Create classification dataset (from Python code)

Create a classification dataset from Python code and store the result as a pickle file.

Usage:

1. Open the algorithm from the processing toolbox.

2. Modify the python script to match your needs, then click run.

   

3. The output classification dataset will be listed under Models in your Data Sources panel.

Parameters

Code [string]

Python code specifying the classification dataset.

Default:

from enmapboxprocessing.typing import Number, List, Category, ClassifierDump

# specify categories and feature names
categories: List[Category] = [
    Category(value=1, name='class 1', color='#ff0000'),
    Category(value=2, name='class 2', color='#00ff00')
]
features: List[str] = ['Feature 1', 'Feature 2', 'Feature 3']

# specify features X as 2d-array with shape (samples, features)
X: List[List[Number]] = [
    [1, 2, 3],
    [4, 5, 6]
]
# specify targets y as 2d-array with shape (samples, 1)
y: List[List[int]] = [
    [1], [2]
]

Outputs

Output dataset [fileDestination]

Pickle file destination.

Command-line usage

>qgis_process help enmapbox:CreateClassificationDatasetFromPythonCode:

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

code: Code
    Default value:  from enmapboxprocessing.typing import Number, List, Category, ClassifierDump

# specify categories and feature names
categories: List[Category] = [
    Category(value=1, name='class 1', color='#ff0000'),
    Category(value=2, name='class 2', color='#00ff00')
]
features: List[str] = ['Feature 1', 'Feature 2', 'Feature 3']

# specify features X as 2d-array with shape (samples, features)
X: List[List[Number]] = [
    [1, 2, 3],
    [4, 5, 6]
]
# specify targets y as 2d-array with shape (samples, 1)
y: List[List[int]] = [
    [1], [2]
]

    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
outputClassificationDataset: Output dataset
    Argument type:  fileDestination
    Acceptable values:
            - Path for new file

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

outputClassificationDataset: <outputFile>
    Output dataset