### Run All Examples

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Execute all examples to verify that new changes do not impact existing ones. Navigate to the sphinx directory before running.

```bash
cd sphinx && make html
```

--------------------------------

### Install skore with Sphinx Dependencies

Source: https://github.com/probabl-ai/skore/blob/main/examples/README.txt

Install the skore library along with the necessary dependencies for running the documentation examples, which include Sphinx.

```bash
pip install -U skore[sphinx]
```

--------------------------------

### Run Individual Example

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Execute a single example file to test specific functionality. Replace <example_file> with the actual file name.

```bash
python <example_file>
```

--------------------------------

### Build Docs Without Examples

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Build the documentation while skipping the execution of examples, which can be time-consuming.

```bash
make html-noplot
```

--------------------------------

### Gallery Examples

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/class_with_accessors.rst

Illustrative examples demonstrating the usage of the class and its methods.

```APIDOC
## Gallery Examples

This section provides practical examples of how to use the class and its associated methods. These examples are designed to help users understand the functionality and integrate it into their projects.
```

--------------------------------

### Install skore with LTS CPU Support

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Install skore with Long-Term Support (LTS) CPU support for older CPU architectures. This is an alternative installation command if the default one causes issues.

```bash
make install-skore-lts-cpu
```

--------------------------------

### Load Example Data

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Loads a sample dataset for use in Skore.

```python
from skore.datasets import load_iris
df = load_iris()
```

--------------------------------

### Install Skore with Pip and Hub Support

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/install.rst

Install Skore with additional support for interacting with Skore Hub. Requires Python 3.10+.

```bash
pip install -U skore[hub]
```

--------------------------------

### Install Skore with Pip

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/install.rst

Use this command to install the base Skore library locally. Ensure you have Python 3.10 or higher.

```bash
pip install -U skore
```

--------------------------------

### Install Skore with Pip and MLflow Persistence

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/install.rst

Install Skore with support for persisting projects in MLflow. Requires Python 3.10+.

```bash
pip install -U skore[mlflow]
```

--------------------------------

### Install Skore with Conda

Source: https://github.com/probabl-ai/skore/blob/main/README.md

Install Skore using conda from the conda-forge channel. This command installs Skore for both local use and interaction with Skore Hub.

```bash
conda install conda-forge::skore
```

--------------------------------

### Install Skore with Pip

Source: https://github.com/probabl-ai/skore/blob/main/README.md

Install the Skore library using pip. Choose the appropriate command based on whether you need local functionality, Hub interaction, or MLflow logging.

```bash
pip install -U skore
```

```bash
pip install -U skore[hub]
```

```bash
pip install -U skore[mlflow]
```

--------------------------------

### Install skore Development Dependencies

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Install the necessary development dependencies for skore, including pre-commit hooks. This command should be re-executed after rebasing your branch with main.

```bash
make install-skore
```

--------------------------------

### Generate ML Pipeline Insights with Skore

Source: https://github.com/probabl-ai/skore/blob/main/README.md

Use Skore's CrossValidationReport to evaluate a model and obtain structured insights. Requires scikit-learn and skore to be installed. The report object provides methods to access metrics and visualizations.

```python
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from skore import CrossValidationReport

X, y = make_classification(n_classes=2, n_samples=100_000, n_informative=4)
clf = LogisticRegression()

# Get structured insights that matter for your use case
cv_report = CrossValidationReport(clf, X, y)

# See what insights are available
cv_report.help()

# Example: Access the metrics summary
metrics_summary = cv_report.metrics.summarize().frame()

# Example: Get the ROC curve
roc_plot = cv_report.metrics.roc()
roc_plot.plot()
```

--------------------------------

### Get Raw Data Frame

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Retrieves the raw data used for generating reports.

```python
from skore.datasets import load_iris
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate, display
df = load_iris()
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
frame = display.frame(report)
```

--------------------------------

### Customize Roc Curve Display Style

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/displays.rst

Customizes the appearance of the RocCurveDisplay before plotting. This example specifically modifies the style of the chance level line.

```python
display.set_style(
    chance_level_kwargs=dict(linestyle="-", linewidth=5, color="tab:purple")
)
display.plot()
```

--------------------------------

### CrossValidationReport.data

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Accessor to get insights about the dataset used in the cross-validation.

```APIDOC
class CrossValidationReport:
    @property
    def data(self):
        """Accessor to get insights about the dataset used in the cross-validation."""
        pass
```

