我尝试使用以下从http://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-xgboost-with-codes-python/改编的代码在XGBC分类器上执行多类别分类问题的交叉验证
9352BE其中import numpy as np
import pandas as pd
import xgboost as xgb
from xgboost.sklearn import XGBClassifier
from sklearn.preprocessing import LabelEncoder
from sklearn import cross_validation, metrics
from sklearn.grid_search import GridSearchCV
def modelFit(alg, X, y, useTrainCV=True, cvFolds=5, early_stopping_rounds=50):
if useTrainCV:
xgbParams = alg.get_xgb_params()
xgTrain = xgb.DMatrix(X, label=y)
cvresult = xgb.cv(xgbParams,
xgTrain,
num_boost_round=alg.get_params()['n_estimators'],
nfold=cvFolds,
stratified=True,
metrics={'mlogloss'},
early_stopping_rounds=early_stopping_rounds,
seed=0,
callbacks=[xgb.callback.print_evaluation(show_stdv=False), xgb.callback.early_stop(3)])
print cvresult
alg.set_params(n_estimators=cvresult.shape[0])
# Fit the algorithm
alg.fit(X, y, eval_metric='mlogloss')
# Predict
dtrainPredictions = alg.predict(X)
dtrainPredProb = alg.predict_proba(X)
# Print model report:
print "\nModel Report"
print "Classification report: \n"
print(classification_report(y_val, y_val_pred))
print "Accuracy : %.4g" % metrics.accuracy_score(y, dtrainPredictions)
print "Log Loss Score (Train): %f" % metrics.log_loss(y, dtrainPredProb)
feat_imp = pd.Series(alg.booster().get_fscore()).sort_values(ascending=False)
feat_imp.plot(kind='bar', title='Feature Importances')
plt.ylabel('Feature Importance Score')
# 1) Read training set
print('>> Read training set')
train = pd.read_csv(trainFile)
# 2) Extract target attribute and convert to numeric
print('>> Preprocessing')
y_train = train['OutcomeType'].values
le_y = LabelEncoder()
y_train = le_y.fit_transform(y_train)
train.drop('OutcomeType', axis=1, inplace=True)
# 4) Extract features and target from training set
X_train = train.values
# 5) First classifier
xgb = XGBClassifier(learning_rate =0.1,
n_estimators=1000,
max_depth=5,
min_child_weight=1,
gamma=0,
subsample=0.8,
colsample_bytree=0.8,
scale_pos_weight=1,
objective='multi:softprob',
seed=27)
modelFit(xgb, X_train, y_train)
包含0到4之间的标签。但是，当我运行此代码时，我从y_train函数xgb.cv收到以下错误。在XGBoost文档中，我读到在多类情况下，xgb从目标向量中的标签中推断出类的数量，因此我不了解发生了什么。
答案 0 :(得分：3)
您必须将参数'num_class'添加到xgb_param字典中。参数说明和上面提供的链接中的注释中也提到了这一点。