lime
lime copied to clipboard
thomasp85
Local Interpretable Model-Agnostic Explanations (R port of original Python package)
Using this tutorial on the RStudio AI blog: https://blogs.rstudio.com/ai/posts/2018-03-09-lime-v04-the-kitten-picture-edition/ Everything runs fine until ``` explanation plot_image_explanation(explanation) Error: Input must be a vector, not a `superpixel_list` object. Run `rlang::last_error()` to see...
When applying LIME to simulated data with a binary outcome, LIME results do not always match the data generating process. This arises because the `family` argument in the call to...
Hi, I am trying to use LIME on R, and I need some explanations about the results produced by the package. I have 144 records with 25 parameters each. Records...
According to the documentation it should be possible to use lime also with libraries that are not directly supported. However, it is unclear if and how this can be exactly...
It seems that when trying the explain function with keras cnn models, following error occurs: "Type error : expected str, bytes or os.pathlike object not list". I tried explanation with...
It seems that lime explanation does not work with variables with just NAs and constant value, which do fit the XGBOOST. For instance, I have a variable that is highly...
Hi there, I am keep experiencing error when I use explain function in r. explainer_xgb % dplyr::select(-tj_year), xgb_fit_1718, bin_continuous = F, quantile_bins = F) explanations_xgb Error in feature_distribution[[i]] : subscript...
Hi, I'm working on a Text classification Problem with Keras and lime. My code talks about credit risk which is a classification problem, Yes or No, When I predict the...
On the [Understanding lime page](https://cran.r-project.org/web/packages/lime/vignettes/Understanding_lime.html), the tabular feature plots do not match the description : 