--------------------------------

### Build Documentation Locally

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Build the project documentation locally. Navigate to the sphinx directory before running.

```bash
cd sphinx
make html
```

--------------------------------

### Create skore Projects in Different Modes

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/project.rst

Demonstrates initializing a skore Project for local persistence, skore hub communication, and MLflow experiment tracking. Ensure skore.login() is called before using the 'hub' mode.

```python
from pathlib import Path
from skore import Project

# Local persistence
project_local = Project(name="my-xp", mode="local", workspace=Path("/tmp/skore"))

# Skore Hub (requires skore.login() first)
project_hub = Project(name="my-xp", mode="hub", workspace="my-workspace")

# MLflow experiment
project_mlflow = Project(
    name="my-experiment",
    mode="mlflow",
    tracking_uri="http://localhost:5000",
)
```

--------------------------------

### Access Local Documentation

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Open the locally built documentation in your web browser.

```bash
open build/html/index.html
```

--------------------------------

### Clone Repository and Set Up Remotes

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Clone your fork of the skore repository and add the original repository as an upstream remote. This is a standard first step for contributing.

```bash
git clone https://github.com/YOUR_USERNAME/skore.git

cd skore

git remote add upstream https://github.com/probabl-ai/skore.git
```

--------------------------------

### Run Pre-commit Hooks

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Manually execute all pre-commit hooks to check code quality before committing changes.

```bash
pre-commit run --all-files
```

--------------------------------

### Run Linter

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Ensure code is formatted correctly according to project standards using the ruff linter.

```bash
make lint
```

--------------------------------

### Display Help Information

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/displays.rst

Interactively displays the available attributes and methods of a skore display object. This is useful for exploring the capabilities of a display.

```python
display.help()
```

--------------------------------

### Utilities

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/index.rst

Utility functions and objects for skore.

```APIDOC
## configuration

### Description
Global configuration for `skore` also usable as a context manager.

## show_versions

### Description
Print version information for skore and its dependencies.

```

--------------------------------

### Define a Multi-Step Task Plan

Source: https://github.com/probabl-ai/skore/blob/main/AGENTS.md

Use this format to outline a plan for multi-step tasks, specifying the action and verification step for each stage. This helps in defining clear success criteria.

```plaintext
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
```

--------------------------------

### login

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/project.rst

Logs into the Skore system. This function is essential for authenticating and gaining access to project management functionalities.

```APIDOC
## login

### Description
Logs into the Skore system. This function is essential for authenticating and gaining access to project management functionalities.

### Method
Not specified (likely a function call in the SDK)

### Endpoint
Not applicable (SDK function)

### Parameters
Not specified in the source text.

### Request Example
Not specified in the source text.

### Response
Not specified in the source text.
```

--------------------------------

### Project Management Functions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/index.rst

Functions and classes related to managing skore projects and logging in.

```APIDOC
## Project

### Description
Main class for managing a skore project and its reports.

## login

### Description
Login to remote backend (e.g. Skore Hub) to later use the project management features.

```

--------------------------------

### Run Local Tests

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Execute all unit tests locally to ensure code quality and feature correctness.

```bash
make test
```

--------------------------------

### Project Class

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/project.rst

Represents a Skore project, providing methods to interact with project data and reports.

```APIDOC
## Project

### Description
Represents a Skore project, providing methods to interact with project data and reports.

### Methods

#### Project.put

##### Description
Stores or updates project data.

##### Method
Not specified (likely a method call on a Project object)

##### Endpoint
Not applicable (SDK method)

#### Project.get

##### Description
Retrieves project data.

##### Method
Not specified (likely a method call on a Project object)

##### Endpoint
Not applicable (SDK method)

#### Project.summarize

##### Description
Generates a summary of the project's reports, returning a Summary object.

##### Method
Not specified (likely a method call on a Project object)

##### Endpoint
Not applicable (SDK method)

#### Project.delete

##### Description
Deletes the project.

##### Method
Not specified (likely a method call on a Project object)

##### Endpoint
Not applicable (SDK method)
```

--------------------------------

### Accessor Methods

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/autosummary/accessor.rst

This section lists the methods available through the accessor. Each method is described with a brief explanation.

```APIDOC
## Accessor Methods

Here are the methods that are available through this accessor:

- :func:`~objname.method_name` -- method_doc
```

--------------------------------

### Summarize Project Reports

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Generates an HTML summary of reports within a Skore project.

```python
from skore.datasets import load_iris
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate, Project
df = load_iris()
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
project = Project(path="./my_project")
project.put(report, name="my_ridge_report")
summary = project.summary()
```

