Skip to content
#

explainability

Star

Here are 40 public repositories matching this topic...

Language: All
Filter by language
All 40 Python 16 Jupyter Notebook 15 C++ 2 R 2 CSS 1 Java 1
Sort: Best match
Sort options
Best match Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

slundberg / shap

Star
Open

[DOC]Can you sort variables in TreeExplainer ->summaryPlot?

AlejandroBaron
AlejandroBaron commented Apr 28, 2020

I don't see any documentation on how to sort the variables in the plot. I don't want them sorted by shap value but in the original order, since i'm studying the behaviour of a Wave and I want to see a multiclass distribution of shap values over time

Currently they appear as

t=24
t=32
t=1
....

I want them to appear as
t=1
t=2
t=3
t=4
...

Is it possible?

Read more
Find more good first issues →

EthicalML / awesome-production-machine-learning

Star

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

machine-learning data-mining privacy deep-learning interpretability privacy-preserving production-machine-learning mlops privacy-preserving-machine-learning explainability responsible-ai responsible-ml machine-learning-operations ml-ops ml-operations privacy-preserving-ml large-scale-ml production-ml large-scale-machine-learning
  • Updated Jun 8, 2020

interpretml / interpret

Star
Open

show method while running in AWS EMR

1
matheus-asilva
matheus-asilva commented Nov 27, 2019

When running
from interpret import show
from interpret.perf import ROC
blackbox_perf = ROC(blackbox_model.predict_proba).explain_perf(X_test, y_test, name='Blackbox')
show(blackbox_perf)

I have the following error

RuntimeError: Could not find open port.
Consider calling interpret.set_show_addr(("127.0.0.1", 7001)) first..

Even calling the set_show_addr, I

Read more
hierarchical-dnn-interpretations

csinva / hierarchical-dnn-interpretations

Star

Using / reproducing ACD (ICLR 2019) from the paper "Hierarchical interpretations for neural network predictions"

python data-science machine-learning statistics deep-neural-networks ai deep-learning neural-network jupyter-notebook ml pytorch artificial-intelligence convolutional-neural-networks acd interpretation interpretability feature-importance explainable-ai iclr2019 explainability
  • Updated Jan 20, 2020
  • Jupyter Notebook
deep-explanation-penalization

laura-rieger / deep-explanation-penalization

Star

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

python data-science machine-learning ai deep-learning neural-network jupyter-notebook ml pytorch artificial-intelligence convolutional-neural-network fairness interpretability cdep feature-importance recurrent-neural-network interpretable-deep-learning explainable-ai explainability fairness-ml
  • Updated Jun 7, 2020
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the explainability topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the explainability topic, visit your repo's landing page and select "manage topics."

Learn more

You can’t perform that action at this time.