对于 450 个 50000 维的数据样本，有什么好的方法做降维嘛？ - V2EX
Home Sign Up Sign In
V2EX = way to explore
V2EX 是一个关于分享和探索的地方
Sign Up Now
For Existing Member  Sign In
Leesky

对于 450 个 50000 维的数据样本，有什么好的方法做降维嘛？

  •   
  •   Leesky Dec 7, 2018 1649 views
    This topic created in 2700 days ago, the information mentioned may be changed or developed.

    数据可能存在共线性问题，但是想用非线性降维，然后用非线性分类器做二分类预测，但是想不到好的降维方法。

  • 降维
  • 非线性
  • 分类器
  • 线性
    6 replies    2018-12-08 22:23:12 +08:00
    szxczyc
        1
    szxczyc  
       Dec 7, 2018 via iPhone
    做过 100000 个 8000 维的，二分类，没有降维，特征工程。
    binux
        2
    binux  
       Dec 7, 2018 via Android
    维度比样本数多那么多。。。人肉先验知识降吧。。
    Mohanson
        3
    Mohanson  
       Dec 7, 2018 via Android
    流形学习。http://accu.cc/content/daze/sklearn/manifold/
    shakoon
        4
    shakoon  
       Dec 7, 2018
    乘法交换律了解一下
    Leesky
        5
    Leesky  
    OP
       Dec 8, 2018
    @Mohanson 我是想尝试用 t-sne 来着，但是看了下是做降维可视化的，而且降到 2,3 维，但是我需要找的维数不可能这么低，所以现在也在试试用这个 t-sne 自己设置自由度，看效果如何
    Leesky
        6
    Leesky  
    OP
       Dec 8, 2018
    @szxczyc 我也是做二分类的
    About     Help     Advertise     Blog     API     FAQ     Solana     3706 Online   Highest 6679       Select Language
    创意工作者们的社区
    World is powered by solitude
    VERSION: 3.9.8.5 41ms UTC 10:34 PVG 18:34 LAX 03:34 JFK 06:34
    Do have faith in what you're doing.
    ubao msn snddm index pchome yahoo rakuten mypaper meadowduck bidyahoo youbao zxmzxm asda bnvcg cvbfg dfscv mmhjk xxddc yybgb zznbn ccubao uaitu acv GXCV ET GDG YH FG BCVB FJFH CBRE CBC GDG ET54 WRWR RWER WREW WRWER RWER SDG EW SF DSFSF fbbs ubao fhd dfg ewr dg df ewwr ewwr et ruyut utut dfg fgd gdfgt etg dfgt dfgd ert4 gd fgg wr 235 wer3 we vsdf sdf gdf ert xcv sdf rwer hfd dfg cvb rwf afb dfh jgh bmn lgh rty gfds cxv xcv xcs vdas fdf fgd cv sdf tert sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf sdf shasha9178 shasha9178 shasha9178 shasha9178 shasha9178 liflif2 liflif2 liflif2 liflif2 liflif2 liblib3 liblib3 liblib3 liblib3 liblib3 zhazha444 zhazha444 zhazha444 zhazha444 zhazha444 dende5 dende denden denden2 denden21 fenfen9 fenf619 fen619 fenfe9 fe619 sdf sdf sdf sdf sdf zhazh90 zhazh0 zhaa50 zha90 zh590 zho zhoz zhozh zhozho zhozho2 lislis lls95 lili95 lils5 liss9 sdf0ty987 sdft876 sdft9876 sdf09876 sd0t9876 sdf0ty98 sdf0976 sdf0ty986 sdf0ty96 sdf0t76 sdf0876 df0ty98 sf0t876 sd0ty76 sdy76 sdf76 sdf0t76 sdf0ty9 sdf0ty98 sdf0ty987 sdf0ty98 sdf6676 sdf876 sd876 sd876 sdf6 sdf6 sdf9876 sdf0t sdf06 sdf0ty9776 sdf0ty9776 sdf0ty76 sdf8876 sdf0t sd6 sdf06 s688876 sd688 sdf86