Skip to main content

Compares weaknesses in multiple models

Project description

AutoRA Model Disagreement Experimentlist

The model disagreement experimentlist identifies experimental conditions $\vec{x}' \in X'$ with respect to a pairwise distance metric between theorist models, $P_{M_{i}}(\hat{y}, \vec{x}')$:

$$ \underset{\vec{x}'}{\arg\max}~(P_{M_{1}}(\hat{y}, \vec{x}') - P_{M_{2}}(\hat{y}, \vec{x}'))^2 $$

Example Code

from autora.experimentalist.model_disagreement import model_disagreement_sample
from autora.theorist.bms import BMSRegressor; BMSRegressor()
from autora.theorist.darts import DARTSRegressor; DARTSRegressor()
import numpy as np

#Meta-Setup
X = np.linspace(start=-3, stop=6, num=10).reshape(-1, 1)
y = (X**2).reshape(-1, 1)
n = 5

#Theorists
bms_theorist = BMSRegressor()
darts_theorist = DARTSRegressor()
bms_theorist.fit(X,y)
darts_theorist.fit(X,y)

#experimentlist
X_new = model_disagreement_sample(X, [bms_theorist, darts_theorist], n)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

File details

Details for the file autora_experimentalist_model_disagreement-2.2.0.tar.gz.

File metadata

File hashes

Hashes for autora_experimentalist_model_disagreement-2.2.0.tar.gz
Algorithm Hash digest
SHA256 c110f18ba04fd3b64e8bc52de3e121dc671f31133a3cb5cf38fd61728ffb59b2
MD5 e2dd954c432a8658ab8016f514b7a2e1
BLAKE2b-256 f30287484422e77e8d6d2f0d2b35d6fb2508c243d39c3da74ae5a90f7b12f39d

See more details on using hashes here.

File details

Details for the file autora_experimentalist_model_disagreement-2.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for autora_experimentalist_model_disagreement-2.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9a290d67e86bf0b7bb1c364951ea8ac9a5766072f91fdc40506709c65d829a0a
MD5 3a021d948cfe9fea573392770e1abf2b
BLAKE2b-256 fcf3c881462aea9f4917cb6f9ec85da04deedef6aa2e82ea6dc2c32ada137e35

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page