Arize AI
Search…
5. Prediction ID
An ID specific to a model that indicates a unique prediction event.

Overview

Prediction ID is an ID that should indicate a unique prediction event. It is used as a join key between prediction and actual.
If an actual does not have its prediction_id field match a previously sent prediction_id of a prediction, the actual will not be displayed even if it is received by Arize.
Transaction ID acts as Prediction ID to join the prediction "not fraud" with the actual "fraud"
Arize looks back 14 calendar days to match an actual to its corresponding prediction.

Code Example

1
# Declare the schema of the dataframe you're sending (feature columns, predictions, timestamp, actuals)
2
schema = Schema(
3
prediction_id_column_name="prediction_id",
4
...
5
)
6
7
# Log the dataframe with the schema mapping
8
response = arize_client.log(
9
model_id="sample-model-1",
10
model_version= "v1",
11
model_type=ModelTypes.SCORE_CATEGORICAL,
12
environment=Environments.PRODUCTION,
13
dataframe=test_dataframe,
14
schema=schema,
15
)
Copied!

FAQ

1. What happens if we upload the same data with the same prediction ID twice? Does Arize treat that as one prediction/observation or as two?
They are treated as separate observations. This would mean that 2 predictions sent with the same prediction ID would count as 2 predictions. If there was an actual sent for both 2 predictions, it would show up as 2 separate predictions with both having a corresponding matching actual.
Questions? Email us at [email protected] or Slack us in the #arize-support channel
Copy link