我正在使用R执行我的分析,我将执行四种算法。分类任务中的所有二元预测变量
1. RF
2. Log Reg
3. SVM
4. LDA
我有50个预测变量和1个目标变量。我所有的预测变量和目标变量都只有二进制数字0和1。
我有以下问题:
Should I convert them all into factors?
Converting them into factors, and applying RF algorithms give 100% accuracy, I am very much surprised to see that as well.
Also, for other algorithms, how should i treat my variables priorly, before feeding them into my other algorithms.
感谢
https://stats.stackexchange.com/a/112052/1569 –
@HongOoi,即使在测试数据。 – Shivam