2013-03-01ãã1ã¶æéã®è¨äºä¸è¦§
æ°å¦ãããã®å»ç§çµ±è¨å¦PART7 CHAPTER34ã®ã¢ãã«ã®ç´¹ä»ã®è©±ã ã¢ãã«ããµã³ãã«ãã¼ã¿ã«é©åãããã¨ãã¢ãã«ã®ããããã®ãã©ã¡ã¼ã¿ã«å¯¾ãã¦æ¨å®å¤ãä¿¡é ¼åºéãå¾ãããã ã¨ãã£ã¦ãæè¦å´ããè¨æ¶ãããã®ã ããdrc ããã±ã¼ã¸ä¸ã«ãã®é¢åããã£ã¦ãããâ¦
debug() ã¨ãããããã°é¢æ°ãåå¼·ããã ä»ãé£ç¶ããï¼ã®éå§ç¹ãè¦ã¤ããé¢æ°findruns()ãä½ã£ãã¨ããã ã¨ããããããã¹ããã¼ã¿ã§è©¦ãã¦ã¿ã㨠# 誤ããã findruns <- function(x,k) { n <- length(x) runs <- NULL for (i in 1:(n-k)) { if (all(x[â¦
80M 転å 1wå å³ 3æ¥å æ¯åã å ¥é¢å½æ¥ 転å ã¿ãã³ 20*25y é ç¼é ä¸å DM HT åç«è ºç èºç(2y èºççè) ã¯ã¯ãã³æ¥ç¨®ãã SUè¬ ãããã¬ã¹ ROS (+) åç° å¼å¸è¦(å´ä½æ) å¦æ æ (-) æèæ¶å¤± è±å æ§é³é害 çºç± åè¡ å°¿éå¤å ãã³ã æµ®è « DDx PE, pnâ¦
ããã¯ãã³ãã¼
82F 20æé ãã¤ã¬ã«è¡ãæãæ®æ®µã¯ã¦ããã§ç«ã¦ããããã®æã¯ç«ã¦ãªãã£ãã 22æé ãæ¯é£ããèããã¨ã«å®¶äººãæ°ã¥ããã ãã®å¾ãä½ãç±ã£ã½ããã¨ã«æ°ã¥ããä½æ¸©ã測ãã¨42度ã ã£ãã 24æé ãææ¥è¦è«ã ææ¥ Aï¼å¼å¸æã Bï¼RR 32 SpO2 93% (室å æ°)â9â¦
name age height weight B W H 天海æ¥é¦ 17 158 46 83 56 82 é«æ§»ããã 14 145 37 74 54 78 èå°ç 17 159 44 75 57 78 æé£è¦é¿ 16 152 41 83 56 80 島æå¯æ 17 159 45 83 59 87 ä¸éæé¦ 18 149 40 77 57 81 æ°´æ¬ããã 15 155 42 81 56 82 ç¦å±±è 10 13â¦
Journal Clubã§FRaCã¨ããæ©æ¢°å¦ç¿ãç´¹ä»ããã æå¾ã«ã確èªã¨ãã¦ãããªåé¡ãåºããã ã¢ã¤ãã«174人åã®ãã¼ã¿ã»ããimas1.txtãããã ãã®ä¸ã§ä»ã®ã¡ã³ãã¼ã¨ã¯æããã«éãç¹å¾´ããã£ãã¢ã¤ãã«ããããMinPtsã10ç¨åº¦ã«è¨å®ãã¦æ¤åºãããªã¬ã®å¥½ããªâ¦
æ¥æ¬å°å³ãæãç¨äºããã£ãã®ã§æãã£ãããã«ããä¸åº¦ãããã¨æã£ãã ã ãããããGlobal Administrative Areaããå°å³ãã¼ã¿ããã¦ã³ãã¼ããã¦ãããããã¡ã¤ã«åã®ä»æ§ãå¤ãã£ã¦ãã¦ã¡ãã£ã¨ã¦ããã£ãã library(spsurvey) jpn_GA <- vector("list"â¦
