oegedijk/sagemaker-creditscore-explainer

Stars
6
Rank 2,539,965 (Top 51 %)
Language
Jupyter Notebook
Created over 4 years ago
Updated over 4 years ago

oegedijk/sagemaker-creditscore-explainer

oegedijk

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Example of how to deploy an ML algorithm together with SHAP explanations to AWS Sagemaker, including a front end dashboard.

explainerdashboard

Quickly build Explainable AI dashboards that show the inner workings of so-called "blackbox" machine learning models.

dash_oop_components

OOP components for plotly dash that make dashboard components composable, reusable and configurable

Jupyter Notebook

rule_estimator

A scikit-learn compatible estimator based on business-rules with interactive dashboard included

Jupyter Notebook

dash_querystrings

Example of how to include querystrings to save state url in plotly's Dash

explainingtitanic

A demonstration of the explainerdashboard package that that displays model quality, permutation importances, SHAP values and interactions, and individual trees for sklearn RandomForestClassifiers, etc

keras-embeddings

Example of how to use entity embeddings (similar to word embeddings such as word2vec, but then generalized for any categorical feature) in a Keras model.

dash_oop_demo

Deployment example of dash_oop_components library

dash-tabs

Example of how to use tabs in a plotly's Dash framework across multiple files

blog

Repository that hosts my blog (created using fastpages)

Jupyter Notebook

deploy-xgboost-to-aws-lambda

short guide on how to deploy xgboost machine learning models to production on AWS lambda

python-datascience-course

notebooks for internal Python for Datascience course that I teach at UWV.

Jupyter Notebook

sklearn-transformers

A collection of sklearn compatible transformer classes. Sklearn's standard transformers have some annoying lacunes (especially when fitting on new data with labels missing in training data for example), so these transformers fix that. Also some other more adventurous transformer classes. Shows how to quickly make transformer pipelines for e.g. making dataframe ready for neural net with embeddings.

oegedijk