Distinguish between Calibrated and NonCalibrated methods

[natke]

When would I use one versus the other?

---

Document Details

⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.

• ID: b147624e-e01f-679a-900c-37f48f9d9e15
• Version Independent ID: 55d26134-c3a9-3a4f-5833-2f9b1dc8e0b1
• Content: BinaryClassificationCatalog.CrossValidateNonCalibrated(IDataView, IEstimator<ITransformer>, Int32, String, String, Nullable<Int32>) Method (Microsoft.ML)
• Content Source: dotnet/xml/Microsoft.ML/BinaryClassificationCatalog.xml
• Product: dotnet-ml-api
• GitHub Login: @sfilipi
• Microsoft Alias: johalex

[wschin]

Calibrated means you want to see probabilities. Noncalibrated doesn't provide probability.

[natke]

Yep @wschin. Can we clarify that in the method documentation please

[wschin]

I guess we can add a new markdown file and include it in all calibrated/uncalibrated estimators?