Very quick start
- Launch the software
- Draw samples by clicking either the left or right mouse button.
- left-click generates samples of class 0
- right-click generates samples of the class selected in the toolbar (default: 1)
- Select the Display Options icon
- this will allow you to display model information, confidence/likelihood maps and to hide the original samples
- the mouse wheel will allow you to zoom in and out
- alt+dragging will allow you to pan around the space
- - Select the Algorithms Options icon
- - Select one of the algorithm icons to open their respective option panels
- - Click the Classify button to run the algorithm on the current data
Importing dataGenerating data in MLDemos is done in three different ways: by manually drawing samples, by projecting image data through PCA (via the PCAFaces plugin), or by loading external data.
Comma separated values, or other text-file based value tables can be drag-and-dropped into the interface. In this case a Data Loading dialog will appear to allow choosing which columns or rows should loaded, interpreted as class labels or headers, etc.
Alternatively, a native data format used by the software is ascii-based and contains:
- The # of samples followed by # of dimensions
- For each sample, one line containing
- The sample values space-separated (float, one per each dimension)
- The sample class index (integer 0 ... 255)
- A flag value (integer 0-3) to terminate the line (unused for
the time being)
0.10 0.11 0.12 0 0
0.14 0.91 0.11 0 0
0.43 0.74 0.41 1 0
0.28 0.34 0.33 1 0
which presents 4 three-dimensional samples, two from class 0 and one from class 1.
When the file is saved from MLDemos, the software adds the current algorithm parameters (provided an algorithm was selected), which can be useful for demonstration purposes. If no such information is present, the default algorithm parameters are selected.
Drawing manually some samples, or importing a standard dataset and saving it from within MLDemos should give you ample examples on the file syntax.