pbiecek / Breakdown
Model Agnostics breakDown plots
Stars: ✭ 93
Programming Languages
r
7636 projects
Projects that are alternatives of or similar to Breakdown
Awesome Machine Learning Interpretability
A curated list of awesome machine learning interpretability resources.
Stars: ✭ 2,404 (+2484.95%)
Mutual labels: data-science, interpretability
Mli Resources
H2O.ai Machine Learning Interpretability Resources
Stars: ✭ 428 (+360.22%)
Mutual labels: data-science, interpretability
Imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Stars: ✭ 194 (+108.6%)
Mutual labels: data-science, interpretability
Interpretable machine learning with python
Examples of techniques for training interpretable ML models, explaining ML models, and debugging ML models for accuracy, discrimination, and security.
Stars: ✭ 530 (+469.89%)
Mutual labels: data-science, interpretability
Dalex
moDel Agnostic Language for Exploration and eXplanation
Stars: ✭ 795 (+754.84%)
Mutual labels: data-science, interpretability
Daily Coding Problem
Series of the problem 💯 and solution ✅ asked by Daily Coding problem👨🎓 website.
Stars: ✭ 90 (-3.23%)
Mutual labels: data-science
Applied Ml
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Stars: ✭ 17,824 (+19065.59%)
Mutual labels: data-science
Interpretability By Parts
Code repository for "Interpretable and Accurate Fine-grained Recognition via Region Grouping", CVPR 2020 (Oral)
Stars: ✭ 88 (-5.38%)
Mutual labels: interpretability
Awesome Computer Vision
Awesome Resources for Advanced Computer Vision Topics
Stars: ✭ 92 (-1.08%)
Mutual labels: interpretability
Epfl
EPFL summaries & cheatsheets over 5 years (computer science, communication systems, data science and computational neuroscience).
Stars: ✭ 90 (-3.23%)
Mutual labels: data-science
Lda Topic Modeling
A PureScript, browser-based implementation of LDA topic modeling.
Stars: ✭ 91 (-2.15%)
Mutual labels: data-science
Pyvtreat
vtreat is a data frame processor/conditioner that prepares real-world data for predictive modeling in a statistically sound manner. Distributed under a BSD-3-Clause license.
Stars: ✭ 92 (-1.08%)
Mutual labels: data-science
Vvedenie Mashinnoe Obuchenie
📝 Подборка ресурсов по машинному обучению
Stars: ✭ 1,282 (+1278.49%)
Mutual labels: data-science
Sci Pype
A Machine Learning API with native redis caching and export + import using S3. Analyze entire datasets using an API for building, training, testing, analyzing, extracting, importing, and archiving. This repository can run from a docker container or from the repository.
Stars: ✭ 90 (-3.23%)
Mutual labels: data-science
Pytorch Wrapper
Provides a systematic and extensible way to build, train, evaluate, and tune deep learning models using PyTorch.
Stars: ✭ 92 (-1.08%)
Mutual labels: data-science
Break Down: Model Agnostic Explainers for Individual Predictions
The breakDown package is a model agnostic tool for decomposition of predictions from black boxes.
Break Down Table shows contributions of every variable to a final prediction.
Break Down Plot presents variable contributions in a concise graphical way.
This package works for binary classifiers and general regression models.
Find lots of R examples at breakDown website: https://pbiecek.github.io/breakDown/
Interested in the methodology? Find the math behind breakDown and live at: https://arxiv.org/abs/1804.01955
Looking for the python version of Break Down? Find it here: https://github.com/bondyra/pyBreakDown
New generation of the Break-Down algorithm is implemented in the iBreakDown package https://github.com/ModelOriented/iBreakDown. All new features will be added to the iBreakDown.
Installation
Install from CRAN
install.packages("breakDown")
Install from GitHub
devtools::install_github("pbiecek/breakDown")
Cheatsheets
Example for lm model
Get data with archivist
- broken object:
archivist::aread("pbiecek/breakDown/arepo/81c5be568d4db2ec795dedcb5d7d6599") - the plot:
archivist::aread("pbiecek/breakDown/arepo/7b40949a0fdf9c22780454581d4b556e")
The R code
library(breakDown)
url <- 'https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv'
wine <- read.table(url, header = T, sep=";")
head(wine, 3)
## fixed.acidity volatile.acidity citric.acid residual.sugar chlorides free.sulfur.dioxide total.sulfur.dioxide density pH
## 1 7.0 0.27 0.36 20.7 0.045 45 170 1.0010 3.00
## 2 6.3 0.30 0.34 1.6 0.049 14 132 0.9940 3.30
## 3 8.1 0.28 0.40 6.9 0.050 30 97 0.9951 3.26
## sulphates alcohol quality
## 1 0.45 8.8 6
## 2 0.49 9.5 6
## 3 0.44 10.1 6
model <- lm(quality ~ fixed.acidity + volatile.acidity + citric.acid + residual.sugar + chlorides + free.sulfur.dioxide + total.sulfur.dioxide + density + pH + sulphates + alcohol,
data = wine)
new_observation <- wine[1,]
br <- broken(model, new_observation)
br
## contribution
## (Intercept) 5.90000
## residual.sugar = 20.7 1.20000
## density = 1.001 -1.00000
## alcohol = 8.8 -0.33000
## pH = 3 -0.13000
## free.sulfur.dioxide = 45 0.03600
## sulphates = 0.45 -0.02500
## volatile.acidity = 0.27 0.01500
## fixed.acidity = 7 0.00950
## total.sulfur.dioxide = 170 -0.00900
## citric.acid = 0.36 0.00057
## chlorides = 0.045 0.00019
## final_prognosis 5.60000
plot(br)
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].