# reading in an external cvs (comma separated values) file
faith=read.csv('https://webpages.uidaho.edu/~renaes/Data/faithdata.csv',header=T)

# or use the "Import dataset" option in the Environment window (upper right window in RStudio)

# see the first 6 observations
head(faith)
# or just type in the dataset name in the console to see the whole dataset
# or use View() to see the dataset in a spreadsheet type format (note the capital V)
View(faith)

hist(eruptions) 
# error
# the variable is an object inside the faith dataset so to access just one variable
# you need to either use a two-level name (datasetname$variablename) such as faith$eruptions
# or use attach(datasetname) to access the variables without the two-level name

faith$duration

attach(faith)
duration

hist(duration)
hist(wait)

boxplot(duration)
# put a title in since boxplot() does not have a title by default
boxplot(duration,main='Eruptions')
# or use title() after boxplot()

boxplot(duration,horizontal=T); title('Eruptions')

# scatterplot x=eruptions y=waiting

plot(duration, wait,main='Old Faithful')

# summary statistics
# individual commands

mean(duration); mean(wait)
var(duration); var(wait)
sd(duration); sd(wait)
median(duration); median(wait)
max(duration); max(wait)
min(duration); min(wait)
length(duration) # gives the sample size

# the mode needs the modeest package (but will actually need the statip package loaded)

# install.packages("modeest")
library(statip)
mfv(duration)
mfv(wait)

# using summary() but only gives mean, min, max, median, q1, q3
summary(faith) 
# or use summary(eruptions); summary(waiting)

# using a package in R
# packages install functions that are not in the base version
# using stargazer package

install.packages("stargazer") # only install one time (not every time you need it)

# once it is installed, load the package using library()
library(stargazer)
stargazer(faith,type='text')

# there are more...

# pasetecs pkg, stat.desc
install.packages("pastecs") # install only once
library(pastecs)
stat.desc(faith)

colors=c('Red','Blue','Green','Orange','Yellow','Brown')
observed=c(92,157,102,190,91,101)
barplot(observed,names.arg=colors,col=colors,ylim=c(0,200),
        ylab='Counts',main="Distribution of M&M Colors")