search for: wpk

...data, I came across the use of the Hellinger distance as an alternative to information gain [1,2], when dealing with skewed data. Does anybody know of R implementations of this approach to decision trees? Thanks, [1] http://www.cse.nd.edu/Reports/2008/TR-2008-06.pdf [2] http://csmr.ca.sandia.gov/~wpk/slides/wdmda-sem.pdf -- Rajarshi Guha NIH Chemical Genomics Center [[alternative HTML version deleted]]

...1200Kbits/second. However, in testing, if I set that for a VNIC, the domU gets no traffic at all (maybe the occassional packet). Is the minimum too low? If I set a maximum of 2000Kbits/second, I get this from nicstat (expecting around 250Kbytes/s total: Time Int rKB/s wKB/s rPk/s wPk/s rAvs wAvs %Util Sat 04:35:38 xvm15_0 146.6 5.32 102.0 73.65 1471.3 74.00 62.21 0.00 04:35:43 xvm15_0 161.6 5.92 112.0 82.24 1477.4 73.68 68.60 0.00 What is the expected accuracy of the bandwidth limiting? I''m using b111. thanks john

...1200Kbits/second. However, in testing, if I set that for a VNIC, the domU gets no traffic at all (maybe the occassional packet). Is the minimum too low? If I set a maximum of 2000Kbits/second, I get this from nicstat (expecting around 250Kbytes/s total: Time Int rKB/s wKB/s rPk/s wPk/s rAvs wAvs %Util Sat 04:35:38 xvm15_0 146.6 5.32 102.0 73.65 1471.3 74.00 62.21 0.00 04:35:43 xvm15_0 161.6 5.92 112.0 82.24 1477.4 73.68 68.60 0.00 What is the expected accuracy of the bandwidth limiting? I''m using b111. thanks john

...d z?R-s_i<whH38dJQ2kR^yTPL{*FA8F- at 0$O)xug<Vjg%<(t?LoNke1ldaErJPRIpWj zf;H0F9Ucq~Ev&6=@tYq%4AU3r?XAtMsH?6`8nW1LO}^Z4U2SbJ6iKQ)?DoW62{_Pm z`K`zy?DGJ`GHgm0o6^L3CQ^qb)g5k5|0*v|5SPZiC+X5ChodY|0>8g5>?jMF5xrdO z1kQl3GGekgt<Uk^h}ZB$EOw{xsLgy3?V|FX3iHUoh}dmpnG4cPn3cg#hl`Ewl>1yE zaWpkEQB)jOSlFuA?h|5GyUZiI=dhb}mj&U;R9l0wd*`q#=jLOQislJ|NP1Y~#=651 z-YlBkm at jRJPmt2Um|r91dkH(@^h9%==3R=IkgVtw#c0vnHS0N!(^rkrijRdA;shS( zC7#3l)@KgeEt8))Ebq+_Ga=cW5pS7AbVMwtEkk}_>k-HA68_~KsN8Q}%|x#PE!ss# z1XF35>5Am~YCHq_w>BBXUT8VgIk5*rUE&@L>2jmuI63*eVV^GdFbY?}%dK~nI{dA= z+7z>dHO{=a...