i'm trying to explain the prediction for binary text classification model (LSTM&GRU using BERT embedding) with LIME, it highlights the features for both classes, but it shows the score for each feature just for class 0. even if i tried different text and num_samples. how can i know what is the problem? here is the code and pictures for the explanations.
the explainer
explainer = LimeTextExplainer()
Generate an explanation for a single instance
exp = explainer.explain_instance(text, predict_proba, num_features=7, num_samples=700) exp.show_in_notebook(text = True)
enter image description here enter image description here
i tried to explain the text classififcation prediction, and i expected to see the important features with its score, but the score did not show just for the positive class
