Tank conditions
Ana Palacio
2022-09-05
General project set-up
# Libraries
library(reshape2)
library(tidyverse)
library(tidyr)
library(lubridate)
library(gridExtra)
# Graphs
theme_set (theme_classic() + theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
axis.line = element_line(colour = "black"),
legend.position="bottom",
legend.title=element_blank(),
#axis.text.x = element_text(angle = 90, vjust = 0.5),
plot.title = element_text(size=12, face="bold"),
panel.border = element_rect(colour = "black", fill=NA, size=1)
#panel.border = element_blank()
))
col_4_col<-scale_colour_manual(values = c("#88CCEE", "#332288",
"#DDCC77","#117733"))
col_4_fill<-scale_fill_manual(values = c("#88CCEE", "#332288",
"#DDCC77","#117733"))Temperature data
Temperature.data<-read.csv("Data/Temp_experiment.csv", header = T)
summary(Temperature.data)## Time Tank Temperature
## 2020-09-14 19:30:00: 8 Tank.1 :16856 Min. :18.06
## 2020-09-14 19:35:00: 8 Tank.2 :16856 1st Qu.:27.99
## 2020-09-14 19:40:00: 8 Tank.3 :16856 Median :28.02
## 2020-09-14 19:45:00: 8 Tank.4 :16856 Mean :27.90
## 2020-09-14 19:50:00: 8 Tank.5 :16856 3rd Qu.:28.05
## 2020-09-14 19:55:00: 8 Tank.6 :16856 Max. :33.78
## (Other) :134800 (Other):33712
## Period Content
## Experiment:134848 A-T1 :13118
## A-T2 :13118
## A-T5 :13118
## A-T6 :13118
## N-T3 :13118
## N-T4 :13118
## (Other):56140# Data types
Temperature.data$Temperature<-as.numeric(Temperature.data$Temperature)
Temperature.data$Tank<-as.factor(Temperature.data$Tank)
Temperature.data$Content<-factor(Temperature.data$Content)
Temperature.data$Time<-strptime(Temperature.data$Time, "%Y-%m-%d %H:%M:%S")
Temperature.data$Time <- as.POSIXct(Temperature.data$Time)
Temperature.data$Date<-as.Date(ymd_hms(Temperature.data$Time))
Temperature.data<- Temperature.data %>%
group_by(Tank, Content, Date)%>%
dplyr::summarise(Temperature=mean(Temperature))
Temperature.data Temperature.data$Day<-weekdays(Temperature.data$Date)
Temperature.data$Data<-ifelse (Temperature.data$Day=="Friday",
15, NA)
Temperature.data$Day<-as.numeric(Temperature.data$Date)-18518
Temperature.data<-Temperature.data[Temperature.data$Day>0, ]
Temperature.data$Week<-(Temperature.data$Day)/7
Temperature.data$Week<-as.integer(Temperature.data$Week)+1
summary(Temperature.data)## Tank Content Date Temperature Day
## Tank.1 : 61 A-T1 : 47 Min. :2020-09-14 Min. :20.05 Min. : 1
## Tank.2 : 61 A-T2 : 47 1st Qu.:2020-09-29 1st Qu.:27.97 1st Qu.:16
## Tank.3 : 61 A-T5 : 47 Median :2020-10-14 Median :28.01 Median :31
## Tank.4 : 61 A-T6 : 47 Mean :2020-10-14 Mean :27.89 Mean :31
## Tank.5 : 61 N-T3 : 47 3rd Qu.:2020-10-29 3rd Qu.:28.03 3rd Qu.:46
## Tank.6 : 61 N-T4 : 47 Max. :2020-11-13 Max. :29.44 Max. :61
## (Other):122 (Other):206
## Data Week
## Min. :15 Min. :1
## 1st Qu.:15 1st Qu.:3
## Median :15 Median :5
## Mean :15 Mean :5
## 3rd Qu.:15 3rd Qu.:7
## Max. :15 Max. :9
## NA's :416ExperimentTemperature<- ggplot(Temperature.data) +
#geom_vline(xintercept=1500)+
