【集成学习】sklearn中xgboot模块中fit函数参数详解（fit model for train data）

参数解释，后续补上。

  1 # -*- coding: utf-8 -*-
  2 """
  3 ###############################################################################
  4 # 作者：wanglei5205
  5 # 邮箱：[e-mail]
  6 # 代码：http://github.com/wanglei5205
  7 # 博客：http://cnblogs.com/wanglei5205
  8 # 目的：学习xgboost的XGBClassifier函数
  9 # 官方API文档：http://xgboost.readthedocs.io/en/latest/python/python_api.html#module-xgboost.training
 10 ###############################################################################
 11 """
 12 ### load module
 13 from sklearn import datasets
 14 from sklearn.model_selection import train_test_split
 15 from xgboost import XGBClassifier
 16
 17 ### load datasets
 18 digits = datasets.load_digits()
 19
 20 ### data analysis
 21 print(digits.data.shape)
 22 print(digits.target.shape)
 23
 24 ### data split
 25 x_train,x_test,y_train,y_test = train_test_split(digits.data,
 26                                                  digits.target,
 27                                                  test_size = 0.3,
 28                                                  random_state = 33)
 29
 30 ### fit model for train data
 31 # fit函数参数：eval_set=[(x_test,y_test)]  评估数据集,list类型
 32 # fit函数参数：eval_metric="mlogloss"      评估标准(多分类问题，使用mlogloss作为损失函数)
 33 # fit函数参数：early_stopping_rounds= 10   如果模型的loss十次内没有减小，则提前结束模型训练
 34 # fit函数参数：verbose = True              True显示，False不显示
 35 model = XGBClassifier()
 36 model.fit(x_train,
 37           y_train,
 38           eval_set = [(x_test,y_test)],  # 评估数据集
 39
 40           eval_metric = "mlogloss",
 41           early_stopping_rounds = 10,
 42           verbose = True)
 43
 44 ### make prediction for test data
 45 y_pred = model.predict(x_test)
 46
 47 ### model evaluate
 48 from sklearn.metrics import accuracy_score
 49 accuracy = accuracy_score(y_test,y_pred)
 50 print("accuarcy: %.2f%%" % (accuracy*100.0))
 51 """
 52 95.0%
 53 """