getwd() # Show working directory

# Set the working directory
# setwd("D:/Programming Guide/R Guide/code")
# getwd()

# Set the working directory
setwd("D:/Programming Guide/code")
getwd()

### 2.1 Packages

# Use the readxl library to get the data
library (readxl)

### 2.2 Importing data

UKHP <- read_excel("D:/Programming Guide/data/UKHP.xls ", 
                   col_types = c("date", "numeric"))
# Show the data
View (UKHP)

# Data classes
class(UKHP)

# Variable names
names(UKHP)

# First 6 observations
head(UKHP)

# Last 6 observation
tail(UKHP)

### 2.3 Data description

# Summary statistics
summary(UKHP)

x = mean(UKHP$'Average House Price')
x
x <- mean(UKHP$'Average House Price')
x

### 2.4 Changing and creating data

names(UKHP)[2] = "hp"
names(UKHP)

# Writing a new variable; return dhp
UKHP$dhp = c(NA,100*diff(UKHP$hp)/UKHP$hp[1:nrow(UKHP)-1])
head(UKHP$dhp)

dhp = 100*diff(UKHP$hp)/UKHP$hp[1:nrow(UKHP)-1]
head(dhp)

### 2.5 Graphs and plots

# Time series plot
par(cex.axis = 1.5,cex.lab = 1.5,lwd = 2)
plot(UKHP$Month,UKHP$hp,type = 'l',xlab ="Date",ylab ="House price",main = "Average house price")

# Histogram
hist(UKHP$hp)
box()


### 2.6 Keeping track of your work


### 3 Linear regression

SandPhedge <- read_excel("D:/Programming Guide/data/SandPhedge.xls",
                          col_types = c("date","numeric","numeric"))

View(SandPhedge)

names(SandPhedge)
head(SandPhedge)
tail(SandPhedge)

# Create log returns
SandPhedge$rspot = c(NA,100*diff(log(SandPhedge$Spot)))
SandPhedge$rfutures = c(NA,100*diff(log(SandPhedge$Futures)))

summary(SandPhedge[c("rspot","rfutures")])

lm_returns = lm(rspot ~ rfutures, data = SandPhedge)
summary(lm_returns )

lm_prices = lm(Spot ~ Futures, data = SandPhedge )
summary (lm_prices)