【发布时间】:2016-01-30 06:41:50
【问题描述】:
我有一个数据集,我在其中使用 WEKA 中的信息增益特征选择方法来获取重要特征。下面是我得到的输出。
Ranked attributes:
0.97095 1 Opponent
0.41997 11 Field_Goals_Made
0.38534 24 Opp_Free_Throws_Made
0.00485 4 Home
0 8 Field_Goals_Att
0 12 Opp_Total_Rebounds
0 10 Def_Rebounds
0 9 Total_Rebounds
0 6 Opp_Field_Goals_Made
0 7 Off_Rebounds
0 14 Opp_3Pt_Field_Goals_Made
0 2 Fouls
0 3 Opp_Blocks
0 5 Opp_Fouls
0 13 Opp_3Pt_Field_Goals_Att
0 29 3Pt_Field_Goal_Pct
0 28 3Pt_Field_Goals_Made
0 22 3Pt_Field_Goals_Att
0 25 Free_Throws_Made
这告诉我所有得分为 0 的特征都可以忽略,对吗?
现在,当我在 WEKA 中尝试 Wrapper 子集评估时,我得到了在信息增益方法中被忽略的选定属性(即其分数为 0)。下面是输出
Selected attributes: 3,8,9,11,24,25 : 6
Opp_Blocks
Field_Goals_Att
Total_Rebounds
Field_Goals_Made
Opp_Free_Throws_Made
Free_Throws_Made
我想明白,被信息增益忽略的属性被包装子集评估方法强烈考虑的原因是什么?
【问题讨论】:
标签: machine-learning artificial-intelligence weka feature-selection