pred.data: selection of veriables neccessary for prediction
In dprocter/modeid: modeid: Identification of travel modes from GPS and accelerometry data

Takes merged gps/acc data, with rolling averages calculated, subsets to only those variables that are needed to determine travel mode

1	pred.data(merged.data)

merged.data

a dataset of merged data with rolling averages calculated

Here we assume you have processed acceleormeter data using process.acc, gps.acc.merge and rollav.calc.

This funciton then selects only the necessary variables for prediction, and outputs them as a matrix, ready to be fed to a fitted xgboost model

dprocter/modeid documentation built on May 19, 2019, 8:21 a.m.

dprocter/modeid index

README.md

Note that we can't provide technical support on individual packages. You should contact the package authors for that.

Description