Custom Metrics Overview

Custom metrics offer the flexibility to define metrics that align precisely with your machine learning requirements. Whether it's tracking business KPIs, crafting specialized performance assessments, or computing weighted averages, custom metrics empower you to tailor measurements to your specific needs. Seamlessly integrate these custom metrics throughout the Fiddler platform, leveraging them in dashboards, alerting, and performance tracking.

Craft novel metrics by harnessing a blend of your model's existing dimensions and functions, employing a familiar query language called Fiddler Query Language (FQL) . This capability enables you to amalgamate features, metadata, predictions, and actual outcomes using a rich array of aggregations, operators, and metric functions, thereby expanding the depth of your analytical insights.

How to Define a Custom Metric

Craft bespoke metrics effortlessly with Fiddler's intuitive Excel-formula-like syntax. Once a custom metrics is defined, Fiddler distinguishes itself by seamlessly managing time granularity and ranges within the platform's charting, dashboarding and analytics experience. This empowers you to effortlessly adjust time ranges and granularities without the need to modify your query, ensuring a smooth and efficient analytical experience.

Fiddler Custom Metrics are constructed using the Fiddler Query Language (FQL).

📘

Custom metrics must return either:

1. an aggregate (produced by aggregate functions or built-in metric functions), or
2. a combination of aggregates

Let us illustrate further by providing a few examples.

Examples

Simple

Let’s say you wanted to create a custom metric for the following:

If an event is a false negative, assign a value of -40. If the event is a false positive, assign a value of -400. If the event is a true positive or true negative, then assign a value of 250.

We can formulate this metric using FQL with the following code:

average(if(fn(), -40, if(fp(), -400, 250)))

Fiddler offers convenience functions, like fp() and fn(). Alternatively, we could also identify false positives and false negatives the old fashioned way.

average(if(Prediction < 0.5 and Target == 1, -40, if(Prediction >= 0.5 and Target == 0, -400, 250)))

Here, we assume Prediction is the name of the output column for a binary classifier and Target is the name of our label column

Tweedie Loss

In our next example, we provide an example implementation of the Tweedie Loss Function. Here, Target is the name of the target column and Prediction is the name of the prediction/output column.

average((Target \* Prediction ^ (1 - 0.5)) / (1 - 0.5) + Prediction ^ (2 - 0.5) / (2 - 0.5))

Adding a Custom Metric

Note: To add a Custom Metric using the Python client, see fdl.CustomMetric

From the model schema page, you can access the model's custom metrics by clicking the Custom Metrics tab at the top of the page.

Then click Add Custom Metric to add a new Custom Metric.

Finally, enter the name, description, and FQL definition for your custom metric and click Save.

Accessing Custom Metrics in Charts and Alerts

After your custom metric is saved, it can be used in your chart and alert definitions.

Charts:

Alerts:

Modifying Custom Metrics

Since alerts can be set on Custom Metrics, making modifications to a metric may introduce inconsistencies in alerts.

🚧

Therefore, custom metrics cannot be modified once they are created.

If you'd like to try out a new metric, you can create a new one with a different name and definition.

Deleting Custom Metrics

To delete a custom metric using the Python client, see custom_metric.delete(). Alternatively, from the custom metrics tab, you can delete a metric by clicking the trash icon next to the metric.