lime
lime copied to clipboard
marcotcr
Lime: Explaining the predictions of any machine learning classifier
My input value: `Log.e("t","api_key="123"); val tt = "ddd"` ```bash main.py", line 139, in show_reason_binary word_list = str(exp.as_list()) ^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/lime/explanation.py", line 141, in as_list ans = self.domain_mapper.map_exp_ids(self.local_exp[label_to_use], **kwargs) ~~~~~~~~~~~~~~^^^^^^^^^^^^^^ KeyError:...
Implement dark mode for explanation.show_in_notebook method by post-processing the formatted HTML. Without this, in a notebook that is rendered in dark mode, the text is scarcely legible. Example (from tutorial):...
I have used LIME on tabular data of ECG signals which have 34 features, and my aim to to figure out which features are deemed important for the respective classes....
I am trying to explaine the following neural network trained on toy data ``` import keras import numpy as np import tensorflow as tf from tensorflow import keras from tensorflow.keras...
Had difficulty in viewing the X and Y axis data labels of pyplot when there were 100+ features, especially in small figsize such as the default (10,10). Increasing the figsize...
I have generated lightGBM models for prediction. I can explain the predictions with all features by filling user input data with NAs. Is there any way to explain prediction for...
I'm getting plenty of errors when using pandas as the data for this repo. Is this repo still maintained or it's obsolete? is there any alternative to this one that...
Thank you for this amazing library and your contribution to the critical field of Explainable AI. I would like to know is there any function/method in the LIME library that...
While trying to explain a skmultilearn binary relevance model It kept throwing an error about output being sparse. Changed a few lines of code to handle when classifier_fn produces sparse...
Hello, Thank you very much for the package! I'm attempting to find the best set of parameters for the local explanations, such as kernel_width and num_samples, in order to produce...
