Regression workflow

The regression workflow combines regressor fitting and map prediction.Optionally, the cross-validation performance of the regressor can be assessed.

Parameters

Training dataset [file]

Training dataset pickle file used for fitting the regressor.

Regressor [string]

Scikit-Learn Python code specifying a regressor.

Raster layer with features [raster]

A raster layer with bands used as features for mapping. Regressor features and raster bands are matched by name. Will be ignored, if map prediction is skipped.

Match regressor features and raster bands by name [boolean]

Whether to match raster bands and regressor features by name.

Default: False

Number of cross-validation folds [number]

The number of folds used for assessing cross-validation performance. Will be ignored, if the cross-validation performance assessment is skipped.

Default: 10

Open output cross-validation regressor performance report in webbrowser after running algorithm [boolean]

Whether to open the cross-validation performance report in the web browser. Will be ignored, if the cross-validation performance assessment is skipped.

Default: True

Outputs

Output cross-validation regressor performance report [fileDestination]

Output cross-validation performance report file destination.

Output regressor [fileDestination]

Pickle file destination.

Output regression layer [rasterDestination]

Predicted map file destination.

Command-line usage

>qgis_process help enmapbox:RegressionWorkflow:

----------------
Arguments
----------------

dataset: Training dataset
    Argument type:  file
    Acceptable values:
            - Path to a file
regressor: Regressor
    Argument type:  string
    Acceptable values:
            - String value
raster: Raster layer with features
    Argument type:  raster
    Acceptable values:
            - Path to a raster layer
matchByName: Match regressor features and raster bands by name (optional)
    Default value:  false
    Argument type:  boolean
    Acceptable values:
            - 1 for true/yes
            - 0 for false/no
nfold: Number of cross-validation folds (optional)
    Default value:  10
    Argument type:  number
    Acceptable values:
            - A numeric value
openReport: Open output cross-validation regressor performance report in webbrowser after running algorithm
    Default value:  true
    Argument type:  boolean
    Acceptable values:
            - 1 for true/yes
            - 0 for false/no
outputRegressorPerformance: Output cross-validation regressor performance report (optional)
    Argument type:  fileDestination
    Acceptable values:
            - Path for new file
outputRegressor: Output regressor
    Argument type:  fileDestination
    Acceptable values:
            - Path for new file
outputRegression: Output regression layer (optional)
    Argument type:  rasterDestination
    Acceptable values:
            - Path for new raster layer

----------------
Outputs
----------------

outputRegressorPerformance: <outputHtml>
    Output cross-validation regressor performance report
outputRegressor: <outputFile>
    Output regressor
outputRegression: <outputRaster>
    Output regression layer