Implementation:Evidentlyai Evidently RegressionQuality Preset

Knowledge Sources	Evidently Evidently Regression
Domains	ML_Evaluation, Regression
Last Updated	2026-02-14 12:00 GMT

Overview

Concrete preset container for computing regression quality metrics provided by the Evidently library.

Description

RegressionQuality is a MetricContainer that expands into individual regression metrics (MeanError, MAPE, RMSE, MAE, R2Score, AbsMaxError) plus optional visualizations (predicted vs actual, error plot, error distribution).

Usage

Include in a Report metrics list when evaluating regression model performance.

Code Reference

Source Location

• Repository: evidently
• File: src/evidently/presets/regression.py
• Lines: L36-90

Signature

class RegressionQuality(MetricContainer):
    def __init__(
        self,
        pred_actual_plot: bool = False,
        error_plot: bool = False,
        error_distr: bool = False,
        mean_error_tests: MeanStdMetricsPossibleTests = None,
        mape_tests: MeanStdMetricsPossibleTests = None,
        rmse_tests: GenericSingleValueMetricTests = None,
        mae_tests: MeanStdMetricsPossibleTests = None,
        r2score_tests: GenericSingleValueMetricTests = None,
        abs_max_error_tests: GenericSingleValueMetricTests = None,
        include_tests: bool = True,
        regression_name: str = "default",
    ):

Import

from evidently.presets import RegressionQuality

I/O Contract

Inputs

Name	Type	Required	Description
regression_name	str	No	Task name matching DataDefinition (default: "default")
pred_actual_plot	bool	No	Show predicted vs actual plot
error_plot	bool	No	Show error plot
error_distr	bool	No	Show error distribution
include_tests	bool	No	Enable auto-tests (default: True)

Outputs (Expanded Metrics)

Metric	Type	Description
MeanError	float	Average prediction error (mean and std)
MAPE	float	Mean absolute percentage error
RMSE	float	Root mean squared error
MAE	float	Mean absolute error
R2Score	float	Coefficient of determination
AbsMaxError	float	Absolute maximum error

Usage Examples

from evidently import Report, Dataset, DataDefinition
from evidently.core.datasets import Regression
from evidently.presets import RegressionQuality

data_def = DataDefinition(
    regression=[Regression(target="price", prediction="predicted_price")]
)

report = Report([RegressionQuality(pred_actual_plot=True)], include_tests=True)
snapshot = report.run(
    Dataset.from_pandas(df_current, data_def),
    Dataset.from_pandas(df_reference, data_def),
)
snapshot.save_html("regression_report.html")

Related Pages

Implements Principle

• Principle:Evidentlyai_Evidently_Regression_Quality_Evaluation