# Processing a Dose Response Curve Using R
library(drc) # Dose Response Curve Package--must be downloaded separately
import <- read.csv(file.choose())

names(import) # Shows the name of the variables
control <- subset(import,Treat=="C") #Brute force to create separate date.frames
test <- subset(import,Treat=="I")
plot(control$ATP,control$PI, col="Blue", ylim=c(0,120), xlab="mM ATP", ylab="Pi (mM)")
points(test$ATP,test$PI, col="Red", pch="X") #Creates a plot and overlay of data


# Below use the package that must be loaded installed from wehsite and installed
model_AR3 <- drm(PI~ATP, Treat, data=import, fct=AR.3(),
pmodels=list(~1, ~factor(Treat), ~factor(Treat))) # Function Creates Model
#Not sure which model to pick so I picked AR.3 because it was used in other examples.
summary(model_AR3) #summarize statistical tests--help help(AR.3) to figure out what it means
plot(model_AR3, legendPos=c(0.2,110)) # Legend is in the way, so I used legendPos to move it, see help(plot.drc)

#Below is a short intro to R...
# Introduction to R ESSP 250
# the pound sign if for comments...

# getting data in by typing
data1 <- data.frame()
fix(data1)  # Yes, closing the window is okay, the data is already saved

# importing comma separated values
import<- read.csv(file.choose()) #File.choose opens a broswer window--pretty cool!

# existing data
help(InsectSprays)
data(InsectSprays)

names(InsectSprays)

# means and standard deviations
mean(InsectSprays$count) # The dollar sign is used to select the vector inside the data.frame
sd(InsectSprays$count)

# view the data, beat excel ANYDAY, where boxplots are an absolute nightmare to format
boxplot(count ~ spray, data = InsectSprays,
        xlab = "Type of spray", ylab = "Insect count",
        main = "Insect Sprays Results", varwidth = TRUE, col = "lightgray")

# Analysis of Variance
fm1 <- aov(count ~ spray, data = InsectSprays)
summary(fm1)
opar <- par(mfrow = c(2,2), oma = c(0, 0, 1.1, 0))
plot(fm1)
fm2 <- aov(sqrt(count) ~ spray, data = InsectSprays)
summary(fm2)
plot(fm2)
par(opar)

# Regression Example
plot(co2, ylab = expression("Atmospheric concentration of CO"[2]),
     las = 1)
title(main = "Mauna Loa Atmospheric CO2 Concentration")


carbon <- lm(co2 ~ 1, data=co2)

carbon

data(airquality)
names(airquality)

airquality
plot(Ozone~Temp, data=airquality)


lm1 <- lm(Ozone ~ Temp, data=airquality)
summary(lm1)
plot(lm1)

plot(Ozone~Temp, data=airquality)
abline(lm1)

airquality$Temp2 <- airquality$Temp^2
lm2 <- lm(Ozone ~ Temp2 + Temp, data=airquality)
summary(lm2)
plot(lm2)

AIC(lm1,lm2)