#Renaming variable names
names(NYC_Trees)[5]
names(NYC_Trees)[5] <- "Diameter"

names(NYC_Trees)[6] <- "Height"
names(NYC_Trees)[9] <- "CanopyArea"

#Basic Summary Statistics
#Measures of location
mean(NYC_Trees$Height)
median(NYC_Trees$Height)
min(NYC_Trees$Height)
max(NYC_Trees$Height)

#Working with quantiles
quantile(NYC_Trees$Height)
quantile(NYC_Trees$Height,c(0.10,0.90))

#Specifing additional quantiles
whichones <- seq(0,1,by=0.05)
quantile(NYC_Trees$Height, whichones)

#Creating a Cumulative Density Plot of Height
plot(quantile(NYC_Trees$Height, whichones),whichones,xlab="Height",ylab="Percentiles")
lines(quantile(NYC_Trees$Height, whichones),whichones)

#########################################
#Measures of spread
sd(NYC_Trees$Height)
range(NYC_Trees$Height)

mad(NYC_Trees$Height)


library(lsr)
aad(NYC_Trees$Height)

#Getting the mean absolute deviation via brute force
mean.vector <- rep(mean(NYC_Trees$Height),319)
deviation<-NYC_Trees$Height - mean.vector
abs.deviation<-abs(deviation)
mean(abs.deviation)

View(data.frame(Height=NYC_Trees$Height[1:10],mean.vector=mean.vector[1:10],deviation=deviation[1:10],abs.deviation=abs.deviation[1:10]))



table(NYC_Trees$Condition)

table(NYC_Trees$Condition) / length(NYC_Trees$Condition)

100 * table(NYC_Trees$Condition) / length(NYC_Trees$Condition)

round(100 * table(NYC_Trees$Condition) / length(NYC_Trees$Condition),1)


table(NYC_Trees$Native, NYC_Trees$Condition)
plot(table(NYC_Trees$Native, NYC_Trees$Condition))


native.condition.table <- table(NYC_Trees$Native, NYC_Trees$Condition)

margin.table(native.condition.table,1)
margin.table(native.condition.table,2)

prop.table(native.condition.table,1)
prop.table(native.condition.table,2)


mean(NYC_Trees$Diameter);mean(NYC_Trees$Height);mean(NYC_Trees$Age);mean(NYC_Trees$PercentFoliageDensity);mean(NYC_Trees$CanopyArea);mean(NYC_Trees$CompensatoryValue)


apply(NYC_Trees[,5:10],2,function(x){sd(x)/mean(x)})


apply(NYC_Trees[,5:10],2,mean)

apply(NYC_Trees[,5:10],2,mean)
colMeans(NYC_Trees[,5:10])


aggregate(NYC_Trees[,5:10],by=list(NYC_Trees$Native),mean)

aggregate(NYC_Trees[,5:10],by=list(NYC_Trees$Condition,NYC_Trees$Native),mean)