Skip to main content

Publish data for modeling (gold)

Time to complete: ~5 minutes
What you'll accomplish: Create a gold artifact that ML or Forecast can use in the training wizard.

Before you start
  • A bronze or silver dataset in Lake (/data)
  • Know your modeling goal: classification/regression (ML) or time series (Forecast)

Steps

  1. Sidebar → Lake → open bronze or silver table in the catalog.
  2. Click Publish gold (in the detail panel or row actions).
  3. Enter a gold artifact name.
  4. Select use case:
    • Machine learning — choose target column to predict
    • Forecast — choose time column; values must form a valid time series
  5. Click Validate — read errors in the dialog and fix source data if needed.
  6. Click Publish → artifact appears under Gold tab, status ready.

Start training from gold

ProductUI path
MLMachine LearningNew modelPublished dataset (Gold) → select artifact
ForecastForecast → new build → select gold forecast dataset
ShortcutGold detail → Start ML project / forecast equivalent (pre-fills wizard)

Requirements (verified in app)

Use caseMinimum rowsNotes
ML100Target column required; needs variation in the target
Forecast30Parseable datetime + numeric value column

Common mistakes

MistakeFix
Gold missing in ML wizardConfirm Gold tab shows ready and ML use case was enabled at publish
Validation failed (ML)Add rows (100+), fix target column, check dtypes
Validation failed (Forecast)Ensure datetime parses; value column is numeric
Skipped gold for "speed"Direct CSV upload in ML wizard is disabled — gold is required

Next steps