R Homework 4
Jonathan Batross
Ecology Lab - Summer 2017
# Load the CO2 Dataset Now! Answer the questions below.
# Carbon Dioxide Uptake in Grass Plants ####
# The CO2 dataframe is from an experiment on the cold tolerance of the
# grass species Echinochloa crus-galli. The CO2 uptake of six plants
# from Quebec and six plants from Mississippi was measured at
# several levels of ambient CO2 concentration. Half the plants
# of each type were chilled overnight before the experiment.
data("CO2")
head(CO2)## Plant Type Treatment conc uptake
## 1 Qn1 Quebec nonchilled 95 16.0
## 2 Qn1 Quebec nonchilled 175 30.4
## 3 Qn1 Quebec nonchilled 250 34.8
## 4 Qn1 Quebec nonchilled 350 37.2
## 5 Qn1 Quebec nonchilled 500 35.3
## 6 Qn1 Quebec nonchilled 675 39.2# Important Note: R thinks that the Plant, Type, and Treatment
# columns contain text. Don't forget the quotation marks around
# "text" when subsetting in your homework. Q1: Inspect the CO2 dataset. Does this dataset contain missing data? Include the code you used to check in the box. Why is it important to always check for missing data before running statistics in R?
It’s important to check for missing data because some of the functions won’t be able to work because they can’t compute the missing data.
mean("CO2")## [1] NAQ2: Your boss at the EPA is thrilled with your R skills! There is an international conference coming up and you need to produce two graphs from the CO2 dataset ASAP. Present the code and first six lines of output for both subsets in the box below.
HINT: the | symbol means ‘or’. This may be useful in your answer!
Subset 1 Criteria: Your boss wants the chilled vs nonchilled data for uptake in the CO2 dataset. This dataset should only contain Quebec data where conc are greater than or equal to 675.
New<-subset(CO2,Type=="Quebec"& conc>=675)
head(New)## Plant Type Treatment conc uptake
## 6 Qn1 Quebec nonchilled 675 39.2
## 7 Qn1 Quebec nonchilled 1000 39.7
## 13 Qn2 Quebec nonchilled 675 41.4
## 14 Qn2 Quebec nonchilled 1000 44.3
## 20 Qn3 Quebec nonchilled 675 43.9
## 21 Qn3 Quebec nonchilled 1000 45.5Subset 2 Criteria: You boss wants the Quebec vs Mississippi data for uptake in the CO2 dataset. This dataset should only include chilled treatments only where conc equal to 250.
Water<-subset(CO2,Treatment=="chilled"&conc==250)
head(Water)## Plant Type Treatment conc uptake
## 24 Qc1 Quebec chilled 250 30.3
## 31 Qc2 Quebec chilled 250 35.0
## 38 Qc3 Quebec chilled 250 38.1
## 66 Mc1 Mississippi chilled 250 18.1
## 73 Mc2 Mississippi chilled 250 12.3
## 80 Mc3 Mississippi chilled 250 17.9Q3: Using the plotting gizmo, properly plot subset 1 and subset 2 from above. Present the code and graphs below. Be sure to add a figure caption explaining the graphs.
library(plyr)
library(ggplot2)
xData <- New$Treatment
xLabel <- "Treatment"
yData <- New$uptake
yLabel <- "Uptake (ppb)"
myTitle <- "Quebec Treatment vs Uptake"
fontSize <- 18
temp.df <- data.frame(xData, yData)
temp.df <- na.omit(temp.df)
meansErrBars.df <- ddply(temp.df, c("xData"), summarise, N=sum(yData), mean=mean(yData), sd=sd(yData), se=sd/sqrt(N))
graphIT <- ggplot(data = meansErrBars.df, aes(x = xData, y = mean))
limits <- aes(ymax = meansErrBars.df$mean + meansErrBars.df$se, ymin = meansErrBars.df$mean - meansErrBars.df$se)
dodge <- position_dodge(width = 1)
graph_output <- graphIT +
labs(x = xLabel, y = yLabel, title = myTitle) +
geom_bar(stat = "identity", position = dodge, fill="gray", color = "black") +
geom_errorbar(limits, width = 0.6, stat ="identity", position = dodge, size = 1) +
geom_point(data = temp.df, aes(x = xData, y = yData), position = dodge, size = 8, shape=1) +
theme_classic() + theme(axis.text=element_text(size=fontSize*3.5/4),
axis.title.y=element_text(size=fontSize,face="bold", vjust=1.5),
axis.title.x=element_text(size=fontSize,face="bold", vjust=-0.3),
plot.title = element_text(size=fontSize,face="bold", vjust=1.5),
panel.border = element_rect(colour = "black", fill=NA, size=3))
print(graph_output)
remove(temp.df, meansErrBars.df, graphIT, limits, dodge, fontSize, myTitle, xData, xLabel, yData, yLabel) library(plyr)
library(ggplot2)
xData <- Water$Type
xLabel <- "Type"
yData <- Water$uptake
yLabel <- "Uptake (ppb)"
myTitle <- "Mississippi vs Quebec based on Uptake"
fontSize <- 18
temp.df <- data.frame(xData, yData)
temp.df <- na.omit(temp.df)
meansErrBars.df <- ddply(temp.df, c("xData"), summarise, N=sum(yData), mean=mean(yData), sd=sd(yData), se=sd/sqrt(N))
graphIT <- ggplot(data = meansErrBars.df, aes(x = xData, y = mean))
limits <- aes(ymax = meansErrBars.df$mean + meansErrBars.df$se, ymin = meansErrBars.df$mean - meansErrBars.df$se)
dodge <- position_dodge(width = 1)
graph_output <- graphIT +
labs(x = xLabel, y = yLabel, title = myTitle) +
geom_bar(stat = "identity", position = dodge, fill="gray", color = "black") +
geom_errorbar(limits, width = 0.6, stat ="identity", position = dodge, size = 1) +
geom_point(data = temp.df, aes(x = xData, y = yData), position = dodge, size = 8, shape=1) +
theme_classic() + theme(axis.text=element_text(size=fontSize*3.5/4),
axis.title.y=element_text(size=fontSize,face="bold", vjust=1.5),
axis.title.x=element_text(size=fontSize,face="bold", vjust=-0.3),
plot.title = element_text(size=fontSize,face="bold", vjust=1.5),
panel.border = element_rect(colour = "black", fill=NA, size=3))
print(graph_output)
remove(temp.df, meansErrBars.df, graphIT, limits, dodge, fontSize, myTitle, xData, xLabel, yData, yLabel) Please turn–in your homework via Sakai by saving and submitting an R Markdown PDF or HTML file from R Pubs!