lime
lime copied to clipboard
marcotcr
Lime: Explaining the predictions of any machine learning classifier
Hello, I have a dataframe of tabular data. Let's say that data columns are already in format of 0,1,2,3 etc. How can I handle these columns? Thank you!
Hi, I have a question regarding the _explain_instance()_ method in the _LimeTabularExplainer_ class. When using the LIME formula, we should compute the kernel using the distances between the points in...
Using Stratified Sampling to Improve LIME Image Explanations - This repository contains the changes needed to add the stratified sampling strategy to the original codebase of LIME proposed for the...
Hi, I am trying to use lime on my lstm model which is a classifier based on 3 dimensional numerical time series data (num_samples, num_time_length (varying depending on sample), num_features)....
Dear @marcotcr Im using a two class data set with 6 features. everything properly works except this block of code: i = np.random.randint(0, X_test.shape[0]) exp = explainer.explain_instance(X_test[i], rf.predict_proba, num_features=6, top_labels=1)...
Hello everyone, I've encountered an issue while integrating LIME into my code for breast cancer image classification. Despite my attempts to address it, I consistently receive white images as output....
Similar to issue #660 and #480 (specifically [this](https://github.com/marcotcr/lime/issues/480#issuecomment-877582860) part), `lime_image.LimeImageExplainer().explain_instance()` throws out an error when trying to hide tqdm progress bar. This is for lime `0.2.0.1` installed via `pip`. I...
Hi, is it possible to get the importance score for all tokens? apparently `exp.as_list()` returns score of limited number of words, e.g. ``` [('dyspnea', -7.306849349215826e-32), ('CVAs', 5.520306761778833e-32), ('Response', 3.6862688360175885e-32), ('note',...
Hey there, everything works fine except that I got no bars in `show_in_notebook`:  ``` Python 3.9.7 Name: lime Version: 0.2.0.1 ``` Thanks for your...
Getting this error when my predict_fn is actually a function within a class. ``` lime_exp = lime_explainer.explain_instance(data_row=instance, predict_fn=self.explain_pipe) ``` This is how my methods looks like: ``` def explain_pipe(self): temp_df...
