LightGBM用法速查表

1.读取csv数据并指定参数建模

# coding: utf-8
import json
import lightgbm as lgb
import pandas as pd
from sklearn.metrics import mean_squared_error
# 加载数据集合
print('Load data...')
df_train = pd.read_csv('regression.train.txt', header=None, sep='\t')
df_test = pd.read_csv('regression.test.txt', header=None, sep='\t')
# 设定训练集和测试集
y_train = df_train[0].values
y_test = df_test[0].values
X_train = df_train.drop(0, axis=1).values
X_test = df_test.drop(0, axis=1).values

# 构建lgb中的Dataset格式
lgb_train = lgb.Dataset(X_train, y_train)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train)# 敲定好一组参数
params = {'task': 'train','boosting_type': 'gbdt','objective': 'regression','metric': {'l2', 'auc'},'num_leaves': 31,'learning_rate': 0.05,'feature_fraction': 0.9,'bagging_fraction': 0.8,'bagging_freq': 5,'verbose': 0
}print('开始训练...')
# 训练
gbm = lgb.train(params,lgb_train,num_boost_round=20,valid_sets=lgb_eval,early_stopping_rounds=5)# 保存模型
print('保存模型...')
# 保存模型到文件中
gbm.save_model('model.txt')print('开始预测...')
# 预测
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration)
# 评估
print('预估结果的rmse为:')
print(mean_squared_error(y_test, y_pred) ** 0.5)
#Load data...
#开始训练...
#[1]    valid_0's l2: 0.24288  valid_0's auc: 0.764496
#Training until validation scores don't improve for 5 rounds.
#[2]    valid_0's l2: 0.239307 valid_0's auc: 0.766173
#[3]    valid_0's l2: 0.235559 valid_0's auc: 0.785547
#[4]    valid_0's l2: 0.230771 valid_0's auc: 0.797786
#[5]    valid_0's l2: 0.226297 valid_0's auc: 0.805155
#[6]    valid_0's l2: 0.223692 valid_0's auc: 0.800979
#[7]    valid_0's l2: 0.220941 valid_0's auc: 0.806566
#[8]    valid_0's l2: 0.217982 valid_0's auc: 0.808566
#[9]    valid_0's l2: 0.215351 valid_0's auc: 0.809041
#[10]   valid_0's l2: 0.213064 valid_0's auc: 0.805953
#[11]   valid_0's l2: 0.211053 valid_0's auc: 0.804631
#[12]   valid_0's l2: 0.209336 valid_0's auc: 0.802922
#[13]   valid_0's l2: 0.207492 valid_0's auc: 0.802011
#[14]   valid_0's l2: 0.206016 valid_0's auc: 0.80193
#Early stopping, best iteration is:
#[9]    valid_0's l2: 0.215351 valid_0's auc: 0.809041
#保存模型...
#开始预测...
#预估结果的rmse为:
#0.4640593794679212

