ML之xgboost：利用xgboost算法(sklearn+GridSearchCV)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)

晴空万里
晴空万里 2022-09-19 14:44:18 50195
分类专栏： 资讯

ML之xgboost：利用xgboost算法(sklearn+GridSearchCV)训练mushroom蘑菇数据集(22+1,6513+1611)来预测蘑菇是否毒性(二分类预测)

目录

输出结果

设计思路

核心代码

更多输出

输出结果

正在更新……

设计思路

正在更新……

核心代码

  1. from sklearn.grid_search import GridSearchCV
  2.  
  3. param_test = { 'n_estimators': range(1, 51, 1)}
  4. clf = GridSearchCV(estimator = bst, param_grid = param_test, cv=5)
  5. clf.fit(X_train, y_train)
  6. clf.grid_scores_, clf.best_params_, clf.best_score_
  7.  
  8.  
  9.  
  10. grid_scores_mean= [0.90542,  0.94749,  0.90542,  0.94749,  0.90573,  0.94718, 
  11.                    0.90542,  0.94242,  0.94473,  0.97482,  0.94887,  0.97850, 
  12.                    0.97298,  0.97850,  0.97298,  0.97850,  0.97850,  0.97850, 
  13.                    0.97850,  0.97850,  0.97850,  0.97850,  0.97850,  0.97850, 
  14.                    0.97850,  0.97804,  0.97774,  0.97835,  0.98296,  0.98419,    
  15.                    0.98342,  0.98372,  0.98419,  0.98419,  0.98419,  0.98419, 
  16.                    0.98419,  0.98419,  0.98419,  0.98419,  0.98419,  0.98419, 
  17.                    0.98419,  0.98419,  0.98419,  0.98419,  0.98419,  0.98419, 
  18.                    0.98419 ]
  19.  
  20.  
  21. grid_scores_std = [0.08996,  0.07458,  0.08996,  0.07458,  0.09028,  0.07436,  
  22.                    0.08996,  0.07331,  0.07739,  0.02235,  0.07621,  0.02387,  
  23.                    0.03186,  0.02387,  0.03186,  0.02387,  0.02387,  0.02387,  
  24.                    0.02387,  0.02387,  0.02387,  0.02387,  0.02387,  0.02387,  
  25.                    0.02387,  0.02365,  0.02337,  0.02383,  0.01963,  0.02040,  
  26.                    0.01988,  0.02008,  0.02040,  0.02040,  0.02040,  0.02040,  
  27.                    0.02040,  0.02040,  0.02040,  0.02040,  0.02040,  0.02040,  
  28.                    0.02040,  0.02040,  0.02040,  0.02040,  0.02040,  0.02040,  
  29.                    0.02040  ]
  30.  
  31.  
  32. 7-CrVa交叉验证曲线可视化
  33. import matplotlib.pyplot as plt
  34.  
  35. x = range(0,len(grid_scores_mean))
  36. y1 = grid_scores_mean
  37. y2 = grid_scores_std
  38. Xlabel = 'n_estimators'
  39. Ylabel = 'value'
  40. title = 'mushroom datase: xgboost(sklearn+GridSearchCV) model'
  41.  
  42. plt.plot(x,y1,'r',label='Mean')                      绘制mean曲线
  43. plt.plot(x,y2,'g',label='Std')                       绘制std曲线
  44.  
  45. plt.rcParams['font.sans-serif']=['Times New Roman']  手动添加中文字体，或者['font.sans-serif'] = ['FangSong']   SimHei
  46. myfont = matplotlib.font_manager.FontProperties(fname='C:/Windows/Fonts/msyh.ttf')  也可以指定win系统字体路径
  47. plt.rcParams['axes.unicode_minus'] = False  对坐标轴的负号进行正常显示
  48.  
  49. plt.xlabel(Xlabel)
  50. plt.ylabel(Ylabel)
  51. plt.title(title)
  52.  
  53. plt.legend(loc=1)   
  54. plt.show()

