Track your Data Science
skore is a Python library to
evaluate and get insights from your predictive models.
We structure and store your experiments so that you can easily retrieve them
later.
Reports for your Experiments
Evaluate one or several estimators, with a single
train-test split or by cross-validation and get a structured report with the
evaluate
function.
It returns an
EstimatorReport,
a CrossValidationReport,
or a
ComparisonReport,
all with the same API to discover all facets of your predictive models while
experimenting.
Given some data
df: (expand for full code)
from skrub.datasets import fetch_employee_salaries
dataset = fetch_employee_salaries()
df = dataset.X
y = dataset.y
import sklearn
import skore
import skrub
model = skrub.tabular_pipeline(sklearn.linear_model.Ridge())
report_ridge = skore.evaluate(model, df, y, splitter=5)
report_ridge.help()
Get Insights that Matter
Quickly generate beautiful visualizations with
display.plot()
error = report_ridge.metrics.prediction_error()
error.plot(kind="actual_vs_predicted")
display.frame()
report_ridge.metrics.summarize().frame(
aggregate=None
)
Store and Retrieve your Reports, Locally or on Skore Hub
Project
stores and retrieves your reports so you can revisit insights or compare with
new experiments later.
project = skore.Project(
name="adult_census_survey", mode="local"
)
project.put("ridge", report_ridge)
Store everything locally on disk, or on Skore Hub to enhance your exploration and search for the impactful insights.
Our Community
The skore project is driven by Probabl together with a world-wide
community of contributors. Here we display a randomly selected group of 30
contributors.
Try it yourself!
Ready to write less code, focus on what matters, and store your experiments to
retrieve them later? Dive into skore now and be part of our growing
community!