2.添加样本权重训练

# coding: utf-8
import json
import lightgbm as lgb
import pandas as pd
import numpy as np
from sklearn.metrics import mean_squared_error
import warnings
warnings.filterwarnings("ignore")
# 加载数据集
print('加载数据...')
df_train = pd.read_csv('binary.train', header=None, sep='\t')
df_test = pd.read_csv('./data/binary.test', header=None, sep='\t')
W_train = pd.read_csv('binary.train.weight', header=None)[0]
W_test = pd.read_csv('binary.test.weight', header=None)[0]y_train = df_train[0].values
y_test = df_test[0].values
X_train = df_train.drop(0, axis=1).values
X_test = df_test.drop(0, axis=1).values
num_train, num_feature = X_train.shape# 加载数据的同时加载权重
lgb_train = lgb.Dataset(X_train, y_train,weight=W_train, free_raw_data=False)
lgb_eval = lgb.Dataset(X_test, y_test, reference=lgb_train,weight=W_test, free_raw_data=False)# 设定参数
params = {'boosting_type': 'gbdt','objective': 'binary','metric': 'binary_logloss','num_leaves': 31,'learning_rate': 0.05,'feature_fraction': 0.9,'bagging_fraction': 0.8,'bagging_freq': 5,'verbose': 0
}# 产出特征名称
feature_name = ['feature_' + str(col) for col in range(num_feature)]print('开始训练...')
gbm = lgb.train(params,lgb_train,num_boost_round=10,valid_sets=lgb_train,  # 评估训练集feature_name=feature_name,categorical_feature=[21])
#加载数据...
#开始训练...
#[1]    valid_0's binary_logloss: 0.681265
#[2]    valid_0's binary_logloss: 0.673318
#[3]    valid_0's binary_logloss: 0.664193
#[4]    valid_0's binary_logloss: 0.655501
#[5]    valid_0's binary_logloss: 0.650956
#[6]    valid_0's binary_logloss: 0.644803
#[7]    valid_0's binary_logloss: 0.637567
#[8]    valid_0's binary_logloss: 0.631224
#[9]    valid_0's binary_logloss: 0.624958
#[10]   valid_0's binary_logloss: 0.619398

3.模型的载入与预测

# 查看特征名称
print('完成10轮训练...')
print('第7个特征为:')
print(repr(lgb_train.feature_name[6]))# 存储模型
gbm.save_model('./model/lgb_model.txt')# 特征名称
print('特征名称:')
print(gbm.feature_name())# 特征重要度
print('特征重要度:')
print(list(gbm.feature_importance()))# 加载模型
print('加载模型用于预测')
bst = lgb.Booster(model_file='./model/lgb_model.txt')
# 预测
y_pred = bst.predict(X_test)
# 在测试集评估效果
print('在测试集上的rmse为:')
print(mean_squared_error(y_test, y_pred) ** 0.5)
# 查看特征名称
print('完成10轮训练...')
print('第7个特征为:')
print(repr(lgb_train.feature_name[6]))# 存储模型
gbm.save_model('./model/lgb_model.txt')# 特征名称
print('特征名称:')
print(gbm.feature_name())# 特征重要度
print('特征重要度:')
print(list(gbm.feature_importance()))# 加载模型
print('加载模型用于预测')
bst = lgb.Booster(model_file='./model/lgb_model.txt')
# 预测
y_pred = bst.predict(X_test)
# 在测试集评估效果
print('在测试集上的rmse为:')
print(mean_squared_error(y_test, y_pred) ** 0.5)
# 查看特征名称
print('完成10轮训练...')
print('第7个特征为:')
print(repr(lgb_train.feature_name[6]))
​
# 存储模型
gbm.save_model('./model/lgb_model.txt')
​
# 特征名称
print('特征名称:')
print(gbm.feature_name())
​
# 特征重要度
print('特征重要度:')
print(list(gbm.feature_importance()))
​
# 加载模型
print('加载模型用于预测')
bst = lgb.Booster(model_file='./model/lgb_model.txt')
# 预测
y_pred = bst.predict(X_test)
# 在测试集评估效果
print('在测试集上的rmse为:')
print(mean_squared_error(y_test, y_pred) ** 0.5)
#完成10轮训练...
#第7个特征为:
#'feature_6'
#特征名称:
#[u'feature_0', u'feature_1', u'feature_2', u'feature_3', u'feature_4', u'feature_5', u'feature_6', u'feature_7', u'feature_8', u'feature_9', u'feature_10', u'feature_11', u'feature_12', u'feature_13', u'feature_14', u'feature_15', u'feature_16', u'feature_17', u'feature_18', u'feature_19', u'feature_20', u'feature_21', u'feature_22', u'feature_23', u'feature_24', u'feature_25', u'feature_26', u'feature_27']
#特征重要度:
#[8, 5, 1, 19, 7, 33, 2, 0, 2, 10, 5, 2, 0, 9, 3, 3, 0, 2, 2, 5, 1, 0, 36, 3, 33, 45, 29, 35]
#加载模型用于预测
#在测试集上的rmse为:
#0.4629245607636925

