Python implementation of R package breakDown

Overview

pyBreakDown

Python implementation of breakDown package (https://github.com/pbiecek/breakDown).

Docs: https://pybreakdown.readthedocs.io.

Requirements

Nothing fancy, just python 3.5.2+ and pip.

Installation

Install directly from github

    git clone https://github.com/bondyra/pyBreakDown
    cd ./pyBreakDown
    python3 setup.py install  # (or use pip install . instead)

Basic usage

Load dataset

from sklearn import datasets
x = datasets.load_boston()
data = x.data
feature_names = x.feature_names
y = x.target

Prepare model

import numpy as np
from sklearn import tree
model = tree.DecisionTreeRegressor()

Train model

train_data = data[1:300,:]
train_labels=y[1:300]
model = model.fit(train_data,y=train_labels)

Explain predictions on test data

#necessary imports
from pyBreakDown.explainer import Explainer
from pyBreakDown.explanation import Explanation
#make explainer object
exp = Explainer(clf=model, data=train_data, colnames=feature_names)
#make explanation object that contains all information
explanation = exp.explain(observation=data[302,:],direction="up")

Text form of explanations

#get information in text form
explanation.text()
Feature                  Contribution        Cumulative          
Intercept = 1            29.1                29.1                
RM = 6.495               -1.98               27.12               
TAX = 329.0              -0.2                26.92               
B = 383.61               -0.12               26.79               
CHAS = 0.0               -0.07               26.72               
NOX = 0.433              -0.02               26.7                
RAD = 7.0                0.0                 26.7                
INDUS = 6.09             0.01                26.71               
DIS = 5.4917             -0.04               26.66               
ZN = 34.0                0.01                26.67               
PTRATIO = 16.1           0.04                26.71               
AGE = 18.4               0.06                26.77               
CRIM = 0.09266           1.33                28.11               
LSTAT = 8.67             4.6                 32.71               
Final prediction                             32.71               
Baseline = 0
#customized text form
explanation.text(fwidth=40, contwidth=40, cumulwidth = 40, digits=4)
Feature                                 Contribution                            Cumulative                              
Intercept = 1                           29.1                                    29.1                                    
RM = 6.495                              -1.9826                                 27.1174                                 
TAX = 329.0                             -0.2                                    26.9174                                 
B = 383.61                              -0.1241                                 26.7933                                 
CHAS = 0.0                              -0.0686                                 26.7247                                 
NOX = 0.433                             -0.0241                                 26.7007                                 
RAD = 7.0                               0.0                                     26.7007                                 
INDUS = 6.09                            0.0074                                  26.708                                  
DIS = 5.4917                            -0.0438                                 26.6642                                 
ZN = 34.0                               0.0077                                  26.6719                                 
PTRATIO = 16.1                          0.0385                                  26.7104                                 
AGE = 18.4                              0.0619                                  26.7722                                 
CRIM = 0.09266                          1.3344                                  28.1067                                 
LSTAT = 8.67                            4.6037                                  32.7104                                 
Final prediction                                                                32.7104                                 
Baseline = 0

Visual form of explanations

explanation.visualize()

png

#customize height, width and dpi of plot
explanation.visualize(figsize=(8,5),dpi=100)

png

#for different baselines than zero
explanation = exp.explain(observation=data[302,:],direction="up",useIntercept=True)  # baseline==intercept
explanation.visualize(figsize=(8,5),dpi=100)

png

Owner
MI^2 DataLab
MI^2 DataLab
👋🦊 Xplique is a Python toolkit dedicated to explainability, currently based on Tensorflow.

👋🦊 Xplique is a Python toolkit dedicated to explainability, currently based on Tensorflow.

