Model introspection?

[Hummer311]

Hi. I followed along the tutorial without major issues. Thanks for providing those! They're really helpful.

I'm wondering if there exists a way to look "into" the trained model? I'm basically trying to figure out the key feature, i.e., the feature that has the biggest impact on the trained model.

---

Document Details

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

• ID: a30b3ff-b5e6-ff02-6f60-b5cef6f34666
• Version Independent ID: fdf962e2-620e-d9ad-5057-5f96f52dc60f
• Content: Use ML.NET to predict New York taxi fares (regression)
• Content Source: docs/machine-learning/tutorials/taxi-fare.md
• Product: dotnet-ml
• GitHub Login: @aditidugar
• Microsoft Alias: johalex

[JRAlexander]

@GalOshri, any thoughts?

[GalOshri]

It is not easy to view feature importance with the existing APIs, but the new APIs will make this possible. This is discussed here.

[Hummer311]

Thanks for the info, looking forward to the new API.

[mangeshw]

Can you update the tutorial with TaxiTripFarePrediction.FareAmount as string? Currently it appears as float. Below is the link:
Link: https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/taxi-fare

Also can you explain why is FareAmount's data type is different in TaxiTrip and TaxiTripFarePrediction?