更多输出

  1. GridSearchCV time： 79.7655139499154
  2. clf.grid_scores_： [mean: 0.90542, std: 0.08996, params: {'n_estimators': 1}, mean: 0.94749, std: 0.07458, params: {'n_estimators': 2}, 
  3.                    mean: 0.90542, std: 0.08996, params: {'n_estimators': 3}, mean: 0.94749, std: 0.07458, params: {'n_estimators': 4}, 
  4.                    mean: 0.90573, std: 0.09028, params: {'n_estimators': 5}, mean: 0.94718, std: 0.07436, params: {'n_estimators': 6}, 
  5.                    mean: 0.90542, std: 0.08996, params: {'n_estimators': 7}, mean: 0.94242, std: 0.07331, params: {'n_estimators': 8}, 
  6.                    mean: 0.94473, std: 0.07739, params: {'n_estimators': 9}, mean: 0.97482, std: 0.02235, params: {'n_estimators': 10}, 
  7.                    mean: 0.94887, std: 0.07621, params: {'n_estimators': 11}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 12}, 
  8.                    mean: 0.97298, std: 0.03186, params: {'n_estimators': 13}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 14}, 
  9.                    mean: 0.97298, std: 0.03186, params: {'n_estimators': 15}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 16}, 
  10.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 17}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 18}, 
  11.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 19}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 20}, 
  12.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 21}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 22}, 
  13.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 23}, mean: 0.97850, std: 0.02387, params: {'n_estimators': 24}, 
  14.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 25}, mean: 0.97804, std: 0.02365, params: {'n_estimators': 26}, 
  15.                    mean: 0.97774, std: 0.02337, params: {'n_estimators': 27}, mean: 0.97835, std: 0.02383, params: {'n_estimators': 28}, 
  16.                    mean: 0.98296, std: 0.01963, params: {'n_estimators': 29}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 30}, 
  17.                    mean: 0.98342, std: 0.01988, params: {'n_estimators': 31}, mean: 0.98372, std: 0.02008, params: {'n_estimators': 32}, 
  18.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 33}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 34}, 
  19.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 35}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 36}, 
  20.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 37}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 38}, 
  21.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 39}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 40}, 
  22.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 41}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 42}, 
  23.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 43}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 44}, 
  24.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 45}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 46}, 
  25.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 47}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 48}, 
  26.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 49}, mean: 0.98419, std: 0.02040, params: {'n_estimators': 50}]
  27. clf.best_params_： {'n_estimators': 30}
  28. clf.best_score_： 0.9841854752034392
  1. [mean: 0.90542, std: 0.08996, params: {'n_estimators': 1}, 
  2.                    mean: 0.94749, std: 0.07458, params: {'n_estimators': 2}, 
  3.                    mean: 0.90542, std: 0.08996, params: {'n_estimators': 3}, 
  4.                    mean: 0.94749, std: 0.07458, params: {'n_estimators': 4}, 
  5.                    mean: 0.90573, std: 0.09028, params: {'n_estimators': 5}, 
  6.                    mean: 0.94718, std: 0.07436, params: {'n_estimators': 6}, 
  7.                    mean: 0.90542, std: 0.08996, params: {'n_estimators': 7}, 
  8.                    mean: 0.94242, std: 0.07331, params: {'n_estimators': 8}, 
  9.                    mean: 0.94473, std: 0.07739, params: {'n_estimators': 9}, 
  10.                    mean: 0.97482, std: 0.02235, params: {'n_estimators': 10}, 
  11.                    mean: 0.94887, std: 0.07621, params: {'n_estimators': 11}, 
  12.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 12}, 
  13.                    mean: 0.97298, std: 0.03186, params: {'n_estimators': 13}, 
  14.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 14}, 
  15.                    mean: 0.97298, std: 0.03186, params: {'n_estimators': 15}, 
  16.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 16}, 
  17.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 17}, 
  18.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 18}, 
  19.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 19}, 
  20.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 20}, 
  21.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 21}, 
  22.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 22}, 
  23.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 23}, 
  24.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 24}, 
  25.                    mean: 0.97850, std: 0.02387, params: {'n_estimators': 25}, 
  26.                    mean: 0.97804, std: 0.02365, params: {'n_estimators': 26}, 
  27.                    mean: 0.97774, std: 0.02337, params: {'n_estimators': 27}, 
  28.                    mean: 0.97835, std: 0.02383, params: {'n_estimators': 28}, 
  29.                    mean: 0.98296, std: 0.01963, params: {'n_estimators': 29}, 
  30.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 30}, 
  31.                    mean: 0.98342, std: 0.01988, params: {'n_estimators': 31}, 
  32.                    mean: 0.98372, std: 0.02008, params: {'n_estimators': 32}, 
  33.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 33}, 
  34.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 34}, 
  35.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 35}, 
  36.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 36}, 
  37.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 37}, 
  38.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 38}, 
  39.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 39}, 
  40.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 40}, 
  41.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 41}, 
  42.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 42}, 
  43.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 43}, 
  44.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 44}, 
  45.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 45}, 
  46.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 46}, 
  47.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 47}, 
  48.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 48}, 
  49.                    mean: 0.98419, std: 0.02040, params: {'n_estimators': 49}]
  50.  
  51.  
  52. grid_scores_ = [mean: 0.90542, std: 0.08996, 
  53.                    mean: 0.94749, std: 0.07458, 
  54.                    mean: 0.90542, std: 0.08996, 
  55.                    mean: 0.94749, std: 0.07458, 
  56.                    mean: 0.90573, std: 0.09028, 
  57.                    mean: 0.94718, std: 0.07436,
  58.                    mean: 0.90542, std: 0.08996, 
  59.                    mean: 0.94242, std: 0.07331, 
  60.                    mean: 0.94473, std: 0.07739,  
  61.                    mean: 0.97482, std: 0.02235,
  62.                    mean: 0.94887, std: 0.07621, 
  63.                    mean: 0.97850, std: 0.02387, 
  64.                    mean: 0.97298, std: 0.03186,  
  65.                    mean: 0.97850, std: 0.02387, 
  66.                    mean: 0.97298, std: 0.03186,  
  67.                    mean: 0.97850, std: 0.02387, 
  68.                    mean: 0.97850, std: 0.02387,  
  69.                    mean: 0.97850, std: 0.02387, 
  70.                    mean: 0.97850, std: 0.02387, 
  71.                    mean: 0.97850, std: 0.02387, 
  72.                    mean: 0.97850, std: 0.02387, 
  73.                    mean: 0.97850, std: 0.02387, 
  74.                    mean: 0.97850, std: 0.02387,
  75.                    mean: 0.97850, std: 0.02387, 
  76.                    mean: 0.97850, std: 0.02387,
  77.                    mean: 0.97804, std: 0.02365,  
  78.                    mean: 0.97774, std: 0.02337, 
  79.                    mean: 0.97835, std: 0.02383, 
  80.                    mean: 0.98296, std: 0.01963, 
  81.                    mean: 0.98419, std: 0.02040,  
  82.                    mean: 0.98342, std: 0.01988, 
  83.                    mean: 0.98372, std: 0.02008, 
  84.                    mean: 0.98419, std: 0.02040,  
  85.                    mean: 0.98419, std: 0.02040,  
  86.                    mean: 0.98419, std: 0.02040,
  87.                    mean: 0.98419, std: 0.02040,
  88.                    mean: 0.98419, std: 0.02040,
  89.                    mean: 0.98419, std: 0.02040, 
  90.                    mean: 0.98419, std: 0.02040,
  91.                    mean: 0.98419, std: 0.02040,
  92.                    mean: 0.98419, std: 0.02040,
  93.                    mean: 0.98419, std: 0.02040, 
  94. 
            
