Create unsupervised dataset (from feature raster)

Create an unsupervised dataset by sampling data from valid pixels and store the result as a pickle file. A pixel is concidered valid, if the pixel profile is free of no data values, and not excluded by the (optionally) selected mask layer.


Raster layer with features [raster]

Raster layer used for sampling feature data X.

Mask layer [layer]

A mask layer for limitting sample locations.

Sample size [number]

Approximate number of samples drawn from raster. If 0, whole raster will be used. Note that this is only a hint for limiting the number of rows and columns.

Default: 0

Exclude bad bands [boolean]

Whether to exclude bands, that are marked as bad bands, or contain no data, inf or nan values in all samples.

Default: True


Output dataset [fileDestination]

Pickle file destination.

Command-line usage

>qgis_process help enmapbox:CreateUnsupervisedDatasetFromFeatureRaster:


featureRaster: Raster layer with features
    Argument type:  raster
    Acceptable values:
            - Path to a raster layer
mask: Mask layer (optional)
    Argument type:  layer
    Acceptable values:
            - Path to a vector, raster or mesh layer
sampleSize: Sample size (optional)
    Default value:  0
    Argument type:  number
    Acceptable values:
            - A numeric value
excludeBadBands: Exclude bad bands (optional)
    Default value:  true
    Argument type:  boolean
    Acceptable values:
            - 1 for true/yes
            - 0 for false/no
outputUnsupervisedDataset: Output dataset
    Argument type:  fileDestination
    Acceptable values:
            - Path for new file


outputUnsupervisedDataset: <outputFile>
    Output dataset