--------------------------------

### Store Report Locally

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Saves a report to the local file system using the Project class.

```python
from skore.datasets import load_iris
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate, Project
df = load_iris()
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
project = Project(path="./my_project")
project.put(report, name="my_ridge_report")
```

--------------------------------

### Create an Estimator Report

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Generates a report for a single estimator with a train-test split.

```python
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
```

--------------------------------

### Set global ignore list for checks

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/automated_checks.rst

Configure a global ignore list for automated checks by assigning a list of check codes to skore.configuration.ignore_checks.

```python
from skore import configuration
configuration.ignore_checks = ["SKD001"]
```

--------------------------------

### EstimatorReport.help

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Provides help information for the EstimatorReport class.

```APIDOC
## EstimatorReport.help

### Description
Provides help information for the EstimatorReport class.

### Method
N/A (Method call)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### ComparisonReport Methods

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/comparison_report.rst

Provides access to various methods for managing and creating reports within the ComparisonReport class.

```APIDOC
## ComparisonReport Methods

### Description
Provides access to various methods for managing and creating reports within the ComparisonReport class.

### Methods
- **help()**: Displays help information for the ComparisonReport.
- **cache_predictions()**: Caches predictions for the report.
- **clear_cache()**: Clears the cached predictions for the report.
- **create_estimator_report()**: Creates an estimator report.
- **get_predictions()**: Retrieves the predictions for the report.
```

--------------------------------

### Display Classes

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/index.rst

Classes for visualizing various reports and metrics.

```APIDOC
## TableReportDisplay

### Description
Display for tabular data reports.

## MetricsSummaryDisplay

### Description
Display for summarizing multiple metrics.

## ConfusionMatrixDisplay

### Description
Confusion matrix visualization.

## RocCurveDisplay

### Description
ROC (Receiver Operating Characteristic) curve visualization.

## PrecisionRecallCurveDisplay

### Description
Precision-Recall curve visualization.

## PredictionErrorDisplay

### Description
Prediction error visualization.

## CoefficientsDisplay

### Description
Display for visualizing feature importance via model coefficients.

## ImpurityDecreaseDisplay

### Description
Display for visualizing feature importance via Mean Decrease in Impurity (MDI).

## PermutationImportanceDisplay

### Description
Display for visualizing feature importance via permutation importance.

## ChecksSummaryDisplay

### Description
Display for check results returned by the ``checks`` accessor.

## Check

### Description
Protocol for defining custom checks.

## CheckNotApplicable

### Description
Exception raised when a check cannot run on the given report.

```

--------------------------------

### ConfusionMatrixDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the ConfusionMatrixDisplay, used to visualize confusion matrices.

```APIDOC
## ConfusionMatrixDisplay

### Description
API for the ConfusionMatrixDisplay, used to visualize confusion matrices.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### Display

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

General API for the Display class, serving as a base for all display types.

```APIDOC
## Display

### Description
General API for the Display class, serving as a base for all display types.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### Store Report on Skore Hub

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Saves a report to Skore Hub for remote access and collaboration.

```python
from skore.datasets import load_iris
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate, Project
df = load_iris()
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
project = Project(hub=True)
project.put(report, name="my_ridge_report")
```

--------------------------------

### ML Assistance Functions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

Functions that build upon scikit-learn's functionality to assist in ML/DS project development.

```APIDOC
## skore ML Assistance Functions

### Description
These functions provide utilities for ML development, building upon scikit-learn.

### Functions
- `evaluate`: Evaluate ML models.
- `compare`: Compare ML models.
- `TrainTestSplit`: Split data into training and testing sets.
```

--------------------------------

### Run checks in fast mode

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/automated_checks.rst

Skip expensive checks that require model refits or permutation predictions by setting 'fast_mode=True'. Cached results from slow checks are still displayed.

```python
report.checks.summarize(fast_mode=True)
```

--------------------------------

### CrossValidationReport.help

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Provides help information for the CrossValidationReport.

```APIDOC
def help(self):
    """Provides help information for the CrossValidationReport."""
    pass
```

--------------------------------

### Fetch and Display GitHub Contributors

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/index.html

This JavaScript code fetches contributors from the GitHub API, shuffles them, selects the first 30, and displays them on the page. It requires an HTML element with the ID 'contributors-list' to render the contributor information.

