devbox
盐析白兔
这个屌丝很懒，什么也没留下！
关注作者
热门标签
热门文章
当前位置:   article > 正文

lightGBM使用案例_lightgbm示例

作者：盐析白兔 | 2024-03-17 21:27:28

赞

踩

lightgbm示例

转载于文本

xgboost:https://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-xgboost-with-codes-python/

lightgbm的两种使用方式

lightgbm

  1. #!/usr/bin/env python2
  2. # -*- coding: utf-8 -*-
  3. """
  4. Created on Sat Mar 31 21:19:09 2018
  6. @author: hello4720
  7. """
  8. import numpy as np
  9. import pandas as pd
  10. import lightgbm as lgb
  11. from sklearn import metrics
  12. from sklearn.model_selection import train_test_split
  13.  
  14. ### 读取数据
  15. print("载入数据")
  16. dataset1 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data1.csv')
  17. dataset2 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data2.csv')
  18. dataset3 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data3.csv')
  19. dataset4 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data4.csv')
  20. dataset5 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data5.csv')
  21.  
  22. dataset1.drop_duplicates(inplace=True)
  23. dataset2.drop_duplicates(inplace=True)
  24. dataset3.drop_duplicates(inplace=True)
  25. dataset4.drop_duplicates(inplace=True)
  26. dataset5.drop_duplicates(inplace=True)
  27.  
  28. ### 数据合并
  29. print("数据合并")
  30. trains = pd.concat([dataset1,dataset2],axis=0)
  31. trains = pd.concat([trains,dataset3],axis=0)
  32. trains = pd.concat([trains,dataset4],axis=0)
  33.  
  34. online_test = dataset5
  35.  
  36. ### 数据拆分
  37. print("数据拆分")
  38. train_xy,offline_test = train_test_split(trains, test_size = 0.2,random_state=21)
  39. train,val = train_test_split(train_xy, test_size = 0.2,random_state=21)
  40.  
  41. print("训练集")
  42. y = train.is_trade                                                  # 训练集标签
  43. X = train.drop(['instance_id','is_trade'],axis=1)                   # 训练集特征矩阵
  44.  
  45. print("验证集")
  46. val_y = val.is_trade                                                # 验证集标签
  47. val_X = val.drop(['instance_id','is_trade'],axis=1)                 # 验证集特征矩阵
  48.  
  49. print("测试集")
  50. offline_test_X=offline_test.drop(['instance_id','is_trade'],axis=1) # 线下测试特征矩阵
  51. online_test_X=online_test.drop(['instance_id'],axis=1)              # 线上测试特征矩阵
  52.  
  53. ### 数据转换
  54. lgb_train = lgb.Dataset(X, y, free_raw_data=False)
  55. lgb_eval = lgb.Dataset(val_X, val_y, reference=lgb_train,free_raw_data=False)
  56.  
  57. ### 开始训练
  58. print('设置参数')
  59. params = {
  60.             'boosting_type': 'gbdt',
  61.             'boosting': 'dart',
  62.             'objective': 'binary',
  63.             'metric': 'binary_logloss',
  64.  
  65.             'learning_rate': 0.01,
  66.             'num_leaves':25,
  67.             'max_depth':3,
  68.  
  69.             'max_bin':10,
  70.             'min_data_in_leaf':8,
  71.  
  72.             'feature_fraction': 0.6,
  73.             'bagging_fraction': 1,
  74.             'bagging_freq':0,
  75.  
  76.             'lambda_l1': 0,
  77.             'lambda_l2': 0,
  78.             'min_split_gain': 0
  79. }
  80.  
  81. print("开始训练")
  82. gbm = lgb.train(params,                     # 参数字典
  83.                 lgb_train,                  # 训练集
  84.                 num_boost_round=2000,       # 迭代次数
  85.                 valid_sets=lgb_eval,        # 验证集
  86.                 early_stopping_rounds=30)   # 早停系数
  87. ### 线下预测
  88. print ("线下预测")
  89. preds_offline = gbm.predict(offline_test_X, num_iteration=gbm.best_iteration) # 输出概率
  90. offline=offline_test[['instance_id','is_trade']]
  91. offline['preds']=preds_offline
  92. offline.is_trade = offline['is_trade'].astype(np.float64)
  93. print('log_loss', metrics.log_loss(offline.is_trade, offline.preds))
  94.  
  95. ### 线上预测
  96. print("线上预测")
  97. preds_online =  gbm.predict(online_test_X, num_iteration=gbm.best_iteration)  # 输出概率
  98. online=online_test[['instance_id']]
  99. online['preds']=preds_online
  100. online.rename(columns={'preds':'predicted_score'},inplace=True)
  101. online.to_csv("./data/20180405.txt",index=None,sep=' ')
  102.  
  103. ### 保存模型
  104. from sklearn.externals import joblib
  105. joblib.dump(gbm,'gbm.pkl')
  106.  
  107. ### 特征选择
  108. df = pd.DataFrame(X.columns.tolist(), columns=['feature'])
  109. df['importance']=list(gbm.feature_importance())
  110. df = df.sort_values(by='importance',ascending=False)
  111. df.to_csv("./data/feature_score_20180405.csv",index=None,encoding='gbk')