geom_jitter(aes(Date, Temperature, colour=factor(Content)),
alpha=0.5, size=0.01)+
geom_line(aes(Date, Data), alpha=1, size=0.05)+
scale_y_continuous(limits = c(15, 35),
breaks = seq(15, 35, 2),
expand = c(0, 0),
name=("Temperature (C)"))
ExperimentTemperature+facet_wrap(~Tank)
Salinity data
## Salinity
Salinity.data<-read.csv("Data/System.csv")
Salinity.data<-Salinity.data %>% select(Time, Salinity)
Salinity.data$Time<-strptime(Salinity.data$Time, "%m/%d/%y %H:%M")
Salinity.data$Time <- as.POSIXct(Salinity.data$Time)
Salinity.data$Date <- as.Date(Salinity.data$Time)
Salinity.data<- Salinity.data %>%
group_by(Date)%>%
dplyr::summarise(Salinity=mean(Salinity))
Salinity.data Temperature.data<-left_join(Temperature.data, Salinity.data, by=("Date"))Tank treatment info
# Get tank treatment info
Tank.info<-read.csv("Data/Tank_treatment.csv", header = T)
# Merge with temperature
Temperature.data<-left_join(Temperature.data, Tank.info, by=("Tank"))
Temperature.data$Treatment<-factor(Temperature.data$Combo, levels = c("Ambient+Placebo", "Ambient+Disease",
"NH4+Placebo", "NH4+Disease"))Temp + Sal plot
meanTemp<-ggplot(Temperature.data, aes(Week, Temperature, fill=Treatment)) +
geom_line(data=Temperature.data, aes(x=Temperature.data$Day/7, y=Temperature.data$Salinity), linetype=2) +
stat_summary(fun=mean, geom="line", position=position_dodge(width=0.3)) +
stat_summary(fun.data = mean_cl_boot, geom = "errorbar", width = 0.2, position=position_dodge(width=0.3)) +
stat_summary(fun=mean, geom="point", shape=21, size=3, position=position_dodge(width=0.3)) +
scale_x_continuous(limits = c(0.8, 9.2),
breaks = seq(1, 9, 1),
expand = c(0, 0))+
scale_y_continuous(limits = c(25, 33),
# breaks = seq(0, 35, 2),
# expand = c(0, 0),
name=expression("Temperature ("~degree~"C)"))+
geom_vline(xintercept=7.8, linetype="dashed", colour="#990033") +
col_4_fill+
col_4_col
meanTemp
#ggsave(file="Outputs/Temperature_plot.svg", meanTemp, width=5.5, height=4)Temp and sal summary
Temp.Summary<- as.data.frame(Temperature.data %>%
group_by(Week, Treatment) %>%
summarize(Temp_mean = mean (Temperature, na.rm = T),
Temp_sd = sd (Temperature, na.rm = T)))
Temp.Summary<-reshape(Temp.Summary, idvar = "Treatment", timevar = "Week", direction = "wide")
Temp.Summarywrite.csv(Temp.Summary, "Outputs/Temp_Summary.csv", row.names = F)
Sal.Summary<- as.data.frame(Temperature.data %>%
group_by(Week, Treatment) %>%
summarize(Sal_mean = min (Salinity, na.rm = T),
Sal_sd = sd (Salinity, na.rm = T)))
Sal.Summary<-reshape(Sal.Summary, idvar = "Treatment", timevar = "Week", direction = "wide")
Sal.Summarywrite.csv(Sal.Summary, "Outputs/Sal_Summary.csv", row.names = F)Nutrients
# Nutrients
Nutrients<-read.csv("Data/Nutrients.csv")
