Implementation:Evidentlyai Evidently Report Init

Knowledge Sources	Evidently Evidently Report Guide
Domains	ML_Monitoring, Evaluation
Last Updated	2026-02-14 12:00 GMT

Overview

Concrete constructor for configuring Evidently Report objects with metrics and presets provided by the Evidently library.

Description

Report.__init__() creates a report configuration by accepting a list of metrics/presets and optional metadata. The Report stores its configuration and defers computation to the run() method. Convenience parameters (model_id, reference_id, batch_size, dataset_id) are stored in the metadata dictionary.

Usage

Import the Report class and initialize it with a list of metrics or presets before calling run() with your datasets.

Code Reference

Source Location

• Repository: evidently
• File: src/evidently/core/report.py
• Lines: L820-901

Signature

class Report:
    def __init__(
        self,
        metrics: List[MetricOrContainer],
        metadata: Dict[str, MetadataValueType] = None,
        tags: List[str] = None,
        model_id: str = None,
        reference_id: str = None,
        batch_size: str = None,
        dataset_id: str = None,
        include_tests: bool = False,
    ):
        """
        Args:
            metrics: List of metrics or metric containers (presets) to include.
            metadata: Optional metadata key-value pairs.
            tags: Optional tags for categorizing reports.
            model_id: Optional model identifier (stored in metadata).
            reference_id: Optional reference identifier (stored in metadata).
            batch_size: Optional batch size identifier (stored in metadata).
            dataset_id: Optional dataset identifier (stored in metadata).
            include_tests: Whether to include automatic tests for metrics.
        """

Import

from evidently import Report
# or
from evidently.core.report import Report

I/O Contract

Inputs

Name	Type	Required	Description
metrics	List[MetricOrContainer]	Yes	Metrics and/or presets to compute
metadata	Dict[str, MetadataValueType]	No	Metadata key-value pairs
tags	List[str]	No	Tags for categorization
include_tests	bool	No	Enable auto-tests (default: False)
model_id	str	No	Model identifier (stored in metadata)

Outputs

Name	Type	Description
Report	Report	Configured report ready for run() execution

Usage Examples

Drift Monitoring Report

from evidently import Report
from evidently.metrics import ValueDrift, MissingValueCount
from evidently.metrics.dataset_statistics import DriftedColumnsCount

report = Report(
    metrics=[
        ValueDrift(column="age"),
        ValueDrift(column="salary"),
        DriftedColumnsCount(),
        MissingValueCount(column="age"),
    ]
)

Quality Report with Tests

from evidently import Report
from evidently.presets import ClassificationQuality

report = Report(
    metrics=[ClassificationQuality()],
    include_tests=True,
    model_id="fraud_detector_v2",
)

Related Pages

Implements Principle

• Principle:Evidentlyai_Evidently_Report_Configuration

Requires Environment

• Environment:Evidentlyai_Evidently_Python_Core_Environment