调参案例

  lightgbm使用leaf_wise tree生长策略，leaf_wise_tree的优点是收敛速度快，缺点是容易过拟合。

# lightgbm关键参数

image

  1. # -*- coding: utf-8 -*-
  2. """
  3. # 作者：wanglei5205
  4. # 邮箱：wanglei5205@126.com
  5. # 博客：http://cnblogs.com/wanglei5205
  6. # github：http://github.com/wanglei5205
  7. """
  8. ### 导入模块
  9. import numpy as np
  10. import pandas as pd
  11. import lightgbm as lgb
  12. from sklearn import metrics
  13.  
  14. ### 载入数据
  15. print('载入数据')
  16. dataset1 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data1.csv')
  17. dataset2 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data2.csv')
  18. dataset3 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data3.csv')
  19. dataset4 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data4.csv')
  20. dataset5 = pd.read_csv('G:/ML/ML_match/IJCAI/data3.22/3.22ICJAI/data/7_train_data5.csv')
  21.  
  22. print('数据去重')
  23. dataset1.drop_duplicates(inplace=True)
  24. dataset2.drop_duplicates(inplace=True)
  25. dataset3.drop_duplicates(inplace=True)
  26. dataset4.drop_duplicates(inplace=True)
  27. dataset5.drop_duplicates(inplace=True)
  28.  
  29. print('数据合并')
  30. trains = pd.concat([dataset1,dataset2],axis=0)
  31. trains = pd.concat([trains,dataset3],axis=0)
  32. trains = pd.concat([trains,dataset4],axis=0)
  33.  
  34. online_test = dataset5
  35.  
  36. ### 数据拆分(训练集+验证集+测试集)
  37. print('数据拆分')
  38. from sklearn.model_selection import train_test_split
  39. train_xy,offline_test = train_test_split(trains,test_size = 0.2,random_state=21)
  40. train,val = train_test_split(train_xy,test_size = 0.2,random_state=21)
  41.  
  42. # 训练集
  43. y_train = train.is_trade                                               # 训练集标签
  44. X_train = train.drop(['instance_id','is_trade'],axis=1)                # 训练集特征矩阵
  45.  
  46. # 验证集
  47. y_val = val.is_trade                                                   # 验证集标签
  48. X_val = val.drop(['instance_id','is_trade'],axis=1)                    # 验证集特征矩阵
  49.  
  50. # 测试集
  51. offline_test_X = offline_test.drop(['instance_id','is_trade'],axis=1)  # 线下测试特征矩阵
  52. online_test_X  = online_test.drop(['instance_id'],axis=1)              # 线上测试特征矩阵
  53.  
  54. ### 数据转换
  55. print('数据转换')
  56. lgb_train = lgb.Dataset(X_train, y_train, free_raw_data=False)
  57. lgb_eval = lgb.Dataset(X_val, y_val, reference=lgb_train,free_raw_data=False)
  58.  
  59. ### 设置初始参数--不含交叉验证参数
  60. print('设置参数')
  61. params = {
  62.           'boosting_type': 'gbdt',
  63.           'objective': 'binary',
  64.           'metric': 'binary_logloss',
  65.           }
  66.  
  67. ### 交叉验证(调参)
  68. print('交叉验证')
  69. min_merror = float('Inf')
  70. best_params = {}
  71.  
  72. # 准确率
  73. print("调参1：提高准确率")
  74. for num_leaves in range(20,200,5):
  75.     for max_depth in range(3,8,1):
  76.         params['num_leaves'] = num_leaves
  77.         params['max_depth'] = max_depth
  78.  
  79.         cv_results = lgb.cv(
  80.                             params,
  81.                             lgb_train,
  82.                             seed=2018,
  83.                             nfold=3,
  84.                             metrics=['binary_error'],
  85.                             early_stopping_rounds=10,
  86.                             verbose_eval=True
  87.                             )
  88.  
