[英]Sklearn pass fit() parameters to xgboost in pipeline
類似於如何在 scikit learn 中僅將參數傳遞給管道對象的一部分? 我只想將參數傳遞給管道的一部分。 通常,它應該可以正常工作,例如:
estimator = XGBClassifier()
pipeline = Pipeline([
('clf', estimator)
])
並執行
pipeline.fit(X_train, y_train, clf__early_stopping_rounds=20)
但它失敗了:
/usr/local/lib/python3.5/site-packages/sklearn/pipeline.py in fit(self, X, y, **fit_params)
114 """
115 Xt, yt, fit_params = self._pre_transform(X, y, **fit_params)
--> 116 self.steps[-1][-1].fit(Xt, yt, **fit_params)
117 return self
118
/usr/local/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/sklearn.py in fit(self, X, y, sample_weight, eval_set, eval_metric, early_stopping_rounds, verbose)
443 early_stopping_rounds=early_stopping_rounds,
444 evals_result=evals_result, obj=obj, feval=feval,
--> 445 verbose_eval=verbose)
446
447 self.objective = xgb_options["objective"]
/usr/local/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/training.py in train(params, dtrain, num_boost_round, evals, obj, feval, maximize, early_stopping_rounds, evals_result, verbose_eval, learning_rates, xgb_model, callbacks)
201 evals=evals,
202 obj=obj, feval=feval,
--> 203 xgb_model=xgb_model, callbacks=callbacks)
204
205
/usr/local/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/training.py in _train_internal(params, dtrain, num_boost_round, evals, obj, feval, xgb_model, callbacks)
97 end_iteration=num_boost_round,
98 rank=rank,
---> 99 evaluation_result_list=evaluation_result_list))
100 except EarlyStopException:
101 break
/usr/local/lib/python3.5/site-packages/xgboost-0.6-py3.5.egg/xgboost/callback.py in callback(env)
196 def callback(env):
197 """internal function"""
--> 198 score = env.evaluation_result_list[-1][1]
199 if len(state) == 0:
200 init(env)
IndexError: list index out of range
而一個
estimator.fit(X_train, y_train, early_stopping_rounds=20)
工作得很好。
對於提前停止輪次,您必須始終指定參數 eval_set 給出的驗證集。 以下是修復代碼中錯誤的方法。
pipeline.fit(X_train, y_train, clf__early_stopping_rounds=20, clf__eval_set=[(test_X, test_y)])
這是解決方案: https ://www.kaggle.com/c/otto-group-product-classification-challenge/forums/t/13755/xgboost-early-stopping-and-other-issues early_stooping_rounds 和觀察名單/ eval_set 需要通過。 不幸的是,這對我不起作用,因為監視列表中的變量需要一個僅在管道中應用的預處理步驟/我需要手動應用此步驟。
我最近使用以下步驟為 Xgboost 使用 eval 指標和 eval_set 參數。
pipeline_temp = pipeline.Pipeline(pipeline.cost_pipe.steps[:-1])
X_trans = pipeline_temp.fit_transform(X_train[FEATURES],y_train)
eval_set = [(X_trans, y_train), (pipeline_temp.transform(X_test), y_test)]
pipeline_temp.steps.append(pipeline.cost_pipe.steps[-1])
pipeline_temp.fit(X_train[FEATURES], y_train,
xgboost_model__eval_metric = ERROR_METRIC,
xgboost_model__eval_set = eval_set)
joblib.dump(pipeline_temp, save_path)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.