Ranking

View source on Github

RankingPredictionLabel

Arize class to define the prediction arguments associated with the ranking model type

class RankingPredictionLabel(
    group_id: str # required
    rank: int # required
    score: Optional[float]
    label: Optional[str]
)

Argument	Data Type	Definitions
group_id	str	(Required) Name for ranking groups or lists in ranking models
rank	int	(Required) Name for rank of each element on the its group or list. The content of this column must be integer between 1-100.
score	float	(Optional) Numeric prediction score
label	str	(Optional) Categorical prediction score

RankingActualLabel

Arize class to define the ground truth arguments associated with the ranking model type

class RankingActualLabel(
    relevance_labels: Optional[List[str]]
    relevance_score: Optional[float]
)

Argument	Data Type	Description
relevance_labels	List[str]	(Optional) Categorical ground truth score
relevance_score	float	(Optional) Numeric Ground truth score

Code Example

from arize.utils.types import Environments, ModelTypes, Schema, RankingPredictionLabel, RankingActualLabel

pred_label = RankingPredictionLabel(
    group_id="A",
    rank=1,
    score=1.0,
    label="click",
)

act_label = RankingActualLabel(
    relevance_labels=["click", "save"],
    relevance_score=0.5,
)

response = arize.log(
    model_id="demo-ranking-single-log",
    model_version="v1",
    environment=Environments.PRODUCTION,
    model_type=ModelTypes.RANKING,
    prediction_id="123",
    prediction_label=pred_label,
    actual_label=act_label,
    features=features,
)