Skip to main content

Tiny sklearn-based AutoML tool.

Project description

tiresia

Installation

pip install tiresia

Description

tiresia is just a wrapper around scikit-learn GridSearchCV. The idea is to simplify the model testing workflow. With tiresia you can choose which models to test and to exclude and provide a param_grid for the ones you want to explore deeper, while keeping the parameters of the less interesting ones on default.

Example

from tiresia.predictor import AutoPredictor

from sklearn.datasets import make_regression, make_classification
from sklearn.model_selection import train_test_split
from sklearn.metrics import roc_auc_score, r2_score

test_type = "regressor"

if test_type == "classifier":
    train, target = make_classification(5000, 20)
elif test_type == "regressor":
    train, target = make_regression(5000, 20)

x_train, x_test, y_train, y_test = train_test_split(train, target, test_size=0.3)

autopred = AutoPredictor(estimator_type=test_type,
                         scoring=r2_score,
                         greater_is_better=True)
autopred.fit(x_train, y_train, x_test, y_test)

predictions = autopred.predictions
results     = autopred.results

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

tiresia-0.0.1.tar.gz (3.7 kB view hashes)

Uploaded Source

Built Distribution

tiresia-0.0.1-py3-none-any.whl (4.8 kB view hashes)

Uploaded Python 3

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