4.接着之前的模型继续训练

# 继续训练
# 从./model/model.txt中加载模型初始化
gbm = lgb.train(params,lgb_train,num_boost_round=10,init_model='./model/lgb_model.txt',valid_sets=lgb_eval)print('以旧模型为初始化，完成第 10-20 轮训练...')# 在训练的过程中调整超参数
# 比如这里调整的是学习率
gbm = lgb.train(params,lgb_train,num_boost_round=10,init_model=gbm,learning_rates=lambda iter: 0.05 * (0.99 ** iter),valid_sets=lgb_eval)print('逐步调整学习率完成第 20-30 轮训练...')# 调整其他超参数
gbm = lgb.train(params,lgb_train,num_boost_round=10,init_model=gbm,valid_sets=lgb_eval,callbacks=[lgb.reset_parameter(bagging_fraction=[0.7] * 5 + [0.6] * 5)])
#print('逐步调整bagging比率完成第 30-40 轮训练...')
#[11]   valid_0's binary_logloss: 0.616177
#[12]   valid_0's binary_logloss: 0.611792
#[13]   valid_0's binary_logloss: 0.607043
#[14]   valid_0's binary_logloss: 0.602314
#[15]   valid_0's binary_logloss: 0.598433
#[16]   valid_0's binary_logloss: 0.595238
#[17]   valid_0's binary_logloss: 0.592047
#[18]   valid_0's binary_logloss: 0.588673
#[19]   valid_0's binary_logloss: 0.586084
#[20]   valid_0's binary_logloss: 0.584033
#以旧模型为初始化，完成第 10-20 轮训练...
#[21]   valid_0's binary_logloss: 0.616177
#[22]   valid_0's binary_logloss: 0.611834
#[23]   valid_0's binary_logloss: 0.607177
#[24]   valid_0's binary_logloss: 0.602577
#[25]   valid_0's binary_logloss: 0.59831
#[26]   valid_0's binary_logloss: 0.595259
#[27]   valid_0's binary_logloss: 0.592201
#[28]   valid_0's binary_logloss: 0.589017
#[29]   valid_0's binary_logloss: 0.586597
#[30]   valid_0's binary_logloss: 0.584454
#逐步调整学习率完成第 20-30 轮训练...
#[31]   valid_0's binary_logloss: 0.616053
#[32]   valid_0's binary_logloss: 0.612291
#[33]   valid_0's binary_logloss: 0.60856
#[34]   valid_0's binary_logloss: 0.605387
#[35]   valid_0's binary_logloss: 0.601744
#[36]   valid_0's binary_logloss: 0.598556
#[37]   valid_0's binary_logloss: 0.595585
#[38]   valid_0's binary_logloss: 0.593228
#[39]   valid_0's binary_logloss: 0.59018
#[40]   valid_0's binary_logloss: 0.588391
#逐步调整bagging比率完成第 30-40 轮训练...

