lime
lime copied to clipboard
marcotcr
Lime: Explaining the predictions of any machine learning classifier
Dear Team, @marcotcr, How can I get explanations for multiple classes? Currently, I am only getting for the top three classes with the below code. ``` exp.show_in_notebook() ``` The "label"...
Creating LIME explanations from a lgbm model, the model prediction gives Class 1 probability as 99.99% and LIME explanations shows all positive values, when the model prediction gives Class 1...
I was wondering if there is a way to extract the features and range of values provided in the LIME explanations. For example, if I use: `exp.as_list()` I can get...
Hello everyone. I am using LIME to set up explanations about the decisions of different models with tabular data. For the training of AI models, I applied StandardScaler to the...
Which existing XAI method can explain the Siamese neural network?
I am also getting the same error as mentioned in issue #632 " labels_column = neighborhood_labels[:, label] TypeError: list indices must be integers or slices, not tuple". This seems like...
Having used this library, I encountered some problems, which required frequent edits in the source code. Here I have added three functions : 1) Generate Samples -> Sometimes we just...
I am using some product descriptions to generate a content-based recommender system where I am using TF_IDF for generating vectors for descriptions and then calculating the similarity using cosine_similarity. Based...
Hi, how can I use LIME to generate explanations for mixed data types (categorical and continuous)? I am using sklearn pipelines for the data transformation and classification.
For a regression model explainer below ``` explainer = LimeTabularExplainer(X_train, feature_names, mode="regression") exp = explainer.explain_instance(X_test[0], model, num_features=11) ``` The returned explanation still has two intercept ``` print(exp.intercept) >>>{0: 6.051529868550603, 1:...
