python机器学习库xgboost的使用

yipeiwu_com5年前Python基础

1.数据读取

利用原生xgboost库读取libsvm数据

 import xgboost as xgb
 data = xgb.DMatrix(libsvm文件)

使用sklearn读取libsvm数据

 from sklearn.datasets import load_svmlight_file
 X_train,y_train = load_svmlight_file(libsvm文件)

使用pandas读取完数据后在转化为标准形式

2.模型训练过程

1.未调参基线模型

使用xgboost原生库进行训练

import xgboost as xgb
from sklearn.metrics import accuracy_score

dtrain = xgb.DMatrix(f_train, label = l_train)
dtest = xgb.DMatrix(f_test, label = l_test)
param = {'max_depth':2, 'eta':1, 'silent':0, 'objective':'binary:logistic' }
num_round = 2
bst = xgb.train(param, dtrain, num_round)
train_preds = bst.predict(dtrain)
train_predictions = [round(value) for value in train_preds] #进行四舍五入的操作--变成0.1(算是设定阈值的符号函数)
train_accuracy = accuracy_score(l_train, train_predictions) #使用sklearn进行比较正确率
print ("Train Accuary: %.2f%%" % (train_accuracy * 100.0))

from xgboost import plot_importance #显示特征重要性
plot_importance(bst)#打印重要程度结果。
pyplot.show()

使用XGBClassifier进行训练

# 未设定早停止, 未进行矩阵变换
from xgboost import XGBClassifier
from sklearn.datasets import load_svmlight_file #用于直接读取svmlight文件形式, 否则就需要使用xgboost.DMatrix(文件名)来读取这种格式的文件
from sklearn.metrics import accuracy_score
from matplotlib import pyplot


num_round = 100
bst1 =XGBClassifier(max_depth=2, learning_rate=1, n_estimators=num_round, #弱分类树太少的话取不到更多的特征重要性
          silent=True, objective='binary:logistic')
bst1.fit(f_train, l_train)

train_preds = bst1.predict(f_train)
train_accuracy = accuracy_score(l_train, train_preds)
print ("Train Accuary: %.2f%%" % (train_accuracy * 100.0))

preds = bst1.predict(f_test)
test_accuracy = accuracy_score(l_test, preds)
print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0))

from xgboost import plot_importance #显示特征重要性
plot_importance(bst1)#打印重要程度结果。
pyplot.show()

2.两种交叉验证方式

使用cross_val_score进行交叉验证

#利用model_selection进行交叉训练
from xgboost import XGBClassifier
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import cross_val_score
from sklearn.metrics import accuracy_score
from matplotlib import pyplot

param = {'max_depth':2, 'eta':1, 'silent':0, 'objective':'binary:logistic' }
num_round = 100
bst2 =XGBClassifier(max_depth=2, learning_rate=0.1,n_estimators=num_round, silent=True, objective='binary:logistic')
bst2.fit(f_train, l_train)
kfold = StratifiedKFold(n_splits=10, random_state=7)
results = cross_val_score(bst2, f_train, l_train, cv=kfold)#对数据进行十折交叉验证--9份训练,一份测试
print(results)
print("CV Accuracy: %.2f%% (%.2f%%)" % (results.mean()*100, results.std()*100))

from xgboost import plot_importance #显示特征重要性
plot_importance(bst2)#打印重要程度结果。
pyplot.show()

 

使用GridSearchCV进行网格搜索

#使用sklearn中提供的网格搜索进行测试--找出最好参数,并作为默认训练参数
from xgboost import XGBClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import accuracy_score
from matplotlib import pyplot

params = {'max_depth':2, 'eta':0.1, 'silent':0, 'objective':'binary:logistic' }
bst =XGBClassifier(max_depth=2, learning_rate=0.1, silent=True, objective='binary:logistic')
param_test = {
 'n_estimators': range(1, 51, 1)
}
clf = GridSearchCV(estimator = bst, param_grid = param_test, scoring='accuracy', cv=5)# 5折交叉验证
clf.fit(f_train, l_train) #默认使用最优的参数


preds = clf.predict(f_test)

test_accuracy = accuracy_score(l_test, preds)
print("Test Accuracy of gridsearchcv: %.2f%%" % (test_accuracy * 100.0))

clf.cv_results_, clf.best_params_, clf.best_score_
 

3.早停止调参–early_stopping_rounds(查看的是损失是否变化)

#进行提早停止的单独实例
import xgboost as xgb
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score
from matplotlib import pyplot

param = {'max_depth':2, 'eta':1, 'silent':0, 'objective':'binary:logistic' }
num_round = 100
bst =XGBClassifier(max_depth=2, learning_rate=0.1, n_estimators=num_round, silent=True, objective='binary:logistic')
eval_set =[(f_test, l_test)]
bst.fit(f_train, l_train, early_stopping_rounds=10, eval_metric="error",eval_set=eval_set, verbose=True) #early_stopping_rounds--当多少次的效果差不多时停止  eval_set--用于显示损失率的数据 verbose--显示错误率的变化过程

# make prediction
preds = bst.predict(f_test)

test_accuracy = accuracy_score(l_test, preds)
print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0))

4.多数据观察训练损失

#多参数顺
import xgboost as xgb
from xgboost import XGBClassifier
from sklearn.metrics import accuracy_score
from matplotlib import pyplot

num_round = 100
bst =XGBClassifier(max_depth=2, learning_rate=0.1, n_estimators=num_round, silent=True, objective='binary:logistic')
eval_set = [(f_train, l_train), (f_test, l_test)]
bst.fit(f_train, l_train, eval_metric=["error", "logloss"], eval_set=eval_set, verbose=True)

# make prediction
preds = bst.predict(f_test)
test_accuracy = accuracy_score(l_test, preds)
print("Test Accuracy: %.2f%%" % (test_accuracy * 100.0))

5.模型保存与读取

#模型保存
bst.save_model('demo.model')

#模型读取与预测
modelfile = 'demo.model'

# 1
bst = xgb.Booster({'nthread':8}, model_file = modelfile)

# 2

f_test1 = xgb.DMatrix(f_test) #尽量使用xgboost的自己的数据矩阵
ypred1 = bst.predict(f_test1)
train_predictions = [round(value) for value in ypred1]
test_accuracy1 = accuracy_score(l_test, train_predictions)
print("Test Accuracy: %.2f%%" % (test_accuracy1 * 100.0))

以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持【听图阁-专注于Python设计】。

相关文章

python3实现暴力穷举博客园密码

我之前想写路由器的密码暴力破解器,我手上只有极路由,发现极路由有安全限制,只能允许连续10密码错误,所以我改拿博客园练手。 博客园的博客有个功能是给博文设置一个密码,输入正确的密码才能看...

跟老齐学Python之让人欢喜让人忧的迭代

哦,这就是真正牛X的程序员。不过,他也仅仅是牛X罢了,还不是大神。大神程序员是什么样儿呢?他是扫地僧,大隐隐于市。 先搞清楚这些名词再说别的: 循环(loop),指的是在满足条件的情况下...

Python常见内置高效率函数用法示例

本文实例讲述了Python常见内置高效率函数用法。分享给大家供大家参考,具体如下: 1.  filter(function,sequence) 将sequence中的每个元素,...

Pytorch to(device)用法

如下所示: device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") model.to(devi...

Python实现简单的四则运算计算器

一、算法      1、算法的主要思想就是将一个中缀表达式(Infix expression)转换成便于处理的后缀表达式(Postfix expr...