```javascript
function shuffleArray(array) { for (let i = array.length - 1; i > 0; i--) { const j = Math.floor(Math.random() * (i + 1)); // random index from 0 to i [array[i], array[j]] = [array[j], array[i]]; // swap elements } return array; }
function selectFirst30(array) { // Shuffle the array shuffleArray(array); // Return the first 30 elements return array.slice(0, 30); }
async function fetchContributors() { const response = await fetch('https://api.github.com/repos/probabl-ai/skore/contributors?per_page=100'); var contributors = await response.json(); contributors = selectFirst30(contributors)
const contributorsList = document.getElementById('contributors-list'); contributors.forEach(contributor => { const contributorElement = document.createElement('div'); contributorElement.classList.add('contributor'); contributorElement.innerHTML = ` <a href="${contributor.html_url}" target="_blank"> <img src="${contributor.avatar_url}" alt="${contributor.login}"> <div class="contributor-name">${contributor.login}</div> </a> `; contributorsList.appendChild(contributorElement); }); // Add "And many more" link as the last element
const andMoreElement = document.createElement('div'); andMoreElement.classList.add('more-contributors'); andMoreElement.innerHTML = ` <a href="https://github.com/probabl-ai/skore/graphs/contributors" target="_blank"> And many more → </a> `; contributorsList.appendChild(andMoreElement); }
fetchContributors();
```

--------------------------------

### MetricsSummaryDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the MetricsSummaryDisplay, used for summarizing various metrics.

```APIDOC
## MetricsSummaryDisplay

### Description
API for the MetricsSummaryDisplay, used for summarizing various metrics.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### Create a New Branch for an Issue

Source: https://github.com/probabl-ai/skore/blob/main/CONTRIBUTING.rst

Create a new Git branch to work on a specific issue. This helps in organizing your work and keeping it separate from the main development line.

```bash
git checkout -b issue-NAME_OF_ISSUE
```

--------------------------------

### Visualization Displays

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

A set of displays available through the different reports for visualization.

```APIDOC
## skore Visualization Displays

### Description
A set of displays are available through the different reports. Find in this section the API of each display.
```

--------------------------------

### Create a Cross-Validation Report

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Generates a report using cross-validation for more robust evaluation.

```python
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, y_train, cv=5)
```

--------------------------------

### ImpurityDecreaseDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the ImpurityDecreaseDisplay, used to visualize impurity decrease.

```APIDOC
## ImpurityDecreaseDisplay

### Description
API for the ImpurityDecreaseDisplay, used to visualize impurity decrease.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### CoefficientsDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the CoefficientsDisplay, used to visualize model coefficients.

```APIDOC
## CoefficientsDisplay

### Description
API for the CoefficientsDisplay, used to visualize model coefficients.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### ComparisonReport

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

Provides comprehensive capabilities for comparing EstimatorReport or CrossValidationReport instances and reporting the results.

```APIDOC
## skore.ComparisonReport

### Description
Provides comprehensive capabilities for comparing :class:`skore.EstimatorReport` or :class:`skore.CrossValidationReport` instances, and reporting the results.
```

--------------------------------

### Summary Class

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/project.rst

Holds metadata and metrics of stored reports, providing methods for data access and analysis.

```APIDOC
## Summary

### Description
Holds metadata and metrics of stored reports, providing methods for data access and analysis. This object is returned by `Project.summarize` and should not be instantiated directly.

### Methods

#### Summary.frame

##### Description
Provides access to the report metadata and metrics as a pandas DataFrame.

##### Method
Not specified (likely a method call on a Summary object)

##### Endpoint
Not applicable (SDK method)

#### Summary.query

##### Description
Allows filtering and retrieval of reports based on specified criteria.

##### Method
Not specified (likely a method call on a Summary object)

##### Endpoint
Not applicable (SDK method)

#### Summary.compare

##### Description
Enables comparison of reports.

##### Method
Not specified (likely a method call on a Summary object)

##### Endpoint
Not applicable (SDK method)
```

--------------------------------

### Retrieve Display Data as DataFrame

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/displays.rst

Retrieves the underlying data used for generating the plot as a pandas DataFrame. The `head()` method is then used to display the first few rows of this DataFrame.

```python
df = display.frame()
df.head()
```

--------------------------------

### Plot Error Metrics

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/landing.html

Generates a visualization of error metrics from a report.

```python
from skore.datasets import load_iris
from skore.model_selection import train_test_split
from sklearn.linear_model import Ridge
from skore import evaluate, display
df = load_iris()
X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df.target, test_size=0.2, random_state=42)
report = evaluate(Ridge(), X_train, X_test, y_train, y_test)
fig = display.plot(report, 'error')
```

