Comments (3)
I am assuming the the most common use case is binary prediction. When the prediction is binary, you want to always explain label 1, as that keeps 0 on the left and 1 on the right in the visualization, even if 0 is the top predicted label.
from lime.
Makes sense. You do know the number of classes, so you could default to label 1 for binary classification and the top label otherwise.
I do think a large percentage of users will want to use this library to explain the prediction their model actually made, and it seems like the default options should facilitate that. You could also add another function that wraps explain_instance
, I guess.
from lime.
I will make major changes in the interface to include other explanation methods I've developed soon, so I'll keep the suggestion in mind.
Thanks,
from lime.
Related Issues (20)
- TypeError: TextEncodeInput
- Lime consuming too much RAM for explanations for layoutLM HOT 1
- Value error for more then one word ? any work through ?
- ImportError: cannot import name 'QhullError' from 'scipy.spatial'....
- ValueError: Found input variables with inconsistent numbers of samples: [5000, 20000] ? how does this occur is soemthing wrong with my tokeniser ?
- Multi_Label_Classification
- Is this Repo Maintained? HOT 2
- Can LIME only be used for text classification tasks?
- How to explain prediction for a data with just a few features (from all features of training dataset)? HOT 2
- Trying to explaine a simple Neural Network using LIME
- submodular pick
- ans = self.domain_mapper.map_exp_ids(self.local_exp[label_to_use], **kwargs) KeyError: 1
- Getting error when my predict_fn is actually a method from a class HOT 1
- `show_in_notebook` shows no bars
- importance score for all tokens
- Unexpected keyword argument 'progress_bar' for lime_image.LimeImageExplainer().explain_instance()
- Issues with LIME Implementation in Image Classification
- How to use lime with 3 dim time series data and lstm
- Distances derivation, explain_instance() method in Tabular LIME
- How to handle binary features
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from lime.