éå¡åé¡ã®ãã¼ã¿ã»ãããhundred.txtã¨ãã¦ä¿åããã T:決å®æ¨ãR:RBF-kernel SVMãN:linear-kernel SVMãS:決å®æ ªã®ã¢ãã«ãããã¤ãçµã¿åããã¦ã¿ãã #detectã¹ã¯ãªãããããfracãã£ã¬ã¯ããªã§ python detect -X ~/Desktop/hundred.txt -Q ~/Desktopâ¦
Rã§å®è£ ã§ãã¾ããã§ãããPythonã§ããã¾ãã OSã¯Ubuntu 12.04ã ã¾ãFRaCã®ãµã¤ããããææ°çã®ã¹ã¯ãªããããã¦ã³ãã¼ããã¦è§£åãããfracã¨ãããã©ã«ããã§ãã(ã¨æã)ããããã§ä½æ¥ãããã¨ã«ããã LIBSVMã¨ããSVMè¨ç®ãè¡ãã½ãããå°å ¥ãããâ¦
åã®ãµã³ãã«ãããæè²ç¨ãã¼ã¿ã»ãã ããã£ã¦ããããã¯ãã¹ã¦æ£å¸¸ã®ã¯ã©ã¹ããã¤ã¨ãã(åæ師æãå¦ç¿)ã åã¯æ±ºã¾ã£ãé·ãåã®ç¹å¾´éãæã£ã¦ãã¦ãå義å¤æ°ãé£ç¶å¤æ°ã®å±æ§ããã£ã¦ãæ··åãã¦ãã¦ãããã ãããããã¨ã¯ãå¼æ°ãã¯ãã«ãã²ã¨ã¤ã®å®â¦
Journal Clubãã¿ã§FRaCã¨ããå¤ãå¤æ¤åºãããã éå¡åé¡ã§ã¯ãn次å ä¸ã®åç¹ã¨ã®è·é¢ãèãããSVMã®ãããªDistance modelã¨ãåç¹å¨è¾ºã®å¯åº¦ãèãããLOFã®ãããªDensity modelã¨ãããã FRaCã¯ããã¤ãã®ã¢ãã«ã®ç¹å¾´éãçµã¿åãããããããRã§æ¸ãâ¦
Gene Ontologyã®è©±ã Rã ã¨FunNet, GOSim, geneListPieã¨ããããã±ã¼ã¸ããããããã(GOSimã¯ã¤ã³ã¹ãã¼ã«ããã¾ããããªãã£ãã) library(geneListPie) data(goslim.human.BP) glist <- c("ABCB7", "ABCF1", "ABHD2", "ACAD9", "ACIN1", "AMOTL1", "ANLNâ¦
çãã¯87çªç®ã®ãã¼ã¿ã ä¸ãã³ãããã¦ãåè§ã¹ãã¼ã¹åºåãã§èªã¿è¾¼ãã data0 <- read.delim("clipboard", sep=" ", header=FALSE) cols <- rep(1, nrow(data0)) cols[87] <- 2 69.613 129.070 52.111 70.670 128.161 52.446 72.303 128.450 52.853 73.75â¦
è¿åæ³ã¯è¿ãç¹ã®è·é¢ãè¨ç®ããã library(FNN) #k-nearest neighbor # ??? works not well topn <- 8 alg <- c("cover_tree", "kd_tree", "VR", "CR", "brute") res <- array(0, c(nrow(data0), topn, length(alg))) for(i in seq(nrow(data0))){ for(alg0â¦
k-meansæ³ã¯ãã¨ãã¨ããä¼¼ã¦ãããã®ãã¾ã¨ãããæ¹æ³ãªã®ã§ãã仲éã¯ãããæ¢ããæ¹æ³ã¨ãã¦ã¯ãããªããã¨ãããã ä»åã¯ã°ãã°ãã k0 <- 2:10 kcluster <- matrix(0, nr=length(k0), nc=nrow(data0)) for(k1 in seq(k0)){ kcluster[k1, ] <- kmeans(dâ¦