--------------------------------

### Generate and Plot ROC Curve Display

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/displays.rst

Generates a classification dataset, trains a Logistic Regression model, and then evaluates it to obtain a RocCurveDisplay object. This display can then be plotted.

```python
from sklearn.datasets import make_classification
from sklearn.linear_model import LogisticRegression
from skore import evaluate

X, y = make_classification(
    n_samples=10_000,
    n_classes=3,
    class_sep=0.3,
    n_clusters_per_class=1,
    random_state=42,
)
report = evaluate(LogisticRegression(), X, y, splitter=5)
display = report.metrics.roc()
display.plot()
```

--------------------------------

### EstimatorReport.metrics

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Accessor for evaluating the statistical performance of the estimator.

```APIDOC
## EstimatorReport.metrics

### Description
The `metrics` accessor helps evaluate the statistical performance of the estimator.

### Method
N/A (Accessor)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### PermutationImportanceDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the PermutationImportanceDisplay, used to visualize permutation importance.

```APIDOC
## PermutationImportanceDisplay

### Description
API for the PermutationImportanceDisplay, used to visualize permutation importance.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### EstimatorReport

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

Provides comprehensive reporting capabilities for individual scikit-learn estimators.

```APIDOC
## skore.EstimatorReport

### Description
Provides comprehensive reporting capabilities for individual scikit-learn estimators, including metrics, visualizations, and evaluation tools.
```

--------------------------------

### ComparisonReport Accessors

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/comparison_report.rst

Provides access to different aspects of the ComparisonReport, including metrics, inspection, and checks.

```APIDOC
## ComparisonReport Accessors

### Description
Provides access to different aspects of the ComparisonReport, including metrics, inspection, and checks.

### Accessors
- **checks**: Accessor for running automated checks for common modeling problems.
- **inspection**: Accessor for inspecting the model, such as evaluating feature importance.
- **metrics**: Accessor for evaluating the statistical performance of compared estimators, including plotting capabilities.
```

--------------------------------

### Class Members

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/class_with_accessors.rst

This section lists the public members of the class, including methods and attributes that are intended for direct use by developers. It excludes internal implementation details like metrics, inspection, reports, data, and checks.

```APIDOC
## Class Documentation

This documentation covers the public interface of the class.

### Members

The following members are accessible to users:

- `__call__`: Special method for callable instances.

*Note: Members like `metrics`, `inspection`, `reports`, `data`, and `checks` are excluded as they are considered internal implementation details.*
```

--------------------------------

### PrecisionRecallCurveDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the PrecisionRecallCurveDisplay, used to visualize Precision-Recall curves.

```APIDOC
## PrecisionRecallCurveDisplay

### Description
API for the PrecisionRecallCurveDisplay, used to visualize Precision-Recall curves.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### EstimatorReport.checks

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Accessor for running automated checks to identify common modeling problems.

```APIDOC
## EstimatorReport.checks

### Description
The `checks` accessor runs automated checks to identify common modeling problems such as overfitting and underfitting.

### Method
N/A (Accessor)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### PredictionErrorDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the PredictionErrorDisplay, used to visualize prediction errors.

```APIDOC
## PredictionErrorDisplay

### Description
API for the PredictionErrorDisplay, used to visualize prediction errors.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### CrossValidationReport.create_estimator_report

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Creates a report for the estimator.

```APIDOC
def create_estimator_report(self):
    """Creates a report for the estimator."""
    pass
```

--------------------------------

### CrossValidationReport.checks

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Accessor to run automated checks for common modeling problems.

```APIDOC
class CrossValidationReport:
    @property
    def checks(self):
        """Accessor to run automated checks for common modeling problems."""
        pass
```

--------------------------------

### EstimatorReport.data

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Accessor for insights about the dataset used for training and testing the estimator.

```APIDOC
## EstimatorReport.data

### Description
The `data` accessor provides insights into the dataset used for training and testing the estimator.

### Method
N/A (Accessor)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### CrossValidationReport

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

Provides comprehensive capabilities for evaluating scikit-learn estimators by cross-validation and reporting the results.

```APIDOC
## skore.CrossValidationReport

### Description
Provides comprehensive capabilities for evaluating scikit-learn estimators by cross-validation, and reporting the results.
```

--------------------------------

### Accessor Callable Invocation

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/_templates/autosummary/accessor_callable.rst

