XGBoostError: b'[19:12:58] src/metric/rank_metric.cc:89: Check failed: (preds.size()) == (info.labels.size()) label size predict size not match'
XGBoostError: b'[19:12:58] src/metric/rank_metric.cc:89: Check failed: (preds.size()) == (info.labels.size()) label size predict size not match'
我正在为我的训练集训练 XGBoostClassifier。
我的训练特征的形状为 (45001, 10338)，这是一个 numpy 数组，我的训练标签的形状为 (45001,) [我有 1161 个独特的标签，所以我为labels] 这也是一个 numpy 数组。
文档清楚地表明我可以从 numpy 数组创建 DMatrix。所以我直接使用上面提到的训练特征和标签作为 numpy 数组。但是我收到以下错误
---------------------------------------------------------------------------
XGBoostError Traceback (most recent call last)
<ipython-input-30-3de36245534e> in <module>()
13 scale_pos_weight=1,
14 seed=27)
---> 15 modelfit(xgb1, train_x, train_y)
<ipython-input-27-9d215eac135e> in modelfit(alg, train_data_features, train_labels, useTrainCV, cv_folds, early_stopping_rounds)
6 xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
7 cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
----> 8 metrics='auc',early_stopping_rounds=early_stopping_rounds)
9 alg.set_params(n_estimators=cvresult.shape[0])
10
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in cv(params, dtrain, num_boost_round, nfold, stratified, folds, metrics, obj, feval, maximize, early_stopping_rounds, fpreproc, as_pandas, verbose_eval, show_stdv, seed, callbacks)
399 for fold in cvfolds:
400 fold.update(i, obj)
--> 401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
403 for key, mean, std in res:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in <listcomp>(.0)
399 for fold in cvfolds:
400 fold.update(i, obj)
--> 401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
403 for key, mean, std in res:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in eval(self, iteration, feval)
221 def eval(self, iteration, feval):
222 """"Evaluate the CVPack for one iteration."""
--> 223 return self.bst.eval_set(self.watchlist, iteration, feval)
224
225
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in eval_set(self, evals, iteration, feval)
865 _check_call(_LIB.XGBoosterEvalOneIter(self.handle, iteration,
866 dmats, evnames, len(evals),
--> 867 ctypes.byref(msg)))
868 return msg.value
869 else:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in _check_call(ret)
125 """
126 if ret != 0:
--> 127 raise XGBoostError(_LIB.XGBGetLastError())
128
129
XGBoostError: b'[19:12:58] src/metric/rank_metric.cc:89: Check failed: (preds.size()) == (info.labels.size()) label size predict size not match'
请在下面找到我的型号代码：
def modelfit(alg, train_data_features, train_labels,useTrainCV=True, cv_folds=5, early_stopping_rounds=50):
if useTrainCV:
xgb_param = alg.get_xgb_params()
xgb_param['num_class'] = 1161
xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
metrics='auc',early_stopping_rounds=early_stopping_rounds)
alg.set_params(n_estimators=cvresult.shape[0])
#Fit the algorithm on the data
alg.fit(train_data_features, train_labels, eval_metric='auc')
#Predict training set:
dtrain_predictions = alg.predict(train_data_features)
dtrain_predprob = alg.predict_proba(train_data_features)[:,1]
#Print model report:
print("\nModel Report")
print("Accuracy : %.4g" % metrics.accuracy_score(train_labels, dtrain_predictions))
我上面哪里出错了？
我的分类器如下：
xgb1 = xgb.XGBClassifier(
learning_rate =0.1,
n_estimators=50,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27)
编辑 - 2
更改评估指标后，
---------------------------------------------------------------------------
XGBoostError Traceback (most recent call last)
<ipython-input-9-30c62a886c2e> in <module>()
13 scale_pos_weight=1,
14 seed=27)
---> 15 modelfit(xgb1, train_x_trail, train_y_trail)
<ipython-input-8-9d215eac135e> in modelfit(alg, train_data_features, train_labels, useTrainCV, cv_folds, early_stopping_rounds)
6 xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
7 cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
----> 8 metrics='auc',early_stopping_rounds=early_stopping_rounds)
9 alg.set_params(n_estimators=cvresult.shape[0])
10
