Regression workflow

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

Usage:

1. Start the algorithm from the Processing Toolbox panel.

2. Select a training dataset or create one by clicking the processing algorithm icon. Select a regressor and adjust its parameterization accordingly, then click run.

   

Live Demonstration

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 used for prediction.

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
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
raster: Raster layer with features (optional)
    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
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
nfold: Number of cross-validation folds (optional)
    Default value:  10
    Argument type:  number
    Acceptable values:
            - A numeric value
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
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
            - field:FIELD_NAME to use a data defined value taken from the FIELD_NAME field
            - expression:SOME EXPRESSION to use a data defined value calculated using a custom QGIS expression
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