![how to download and install weka api how to download and install weka api](https://images.slideplayer.com/12/3430325/slides/slide_3.jpg)
When the Entropy Triangle has data plotted, the upper-right button is titled Save data. This is the dataset name, classifier name and options, evaluation metrics, and timestamp information. Each classifier tested is an instance, and their information are the attributes. The information is saved in the Weka instances format, similar way that the Weka Experimenter files. The Entropy Triangle lets you save the plotted data. A clean empty plot will be loaded when opening again the Entropy Triangle window or adding data. To remove a point from the plot, right-click on it to open the point context menu, then select delete. This line defines the limit of performance of the classifier due the test set. Recall that maximum entropy means a balanced dataset, and it is supposedly desirable. This distance determines the upper bound of the mutual information \( MI' \leq 1-\Delta H'_X \). The ΔH'(x) line marks the normalized distance in entropy of the dataset likelihood from the maximum. For more information about this, see the theoretical background of the plugin. The Split button toggles between showing in the plot the points that represent the marginals entropy balance equations. As in the Weka class panel, the color of the text labels can be changed clicking on them. the relation name or the classifier, colored text labels are drawn. When the label represents a non numeric value, i.e. This will open a drop-down list with all the available metrics and related information of the data.Ĭhoosing an evaluation metric draws a colorbar with the values adjusted to the range of the metric. The metric can be changed clicking in the upper-left combo box. The bottom panel of the Entropy Triangle titled Metric colour is a modified version of the Weka's "Class colour" panel. If you do not have the Entropy Triangle window already opened, a clean new plot will be generated. The data will be added to the existing window of the Entropy Triangle.
![how to download and install weka api how to download and install weka api](https://media.geeksforgeeks.org/wp-content/uploads/20211209172425/we.jpeg)
Then, move the cursor to Plugins to open the visualization plugins sub-menu and click Entropy Triangle. The evaluation data of a classifier tested on the Weka Explorer can be added to the Entropy Triangle.įor that, select on the Result list the test you want to add and right-click on it to open the context menu. This is the form to open the visualization to load a file with data of another session. When called from the Weka GUI Chooser window, will be displayed an empty plot. The Entropy Triangle is accessible from the Weka Explorer and the Weka GUI Chooser window. The Entropy Triangle visualization plugin The package can be used from the Weka GUIs and programmatically. The Entropy Triangle package for Weka includes a visualization plugin and new evaluation metrics.