# Extract data to R from YOU CANalytics
data<-read.csv('http://ucanalytics.com/blogs/wp-content/uploads/2016/07/Regression-Analysis-Data.csv')

#Remove missing data
data_without_missing<-data[complete.cases(data),]

# Tagging predictor and response variables
numeric<-c("Dist_Taxi", "Dist_Market", "Dist_Hospital", "Carpet","Builtup", "Rainfall")
categoric <- c("Parking", "City_Category")
Target<-c("House_Price")

# Functions to plot matrix correlation plot and display correlation coef. on bottom and top panels
panel.cor <- function(x, y, digits=3, prefix="", cex.cor) 
{
  usr <- par("usr"); on.exit(par(usr)) 
  par(usr = c(0, 1, 0, 1)) 
  r <- abs(cor(x, y)) 
  txt <- format(c(r, 0.123456789), digits=digits)[1] 
  txt <- paste(prefix, txt, sep="") 
  if(missing(cex.cor)) cex <- 0.8/strwidth(txt) 
  
  test <- cor.test(x,y) 
  Signif <- symnum(test$p.value, corr = FALSE, na = FALSE, 
                   cutpoints = c(0, 0.001, 0.01, 0.05, 0.1, 1),
                   symbols = c("***", "**", "*", ".", " ")) 
  
  text(0.5, 0.5, txt, cex = 4*r^(0.3),col = "dodgerblue") 
  text(.8, .9, Signif, cex= 4, col=2) 
}

# Function for histogram in the diagonal panel
panel.hist <- function(x, ...)
{
  usr <- par("usr"); on.exit(par(usr))
  par(usr = c(usr[1:2], 0, 1.5))
  h <- hist(x, plot = FALSE)
  breaks <- h$breaks; nB <- length(breaks)
  y <- h$counts; y <- y/max(y)
  rect(breaks[-nB], 0, breaks[-1], y, col = "orange", ...)
}


# Matrix plot with outliers
pairs(data_without_missing[,c(numeric,Target)],upper.panel = panel.cor,diag.panel=panel.hist,cex.labels = 2)

# Matrix plot without outliers
data_without_outliers<-data_without_missing[data_without_missing$House_Price<10^8,]
pairs(data_without_outliers[,c(numeric,Target)],upper.panel = panel.cor,diag.panel=panel.hist,cex.labels = 2)