5.自定义损失函数

# 类似在xgboost中的形式
# 自定义损失函数需要
def loglikelood(preds, train_data):labels = train_data.get_label()preds = 1. / (1. + np.exp(-preds))grad = preds - labelshess = preds * (1. - preds)return grad, hess# 自定义评估函数
def binary_error(preds, train_data):labels = train_data.get_label()return 'error', np.mean(labels != (preds > 0.5)), Falsegbm = lgb.train(params,lgb_train,num_boost_round=10,init_model=gbm,fobj=loglikelood,feval=binary_error,valid_sets=lgb_eval)print('用自定义的损失函数与评估标准完成第40-50轮...')
#[41]   valid_0's binary_logloss: 0.614429 valid_0's error: 0.268
#[42]   valid_0's binary_logloss: 0.610689 valid_0's error: 0.26
#[43]   valid_0's binary_logloss: 0.606267 valid_0's error: 0.264
#[44]   valid_0's binary_logloss: 0.601949 valid_0's error: 0.258
#[45]   valid_0's binary_logloss: 0.597271 valid_0's error: 0.266
#[46]   valid_0's binary_logloss: 0.593971 valid_0's error: 0.276
#[47]   valid_0's binary_logloss: 0.591427 valid_0's error: 0.278
#[48]   valid_0's binary_logloss: 0.588301 valid_0's error: 0.284
#[49]   valid_0's binary_logloss: 0.586562 valid_0's error: 0.288
#[50]   valid_0's binary_logloss: 0.584056 valid_0's error: 0.288
#用自定义的损失函数与评估标准完成第40-50轮...

sklearn与LightGBM配合使用

1.LightGBM建模，sklearn评估

# coding: utf-8
import lightgbm as lgb
import pandas as pd
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import GridSearchCV# 加载数据
print('加载数据...')
df_train = pd.read_csv('regression.train.txt', header=None, sep='\t')
df_test = pd.read_csv('.regression.test.txt', header=None, sep='\t')# 取出特征和标签
y_train = df_train[0].values
y_test = df_test[0].values
X_train = df_train.drop(0, axis=1).values
X_test = df_test.drop(0, axis=1).valuesprint('开始训练...')
# 直接初始化LGBMRegressor
# 这个LightGBM的Regressor和sklearn中其他Regressor基本是一致的
gbm = lgb.LGBMRegressor(objective='regression',num_leaves=31,learning_rate=0.05,n_estimators=20)# 使用fit函数拟合
gbm.fit(X_train, y_train,eval_set=[(X_test, y_test)],eval_metric='l1',early_stopping_rounds=5)# 预测
print('开始预测...')
y_pred = gbm.predict(X_test, num_iteration=gbm.best_iteration_)
# 评估预测结果
print('预测结果的rmse是:')
print(mean_squared_error(y_test, y_pred) ** 0.5)#加载数据...
#开始训练...
#[1]    valid_0's l1: 0.491735
#Training until validation scores don't improve for 5 rounds.
#[2]    valid_0's l1: 0.486563
#[3]    valid_0's l1: 0.481489
#[4]    valid_0's l1: 0.476848
#[5]    valid_0's l1: 0.47305
#[6]    valid_0's l1: 0.469049
#[7]    valid_0's l1: 0.465556
#[8]    valid_0's l1: 0.462208
#[9]    valid_0's l1: 0.458676
#[10]   valid_0's l1: 0.454998
#[11]   valid_0's l1: 0.452047
#[12]   valid_0's l1: 0.449158
#[13]   valid_0's l1: 0.44608
#[14]   valid_0's l1: 0.443554
#[15]   valid_0's l1: 0.440643
#[16]   valid_0's l1: 0.437687
#[17]   valid_0's l1: 0.435454
#[18]   valid_0's l1: 0.433288
#[19]   valid_0's l1: 0.431297
#[20]   valid_0's l1: 0.428946
#Did not meet early stopping. Best iteration is:
#[20]   valid_0's l1: 0.428946
#开始预测...
#预测结果的rmse是:
#0.4441153344254208

2.网格搜索查找最优超参数

# 配合scikit-learn的网格搜索交叉验证选择最优超参数
estimator = lgb.LGBMRegressor(num_leaves=31)param_grid = {'learning_rate': [0.01, 0.1, 1],'n_estimators': [20, 40]
}gbm = GridSearchCV(estimator, param_grid)gbm.fit(X_train, y_train)print('用网格搜索找到的最优超参数为:')
print(gbm.best_params_)
#用网格搜索找到的最优超参数为:
#{'n_estimators': 40, 'learning_rate': 0.1}

