#file.choose()
sd <- read.csv("C:\\Users\\gkrochmal\\Downloads\\Seed Dispersal Data - Sheet1.csv") #naming data
library(plyr) #loading packages
library(ggplot2)
head(sd) #summary of first 6 rows
## Factor Seed_Type Distance Angle Season
## 1 No wind Dog 15 86 1
## 2 No wind Dog 10 43 1
## 3 No wind Butterfly 34 132 1
## 4 No wind Dog 55 71 1
## 5 No wind Butterfly 55 82 1
## 6 No wind Fox 68 65 1
str(sd) #looking at data types
## 'data.frame': 182 obs. of 5 variables:
## $ Factor : Factor w/ 2 levels "No wind","Wind": 1 1 1 1 1 1 1 1 1 1 ...
## $ Seed_Type: Factor w/ 3 levels "Butterfly","Dog",..: 2 2 1 2 1 3 3 1 2 1 ...
## $ Distance : int 15 10 34 55 55 68 95 120 119 118 ...
## $ Angle : int 86 43 132 71 82 65 39 49 51 69 ...
## $ Season : int 1 1 1 1 1 1 1 1 1 1 ...
#Using ddply to summarize seed type, season, experimental factor and mean ofdistance data
seed <- ddply(sd, c("Seed_Type", "Season", "Factor"), summarise, meanDistance=mean(Distance))
head(seed)#summmary of first six rows of data
## Seed_Type Season Factor meanDistance
## 1 Butterfly 1 No wind 81.75000
## 2 Butterfly 1 Wind 68.55556
## 3 Butterfly 2 No wind 119.80000
## 4 Butterfly 2 Wind 111.50000
## 5 Butterfly 3 No wind 124.66667
## 6 Butterfly 3 Wind 71.20000
#creating ddply for ggplots
graph1 <- ddply(sd, c("Seed_Type", "Season", "Factor"), summarise,
dataRep = sum(!is.na(Distance)),
dataMean = mean(Distance, na.rm=T),
dataSD = sd(Distance, na.rm=T),
dataSE = dataSD / sqrt(dataRep))
head(graph1)
## Seed_Type Season Factor dataRep dataMean dataSD dataSE
## 1 Butterfly 1 No wind 4 81.75000 43.86627 21.93314
## 2 Butterfly 1 Wind 9 68.55556 89.19517 29.73172
## 3 Butterfly 2 No wind 5 119.80000 84.89228 37.96498
## 4 Butterfly 2 Wind 8 111.50000 34.88348 12.33317
## 5 Butterfly 3 No wind 6 124.66667 56.96900 23.25750
## 6 Butterfly 3 Wind 5 71.20000 41.11812 18.38858
#creating boxplot of experimental factor and distance
boxplotsd <- ggplot(data = sd, aes(x = Factor, y = Distance))
boxplotsd +
theme_classic() +
geom_boxplot()
#creating boxplot with experimental factor, seed type, and distance(two categorical variables)
boxplot2 <- ggplot(data = sd, aes(x = Factor, y = Distance, fill = Seed_Type))
boxplot2 +
theme_classic() +
geom_boxplot()
#creating a two factor bar graph(seed type, factor and distance mean)
bar_2v <- ddply(sd, c("Factor", "Seed_Type"), summarise,
dataRep = sum(!is.na(Distance)),
dataMean = mean(Distance, na.rm=T),
dataSD = sd(Distance, na.rm=T),
dataSE = dataSD / sqrt(dataRep))
head(bar_2v)#summary of six rows of data
## Factor Seed_Type dataRep dataMean dataSD dataSE
## 1 No wind Butterfly 27 93.88889 61.59192 11.85337
## 2 No wind Dog 24 90.04167 71.78863 14.65379
## 3 No wind Fox 32 102.75000 60.08757 10.62208
## 4 Wind Butterfly 32 81.00000 70.03271 12.38015
## 5 Wind Dog 32 100.40625 71.84026 12.69968
## 6 Wind Fox 35 84.88571 61.13956 10.33447
#loading the graphing data for x and y axis
bar_2 <- ggplot(data = bar_2v, aes(x = Factor, y = dataMean, fill = Seed_Type))
#setting error bar limits
limits <- aes(ymax = dataMean + dataSD, ymin = dataMean - dataSD)
dodge <- position_dodge(width = 0.9) # Dodge overlapping objects side-to-side
#running my graph
bar_2 +
theme_classic() +
geom_bar(stat="identity", position = dodge, colour = "black") +
geom_errorbar(limits, width = 0.2, position = dodge) +
scale_fill_brewer(palette="Greens")# Limits
#Assessing my data normality
#histogram of distance
hist(seed$meanDistance)
qqnorm(seed$meanDistance) #qqplots
qqline(seed$meanDistance)
#data was not that normal so log transformation
qqnorm(log10(seed$meanDistance)) #qqplots of transformed data
qqline(log10(seed$meanDistance))
#Running an ANOVA
anova <- aov(log10(meanDistance)~ Seed_Type, data=seed)
plot(anova)
## Df Sum Sq Mean Sq F value Pr(>F)
## Seed_Type 2 0.0218 0.01090 0.542 0.588
## Residuals 27 0.5436 0.02013
anova2 <- aov(log10(meanDistance)~ Seed_Type * Factor, data=seed)
plot(anova2)
summary(anova2) #checking interactions
## Df Sum Sq Mean Sq F value Pr(>F)
## Seed_Type 2 0.0218 0.010903 0.532 0.594
## Factor 1 0.0084 0.008427 0.411 0.527
## Seed_Type:Factor 2 0.0434 0.021701 1.059 0.362
## Residuals 24 0.4918 0.020490
#creating my map
#file.choose()
dispersalmap <- read.csv("C:\\Users\\gkrochmal\\Downloads\\Seed Dispersal Data - Sheet1.csv")
summary(dispersalmap)
## Factor Seed_Type Distance Angle
## No wind:83 Butterfly:59 Min. : 1.00 Min. : 4.00
## Wind :99 Dog :56 1st Qu.: 34.25 1st Qu.: 50.25
## Fox :67 Median : 80.00 Median :127.00
## Mean : 92.09 Mean :128.59
## 3rd Qu.:134.00 3rd Qu.:190.50
## Max. :324.00 Max. :350.00
## Season
## Min. :1.00
## 1st Qu.:2.00
## Median :3.00
## Mean :3.06
## 3rd Qu.:4.00
## Max. :5.00
#X coordinate
dispersalmap$cartX <- dispersalmap$Distance * sin(dispersalmap$Angle)
#y coordinate
dispersalmap$cartY <- dispersalmap$Distance * cos(dispersalmap$Angle)
SeedMap <- ggplot(dispersalmap, aes(x=cartX, y=cartY))
SeedMap +
geom_point() +
geom_text(aes(label=Seed_Type), hjust=-0.5, vjust=-0.5)
