time-interpret 0.2.1

Model interpretability library for PyTorch with a focus on time series.

Time Interpret (tint)

This package expands the captum library with a specific focus on time series. Please see the documentation and examples for more details.

Install

Time Interpret can be installed with pip:

pip install time_interpret

or from source:

with pip:

git clone [e-mail]:babylonhealth/time_interpret.git
cd time_interpret
pip install -e .

or conda:

git clone [e-mail]:babylonhealth/time_interpret.git
cd time_interpret
conda env create
source activate tint
pip install --no-deps -e .

Quick-start

First, let's load an Arma dataset:

from tint.datasets import Arma

arma = Arma()
arma.download()  # This method generates the dataset

We then load some test data from the dataset and the corresponding true saliency:

inputs = arma.preprocess()["x"][0]
true_saliency = arma.true_saliency(dim=1)[0]

We can now load an attribution method and use it to compute the saliency:

from tint.attr import TemporalIntegratedGradients

explainer = TemporalIntegratedGradients(arma.get_white_box)

baselines = inputs * 0
attr = explainer.attribute(
    inputs,
    baselines=baselines,
    additional_forward_args=(true_saliency,),
    temporal_additional_forward_args=(True,),
).abs()

Finally, we evaluate our method using the true saliency and a white box metric:

from tint.metrics.white_box import aup

print(f"{aup(attr, true_saliency):.4})

Methods (under development)

• AugmentedOcclusion
• BayesLime
• BayesShap
• DynaMask
• Discretised Integrated Gradients
• Fit
• Non-linearities Tunnel
• Occlusion
• Retain

Acknowledgment

• Jonathan Crabbe for the DynaMask implementation.
• Sana Tonekaboni for the fit implementation.
• INK Lab for the discretized integrated gradients implementation.
• Dylan Slack for the BayesLime and BayesShap implementations.