python - sklearn GridSearchCV 不在评分函数中使用 sample_weight

Question

我有每个样本具有不同权重的数据。在我的申请中，重要的是在估计模型和比较备选模型时考虑这些权重。

我正在使用 sklearn 来估计模型并比较备选超参数选择。但是这个单元测试表明 GridSearchCV 没有应用 sample_weights 来估计分数。

有没有办法让 sklearn 使用 sample_weight 对模型进行评分？

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))

产生输出:

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.

说明:由于手动计算不带权重的损失会产生与 GridSearchCV 相同的评分，因此我们知道未使用样本权重。

Answer 1

GridSearchCV 将一个scoring 作为输入，它可以被调用。你可以看到如何更改评分功能的详细信息，以及如何传递自己的评分功能here .为了完整起见，以下是该页面的相关代码:

编辑:fit_params 仅传递给拟合函数，而不是评分函数。如果有应该传递给 scorer 的参数，则应将它们传递给 make_scorer。但这仍然没有解决这里的问题，因为这意味着整个 sample_weight 参数将被传递给 log_loss，而只有对应于 的部分计算loss时的y_test应该通过。

sklearn 不支持这样的东西，但您可以使用 padas.DataFrame 破解。好消息是，sklearn 理解 DataFrame，并保持这种状态。这意味着您可以利用 DataFrame 的 index，如您在此处的代码中所见:

  # more code

  X, y = load_iris(return_X_y=True)
  index = ['r%d' % x for x in range(len(y))]
  y_frame = pd.DataFrame(y, index=index)
  sample_weight = np.array([1 + 100 * (i % 25) for i in range(len(X))])
  sample_weight_frame = pd.DataFrame(sample_weight, index=index)

  # more code

  def score_f(y_true, y_pred, sample_weight):
      return log_loss(y_true.values, y_pred,
                      sample_weight=sample_weight.loc[y_true.index.values].values.reshape(-1),
                      normalize=True)

  score_params = {"sample_weight": sample_weight_frame}
  my_scorer = make_scorer(score_f,
                          greater_is_better=False, 
                          needs_proba=True, 
                          needs_threshold=False,
                          **score_params)

  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_frame)

  # more code

如您所见，score_f 使用 y_true 的 index 来查找要使用 sample_weight 的哪些部分.为了完整起见，这里是整个代码:

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
from sklearn.metrics import  make_scorer
import pandas as pd

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_in[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__":
if True:
  RANDOM_STATE = 1337
  X, y = load_iris(return_X_y=True)
  index = ['r%d' % x for x in range(len(y))]
  y_frame = pd.DataFrame(y, index=index)
  sample_weight = np.array([1 + 100 * (i % 25) for i in range(len(X))])
  sample_weight_frame = pd.DataFrame(sample_weight, index=index)
  # 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]}


  def score_f(y_true, y_pred, sample_weight):
      return log_loss(y_true.values, y_pred,
                      sample_weight=sample_weight.loc[y_true.index.values].values.reshape(-1),
                      normalize=True)

  score_params = {"sample_weight": sample_weight_frame}
  my_scorer = make_scorer(score_f,
                          greater_is_better=False, 
                          needs_proba=True, 
                          needs_threshold=False,
                          **score_params)

  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_frame)
  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))

代码的输出是:

This is the best out-of-sample score using GridSearchCV: 0.095439.
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.

编辑 2:正如下面的评论所说:

the difference in my score and the sklearn score using this solution originates in the way that I was computing a weighted average of scores. If you omit the weighted average portion of the code, the two outputs match to machine precision.