#------------------------
# Housing Data example from http://tutorials.iq.harvard.edu/R/Rgraphics/Rgraphics.html

housing <- read.csv("http://gozips.uakron.edu/~nmimoto/R/landdata-states.csv")

View(housing)

colnames(housing)
# [1] "State"            "region"           "Date"             "Home.Value"
# [5] "Structure.Cost"   "Land.Value"       "Land.Share..Pct." "Home.Price.Index"
# [9] "Land.Price.Index" "Year"             "Qrtr"


library(ggplot2)

  #- Histogram of all Home.Value pooled (all states, all times)
  p1 <- ggplot(housing, aes(x = Home.Value))
  p1 + geom_histogram()
  p1 + geom_histogram(stat = "bin", binwidth=4000)


  #- Timeseries of Home.Value by state 
  p2 <- ggplot(housing, aes(x = Date, y = Home.Value))
  
  p2 + geom_line(aes(color = State))                #- Overlay  Home.Value for each state
  p2 + geom_line() + facet_wrap(~State, ncol = 10)  #- Panel of Home.Value for each state


  #- Pick two states and plot Home.Value over time
  p3 <- ggplot(subset(housing, State %in% c("MA", "TX")),  aes(x=Date, y=Home.Value, color=State))
  p3 + geom_point()

  #- Pick 2001 Q1, log-scatter plot with regression line

  hp2001Q1         <- subset(housing, Date==2001.25)                                  # pick only 2001 Q1
  hp2001Q1$reg     <- fitted(   lm(Structure.Cost~log(Land.Value), data=hp2001Q1)  )  # fitted regression line
  
  p4      <- ggplot(hp2001Q1, aes(x=    Land.Value , y=Structure.Cost))
  p4.logx <- ggplot(hp2001Q1, aes(x=log(Land.Value), y=Structure.Cost))

  p4      + geom_point()
  p4.logx + geom_point()
  p4.logx + geom_point(aes(color=Home.Value)) + geom_line(aes(y=reg))    # add reg line
  p4.logx + geom_text(aes(label=State), size = 3)                        # use state name instead

  library("ggrepel")                                                     # install.packages("ggrepel") 
  p4.logx + geom_point()  + geom_text_repel(aes(label=State), size=3)    # add text to scatter plot 
  p4.logx + geom_point(aes(color=Home.Value, shape=region), size=4) + geom_text_repel(aes(label=State), size=3)
  
  



#----------------------------
# MPG dataset
library(ggplot2)

dataset=mtcars #- dataset contained in package ggplot2.


# create factors with value labels
mtcars$gear <- factor(mtcars$gear,levels=c(3,4,5),labels=c("3gears","4gears","5gears"))
mtcars$am   <- factor(mtcars$am,levels=c(0,1), 	  labels=c("Automatic","Manual"))
mtcars$cyl  <- factor(mtcars$cyl,levels=c(4,6,8), labels=c("4cyl","6cyl","8cyl"))

# KDE plots for mpg grouped by gear
qplot(mpg, data=mtcars, geom="density", fill=gear, alpha=I(.5),
      main="Distribution of Gas Milage", xlab="Miles Per Gallon", ylab="Density")


# Scatterplot of mpg vs. hp for each combo of gears and cylinders
qplot(hp, mpg, data=mtcars, shape=am, color=am, facets=gear~cyl, size=I(3),
   xlab="Horsepower", ylab="Miles per Gallon")


# Separate regressions of mpg on weight for each number of cylinders
qplot(wt, mpg, data=mtcars, geom=c("point", "smooth"),
   method="lm", formula=y~x, color=cyl,
   main="Regression of MPG on Weight",
   xlab="Weight", ylab="Miles per Gallon")



# Boxplots of mpg by number of gears
# observations (points) are overlayed and jittered
qplot(gear, mpg, data=mtcars, geom=c("boxplot", "jitter"),
   fill=gear, main="Mileage by Gear Number",
   xlab="", ylab="Miles per Gallon")