lime
lime copied to clipboard
marcotcr
Lime: Explaining the predictions of any machine learning classifier
Rather than removing text which can create oddities, we may want to consider ways to replace tokens that would otherwise be removed. I added a support for a custom replacement_fn,...
While using the iris dataset, I tried to generate LIME values for features with a different random seed and got inconsistency in LIME values and feature importance between each run....
I have noticed that inside Lime Text Explainer, correct me if I am wrong, original text and its perturbed data is converted to binary vector form and there after the...
pip3 install lime==0.2.0.1 of Python 3.9.8 version is failing. ERROR -× Encountered error while trying to install package. ╰─> matplotlib
Hello, I was trying to use LIME explanation generation for other language (Bengali), a non-English language. When I see the work highlighting, the whole words are not properly highlighted. Is...
Situation: 1. saving lime explainer using dill during training and loading it back during prediction. 2. the model is light gbm native api predict - so wrapped it as below...
 i got stuck here!!
I am trying to do error analysis/model interpretation using LIME and my model(deep learning model) is trained on mixed features(Text and tabular features). My model takes 3 inputs(2 text tokenized...
I already read and follow [this tutorial](https://marcotcr.github.io/lime/tutorials/Tutorial%20-%20continuous%20and%20categorical%20features.html) for cases when we have numerical and categorical features in the dataset. The problem is that in this way, LIME explanations and the...
Hi, thank you very much for the package! I have checked the notebook of using Lime on LSTM [here].(https://github.com/marcotcr/lime/blob/master/doc/notebooks/Lime%20with%20Recurrent%20Neural%20Networks.ipynb) I wonder if it can be still used for multi parallel...