  89.         mean_merror = pd.Series(cv_results['binary_error-mean']).min()
  90.         boost_rounds = pd.Series(cv_results['binary_error-mean']).argmin()
  91.  
  92.         if mean_merror < min_merror:
  93.             min_merror = mean_merror
  94.             best_params['num_leaves'] = num_leaves
  95.             best_params['max_depth'] = max_depth
  96.  
  97. params['num_leaves'] = best_params['num_leaves']
  98. params['max_depth'] = best_params['max_depth']
  99.  
  100. # 过拟合
  101. print("调参2：降低过拟合")
  102. for max_bin in range(1,255,5):
  103.     for min_data_in_leaf in range(10,200,5):
  104.             params['max_bin'] = max_bin
  105.             params['min_data_in_leaf'] = min_data_in_leaf
  106.  
  107.             cv_results = lgb.cv(
  108.                                 params,
  109.                                 lgb_train,
  110.                                 seed=42,
  111.                                 nfold=3,
  112.                                 metrics=['binary_error'],
  113.                                 early_stopping_rounds=3,
  114.                                 verbose_eval=True
  115.                                 )
  116.  
  117.             mean_merror = pd.Series(cv_results['binary_error-mean']).min()
  118.             boost_rounds = pd.Series(cv_results['binary_error-mean']).argmin()
  119.  
  120.             if mean_merror < min_merror:
  121.                 min_merror = mean_merror
  122.                 best_params['max_bin']= max_bin
  123.                 best_params['min_data_in_leaf'] = min_data_in_leaf
  124.  
  125. params['min_data_in_leaf'] = best_params['min_data_in_leaf']
  126. params['max_bin'] = best_params['max_bin']
  127.  
  128. print("调参3：降低过拟合")
  129. for feature_fraction in [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]:
  130.     for bagging_fraction in [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]:
  131.         for bagging_freq in range(0,50,5):
  132.             params['feature_fraction'] = feature_fraction
  133.             params['bagging_fraction'] = bagging_fraction
  134.             params['bagging_freq'] = bagging_freq
  135.  
  136.             cv_results = lgb.cv(
  137.                                 params,
  138.                                 lgb_train,
  139.                                 seed=42,
  140.                                 nfold=3,
  141.                                 metrics=['binary_error'],
  142.                                 early_stopping_rounds=3,
  143.                                 verbose_eval=True
  144.                                 )
  145.  
  146.             mean_merror = pd.Series(cv_results['binary_error-mean']).min()
  147.             boost_rounds = pd.Series(cv_results['binary_error-mean']).argmin()
  148.  
  149.             if mean_merror < min_merror:
  150.                 min_merror = mean_merror
  151.                 best_params['feature_fraction'] = feature_fraction
  152.                 best_params['bagging_fraction'] = bagging_fraction
  153.                 best_params['bagging_freq'] = bagging_freq
  154.  
  155. params['feature_fraction'] = best_params['feature_fraction']
  156. params['bagging_fraction'] = best_params['bagging_fraction']
  157. params['bagging_freq'] = best_params['bagging_freq']
  158.  
  159. print("调参4：降低过拟合")
