Differences

This shows you the differences between two versions of the page.

--- r-tutorial [2011/10/12 23:57]
liuyipei
+++ r-tutorial [2011/10/13 14:22]
liuyipei
@@ Line 12: / Line 12: @@
 # R as a graphics tool
 # Define a vector named cars with five values
-cars <- c(1,3,6,4,9)
+my.vector <- c(1,3,6,4,9)
-# Plot the values in cars with default options
+# Some basic variables that come with R to play with
-plot(cars)
+head(cars)
+dim(cars)
-r <- rlnorm(1000)
+plot(x=cars$speed, y=cars$dist,
-h <- hist(r, plot=F, breaks=c(seq(0, max(r)+1, by=0.1)))
+     main="cars",
-plot(h$counts,
+     xlab="speed",
-     log="xy",
+     ylab="dist")
-     pch=20,
+hist(cars$speed)
-     col="blue",
-     main="log-normal distribution",
-     xlab="Value",
-     ylab="Frequency")
 # Primitive data types
@@ Line 181: / Line 178: @@
 my.data <- as.matrix(read.table("http://www.stanford.edu/~kjung/my.data.txt", sep="\t"))
 # The columns of a matrix can have symbolic names
@@ Line 280: / Line 276: @@
 load(file="my.image.RData")
 ls()
-# source - read and execute from a text file containing an R script
+</code>
-# Debugging - Two main options
-# Sprinkle cat(...) liberally throughout your code to monitor what is going on.
-# debug(), undebug() - Turn on/off step through debugging for a function
-# SIMPLE STATISTICS
+====Problem Set 1 Hints and Other Tricks====
-# Some simple statistics - note that many functions that perform statistical tests
+<code>
-# etc, in R return list objects.
+setwd('/Users/liuyipei/BMI215/Module 1 - Nick/DrugSafety-Homework')
-help(t.test)
+dz<-read.csv('single_drug_event_frequencies.csv')
-ttest.result <- t.test(my.data['Hairless',] ~ pheno.data$plays.tuba)
+head(dz)
-ttest.result
-names(ttest.result)
-ttest.result$statistic
-ttest.result$p.value
-help(cor.test)
+cd1<-read.csv('cholesterol_drugs.txt', col.names=F)
-cor.results <- cor.test(my.data['Hedgehog',], my.data['Shaggy',], method="spearman")
+colnames(cd1)<-c('singlet')
+cd1$chole<-'choles'
+head(cd0)
+cd0<-data.frame(singlet=setdiff(as.character(unique(dz$singlet)), cd1),chole=0)
+cd0$chole<-'noncholes'
+cd.table<-rbind(cd1, cd0)
+head(cd1)
+head(cd0)
+head(cd.table)
+q1.table <- merge(cd.table, dz)
+q1.table$hifreq <- ifelse(q1.table$freq > 0.1, 'hifr', 'lofr')
+head(q1.table)
+nrow(q1.table)
+ncol(q1.table)
+sum(q1.table$chole == 'choles')
+sum(q1.table$chole == 'noncholes')
+table(q1.table$chole, q1.table$hifreq)
+library(plyr)
+hard.work<-function(x){
+  c(nrow(x), ncol(x), x$chole[1]=='choles')
+}
+ddply(q1.table, .(singlet), .fun=hard.work)->lets.talk.about.what.happened
+head(lets.talk.about.what.happened)
+dim(lets.talk.about.what.happened)
+summary(lets.talk.about.what.happened)
+colnames(lets.talk.about.what.happened)<-c('singlet', 'row.count', 'col.count', 'ch.drug')
-help(chisq.test)
+library(caTools)
-chisq.results <- chisq.test(pheno.data$rides.bike, pheno.data$plays.tuba)
+my.x<-c(0:10)*0.1
-chisq.results <- chisq.test(table(pheno.data$rides.bike, pheno.data$plays.tuba))
+my.y<-c(0,1,3,5,6,7,7,9,9,10,10)*0.1
+plot(my.x, my.y)
+trapz(my.x, my.y)
-help(prcomp)
+data.frame(a=c(8,12),b=c(31,41))->t
-prcomp.results <- prcomp(my.data)
+t
-my.data[is.na(my.data)] <- 0
+fisher.test(t)->f.t
-prcomp.results <- prcomp(my.data)
+ls(f.t)
+f.t$p.value
+f.t$conf.int
 </code>

Shah Lab

User Tools

Site Tools

Differences

Page Tools