sklearn GridSearchCV在评分函数中没有使用sample_weight。

我有一些具有不同权重的样本数据。在我的应用中，重要的是在估计模型和比较替代模型时考虑到这些权重。

我正在使用sklearn来估计模型和比较替代的超参数选择。但是这个单元测试显示GridSearchCV没有应用sample_weights来估计得分。

有没有办法让sklearn使用sample_weight来评估模型的得分？

单元测试：

from __future__ import division
import numpy as np
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import log_loss
from sklearn.model_selection import GridSearchCV, RepeatedKFold
def grid_cv(X_in, y_in, w_in, cv, max_features_grid, use_weighting):
  out_results = dict()
  for k in max_features_grid:
    clf = RandomForestClassifier(n_estimators=256,
                                 criterion="entropy",
                                 warm_start=False,
                                 n_jobs=-1,
                                 random_state=RANDOM_STATE,
                                 max_features=k)
    for train_ndx, test_ndx in cv.split(X=X_in, y=y_in):
      X_train = X_in[train_ndx, :]
      y_train = y_in[train_ndx]
      w_train = w_in[train_ndx]
      y_test = y[test_ndx]
      clf.fit(X=X_train, y=y_train, sample_weight=w_train)
      y_hat = clf.predict_proba(X=X_in[test_ndx, :])
      if use_weighting:
        w_test = w_in[test_ndx]
        w_i_sum = w_test.sum()
        score = w_i_sum / w_in.sum() * log_loss(y_true=y_test, y_pred=y_hat, sample_weight=w_test)
      else:
        score = log_loss(y_true=y_test, y_pred=y_hat)
      results = out_results.get(k, [])
      results.append(score)
      out_results.update({k: results})
  for k, v in out_results.items():
    if use_weighting:
      mean_score = sum(v)
    else:
      mean_score = np.mean(v)
    out_results.update({k: mean_score})
  best_score = min(out_results.values())
  best_param = min(out_results, key=out_results.get)
  return best_score, best_param
if __name__ == "__main__":
  RANDOM_STATE = 1337
  X, y = load_iris(return_X_y=True)
  sample_weight = np.array([1 + 100 * (i % 25) for i in range(len(X))])
  # sample_weight = np.array([1 for _ in range(len(X))])
  inner_cv = RepeatedKFold(n_splits=3, n_repeats=1, random_state=RANDOM_STATE)
  outer_cv = RepeatedKFold(n_splits=3, n_repeats=1, random_state=RANDOM_STATE)
  rfc = RandomForestClassifier(n_estimators=256,
                               criterion="entropy",
                               warm_start=False,
                               n_jobs=-1,
                               random_state=RANDOM_STATE)
  search_params = {"max_features": [1, 2, 3, 4]}
  fit_params = {"sample_weight": sample_weight}
  my_scorer = make_scorer(log_loss, 
               greater_is_better=False, 
               needs_proba=True, 
               needs_threshold=False)
  grid_clf = GridSearchCV(estimator=rfc,
                          scoring=my_scorer,
                          cv=inner_cv,
                          param_grid=search_params,
                          refit=True,
                          return_train_score=False,
                          iid=False)  # in this usage, the results are the same for `iid=True` and `iid=False`
  grid_clf.fit(X, y, **fit_params)
  print("This is the best out-of-sample score using GridSearchCV: %.6f." % -grid_clf.best_score_)
  msg = """This is the best out-of-sample score %s weighting using grid_cv: %.6f."""
  score_with_weights, param_with_weights = grid_cv(X_in=X,
                                                   y_in=y,
                                                   w_in=sample_weight,
                                                   cv=inner_cv,
                                                   max_features_grid=search_params.get(
                                                     "max_features"),
                                                   use_weighting=True)
  print(msg % ("WITH", score_with_weights))
  score_without_weights, param_without_weights = grid_cv(X_in=X,
                                                         y_in=y,
                                                         w_in=sample_weight,
                                                         cv=inner_cv,
                                                         max_features_grid=search_params.get(
                                                           "max_features"),
                                                         use_weighting=False)
  print(msg % ("WITHOUT", score_without_weights))

输出结果：

This is the best out-of-sample score using GridSearchCV: 0.135692.
This is the best out-of-sample score WITH weighting using grid_cv: 0.099367.
This is the best out-of-sample score WITHOUT weighting using grid_cv: 0.135692.

解释：由于手动计算没有加权的损失产生了与GridSearchCV相同的评分，我们知道样本权重没有被使用。