  160. for lambda_l1 in [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]:
  161.     for lambda_l2 in [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]:
  162.         for min_split_gain in [0.0,0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]:
  163.             params['lambda_l1'] = lambda_l1
  164.             params['lambda_l2'] = lambda_l2
  165.             params['min_split_gain'] = min_split_gain
  166.  
  167.             cv_results = lgb.cv(
  168.                                 params,
  169.                                 lgb_train,
  170.                                 seed=42,
  171.                                 nfold=3,
  172.                                 metrics=['binary_error'],
  173.                                 early_stopping_rounds=3,
  174.                                 verbose_eval=True
  175.                                 )
  176.  
  177.             mean_merror = pd.Series(cv_results['binary_error-mean']).min()
  178.             boost_rounds = pd.Series(cv_results['binary_error-mean']).argmin()
  179.  
  180.             if mean_merror < min_merror:
  181.                 min_merror = mean_merror
  182.                 best_params['lambda_l1'] = lambda_l1
  183.                 best_params['lambda_l2'] = lambda_l2
  184.                 best_params['min_split_gain'] = min_split_gain
  185.  
  186. params['lambda_l1'] = best_params['lambda_l1']
  187. params['lambda_l2'] = best_params['lambda_l2']
  188. params['min_split_gain'] = best_params['min_split_gain']
  189.  
  190.  
  191. print(best_params)
  192.  
  193. ### 训练
  194. params['learning_rate']=0.01
  195. lgb.train(
  196.           params,                     # 参数字典
  197.           lgb_train,                  # 训练集
  198.           valid_sets=lgb_eval,        # 验证集
  199.           num_boost_round=2000,       # 迭代次数
  200.           early_stopping_rounds=50    # 早停次数
  201.           )
  202.  
  203. ### 线下预测
  204. print ("线下预测")
  205. preds_offline = lgb.predict(offline_test_X, num_iteration=lgb.best_iteration) # 输出概率
  206. offline=offline_test[['instance_id','is_trade']]
  207. offline['preds']=preds_offline
  208. offline.is_trade = offline['is_trade'].astype(np.float64)
  209. print('log_loss', metrics.log_loss(offline.is_trade, offline.preds))
  210.  
  211. ### 线上预测
  212. print("线上预测")
  213. preds_online =  lgb.predict(online_test_X, num_iteration=lgb.best_iteration)  # 输出概率
  214. online=online_test[['instance_id']]
  215. online['preds']=preds_online
  216. online.rename(columns={'preds':'predicted_score'},inplace=True)           # 更改列名
  217. online.to_csv("./data/20180405.txt",index=None,sep=' ')                   # 保存结果
  218.  
  219. ### 保存模型
  220. from sklearn.externals import joblib
  221. joblib.dump(lgb,'lgb.pkl')
  222.  
  223. ### 特征选择
  224. df = pd.DataFrame(X_train.columns.tolist(), columns=['feature'])
  225. df['importance']=list(lgb.feature_importance())                           # 特征分数
  226. df = df.sort_values(by='importance',ascending=False)                      # 特征排序
  227. df.to_csv("./data/feature_score_20180331.csv",index=None,encoding='gbk')  # 保存分数

 

声明：本文内容由网友自发贡献，不代表【wpsshop博客】立场，版权归原作者所有，本站不承担相应法律责任。如您发现有侵权的内容，请联系我们。转载请注明出处：https://www.wpsshop.cn/w/盐析白兔/article/detail/258074
推荐阅读
相关标签

Copyright © 2003-2013 www.wpsshop.cn 版权所有，并保留所有权利。

  

闽ICP备14008679号