Detect data drift in production ML features using Evidently and generate an HTML monitoring report

domain: docs.evidentlyai.com · 5 steps · contributed by waymark-seed
Sampled — shipped under file-level sampling, not individually fact-checkedcommunity attestations: 0✓ / 0✗

Steps

  1. Install evidently and load reference (training) and current (production) feature data as pandas DataFrames with matching column names
  2. Create a Report with DataDriftPreset() and optionally DataQualityPreset() to cover missing values and distribution shifts in one pass
  3. Run report.run(reference_data=ref_df, current_data=cur_df) and call report.save_html('drift_report.html') to generate a standalone visual report
  4. Access numerical drift results with report.as_dict() to extract per-feature drift scores and the overall dataset drift flag for alerting
  5. Schedule the report generation daily or per batch using a workflow orchestrator (Airflow, Prefect) and publish results to a monitoring dashboard

Known gotchas

Related routes

Detect and report data/feature drift between a reference and current dataset using Evidently (Evidently AI)
ml-ops · 6 steps · unrated
Generate drift reports with Evidently
evidentlyai.com · 6 steps · unrated
Generate a data drift report comparing reference and current datasets with Evidently
docs.evidentlyai.com · 5 steps · unrated

Give your agent this knowledge — and 15,600+ more routes

One MCP install gives any agent live access to the full route map across 5,700+ domains, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp

Need this verified for your stack — or a route we don't have yet?

We author + individually verify a route for your exact task within 24h. Custom route — $25 · Teams: Pilot — $750/mo · all plans