Comments (4)
Hi, thanks for your interest in the library, I look forward to reading the blog post!
-
I've seen the same issue so I'm going to investigate, the warning suggests that we are looking at synonyms for empty vectors, this could be an alibi bug or intended behaviour according to spacy.
-
This is interesting. First I just want to note that this in an example of an empty anchor not a "no anchor" - no anchor would be a partial anchor which did not satisfy the precision threshold no matter how many features were added in. I agree that it looks like the anchor algorithm is picking up on the model's decision to classify as "neither" if apples/oranges are absent, but it's not entirely clear. Can I ask a bit more about what the sentences in the "neither" category look like?
from alibi.
@mapmeld I believe the cause of 1. is using the small sm
model - the spacy docs say that the sm
models don't ship with word vectors, I would suggest trying the lg
model instead and see if the warnings go away (the quality of synonyms should also improve!).
from alibi.
@mapmeld I was wrong, we use the md
model by default which does have word vectors, the issue arises because there are a lot of lexemes for which the word vector is identically zero. I think we should prune these from the corpus before finding the synonyms. Alternatively we can bump up the default w_prob=-20
to something higher to exclude more words based on rarity.
Edit: I've submitted a PR to fix this #110
Edit2: This is now merged and fixed in v0.2.2
from alibi.
@mapmeld I will close this issue now as the warnings have been fixed and it's hard to debug the Anchor output without knowing the details of your model, feel free open a new issue if you have more details.
from alibi.
Related Issues (20)
- IndexError with AnchorExplainer and Yolov8
- `typing-extensions` 4.6.0 breakage HOT 1
- Predictor attr not properly cleared when saving HOT 2
- `numba` warnings regarding `nopython` keyword HOT 3
- `PartialDependenceVariance` cannot be saved
- CI failing due to use of `np.int` in `shap` HOT 2
- How to pass parameters to the /api/v1.0/explain using AnchorImage? HOT 2
- `KernelShap` returns no explanations when `link='logit'` and predicted proba is 0 or 1
- RuntimeError: The Session graph is empty. Add operations to the graph before calling run() HOT 6
- RuntimeError: tf.placeholder() is not compatible with eager execution.
- RuntimeError: The Session graph is empty. Add operations to the graph before calling run().
- TypeError: 'float' object is not subscriptable
- PDP plots failing with `matplotlib==3.8.0` HOT 1
- `matplotlib` 3.8.0 type hints for public APIs result in type-checking failures
- Logo in README.md HOT 1
- Columns and DataType Not Explicitly Set on line 61 of data.py
- When use explainer.fit(X_train)οΌit went into a loop of error
- After getting anchors, how to use it to predict the label of an instance?
- Mixed continuous and categorical features in the AnchorTabular explainers (my dataset doesn't contain NaNs)
- New release? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alibi.