interpret icon indicating copy to clipboard operation
interpret copied to clipboard

Fit interpretable models. Explain blackbox machine learning.

Results 190 interpret issues
Sort by recently updated
recently updated
newest added

Hi devs, I'm having some confusions reading the graphs so I'll give a context and the confusion I'm facing ### Context I'm working on a NLP , multiclass problem and...

Hi folks! I am exploring this world of XAI in order to adapt it to Motion Prediction for Autonomous Driving. My inputs are map features (such as lanes, nodes, etc.)...

Hi I would like to use LIME interpretation for the dataset, where i have done preprocessing like OneHotCoding, Imputer, Calculating new feature using ColumnTransformation. I found the below sample code...

bug

I'm testing out running a few models and creating an interpret dashboard. Currently, my code runs with no error messages, and if I run to show a singular model e.g....

bug

Hi, This is more of a question, rather than an issue, but I was wondering if it was possible to see the FAST results for all the interactions that are...

I have a model (fit during an Azure automated ml run) that predicts on a dataframe just fine, but fail when the model and dataframe are passed to interpret functions...

bug

Trying to install this in Google Colab with pip I get some issues After restarting the runtime, it cannot find the library ``` ERROR: pip's dependency resolver does not currently...

Hi, I tried training a ExplainableBoostingRegressor using Dask arrays, but I keep running into the following issue: ```python ERROR:interpret.utils.all:Could not unify data of type: --------------------------------------------------------------------------- ValueError Traceback (most recent call...

enhancement

Hi With the Black box explanation technique as follow we have different visualization available. I would like to clarify about kind of visualization available. LIME -> We can use standard...

Hi, 1. How do I get LIME results for a multiclass problem? When I operate the code from the examples (with y_test which are one-hot encoded vectors) the results I...

bug