A python library for decision tree visualization and model interpretation.
visualization python data-science machine-learning random-forest scikit-learn xgboost decision-trees model-interpretation
-
Updated
Mar 6, 2025 - Jupyter Notebook
#
model-interpretation
Here are 44 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
InterpretDL: Interpretation of Deep Learning Models,基于『飞桨』的模型可解释性算法库。
grad-cam convolutional-neural-networks visualizations lime paddlepaddle model-interpretation nlp-models smoothgrad explanations vision-transformer interpretation-algorithms
-
Updated
Sep 4, 2024 - Python
A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.
visualization python machine-learning deep-learning tensorflow image-processing pytorch image-classification image-dataset object-detection hacktoberfest bounding-boxes model-interpretation model-deployment model-serving model-visualization gradcam mlops fastapi
-
Updated
Oct 6, 2025 - Python
-
Updated
May 10, 2021 - Python
Overview of different model interpretability libraries.
-
Updated
Jul 2, 2022 - Jupyter Notebook
A set of tools for leveraging pre-trained embeddings, active learning and model explainability for effecient document classification
python sklearn word-embeddings document-classification flair active-learning model-interpretation eli5 document-classifier model-interpretability
-
Updated
Jan 23, 2025 - HTML
FastAI Model Interpretation with LIME
-
Updated
Feb 7, 2019 - Jupyter Notebook
What Has Been Enhanced in my Knowledge-Enhanced Language Model?
-
Updated
Oct 26, 2022 - Python
Official implementation of "HyPepTox-Fuse: An interpretable hybrid framework for accurate peptide toxicity prediction fusing protein language model-based embeddings with conventional descriptors"
-
Updated
Jul 24, 2025 - Python
Overview of machine learning interpretation techniques and their implementations
python data-science machine-learning transparency interpretation interpretability model-interpretation interpretable-ai interpretable-ml mli xai interpretable-machine-learning machine-learning-interpretability interpretable-classifcation
-
Updated
Jan 5, 2021 - Jupyter Notebook
Integrating multimodal data through heterogeneous ensembles
-
Updated
Dec 27, 2023 - Python
This repository has all of the assignments I had to do for the Standard Bank Data Science Virtual Experience Program. 📉👨💻📊📈
programming-language data-science machine-learning data-mining sql machine-learning-algorithms data-visualization python3 seaborn data-analysis business-solutions model-evaluation automl model-interpretation presentation-slides power-point business-analysis matplotlib-pyplot client-communication statical-analysis
-
Updated
May 30, 2025 - Jupyter Notebook
Model Interpretability via Hierarchical Feature Perturbation
-
Updated
Mar 30, 2020 - Python
Implémentation d'un modèle de scoring (OpenClassrooms | Data Scientist | Projet 7)
dashboard data-visualization dashboards feature-engineering custom-metrics flask-api data-cleaning bayesian-optimization heroku-deployment data-aggregation model-interpretation data-sampling shap imbalanced-classification streamlit local-interpretation risk-modeling pycaret lgbmclassifier data-ag
-
Updated
Jan 31, 2021 - Jupyter Notebook
The tasks I was required to complete as a part of the BCG Open-Access Data Science & Advanced Analytics Virtual Experience Program are all contained in this repository. 📊📈📉👨💻
programming communication exploratory-data-analysis machine-learning-algorithms data-visualization seaborn statistical-analysis synthesis python-3 feature-engineering jupyter-notebooks creativity mathematical-modelling model-evaluation machine-learning-engineering model-interpretation matplotlib-pyplot client-communication hypothesis-framing business-understanding
-
Updated
Jun 2, 2025 - Jupyter Notebook
Using LIME and SHAP for model interpretability of Machine Learning Black-box models.
python random-forest regression classification lime model-interpretation black-box-model shap model-interpretability
-
Updated
Sep 13, 2019 - Jupyter Notebook
Visualize a Decision Tree using dtreeviz
visualization python machine-learning decision-trees decision-tree-classifier decision-tree-algorithm model-interpretation decision-tree-regression dtreeviz
-
Updated
Feb 20, 2022 - Jupyter Notebook
Analyzed customer churn using transaction data. Built ML model to predict lapses. Dataset includes customer status, collection/redemption info, and program tenure. Delivered business presentation outlining modeling approach, findings, and churn reduction strategies.
neural-network random-forest logistic-regression support-vector-machine data-preprocessing feature-engineering decision-tree cluster-analysis gradient-boosting model-interpretation data-driven-decisions data-splitting model-optimization sas-visual-analytics model-selection-and-evaluation
-
Updated
Apr 18, 2024
Successfully established a machine learning model to predict the approval status of a health insurance claim based on patient and claim characteristics, using XGBoost with SHAP-based interpretability and deployed via Streamlit.
machine-learning exploratory-data-analysis xgboost feature-engineering model-interpretation model-deployment shap streamlit health-insurance-claims
-
Updated
Jul 17, 2025 - Jupyter Notebook
Advise one of Cognizant’s clients on a supply chain issue by applying knowledge of machine learning models.
python machine-learning development communication skills presentation machine-learning-algorithms evaluation data-visualization artificial-intelligence data-analysis quality-assurance data-modeling machine-learning-engineering problem-statement model-interpretation cognizant forage virtual-internship job-simulation
-
Updated
Mar 30, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the model-interpretation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the model-interpretation topic, visit your repo's landing page and select "manage topics."