DEEL 343 Jan 02, 2023
pytorch implementation of "Distilling a Neural Network Into a Soft Decision Tree"

Soft-Decision-Tree Soft-Decision-Tree is the pytorch implementation of Distilling a Neural Network Into a Soft Decision Tree, paper recently published

Kim Heecheol 262 Dec 04, 2022
Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

Neural-Backed Decision Trees · Site · Paper · Blog · Video Alvin Wan, *Lisa Dunlap, *Daniel Ho, Jihan Yin, Scott Lee, Henry Jin, Suzanne Petryk, Sarah

Alvin Wan 556 Dec 20, 2022
Portal is the fastest way to load and visualize your deep neural networks on images and videos 🔮

Portal is the fastest way to load and visualize your deep neural networks on images and videos 🔮

Datature 243 Jan 05, 2023
Python Library for Model Interpretation/Explanations

Skater Skater is a unified framework to enable Model Interpretation for all forms of model to help one build an Interpretable machine learning system

Oracle 1k Dec 27, 2022
Algorithms for monitoring and explaining machine learning models

Alibi is an open source Python library aimed at machine learning model inspection and interpretation. The focus of the library is to provide high-qual

Seldon 1.9k Dec 30, 2022
Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University

Contrastive Explanation (Foil Trees) Contrastive and counterfactual explanations for machine learning (ML) Marcel Robeer (2018-2020), TNO/Utrecht Univ

M.J. Robeer 41 Aug 29, 2022
Quickly and easily create / train a custom DeepDream model

Dream-Creator This project aims to simplify the process of creating a custom DeepDream model by using pretrained GoogleNet models and custom image dat

56 Jan 03, 2023
Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

Hierarchical neural-net interpretations (ACD) 🧠 Produces hierarchical interpretations for a single prediction made by a pytorch neural network. Offic

Chandan Singh 111 Jan 03, 2023
Visualization toolkit for neural networks in PyTorch! Demo -->

FlashTorch A Python visualization toolkit, built with PyTorch, for neural networks in PyTorch. Neural networks are often described as "black box". The

Misa Ogura 692 Dec 29, 2022
Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)

Tool for visualizing attention in the Transformer model (BERT, GPT-2, Albert, XLNet, RoBERTa, CTRL, etc.)

Jesse Vig 4.7k Jan 01, 2023
Interpretability and explainability of data and machine learning models

AI Explainability 360 (v0.2.1) The AI Explainability 360 toolkit is an open-source library that supports interpretability and explainability of datase

1.2k Dec 29, 2022
tensorboard for pytorch (and chainer, mxnet, numpy, ...)

tensorboardX Write TensorBoard events with simple function call. The current release (v2.1) is tested on anaconda3, with PyTorch 1.5.1 / torchvision 0

Tzu-Wei Huang 7.5k Jan 07, 2023
A library that implements fairness-aware machine learning algorithms

Themis ML themis-ml is a Python library built on top of pandas and sklearnthat implements fairness-aware machine learning algorithms. Fairness-aware M

Niels Bantilan 105 Dec 30, 2022
FairML - is a python toolbox auditing the machine learning models for bias.

======== FairML: Auditing Black-Box Predictive Models FairML is a python toolbox auditing the machine learning models for bias. Description Predictive

Julius Adebayo 338 Nov 09, 2022
A collection of research papers and software related to explainability in graph machine learning.

A collection of research papers and software related to explainability in graph machine learning.

AstraZeneca 1.9k Dec 26, 2022
Interactive convnet features visualization for Keras

Quiver Interactive convnet features visualization for Keras The quiver workflow Video Demo Build your model in keras model = Model(...) Launch the vis

Keplr 1.7k Dec 21, 2022
Implementation of linear CorEx and temporal CorEx.

Correlation Explanation Methods Official implementation of linear correlation explanation (linear CorEx) and temporal correlation explanation (T-CorEx

Hrayr Harutyunyan 34 Nov 15, 2022
Visualize a molecule and its conformations in Jupyter notebooks/lab using py3dmol

Mol Viewer This is a simple package wrapping py3dmol for a single command visualization of a RDKit molecule and its conformations (embed as Conformer

Benoît BAILLIF 1 Feb 11, 2022
Visualizer for neural network, deep learning, and machine learning models

Netron is a viewer for neural network, deep learning and machine learning models. Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), Tens

Lutz Roeder 20.9k Dec 28, 2022