Comments (1)
To your first suggestion, I have been thinking about how to organize the repository, since I have some new explanation methods, and would like to incorporate my submodular procedure (issue #11), which doesn't fit that well into LIME. I have to think carefully about that before I do anything though, so it's probably something for the next few months instead of weeks.
There are two ways of looking at explanations. They can either be contributions to the prediction (in which case we have to multiply the weight of the linear model with the feature value), or a model that approximates the underlying model in the neighborhood. Assume you have a feature k such that x_k = -1, and the local model approximation has w_k = 10. This feature has negative contribution and positive weight, and I don't know how to show these two things. This is a particular problem for regression problems, because I imagine you want to be able to make predictions about what would change if certain values were changed even more so than with classification. Also, the feature magnitudes and the weights really matter in regression (as opposed to in classification where the output is in the [0,1] range, which makes it simpler), which makes it even harder to interpret. A solution was showing weights in terms of standardized data, but that has its own problems for interpretation.
Discretizing obviously rids us of this problem, as contribution and weight become the same thing (since the feature becomes binary), but we lose information (and require some training data as well).
Anyway, I think we can definitely plug a regressor into LIME, but right now I don't think the result will be very interpretable (and thus useful). Plus, the prediction probability part of the visualization obviously assumes that the results will be in [0,1].
from lime.
Related Issues (20)
- 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 HOT 1
- 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
- RecurrentTabularExplainer for regression task
- Question: using LIME for text generation HOT 1
- LIME and multi-correlated variables
- update Python support
- Inverse scaling/ normalization to get actual unscaled values in explanation : Old issue but I made a way around
- Met the issue about TypeError when using lime_image.LimeImageExplainer()
- Saving the output of show_in_notebook as static image
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.