: 9,125
Number of instances with missing values: 1,446
Number of missing values: 356,160
Multivariate regression data set from: https://link.springer.com/article/10.1007%2Fs10994-016-5546-z : The river flow datasets concern the prediction of river network flows for 48 h in the future at specific locations. The dataset contains data from hourly flow observations for 8 sites in the Mississippi River network in the United States and were obtained from the US National Weather Service. Each row includes the most recent observation for each of the 8 sites as well as time-lagged observations from 6, 12, 18, 24, 36, 48 and 60 h in the past. In RF1, each site contributes 8 attribute variables to facilitate prediction. There are a total of 64 variables plus 8 target variables.The RF2 dataset extends the RF1 data by adding precipitation forecast information for each of the 8 sites (expected rainfall reported as discrete values: 0.0, 0.01, 0.25, 1.0 inches). For each observation and gauge site, the precipitation forecast for 6 h windows up to 48 h in the future is added (6, 12, 18, 24, 30, 36, 42, and 48 h). The two datasets both contain over 1 year of hourly observations ( > 9000 h) collected from September 2011 to September 2012. The domain is a natural candidate for multi-target regression because there are clear physical relationships between readings in the contiguous river network.
This page was built for dataset: rf2