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in cv(params, dtrain, num_boost_round, nfold, stratified, folds, metrics, obj, feval, maximize, early_stopping_rounds, fpreproc, as_pandas, verbose_eval, show_stdv, seed, callbacks)
398 evaluation_result_list=None))
399 for fold in cvfolds:
--> 400 fold.update(i, obj)
401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in update(self, iteration, fobj)
217 def update(self, iteration, fobj):
218 """"Update the boosters for one iteration"""
--> 219 self.bst.update(self.dtrain, iteration, fobj)
220
221 def eval(self, iteration, feval):
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in update(self, dtrain, iteration, fobj)
804
805 if fobj is None:
--> 806 _check_call(_LIB.XGBoosterUpdateOneIter(self.handle, iteration, dtrain.handle))
807 else:
808 pred = self.predict(dtrain)
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in _check_call(ret)
125 """
126 if ret != 0:
--> 127 raise XGBoostError(_LIB.XGBGetLastError())
128
129
XGBoostError: b'[03:43:03] src/objective/multiclass_obj.cc:42: Check failed: (info.labels.size()) != (0) label set cannot be empty'
错误是b/c您正在尝试将 AUC 评估指标用于多 class class化，但 AUC 仅适用于两个 class 问题。在 xgboost 实现中，"auc" 期望预测大小与标签大小相同，而您的 multiclass 预测大小为 45001*1161。使用 "mlogloss" 或 "merror" 多 class 指标。
P.S.：目前，xgboost 对于这么多 classes 会相当慢，因为训练期间预测缓存效率低下。
您得到的原始错误是因为此指标不是为多class class化设计的（参见here）。
您可以使用 xgboost 的 scikit learn wrapper 来解决这个问题。我用这个包装器修改了你的代码，以产生类似的功能。我不确定你为什么要进行网格搜索，因为你没有枚举参数。相反，您使用的是在 xgb1 中指定的参数。这是修改后的代码：
import xgboost as xgb
import sklearn
import numpy as np
from sklearn.model_selection import GridSearchCV
def modelfit(alg, train_data_features, train_labels,useTrainCV=True, cv_folds=5):
if useTrainCV:
params=alg.get_xgb_params()
xgb_param=dict([(key,[params[key]]) for key in params])
boost = xgb.sklearn.XGBClassifier()
cvresult = GridSearchCV(boost,xgb_param,cv=cv_folds)
cvresult.fit(X,y)
alg=cvresult.best_estimator_
#Fit the algorithm on the data
alg.fit(train_data_features, train_labels)
#Predict training set:
dtrain_predictions = alg.predict(train_data_features)
dtrain_predprob = alg.predict_proba(train_data_features)[:,1]
#Print model report:
print("\nModel Report")
print("Accuracy : %.4g" % sklearn.metrics.accuracy_score(train_labels, dtrain_predictions))
xgb1 = xgb.sklearn.XGBClassifier(
learning_rate =0.1,
n_estimators=50,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27)
X=np.random.normal(size=(200,30))
y=np.random.randint(0,5,200)
modelfit(xgb1, X, y)
我得到的输出是
Model Report
Accuracy : 1
请注意，我使用的数据要小得多。以你提到的大小，算法可能会很慢。
我正在为我的训练集训练 XGBoostClassifier。
我的训练特征的形状为 (45001, 10338)，这是一个 numpy 数组，我的训练标签的形状为 (45001,) [我有 1161 个独特的标签，所以我为labels] 这也是一个 numpy 数组。
文档清楚地表明我可以从 numpy 数组创建 DMatrix。所以我直接使用上面提到的训练特征和标签作为 numpy 数组。但是我收到以下错误
---------------------------------------------------------------------------
XGBoostError Traceback (most recent call last)
<ipython-input-30-3de36245534e> in <module>()
13 scale_pos_weight=1,
14 seed=27)
---> 15 modelfit(xgb1, train_x, train_y)
<ipython-input-27-9d215eac135e> in modelfit(alg, train_data_features, train_labels, useTrainCV, cv_folds, early_stopping_rounds)
6 xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
7 cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
----> 8 metrics='auc',early_stopping_rounds=early_stopping_rounds)
9 alg.set_params(n_estimators=cvresult.shape[0])
10
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in cv(params, dtrain, num_boost_round, nfold, stratified, folds, metrics, obj, feval, maximize, early_stopping_rounds, fpreproc, as_pandas, verbose_eval, show_stdv, seed, callbacks)
399 for fold in cvfolds:
400 fold.update(i, obj)
--> 401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
403 for key, mean, std in res:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in <listcomp>(.0)
399 for fold in cvfolds:
400 fold.update(i, obj)
--> 401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
403 for key, mean, std in res:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in eval(self, iteration, feval)
221 def eval(self, iteration, feval):
222 """"Evaluate the CVPack for one iteration."""
