scorer.py module

class Scorer

Bases: object

property model_url: str

URL or local FS path leading to Improve AI booster to be used with this scorer. Allows both raw xgboost files (most commonly having *.xgb extension) as well as gzipped boosters (*.xgb.gz). Can only be set during object initialization.

Returns:

model URL for this Scorer

Return type:

str

property chooser: XGBChooser

Chooser object (for more info please check Chooser tab -> XGBChooser class) for this scorer. Can only be set during object initialization.

Returns:

a chooser object for this Scorer

Return type:

XGBChooser

property TIEBREAKER_MULTIPLIER: float

Small float value used to randomize model’s scores (random numbers sampled uniformly from [0, 1) are multiplied by TIEBREAKER_MULTIPLIER and added to scores)

Returns:

Small float value used to randomize model’s scores

Return type:

float

__init__(model_url)

Init with params

Parameters:

model_url (str) – URL or local FS of a plain or gzip compressed Improve AI model resource

score(items, context=None)

Uses the model to score a list of items with the given context

Parameters:
  • items (list or tuple or np.ndarray) – list of items to be scored

  • context (object) – any JSON encodable extra context info that will be used with each of the item to get its score

Returns:

an array of float64 (double) values representing the scores of the items.

Return type:

np.ndarray