from sklearn.datasets import load_breast_cancer
from sklearn.linear_model import LogisticRegression

from pydvl.utils import Dataset, Scorer, Utility
from pydvl.value import (MaxUpdates, RelativeTruncation,
                         permutation_montecarlo_shapley)

data = Dataset.from_sklearn(
  load_breast_cancer(),
  train_size=10,
  stratify_by_target=True,
  random_state=16,
  )
model = LogisticRegression(n_jobs=1)
u = Utility(
  model,
  data,
  Scorer("accuracy", default=0.0)
  )
values = permutation_montecarlo_shapley(
  u,
  truncation=RelativeTruncation(u, 0.05),
  done=MaxUpdates(1000),
  seed=16,
  n_jobs=1,
  progress=True
  )
df = values.to_dataframe(column="data_value")