require(ggplot2);require(reshape2);require(circlize);require(ggdendro);
require(PerformanceAnalytics);require(ggthemes);require(RColorBrewer);
require(psych)

install.packages(c("ggplot2","reshape2","circlize","ggdendro","ggthemes",
"RColorBrewer","reshape2","PerformanceAnalytics","psych"),dependencies = T)

1+1

x <- 2
for (i in 1:5){
print(x+i)  
}

print("Life, the Universe and Everything")

x <- rnorm(5000) # Generate 5000 random numbers from a Normal distribution
hist(x,col="green") # Plot a histogram

set.seed(1056)              # set seed to replicate example
nobs= 150                   # number of obs in model 
x1 <- runif(nobs,0,5)       # random uniform variable
mu <- 1 + 5 * x1            # linear predictor, xb
y <- rnorm(nobs, mu, sd=1)  # create y as adjusted random normal variate 
fit <- lm(y ~ x1)           # Normal Fit 

summary(fit) # Display results from the fit

xx <- seq(0,5,length=200)
ypred <- predict(fit,newdata=list(x1=xx),type="response")     # Prediction from the model 

plot(x1,y,pch=19,col="red")                                   # Plot regression line 
lines(xx,ypred,col='cyan',lwd=4,lty=2)

segments(x1,fitted(fit),x1,y,lwd=2,col="gray")                # Add the residuals

dat <- data.frame(x1,y)
ggplot(data=dat,aes(x =x1, y = y)) + 
  geom_point() +
  stat_smooth(method = "lm", col = "red")

d <- read.csv("data/exoplanets.csv",header = T)
d <- d[complete.cases(d),]
head(d)

p1 <- ggplot(data = d, aes(x = Period, y = star_mass, group=Discovery_method,
  fill = Discovery_method, text=name, size=Radius)) + geom_point(alpha=0.5) +
  scale_x_log10() + ylab("Stellar Mass") + xlab("Period")+
  theme(legend.position = "none")

p1

p2 <- ggplot(data = d, aes(x = star_mass, y = star_radius, group=Discovery_method, text=name,size=Radius,colour=Discovery_method)) +theme_bw()+
geom_point(alpha=0.6) +scale_x_log10() + xlab("Stellar Mass") + ylab("Stellar Radius")+
theme(legend.position = "right")+scale_size(range=c(2,10))+ scale_color_tableau(name="")

p2

p3 <- ggplot(data = d, aes(x = star_mass,y =star_radius,size=Radius)) +
  geom_point(size=2.5,alpha=0.6,colour="red") + geom_smooth(size=2,method = "loess")+
  xlab("Stellar Mass") + ylab("Stellar Radius")+scale_size(range=c(2,10))

p3

xcut <- cut(log10(d$Period),breaks=5)
d$xcut <- xcut

p4 <- ggplot(data = d, aes(x = log10(Period), y = star_mass)) +
   geom_boxplot(data = d, aes(x = xcut,y = star_mass),fill="red3")+  
   geom_point(aes(group=Discovery_method,  fill = Discovery_method,
   text=name,size=Radius), alpha=0.3) +
   xlab("Stellar Mass") + ylab("Stellar Radius") +
  theme(legend.position = "none")

p4

xcut <- cut(log10(d$Period),breaks=5)
d$xcut <- xcut
p5 <- ggplot(data = d, aes(x = log10(Period), y = star_mass)) +
   geom_boxplot(data = d, aes(x = xcut,y = star_mass),fill="red3")+  
   xlab("Stellar Mass") + ylab("Stellar Radius") +
  theme(legend.position = "none")

p5

xcut <- cut(log10(d$Period),breaks=5)
d$xcut <- xcut
p6 <- ggplot(data = d, aes(x = log10(Period), y = star_mass)) +
   geom_violin(data = d, aes(x = xcut,y = star_mass),fill="red3")+  
   xlab("Stellar Mass") + ylab("Stellar Radius")+
  theme(legend.position = "none")

p6

p7 <- ggplot(data = d, aes(x = Radius)) + geom_histogram(bins = 45,fill="red")

p7

p8 <- ggplot(data = d, aes(x = Radius)) + geom_density(fill="red")

p8

p9 <- ggplot(data = d, aes(x = Radius,group=Discovery_method,fill=Discovery_method)) +
      geom_density()+ scale_fill_discrete(name="")

p9

p10 <- ggplot(data = d, aes(x = Radius,group=Discovery_method,fill=Discovery_method)) +
      geom_density(adjust=1.5, position="fill")+ scale_fill_discrete(name="")

p10

dcor <- cor(d[,c(2,3,5,6,7)])
print(dcor)

c0 <- scale(log10(d[,c(2,3,5,6,7)]))
chart.Correlation(c0, histogram=TRUE, pch=19)

pairs.panels(log10(d[,c(2,3,5,6,7)]), scale=TRUE)

nc <- cor(d[,c(2,3,5,6,7)])
chordDiagram(nc)

beer <- read.csv("data/beer2.csv",header = T)
beer <- beer[complete.cases(beer),]

head(beer)

titan <- as.data.frame(Titanic)
head(titan)

t1 <- ggplot(titan,aes(x=Class,y=Freq,fill=Survived))+geom_bar(stat="identity")+facet_wrap(Sex~Age)+
  theme_dark()+scale_fill_pander()+ylab("Passengers")

t1

library(deSolve)

parameters <- c(P = 15,      # birth rate
                d = 0.0000005,  # natural death percent (per day)
                B = 0.00010,  # transmission percent  (per day)
                G = 0.0005,  # ressurect percent (per day)
                A = 0.000025)  # destroy percent  (per day))


state <- c(S=50000, # initial population
           Z=0,  # initial zombie population
           R=0   # initial death population
           )  

zoombie <- function(t, state, parameters){
with(as.list(c(state, parameters)),{
  #the model equations (see Munz et al. 2009)
  dS <- P - B*S*Z - d*S
  dZ <- B*S*Z + G*R - A*S*Z
  dR <- d*S + A*S*Z - G*R
  output <- list(c(dS,dZ,dR))
  return(output)  
})
}

times <- seq(0, 20, by = 0.025)
out <- ode(y = state, times = times, func = zoombie, parms = parameters)
head(out)

dat <- as.data.frame(out)
dat2 <- melt(dat,id="time")
z1 <-ggplot(data=dat2,aes(x=time,y=value,group=variable,colour=variable,linetype=variable))+
  geom_line(size=2)+theme_hc()+ylab("Population")+xlab("Days after break")+
  scale_color_stata(name="",labels = c("Population", "Zombies","Victims"))+
  scale_linetype_stata(name="",labels = c("Population", "Zombies","Victims"))

z1