3.绘图解释

# coding: utf-8
import lightgbm as lgb
import pandas as pdtry:import matplotlib.pyplot as plt
except ImportError:raise ImportError('You need to install matplotlib for plotting.')# 加载数据集
print('加载数据...')
df_train = pd.read_csv('./data/regression.train.txt', header=None, sep='\t')
df_test = pd.read_csv('./data/regression.test.txt', header=None, sep='\t')# 取出特征和标签
y_train = df_train[0].values
y_test = df_test[0].values
X_train = df_train.drop(0, axis=1).values
X_test = df_test.drop(0, axis=1).values# 构建lgb中的Dataset数据格式
lgb_train = lgb.Dataset(X_train, y_train)
lgb_test = lgb.Dataset(X_test, y_test, reference=lgb_train)# 设定参数
params = {'num_leaves': 5,'metric': ('l1', 'l2'),'verbose': 0
}evals_result = {}  # to record eval results for plottingprint('开始训练...')
# 训练
gbm = lgb.train(params,lgb_train,num_boost_round=100,valid_sets=[lgb_train, lgb_test],feature_name=['f' + str(i + 1) for i in range(28)],categorical_feature=[21],evals_result=evals_result,verbose_eval=10)print('在训练过程中绘图...')
ax = lgb.plot_metric(evals_result, metric='l1')
plt.show()print('画出特征重要度...')
ax = lgb.plot_importance(gbm, max_num_features=10)
plt.show()print('画出第84颗树...')
ax = lgb.plot_tree(gbm, tree_index=83, figsize=(20, 8), show_info=['split_gain'])
plt.show()#print('用graphviz画出第84颗树...')
#graph = lgb.create_tree_digraph(gbm, tree_index=83, name='Tree84')
#graph.render(view=True)#加载数据...
#开始训练...
#[10]   training's l2: 0.217995    training's l1: 0.457448    valid_1's l2: 0.21641  valid_1's l1: 0.456464
#[20]   training's l2: 0.205099    training's l1: 0.436869    valid_1's l2: 0.201616 valid_1's l1: 0.434057
#[30]   training's l2: 0.197421    training's l1: 0.421302    valid_1's l2: 0.192514 valid_1's l1: 0.417019
#[40]   training's l2: 0.192856    training's l1: 0.411107    valid_1's l2: 0.187258 valid_1's l1: 0.406303
#[50]   training's l2: 0.189593    training's l1: 0.403695    valid_1's l2: 0.183688 valid_1's l1: 0.398997
#[60]   training's l2: 0.187043    training's l1: 0.398704    valid_1's l2: 0.181009 valid_1's l1: 0.393977
#[70]   training's l2: 0.184982    training's l1: 0.394876    valid_1's l2: 0.178803 valid_1's l1: 0.389805
#[80]   training's l2: 0.1828  training's l1: 0.391147    valid_1's l2: 0.176799 valid_1's l1: 0.386476
#[90]   training's l2: 0.180817    training's l1: 0.388101    valid_1's l2: 0.175775 valid_1's l1: 0.384404
#[100]  training's l2: 0.179171    training's l1: 0.385174    valid_1's l2: 0.175321 valid_1's l1: 0.382929
#在训练过程中绘图...


画出特征重要度…

画出第84颗树…

LightGBM用法速查表相关推荐

  1. Python Pandas 用法速查表

    文章目录 数据读写 数据创建 数据查看 数据操作 数据提取 数据筛选 数据统计 操作数据表结构 数据表合并 修改列名 插入一列 数据读写 代码 作用 df = pd.DataFrame(pd.read ...

  2. html 右边是iframe 左右结构_HTML速查表

    HTML速查表 网页标题内容...... Document基本标签(Basic Tags) 最大的标题 . . . . . . . . . . . . 最小的标题 这是一个段落. (换行) (水平线) ...

