Local skore Project

This example shows how to use Project in local mode: store reports on your machine and inspect them. A key point is that summarize() returns a Summary, which is a pandas.DataFrame. In Jupyter you get an interactive widget, but you can always inspect and filter the summary as a DataFrame if you prefer.

Create a local project and store reports

We use a temporary directory as the workspace so the example is self-contained. In practice you can omit workspace to use the default (e.g. a skore/ directory in your user cache).

from pathlib import Path
from tempfile import TemporaryDirectory

from skore import Project

tmp_dir = TemporaryDirectory()
tmp_path = Path(tmp_dir.name)
project = Project("example-project", workspace=tmp_path)

from sklearn.datasets import load_breast_cancer
from sklearn.linear_model import LogisticRegression
from skrub import tabular_pipeline

X, y = load_breast_cancer(return_X_y=True, as_frame=True)
estimator = tabular_pipeline(LogisticRegression(max_iter=1_000))

import numpy as np
from sklearn.base import clone
from skore import evaluate

for regularization in np.logspace(-7, 7, 31):
    report = evaluate(
        clone(estimator).set_params(logisticregression__C=regularization),
        X,
        y,
        splitter=0.2,
        pos_label=1,
    )
    project.put(f"lr-regularization-{regularization:.1e}", report)

Summarize: you get a DataFrame

summarize() returns a Summary, which subclasses pandas.DataFrame. In a Jupyter environment it renders an interactive parallel-coordinates widget by default.

summary = project.summarize()

To see the normal DataFrame table instead of the widget (e.g. in scripts or when you prefer the table), wrap the summary in pandas.DataFrame:

import pandas as pd

pandas_summary = pd.DataFrame(summary)
pandas_summary

		key	date	learner	ml_task	report_type	dataset	rmse	log_loss	roc_auc	fit_time	predict_time	rmse_mean	log_loss_mean	roc_auc_mean	fit_time_mean	predict_time_mean
	id
0	313732898560805859928722544442124414154	lr-regularization-1.0e-07	2026-05-28T16:16:20.009889+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.682846	0.984122	0.108293	0.061876	None	None	None	None	None
1	319708312413119946939181119559865541416	lr-regularization-2.9e-07	2026-05-28T16:16:20.405147+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.682710	0.984122	0.093412	0.061999	None	None	None	None	None
2	127717063723287815399151605243545129468	lr-regularization-8.6e-07	2026-05-28T16:16:20.805834+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.682313	0.984122	0.099213	0.056119	None	None	None	None	None
3	223230287871378133934674701927433565491	lr-regularization-2.5e-06	2026-05-28T16:16:21.169675+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.681153	0.984122	0.092752	0.055237	None	None	None	None	None
4	14507951682390207113689379955260547499	lr-regularization-7.4e-06	2026-05-28T16:16:21.528443+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.677790	0.984122	0.084517	0.052158	None	None	None	None	None
5	300226254496485739586635923734371192674	lr-regularization-2.2e-05	2026-05-28T16:16:21.868098+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.668210	0.984122	0.084354	0.054411	None	None	None	None	None
6	177234224797364889299293539092679330105	lr-regularization-6.3e-05	2026-05-28T16:16:22.226993+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.642328	0.985075	0.090340	0.059115	None	None	None	None	None
7	67113183829976952181237015422302251597	lr-regularization-1.8e-04	2026-05-28T16:16:22.633087+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.581579	0.985392	0.101549	0.060517	None	None	None	None	None
8	219084124692606651420792931230965370619	lr-regularization-5.4e-04	2026-05-28T16:16:23.034466+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.476411	0.985710	0.101388	0.049223	None	None	None	None	None
9	67024902395835752917354603527124030461	lr-regularization-1.6e-03	2026-05-28T16:16:23.389526+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.355309	0.987615	0.081715	0.062378	None	None	None	None	None
10	20752087879896747978688749632412702547	lr-regularization-4.6e-03	2026-05-28T16:16:23.772851+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.252513	0.990156	0.107469	0.063545	None	None	None	None	None
11	14082501435874176114521512264340192398	lr-regularization-1.4e-02	2026-05-28T16:16:24.188989+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.178052	0.992379	0.102678	0.066004	None	None	None	None	None
12	141777081551180798461520805566704181350	lr-regularization-4.0e-02	2026-05-28T16:16:24.619023+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.128754	0.995872	0.112194	0.062332	None	None	None	None	None
13	54341517086876419648069300538352128450	lr-regularization-1.2e-01	2026-05-28T16:16:25.037410+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.098897	0.996189	0.110457	0.063259	None	None	None	None	None
14	224615846622658151498223983822987702862	lr-regularization-3.4e-01	2026-05-28T16:16:25.461543+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.083941	0.995872	0.104806	0.061729	None	None	None	None	None
15	152777121554859763738718529567249460444	lr-regularization-1.0e+00	2026-05-28T16:16:25.876931+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.080457	0.995554	0.107326	0.061778	None	None	None	None	None
16	107918063699044483721899120989866953001	lr-regularization-2.9e+00	2026-05-28T16:16:26.282436+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.089466	0.994601	0.107343	0.060852	None	None	None	None	None
17	39131909699945038850504752640150876932	lr-regularization-8.6e+00	2026-05-28T16:16:26.676369+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.104241	0.993649	0.097997	0.055797	None	None	None	None	None
18	235992571473643156109774361781410930764	lr-regularization-2.5e+01	2026-05-28T16:16:27.080408+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.121671	0.992379	0.109852	0.060203	None	None	None	None	None
19	145999848168980483191942623100998716999	lr-regularization-7.4e+01	2026-05-28T16:16:27.507324+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.142282	0.991426	0.105467	0.059415	None	None	None	None	None
20	210292647011529085782953848173331697946	lr-regularization-2.2e+02	2026-05-28T16:16:27.916287+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.162450	0.991426	0.110705	0.062459	None	None	None	None	None
21	241629102986980650640149058905305007542	lr-regularization-6.3e+02	2026-05-28T16:16:28.349872+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.204586	0.991108	0.117996	0.063509	None	None	None	None	None
22	298090923220712231661049497626346014907	lr-regularization-1.8e+03	2026-05-28T16:16:28.784167+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.291953	0.990473	0.123633	0.057950	None	None	None	None	None
23	294540002578425443189166775191868121412	lr-regularization-5.4e+03	2026-05-28T16:16:29.174410+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.471382	0.989838	0.095239	0.050757	None	None	None	None	None
24	194325738171446401574895152690470746001	lr-regularization-1.6e+04	2026-05-28T16:16:29.540095+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	0.796526	0.983169	0.106520	0.052886	None	None	None	None	None
25	288478942548281597877302950445912153631	lr-regularization-4.6e+04	2026-05-28T16:16:29.923090+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.133167	0.984757	0.112277	0.051120	None	None	None	None	None
26	304414933258766212318383365119810995285	lr-regularization-1.4e+05	2026-05-28T16:16:30.298989+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.229179	0.985551	0.113987	0.051754	None	None	None	None	None
27	333649163601906408947538943839928278621	lr-regularization-4.0e+05	2026-05-28T16:16:30.669417+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.276041	0.985869	0.109718	0.051825	None	None	None	None	None
28	321218574946143088662893273481516368100	lr-regularization-1.2e+06	2026-05-28T16:16:31.046404+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.447319	0.975865	0.109800	0.053340	None	None	None	None	None
29	71112058722600159588795706715095923095	lr-regularization-3.4e+06	2026-05-28T16:16:31.421597+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.448698	0.976500	0.110655	0.052064	None	None	None	None	None
30	61791457605704724819839680335272503200	lr-regularization-1.0e+07	2026-05-28T16:16:31.790039+00:00	LogisticRegression	binary-classification	estimator	9f4622fc73c9ccd9bc3725923827edeb	None	1.897034	0.976183	0.104509	0.048507	None	None	None	None	None

