Comments (3)
I have the similar problem when trying to produce the local explanation based on Azure AutoML output. Dataset is the "orange juice store" sample data used in the forecasting notebook. I setup the MimicWrapper as per introduced in the AutoML explain page.
It works perfectly with the global explain, but not as expected for the local. Individual feature importance can be obtained in the json format, but I am not able to visualize it:
- If I try to call dashboard, I got the following error (it also throws error when I pass the fitted model parameter)
from interpret_community.widget import ExplanationDashboard
ExplanationDashboard(engineered_local_explainations, datasetX=automl_explainer_setup_obj.X_test_transform)
Full error message is:
ValueError: Unsupported local explanation type, inner error: Traceback (most recent call last):
File "anaconda3/envs/xxx/lib/python3.6/site-packages/interpret_community/widget/explanation_dashboard_input.py", line 137, in __init__
local_explanation["intercept"] = self._convert_to_list(local_explanation["intercept"])
KeyError: 'intercept'
- I also cannot call
engineered_local_explainations.visualize()
method since it doesn't support "DynamicLocalExplain`.
So, what is the best way of viz the local explanation?
from interpret-community.
@nagapavannukala sorry about the issue you are encountering, and sorry about the late reply. Could you give us more details about this issue? What explainer did you use that caused this error? If the dataset is not private, would you be able to share an example that reproduces this issue?
from interpret-community.
@nagapavannukala @xiaolul @saimachi @konabuta I've sent a PR to fix this issue here:
#387
from interpret-community.
Related Issues (20)
- WrappedClassificationModel() usage HOT 4
- ImportError: cannot import name 'TabularExplainer' HOT 3
- Issue when initializing explainer through TabularExplainer and KernelExplainer HOT 1
- Log scale combo box for Dependence plot's x axis HOT 2
- Replace load_boston with alternate regression dataset
- 'Expecting data to be a DMatrix object, got: ', <class 'pandas.core.frame.DataFrame'> HOT 7
- Question. How is the global explanation measured? HOT 7
- Question. How good is my surrogate model? HOT 8
- Explainers do not work with Keras models with multiple inputs HOT 10
- Calculate r2_score for PFIExplainer HOT 6
- Interpret explainer module question HOT 7
- Code Formatting Standards HOT 5
- TabularExplainer doesn't work with bias-mitigated model from fairlearn HOT 5
- How can I use MimicExplainer with Voting Classifier? [Question] HOT 5
- Dimension errors when using sklearn OneHotEncoder with min_frequency parameter HOT 1
- How can I get the data points of Aggregate feature importance ?
- Converting from NumPy array to list in mimic_explainer.py:_save()
- cannot import MimicExplainer HOT 7
- package `interpret-community` is incompatible with current `shap` version
- Getting <AttributeError: 'DynamicGlobalExplanation' object has no attribute 'get_ranked_per_class_names'> when running PFIExplainer
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 interpret-community.