Since version 0.40, Nkululeko can now show the best performing X acoustic features according to some model.

There is a new section call EXPL (short for exploration), and you could state

[EXPL]
feature_distributions = True
model = ['tree', 'gmm', 'svm']
permutation = True
max_feats = 5
sample_selection = test

in your config file, and then run the exploration module like this:

python -m nkululeko.explore --config my_config.ini

The following values can be set in the config:

• feature_distributions: use this analysis.
• sample_selection: Which sample set/split to use, either all, train or test
• model: Which models to use to estimate feature importance. Can be all models from the MODEL section, If several are stated, the mean result is used.
• max_feats: The best n feats are shown
• permutation: use feature permutation to determine the best features. Make sure to test the models before.

The resulting list will then appear in the result folder and a barplot image in the image folder.

Afterwards you could inspect single features as described here