## ----style, echo = FALSE, results = 'asis'-------------------------------------------------------- options(width=100) knitr::opts_chunk$set( eval=as.logical(Sys.getenv("KNITR_EVAL", "TRUE")), cache=as.logical(Sys.getenv("KNITR_CACHE", "TRUE"))) ## ----file.choose, eval=FALSE---------------------------------------------------------------------- # path <- file.choose() ## ----system.file, echo=FALSE---------------------------------------------------------------------- path <- system.file(package="BiocIntroRPCI", "extdata", "BRFSS-subset.csv") ## ----read.csv------------------------------------------------------------------------------------- brfss <- read.csv(path) ## ----brfss-sex------------------------------------------------------------------------------------ table(brfss$Sex) ## ----brfss-xtabs---------------------------------------------------------------------------------- xtabs(~ Year + Sex, brfss) ## ----brfss-aggregate------------------------------------------------------------------------------ aggregate(Weight ~ Year + Sex, brfss, mean) ## ----t-test-1990---------------------------------------------------------------------------------- brfss_1990 = brfss[brfss$Year == 1990,] t.test(Weight ~ Sex, brfss_1990) ## ----brfss-boxplot, fig.width=5, fig.height=5----------------------------------------------------- boxplot(Weight ~ Year, brfss, subset = (Sex == "Male"), main="Males") ## ----brfss-hist, fig.width=5, fig.height=5-------------------------------------------------------- hist(brfss_1990[brfss_1990$Sex == "Female", "Weight"], main="Females, 1990", xlab="Weight" ) ## ----echo=FALSE----------------------------------------------------------------------------------- path <- system.file(package="BiocIntroRPCI", "extdata", "ALL-phenoData.csv") ## ----ALL-choose, eval=FALSE----------------------------------------------------------------------- # path <- file.choose() # look for ALL-phenoData.csv ## ----ALL-input------------------------------------------------------------------------------------ stopifnot(file.exists(path)) pdata <- read.csv(path) ## ----ALL-properties------------------------------------------------------------------------------- class(pdata) colnames(pdata) dim(pdata) head(pdata) summary(pdata$sex) summary(pdata$cyto.normal) ## ----ALL-subset----------------------------------------------------------------------------------- pdata[1:5, 3:4] pdata[1:5, ] head(pdata[, 3:5]) tail(pdata[, 3:5], 3) head(pdata$age) head(pdata$sex) head(pdata[pdata$age > 21,]) ## ----ALL-subset-NA-------------------------------------------------------------------------------- idx <- pdata$sex == "F" & pdata$age > 40 table(idx, useNA="ifany") dim(pdata[idx,]) # WARNING: 'NA' rows introduced tail(pdata[idx,]) dim(subset(pdata, idx)) # BETTER: no NA rows tail(subset(pdata,idx)) ## work-around for `[`: set NA values to FALSE idx[is.na(idx)] <- FALSE dim(pdata[idx,]) ## ----ALL-BCR/ABL-subset--------------------------------------------------------------------------- bcrabl <- pdata[pdata$mol.biol %in% c("BCR/ABL", "NEG"),] ## ----ALL-BCR/ABL-drop-unused---------------------------------------------------------------------- bcrabl$mol.biol <- droplevels(bcrabl$mol.biol) ## ----ALL-BT--------------------------------------------------------------------------------------- levels(bcrabl$BT) ## ----ALL-BT-recode-------------------------------------------------------------------------------- table(bcrabl$BT) levels(bcrabl$BT) <- substring(levels(bcrabl$BT), 1, 1) table(bcrabl$BT) ## ----ALL-BCR/ABL-BT------------------------------------------------------------------------------- xtabs(~ BT + mol.biol, bcrabl) ## ----ALL-aggregate-------------------------------------------------------------------------------- aggregate(age ~ mol.biol + sex, bcrabl, mean) ## ----ALL-age-------------------------------------------------------------------------------------- t.test(age ~ mol.biol, bcrabl) boxplot(age ~ mol.biol, bcrabl)