    网站声明：如果转载，请联系本站管理员。否则一切后果自行承担。
    
          
    
        
          
    
            
              赞同  0
            
            
          
    
      
    
      
      
    
        评论 0 条
        
      
		              
    
		    
    
        
              
    
      
      
    
        
    相关文章
晴空万里
晴空万里L0
粉丝 0 发表 11 + 关注 私信
上周热门
如何使用 StarRocks 管理和优化数据湖中的数据？  2941
【软件正版化】软件正版化工作要点  2860
统信UOS试玩黑神话：悟空  2819
信刻光盘安全隔离与信息交换系统  2712
镜舟科技与中启乘数科技达成战略合作，共筑数据服务新生态  1246
grub引导程序无法找到指定设备和分区  1213
华为全联接大会2024丨软通动力分论坛精彩议程抢先看！  163
点击报名 | 京东2025校招进校行程预告  162
2024海洋能源产业融合发展论坛暨博览会同期活动-海洋能源与数字化智能化论坛成功举办  160
华为纯血鸿蒙正式版9月底见！但Mate 70的内情还得接着挖...  157
本周热议
我的信创开放社区兼职赚钱历程 40
今天你签到了吗？ 27
信创开放社区邀请他人注册的具体步骤如下 15
如何玩转信创开放社区—从小白进阶到专家 15
方德桌面操作系统 14
我有15积分有什么用? 13
用抖音玩法闯信创开放社区——用平台宣传企业产品服务 13
如何让你先人一步获得悬赏问题信息？（创作者必看） 12
2024中国信创产业发展大会暨中国信息科技创新与应用博览会 9
中央国家机关政府采购中心：应当将CPU、操作系统符合安全可靠测评要求纳入采购需求 8
热门标签更多

  • 关注我们

    信创开放社区公众号二维码

    扫一扫关注公众号

    信创开放社区交流群

    扫一扫加入交流群

加入交流群

请使用微信扫一扫!