  3. [Github项目推荐] 机器学习 Python 知识点速查表

    2019年第 21 篇文章,总第 45 篇文章 今天推荐三份知识点的速查表,分别是机器学习.深度学习和 Python 三方面的知识点速查表.其中前两份都是来自斯坦福大学的课程,分别是 CS229 机器 ...

  4. Linux系统运维人员常用速查表

    Linux系统运维人员常用速查表 walkingcloud 2020-08-09 19:55:41 Linux系统运维人员常用速查表 1.awk速查表 2.bash速查表 3.firewall-cmd ...

  5. 线性代数知识点总结_[Github项目推荐] 机器学习amp; Python 知识点速查表

    今天推荐三份知识点的速查表,分别是机器学习.深度学习和 Python 三方面的知识点速查表.其中前两份都是来自斯坦福大学的课程,分别是 CS229 机器学习 和 CS230 深度学习课程. 1. CS ...

  6. DL4J中文文档/开始/速查表

    快速检索 DL4J(和相关项目)有很多功能.此篇的目标是总结这个功能,以便用户知道存在什么功能,以及在哪里可以找到更多信息. 内容 层 前馈层 输出层 卷积层 循环层 无监督层 其它层 图顶点 输入预 ...

  7. 学习GNU Emacs命令速查表（三）

    博客地址:http://blog.csdn.net/shuxiao9058 原始作者:季亚 第八章简章的文字排版和特效编辑 表8-1:制表位命令速查表 键盘操作 命令名称 动作 (无) edit-ta ...

  8. 图解 Python 编程(9) | for循环（附要点速查表·完结）

    作者:韩信子@ShowMeAI 教程地址:https://www.showmeai.tech/tutorials/56 本文地址:https://www.showmeai.tech/article-d ...

  9. 图解 Python 编程(13) | 字符串及操作（附要点速查表·完结）

    作者:韩信子@ShowMeAI 教程地址:https://www.showmeai.tech/tutorials/56 本文地址:https://www.showmeai.tech/article-d ...

最新文章

  1. vscode c++编译报错：‘nullptr’ was not declared in this scope（-std=c++11）
  2. linux安装cv2踩坑
  3. 一块钱买一瓶水，两个空瓶换一瓶水，三个瓶盖换一瓶水，现在有20块钱，一共可以喝多少瓶水？
  4. 安卓代码迁移：ActionBarActivity: cannot be resolved to a type
  5. MySQL主从复制故障解决
  6. iptables配置详解
  7. java replacefirst第n_Java中replace()、replaceFirst()和replaceAll()区别
  8. 我最喜欢的ORM工具—Simple Data(转)
  9. f-droid_使用F-Droid在Android上开源
  10. Word2Vec模型训练简洁步骤
  11. 计算机操作系统－操作系统的定义
  12. Python的一点人生经验
  13. 【vscode】vscode常用插件介绍
  14. Leetcode 1647. Minimum Deletions to Make Character Frequencies Unique [Python]
  15. android edittext 美化,android EditText的美化
  16. C# 抽象类与接口异同
  17. 图形驱动程序和显卡驱动什么区别_你的安卓机以后也要单独安装显卡驱动程序喽...
  18. 解决WIN10下应用商店不能用,闪退的情况
  19. Django笔记总结
  20. 大一的c与语言期末试题及答案,C语言期末考试试题及详细答案

热门文章

  1. 事件控制块的清空与状态查询
  2. linux 垃圾桶快捷键,Linux的基本：为网上邻居配个垃圾桶
  3. golang mongodb or条件_MongoDB的学习,操作命令详细介绍
  4. java osgi web开发_基于 OSGi 和 Spring 开发 Web 应用
  5. PyTorch中的数据输入和预处理
  6. c语言hailstone序列,第一章 c语言上机试卷.doc
  7. mysql oracle 查询语句执行顺序_MySQL sql语句执行顺序
  8. caffe apt install
  9. 文巾解题 810. 黑板异或游戏
  10. 线性时间冰山查询算法（Linear-time Iceberg Query Algorithm ）