Deep Ensemble learners for explainable AI

The problem is of multi class classification for explainable AI. The dataset consists of 5 different labels (label 0 to label 4). These are the 5 different classes that the model needs to classify the data into. These cant be combined in a single csv file as they may lose their parameters. They need to be loaded seperately in python and then worked upon. There are 4 different ensembles that need to be used (deep neural decision tree, deep neural decision forest, deep svm, deep forest). I will be adding the reference code for all the 4 algorithms here.(if not then these are available on google) The accuracy should be great for all. After this LIME and SHAP libraries need to be used to explain the model. The insights also need to be explained. Use LEAF framework to compare LIME and SHAP based on various metrics and also possibly explain these. Information about leaf framework is also available on google. Use Microsoft Visual Studio code (Python) for all this