#ECO239 R Introduction on Oct. 22, 2015#

#Use it as calculator
#Operators

# Add numbers from 1 to 3 
1+2+3

# Multiplication
1*2*3

# Devision
5/2

# Powers, ** and ^ return the same result
2**3
2^3

# square root
sqrt(2)

# Natural log, ln 2
log(2)

# ln(pi)
pi
log(pi)

# Absolute value
abs(3-5)

# Exponential
exp(3)

# Which operation is first?
4*(3+2)

# And Parenthesis??
(4+5)/3

# Variables, assigning a value to a variable, = or <-
x=5
x
x<-6
x
y<-x^2
y

x<- log(10)*exp(5)
x


#Matrix Algebra in R
# Create a vector of consecutive integers
x<--1:10
x
# Create a vector of sequence from -1 to 1 with 0.1 increment
x<-seq(0,1,0.01)
x

# Scalar addition (2 is added to each component)
x+2

# Scalar multiplication (multiplication of 2 for each component)
x*2

# summation, maximum and minimum of elements in x
x<-1:10
sum(x)
min(x)
max(x)

# sorting
sort(x) # increasing order
sort(x, decreasing=T) # decreasing order

# Matrix Operations
# number of elements in x
x<-c(1,3,5,7,9,11)
length(x)
x[3] # third element
x[2:5] # the third to fifth element of x
x[-2] # all except the second element
x[x>5] # list of elements in x greater than 5

# Matrix multiplication, cross product 
#Row vector
x<-matrix(c(1,2,3),nrow=1)
x

#Column vector
y<-matrix(c(1,2,1),nrow=3)
y

z<-matrix(c(2,3,4),nrow=3)
z
y+z # element by element addition
y*z # element by element multiplication

# Matrix Defition
# 3 by 3 matrix
# by column direction
m1<-matrix(c(1,3,2,5,-1,2,2,3,9),nrow=3)
m1

# by row direction
m2<-matrix(c(1,3,2,5,-1,2,2,3,9),ncol=3,byrow=T)
m2

#Cross Product 

m1%*%m2

#Check for dimension
dim(m2)

#Extracting the components of matrix
m2
m2[2,3] # extracting an element of 2nd row-3rd column
m2[2, ] # extracting 2nd row
m2[ ,3] # extracting 3rd column
m2[2:3,2:3] # extracting 2 and 3rd row and 2 adn 3rd column

# Matrix operations

m3<-matrix(c(2,3,4,5),nrow=2)
m3

t(m3) # transpose

solve(m3) # inverse matrix of m3, works for square matrix
solve(m2)

# Data input and summary statistics
score<-c(31,45,48,55,57,58,67,68,73,75,78,80,82,85,88,89,91,92,95,99)
mean(score)
median(score)
var(score)
sd(score)
IQR(score)

#Covariance and Correlation
x<-c(12, 30,15,24,14)
y<-c(20,60,27,50,23)
cov(x,y)
cor(x,y)



# Working Directory, setting..NOTE: make sure the seperator is / instead of \.
setwd("C:/Shihomi/Shihomi_Office/Courses_HU/2014_2015_Guz/ECO239/R_workplace")

# Loading libraries after installing each package
library(AER)
library(ECDAT)

# Downloading data in .csv format

housingdata <- read.table("C:/Shihomi/Shihomi_Office/Courses_HU/2015_2016_Guz/ECO239/RHW/HousingDataSRT.csv", header=TRUE,
   sep=",")
ls(housingdata) # list the names of variables

# Downloading data in .xlsx format
library(xlsx)
housingdata2 <-read.xlsx("C:/Shihomi/Shihomi_Office/Courses_HU/2015_2016_Guz/ECO239/RHW/HousingDataSRT.xlsx",1)
ls(housingdata2)


#Define each variable
#ID	COUNTY	DPRICE	LOTACR	BATHN	GRGSQF	AGE	AIRCNDD	YR


COUNTY<-housingdata[,2]
DPRICE<-housingdata[,3]
LOTACR<-housingdata[,4]
BATHN<-housingdata[,5]
GRGSQF<-housingdata[,6]
AGE<-housingdata[,7]
AIRCNDD<-housingdata[,8]
YR<-housingdata[,9]

##NOTE: Names are case-sensitive. "COUNTY" is different from "county".

#Summary Statistics

mean(DPRICE)
median(DPRICE)
var(DPRICE)
sd(DPRICE)
IQR(DPRICE)

cov(DPRICE,LOTACR)
cor(DPRICE,LOTACR)

cov(DPRICE,AGE)
cor(DPRICE,AGE)

#Plots
# Simple Bar Plot
counts <- table(housingdata$COUNTY)
barplot(counts, main="COUNTY DISTRIBUTION",
   xlab="COUNTY") 

#Histogram
# Simple Histogram
hist(housingdata$DPRICE)

# Colored Histogram with Different Number of Bins
hist(housingdata$DPRICE, breaks=12, col="green")

hist(housingdata$AGE, breaks=20, col="red") 

# Scatter Plot
attach(housingdata)
plot(AGE, DPRICE, main="Impact of AGE on Housing Price",
   xlab="AGE ", ylab="DPRICE ", pch=19) 

# 3D Scatterplot
library(scatterplot3d)
attach(housingdata)
scatterplot3d(AGE,DPRICE,LOTACR, main="3D Scatterplot")


# Download data in data packages
#For example, use Housing data from ECDAT package
data(Housing)
ls(Housing)

airco <-Housing[,1]
bathrms<-Housing[,2]
bedrooms<-Housing[,3]
driveway<-Housing[,4]
fullbase<-Housing[,5]
garagepl<-Housing[,6]

# Mean
mean(bedrooms)

# standard dev
sd(bedrooms)

# median
median(bedrooms)

# Inter quartile range (75. percentile - 25. percentile)
IQR(bedrooms)

# range
range(bedrooms)


# save workspace
save.image("C:/Shihomi/Shihomi_Office/Courses_HU/2015_2016_Guz/ECO239/R_workplace/ECO239_Oct22_2015.RData")