--> 223 return self.bst.eval_set(self.watchlist, iteration, feval)
224
225
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in eval_set(self, evals, iteration, feval)
865 _check_call(_LIB.XGBoosterEvalOneIter(self.handle, iteration,
866 dmats, evnames, len(evals),
--> 867 ctypes.byref(msg)))
868 return msg.value
869 else:
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in _check_call(ret)
125 """
126 if ret != 0:
--> 127 raise XGBoostError(_LIB.XGBGetLastError())
128
129
XGBoostError: b'[19:12:58] src/metric/rank_metric.cc:89: Check failed: (preds.size()) == (info.labels.size()) label size predict size not match'
请在下面找到我的型号代码：
def modelfit(alg, train_data_features, train_labels,useTrainCV=True, cv_folds=5, early_stopping_rounds=50):
if useTrainCV:
xgb_param = alg.get_xgb_params()
xgb_param['num_class'] = 1161
xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
metrics='auc',early_stopping_rounds=early_stopping_rounds)
alg.set_params(n_estimators=cvresult.shape[0])
#Fit the algorithm on the data
alg.fit(train_data_features, train_labels, eval_metric='auc')
#Predict training set:
dtrain_predictions = alg.predict(train_data_features)
dtrain_predprob = alg.predict_proba(train_data_features)[:,1]
#Print model report:
print("\nModel Report")
print("Accuracy : %.4g" % metrics.accuracy_score(train_labels, dtrain_predictions))
我上面哪里出错了？
我的分类器如下：
xgb1 = xgb.XGBClassifier(
learning_rate =0.1,
n_estimators=50,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27)
编辑 - 2 更改评估指标后，
---------------------------------------------------------------------------
XGBoostError Traceback (most recent call last)
<ipython-input-9-30c62a886c2e> in <module>()
13 scale_pos_weight=1,
14 seed=27)
---> 15 modelfit(xgb1, train_x_trail, train_y_trail)
<ipython-input-8-9d215eac135e> in modelfit(alg, train_data_features, train_labels, useTrainCV, cv_folds, early_stopping_rounds)
6 xgtrain = xgb.DMatrix(train_data_features, label=train_labels)
7 cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=alg.get_params()['n_estimators'], nfold=cv_folds,
----> 8 metrics='auc',early_stopping_rounds=early_stopping_rounds)
9 alg.set_params(n_estimators=cvresult.shape[0])
10
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in cv(params, dtrain, num_boost_round, nfold, stratified, folds, metrics, obj, feval, maximize, early_stopping_rounds, fpreproc, as_pandas, verbose_eval, show_stdv, seed, callbacks)
398 evaluation_result_list=None))
399 for fold in cvfolds:
--> 400 fold.update(i, obj)
401 res = aggcv([f.eval(i, feval) for f in cvfolds])
402
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/training.py in update(self, iteration, fobj)
217 def update(self, iteration, fobj):
218 """"Update the boosters for one iteration"""
--> 219 self.bst.update(self.dtrain, iteration, fobj)
220
221 def eval(self, iteration, feval):
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in update(self, dtrain, iteration, fobj)
804
805 if fobj is None:
--> 806 _check_call(_LIB.XGBoosterUpdateOneIter(self.handle, iteration, dtrain.handle))
807 else:
808 pred = self.predict(dtrain)
/home/carnd/anaconda3/envs/dl/lib/python3.5/site-packages/xgboost/core.py in _check_call(ret)
125 """
126 if ret != 0:
--> 127 raise XGBoostError(_LIB.XGBGetLastError())
128
129
XGBoostError: b'[03:43:03] src/objective/multiclass_obj.cc:42: Check failed: (info.labels.size()) != (0) label set cannot be empty'
错误是b/c您正在尝试将 AUC 评估指标用于多 class class化，但 AUC 仅适用于两个 class 问题。在 xgboost 实现中，"auc" 期望预测大小与标签大小相同，而您的 multiclass 预测大小为 45001*1161。使用 "mlogloss" 或 "merror" 多 class 指标。
P.S.：目前，xgboost 对于这么多 classes 会相当慢，因为训练期间预测缓存效率低下。
您得到的原始错误是因为此指标不是为多class class化设计的（参见here）。
您可以使用 xgboost 的 scikit learn wrapper 来解决这个问题。我用这个包装器修改了你的代码，以产生类似的功能。我不确定你为什么要进行网格搜索，因为你没有枚举参数。相反，您使用的是在 xgb1 中指定的参数。这是修改后的代码：
import xgboost as xgb
import sklearn
import numpy as np
from sklearn.model_selection import GridSearchCV
def modelfit(alg, train_data_features, train_labels,useTrainCV=True, cv_folds=5):
if useTrainCV:
params=alg.get_xgb_params()
xgb_param=dict([(key,[params[key]]) for key in params])
boost = xgb.sklearn.XGBClassifier()
cvresult = GridSearchCV(boost,xgb_param,cv=cv_folds)
cvresult.fit(X,y)
alg=cvresult.best_estimator_
#Fit the algorithm on the data
alg.fit(train_data_features, train_labels)
#Predict training set:
dtrain_predictions = alg.predict(train_data_features)
dtrain_predprob = alg.predict_proba(train_data_features)[:,1]
#Print model report:
print("\nModel Report")
print("Accuracy : %.4g" % sklearn.metrics.accuracy_score(train_labels, dtrain_predictions))
xgb1 = xgb.sklearn.XGBClassifier(
learning_rate =0.1,
n_estimators=50,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
objective='multi:softmax',
nthread=4,
scale_pos_weight=1,
seed=27)
X=np.random.normal(size=(200,30))
y=np.random.randint(0,5,200)
modelfit(xgb1, X, y)
我得到的输出是
Model Report
Accuracy : 1
请注意，我使用的数据要小得多。以你提到的大小，算法可能会很慢。