auto_classify: Classify a preprocessed surface reflectance image
In azvoleff/teamlucc: TEAM land use and cover change data processing toolkit

Description Usage Arguments Examples

First the image should be preprocessed using the auto_preprocess function. For Landsat CDR imagery, predictor layers can be generated using the auto_generate_predictors function.

1 2	auto_classify(predictor_file, train_shp, output_path, class_col = "Poly_Type", training = 0.6, overwrite = FALSE, notify = print)

`predictor_file`	a `Raster*` of predictor layers output by the `auto_preprocess` function or path to an image stack in a format readable by the `raster` package.
`train_shp`	a file readable by readOGR with training polygons
`output_path`	the path to use for the output
`class_col`	the name of the column containing the response variable (for example the land cover type of each pixel)
`training`	indicator of which polygons to use in training. Can be: 1) a string giving the name of a column indicating whether each polygon is to be used in training (column equal to TRUE) or in testing (column equal to FALSE), or 2) a logical vector of length equal to length(polys), or 3) a number between 0 and 1 indicating the fraction of the polygons to be randomly selected for use in training.
`overwrite`	whether to overwrite existing files (otherwise an error will be raised)
`notify`	notifier to use (defaults to `print` function). See the `notifyR` package for one way of sending notifications from R. The `notify` function should accept a string as the only argument.