Basically, our summary contains metadata related to various information that we need to quickly help filtering the reports.

summary.info()

<class 'skore._project._summary.Summary'>
MultiIndex: 31 entries, (0, '313732898560805859928722544442124414154') to (30, '61791457605704724819839680335272503200')
Data columns (total 16 columns):
 #   Column             Non-Null Count  Dtype
---  ------             --------------  -----
 0   key                31 non-null     object
 1   date               31 non-null     object
 2   learner            31 non-null     category
 3   ml_task            31 non-null     object
 4   report_type        31 non-null     object
 5   dataset            31 non-null     object
 6   rmse               0 non-null      object
 7   log_loss           31 non-null     float64
 8   roc_auc            31 non-null     float64
 9   fit_time           31 non-null     float64
 10  predict_time       31 non-null     float64
 11  rmse_mean          0 non-null      object
 12  log_loss_mean      0 non-null      object
 13  roc_auc_mean       0 non-null      object
 14  fit_time_mean      0 non-null      object
 15  predict_time_mean  0 non-null      object
dtypes: category(1), float64(4), object(11)
memory usage: 5.3+ KB

Filter reports by metric (e.g. keep only those above a given accuracy) and work with the result as a table.

summary.query("log_loss < 0.1")["key"].tolist()

['lr-regularization-1.2e-01', 'lr-regularization-3.4e-01', 'lr-regularization-1.0e+00', 'lr-regularization-2.9e+00']

Use reports() to load the corresponding reports from the project (optionally after filtering the summary).

reports = summary.query("log_loss < 0.1").reports(return_as="comparison")
len(reports.reports_)

4

Since we got a ComparisonReport, we can use the metrics accessor to summarize the metrics across the reports.

reports.metrics.summarize().frame()

Estimator	LogisticRegression_1	LogisticRegression_2	LogisticRegression_3	LogisticRegression_4
Metric
Score	0.947368	0.964912	0.964912	0.964912
Accuracy	0.947368	0.964912	0.964912	0.964912
Precision	0.942029	0.970149	0.970149	0.970149
Recall	0.970149	0.970149	0.970149	0.970149
ROC AUC	0.996189	0.995872	0.995554	0.994601
Log loss	0.098897	0.083941	0.080457	0.089466
Brier score	0.027157	0.024990	0.025149	0.026218
Fit time (s)	0.110457	0.104806	0.107326	0.107343
Predict time (s)	0.057329	0.062241	0.060560	0.060325

_ = reports.metrics.roc().plot(subplot_by=None)

project.delete("example-project", workspace=tmp_path)
tmp_dir.cleanup()