決å®æ¨ãããããä½ãRandomForestsã library(randomForest) rf0 <- randomForest(data0) MDSplot(rf0, cols, k=3) ã©ããããããããä¸çªããããããçµæãè¦ãããã¾ã ããã£ã¦ãªãã®ã§ãããªå³ã«ã çãã ãã強調ãããããã¨ãªããããªæ°åã«ãªãã
åãã©ã¡ã¼ã¿ã¯é¢ä¿ããã£ãããããã¨ãããã®ã§ãç¡é¢ä¿ãªä¸»æåã«ãã¦ã¿ãã pca_score <- scale(data0) %*% eigen(cor(data0))$vectors *sqrt(nrow(data0)/(nrow(data0) - 1)) library(rgl) plot3d(pca_score, type="n", xlab="PC1", ylab="PC2", zlab="â¦
è¶ å¹³é¢ã¨ããä¸äºç çå¢çç·ãå¼ãã æ¬å½ã¯tuningãå¿ è¦ãããã®ã ããä»åã¯ç¡è¦ã #one class SVM library(e1071) #non-supervised svm0 <- svm(data0, type="one-classification") pred0 <- predict(svm0, data0) pred0 plot(data0, pch=16, col=(!pred0â¦
ãã®åé¡ã解ãã®ã«æãããã®ã¯LOF(è«æ)ããããããç¹è¿åã®ç¹ã®æ°ããã©ã¡ã¼ã¿ã«ãã¦ãå¤ãå¤ãªãã¾ãããå°ãªãã®ã§ã¯ãªããã¨ãã⦠library(Rlof) lof0 <- lof(data0, 5:10) plot(lof0[,1], pch=16, col=cols) matplot(lof0, pch=16, ylab="LOF score"â¦
æ©æ¢°å¦ç¿ãç¨ãã¦ãé¸ãã§ã¯ãããªãéå¡ãè¦ã¤ãåºãåé¡ã è¨å®ã¯ã100åã®éå¡ã£ã½ããã®ã®ãã¡ã1ã¤ã ããçã®éå¡ãåã ã®éå¡ã£ã½ããã®ã«ã¯ã3ã¤ã®ãã©ã¡ã¼ã¿ãããã æ¬ç©ã®éå¡ãé¸ã¶ã»ããå®ã¯ãããªãã åé¡ã¨ãã¦ã¯ã100åã®ä¸ããç°å¸¸ãªãã¼ã¿â¦
ãããç»åãå¤ãã¦ããã¾ã¨ã¾ã£ã¦ããã ç§å¯è¦å¯ãã¦ãããããããããªã¨æããªãããæ²ãè´ãã¤ã¤ä¼å ´å ¥ããããããã£ã±ãªãããã¦ãã³ã·ã§ã³ä¸ãã£ãã
æ°å¦ãããã®å»ç§çµ±è¨å¦PART5 CHAPTER22ã®å¤éæ¤å®ã®è©±ã å¤éæ¤å®ã«ã¤ãã¦ã¯ãããã¨è²ã åºã¦ããã Rã§ã¯p.adjustã¨ããé¢æ°ã§på¤ãåææ³ã§è£æ£ãã¦ãããããã ãã¨ããããå ¨é¨ãã£ã¦ã¿ãã set.seed(123) x <- rnorm(50, mean = c(rep(0, 25), rep(3, â¦
ç®±ã²ãå³ã«på¤ã¨ã©ã®ç¾¤ãæ¯è¼ãããæ£ãã¤ãã¦ããå³ãè«æã§ããè¦ãããããRã«ã¯ããã楽ã«æãã¦ããããããªæ©è½ããªãã ã¨ããã®ããå¤éæ¯è¼ã«é¢ããããé£ããããæ£ãã¤ãããã¤ããã§ã´ãã£ã´ãã£ãããããªã®ã ãã⦠ãã ããã®å³ãæãããã¨ãâ¦