WeightsBagging

ModelAggregation

The function calculates the weights of each model in the ensemble.

Parameters:

• models_dict: dict
  Dictionary of LogitModel() instances.
• metric: str, {'gini', 'auc', 'f1', 'brier'}
  Metric for calculating weighted average.
• check_sample: str, {'test', 'train'}
  Sample to calculate metrics for averaging.

Returns:

• weights_dict: dict
  A dictionary with weights for each model in the ensemble.

Exceptions:

• ValueError:
  Raised if check_sample is not in [train, test] Raised if metric is not in [gini, auc, f1, brier]

• TypeError:
  Raised if models_dict is not a dictionary

Example:

from combat.combat import ModelAggregation
from combat.models import LogitModel

# Sample input data
models_dict = {1: model1 # LogitModel instance
              , 2: model2 # LogitModel instance
              , 3: model3 # LogitModel instance
              }
metric = 'auc'
check_sample = 'test'

# Calculate weights for model aggregation
weights = ModelAggregation(models_dict, metric, check_sample)
print("Model weights:", weights)