Idea Transcript
# This is a chunk of R code. All test after a # symbol is a comment
# Set working directory using setwd() function setwd('Enter the path to my working directory')
# Clear all variables in R's memory rm(list=ls()) # Standard code to clear R's memory
2 + 4 # Use R to add two numbers
## [1] 6
human = read.table('HEIGHT.CSV', header=T, sep=',') # Import human height data set humanF = subset(human, SEX=='F') # Extract data for females
wolf = read.table('WOLF.CSV', header=T, sep=',') # Import wolf data set
humanF
hist()
hist(humanF$HEIGHT, breaks=30)
µ
rnorm()
# Generate 10000 data point drawn from a normal distribution normal_data = rnorm(n=10000, mean=2, sd=0.5)
# Produce a histogram of the generated data hist(normal_data, breaks=30)
median(humanF$HEIGHT)
## [1] 1.63
mean()
mad(humanF$HEIGHT)
## [1] 0.0652344
sd() IQR()
range()
range(humanF$HEIGHT)
## [1] 1.428 1.870
# Calculate 1% and 99% quantiles quantile(humanF$HEIGHT, prob=c(0.01, 0.99))
## 1% 99% ## 1.49300 1.77985
hist(wolf$Cpgmg, breaks=40) # Display distribution of wolf cortisol
summary(wolf$Cpgmg)
## Min. 1st Qu. Median Mean 3rd Qu. Max. ## 4.75 12.16 15.60 17.74 20.35 73.19
# A quantile-quantile plot for cortisol in the wolf2 data qqnorm(wolf$Cpgmg) qqline(wolf$Cpgmg)
humanF$HEIGHT
# Generate 10000 values from an exponential distribution # with rate parameter=0.2 exp_data = rexp(n=10000, rate=0.2) # Display first 6 values head(exp_data, n=6)
## [1] 1.3200046 11.1079375 0.7374528 12.5272467 10.9808850 1.6811151
# Use a for-loop to repeatly generate 10000 data points from an exponential # distribution and add it to the last set of data generated.
# Display the average of this summed data for n=1 # Only display the distribution out to values of 15 hist(exp_data, breaks=20, xlim=c(0,15), col='darkgreen')
# Add together 5 exponential variables exp_5 = rexp(n=10000, rate=0.2) for (i in 2:5) { exp_5 = exp_5 + rexp(n=10000, rate=0.2) } # Display the average of this summed data for n=5 # Add this data to the histogram hist(exp_5/5, breaks=20, add=T, col='blue')
# Add together 30 exponential variables exp_30 = rexp(n=10000, rate=0.2) for (i in 2:30) { exp_30 = exp_30 + rexp(n=10000, rate=0.2) } # Display the average of this summed data for n=30 # Add this data to the histogram hist(exp_30/30, breaks=20, add=T, col='red')
# Add a legend to the histogram legend('topright', legend = c('n=1','n=5','n=30'), fill=c('darkgreen','blue','red'))
rnorm() for-loop