Details the invocation of an accessor callable object, typically used for accessing attributes or methods within a module.

```APIDOC
## Accessor Callable Invocation

### Description
This section documents the invocation of an accessor callable object. Accessor callables are often used to provide a direct way to access underlying functionality or data within a module.

### Method
Callable

### Endpoint
N/A (SDK/Library Interface)

### Parameters
This method does not explicitly define parameters in the provided source. Parameters would be specific to the underlying functionality being accessed.

### Request Example
N/A (SDK/Library Interface)

### Response
N/A (SDK/Library Interface - response depends on the specific callable)
```

--------------------------------

### TableReportDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the TableReportDisplay, used to display tabular data within reports.

```APIDOC
## TableReportDisplay

### Description
API for the TableReportDisplay, used to display tabular data within reports.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### CrossValidationReport.metrics

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Accessor to evaluate the statistical performance of the estimator across cross-validation splits.

```APIDOC
class CrossValidationReport:
    @property
    def metrics(self):
        """Accessor to evaluate the statistical performance of the estimator across cross-validation splits."""
        pass
```

--------------------------------

### RocCurveDisplay

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/displays.rst

API for the RocCurveDisplay, used to visualize Receiver Operating Characteristic (ROC) curves.

```APIDOC
## RocCurveDisplay

### Description
API for the RocCurveDisplay, used to visualize Receiver Operating Characteristic (ROC) curves.

### Method
N/A (Class/Object)

### Endpoint
N/A (Class/Object)

### Parameters
N/A (Class/Object)

### Request Example
N/A (Class/Object)

### Response
N/A (Class/Object)
```

--------------------------------

### Ignore checks per call

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/automated_checks.rst

Mute specific checks for a single call to summarize by providing a list of check codes to the 'ignore' parameter.

```python
report.checks.summarize(ignore=["SKD001"])
```

--------------------------------

### EstimatorReport.get_predictions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Retrieves the cached predictions for the estimator.

```APIDOC
## EstimatorReport.get_predictions

### Description
Retrieves the cached predictions for the estimator. If predictions are not cached, they may be computed.

### Method
N/A (Method call)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### Checks Classes

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/index.rst

Classes used by the ``checks`` accessor on reports.

```APIDOC
## skore Checks

### Description
Checks classes used by the ``checks`` accessor on reports.

### Classes
- `ChecksSummaryDisplay`: Display for check summaries.
- `Check`: Represents a single check.
- `CheckNotApplicable`: Exception for checks that are not applicable.
```

--------------------------------

### EstimatorReport.inspection

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Accessor for inspecting the model, e.g., evaluating feature importance.

```APIDOC
## EstimatorReport.inspection

### Description
The `inspection` accessor helps inspect the model, for example, by evaluating the importance of features.

### Method
N/A (Accessor)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### CrossValidationReport.get_predictions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Retrieves the predictions from the cross-validation.

```APIDOC
def get_predictions(self):
    """Retrieves the predictions from the cross-validation."""
    pass
```

--------------------------------

### CrossValidationReport.inspection

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Accessor to inspect the model, e.g., evaluating feature importance.

```APIDOC
class CrossValidationReport:
    @property
    def inspection(self):
        """Accessor to inspect the model, e.g., evaluating feature importance."""
        pass
```

--------------------------------

### EstimatorReport.cache_predictions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Caches the predictions made by the estimator.

```APIDOC
## EstimatorReport.cache_predictions

### Description
Caches the predictions made by the estimator for future use.

### Method
N/A (Method call)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### Plot Roc Curve Display

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/user_guide/displays.rst

Plots the RocCurveDisplay object. In Jupyter environments, this will automatically render the plot. In scripts, the returned figure may need to be explicitly shown.

```python
display.plot()
```

--------------------------------

### EstimatorReport.clear_cache

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/estimator_report.rst

Clears the cached predictions for the estimator.

```APIDOC
## EstimatorReport.clear_cache

### Description
Clears any previously cached predictions associated with the estimator.

### Method
N/A (Method call)

### Endpoint
N/A

### Parameters
N/A

### Request Example
N/A

### Response
N/A
```

--------------------------------

### CrossValidationReport.clear_cache

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Clears the cached predictions.

```APIDOC
def clear_cache(self):
    """Clears the cached predictions."""
    pass
```

--------------------------------

### CrossValidationReport.cache_predictions

Source: https://github.com/probabl-ai/skore/blob/main/sphinx/reference/report/cross_validation_report.rst

Caches the predictions made during cross-validation.

```APIDOC
def cache_predictions(self):
    """Caches the predictions made during cross-validation."""
    pass
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.