summary(Nutrients)## Sample.ID Tank Sample Treatment sample
## 29-01 : 2 3 :107 31 : 17 Ambient+Disease:176 Chl :408
## 29-02 : 2 4 :107 43 : 17 Ambient+Placebo:176 frozen:261
## 29-03 : 2 7 :107 29 : 16 NH4+Disease :214 Frozen:139
## 29-04 : 2 8 :107 35 : 16 NH4+Placebo :214
## 29-05 : 2 1 : 88 38 : 16 NA's : 28
## 29-06 : 2 2 : 88 39 : 16
## (Other):796 (Other):204 (Other):710
## NH4 Si.uM. NO2.uM. N.N.uM.
## Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 2.270 1st Qu.: 0.000 1st Qu.: 0.400 1st Qu.: 3.547
## Median : 5.842 Median : 1.550 Median : 1.355 Median : 5.880
## Mean : 6.984 Mean : 2.417 Mean : 1.569 Mean : 5.665
## 3rd Qu.: 9.960 3rd Qu.: 4.067 3rd Qu.: 2.337 3rd Qu.: 7.740
## Max. :31.559 Max. :22.200 Max. :10.290 Max. :24.514
## NA's :3 NA's :298 NA's :306 NA's :306
## NO3.uM. PO4.uM. Day Week
## Min. : 0.000 Min. :0.00000 Min. : 1.00 Min. :1.000
## 1st Qu.: 2.825 1st Qu.:0.08425 1st Qu.:41.00 1st Qu.:6.000
## Median : 4.340 Median :0.25400 Median :51.00 Median :7.000
## Mean : 4.096 Mean :0.69458 Mean :47.45 Mean :6.939
## 3rd Qu.: 5.375 3rd Qu.:0.58000 3rd Qu.:56.00 3rd Qu.:8.000
## Max. :19.948 Max. :8.92000 Max. :64.00 Max. :9.000
## NA's :306 NA's :306
## X X.1
## Min. :14.00 Min. :3.000
## 1st Qu.:27.00 1st Qu.:4.000
## Median :36.00 Median :6.000
## Mean :36.56 Mean :5.812
## 3rd Qu.:46.00 3rd Qu.:7.000
## Max. :58.00 Max. :9.000
## NA's :84 NA's :84 # Nutrients$Date<-as.Date(Nutrients$Date, "%m-%d-%Y")
# Nutrients$Time<-paste(Nutrients$Date, Nutrients$Hour, sep = " ")
# Nutrients$Time<-strptime(Nutrients$Time, "%Y-%m-%d %H:%M:%S")
# Nutrients$Time <- as.POSIXct(Nutrients$Time)
# Nutrients$Date <- as.Date(Nutrients$Time)
# Nutrients$Day<-as.numeric(Nutrients$Date)-18518
# Nutrients$Week<-(Nutrients$Day)/7
# Nutrients$Week<-as.integer(Nutrients$Week)+1
Nutrients$Treatment<-factor(Nutrients$Treatment, levels = c("Ambient+Placebo", "Ambient+Disease",
"NH4+Placebo", "NH4+Disease"))
summary(Nutrients)## Sample.ID Tank Sample Treatment sample
## 29-01 : 2 3 :107 31 : 17 Ambient+Placebo:176 Chl :408
## 29-02 : 2 4 :107 43 : 17 Ambient+Disease:176 frozen:261
## 29-03 : 2 7 :107 29 : 16 NH4+Placebo :214 Frozen:139
## 29-04 : 2 8 :107 35 : 16 NH4+Disease :214
## 29-05 : 2 1 : 88 38 : 16 NA's : 28
## 29-06 : 2 2 : 88 39 : 16
## (Other):796 (Other):204 (Other):710
## NH4 Si.uM. NO2.uM. N.N.uM.
## Min. : 0.000 Min. : 0.000 Min. : 0.000 Min. : 0.000
## 1st Qu.: 2.270 1st Qu.: 0.000 1st Qu.: 0.400 1st Qu.: 3.547
## Median : 5.842 Median : 1.550 Median : 1.355 Median : 5.880
## Mean : 6.984 Mean : 2.417 Mean : 1.569 Mean : 5.665
## 3rd Qu.: 9.960 3rd Qu.: 4.067 3rd Qu.: 2.337 3rd Qu.: 7.740
## Max. :31.559 Max. :22.200 Max. :10.290 Max. :24.514
## NA's :3 NA's :298 NA's :306 NA's :306
## NO3.uM. PO4.uM. Day Week
## Min. : 0.000 Min. :0.00000 Min. : 1.00 Min. :1.000
## 1st Qu.: 2.825 1st Qu.:0.08425 1st Qu.:41.00 1st Qu.:6.000
## Median : 4.340 Median :0.25400 Median :51.00 Median :7.000
## Mean : 4.096 Mean :0.69458 Mean :47.45 Mean :6.939
## 3rd Qu.: 5.375 3rd Qu.:0.58000 3rd Qu.:56.00 3rd Qu.:8.000
## Max. :19.948 Max. :8.92000 Max. :64.00 Max. :9.000
## NA's :306 NA's :306
## X X.1
## Min. :14.00 Min. :3.000
## 1st Qu.:27.00 1st Qu.:4.000
## Median :36.00 Median :6.000
## Mean :36.56 Mean :5.812
## 3rd Qu.:46.00 3rd Qu.:7.000
## Max. :58.00 Max. :9.000
## NA's :84 NA's :84 #write.csv(Nutrients, "Nutrients.csv")
# Tall format
# Nutrients.tall <- gather(Nutrients, Nutrient, Concentration,
# NH4:PO4.uM., factor_key=TRUE)
# Nutrients.tall$Date<-as.Date(Nutrients.tall$Date, "%m-%d-%Y")
# #Nutrients.tall$Time<-paste(Nutrients.tall$Date, Nutrients$Hour, sep = " ")
# summary(Nutrients.tall)NH4
NH4Plot<- ggplot(filter(Nutrients, Treatment!="Source"),
aes (Week, NH4, fill=Treatment)) +
stat_summary(fun.data = "mean_cl_boot",geom = "errorbar", width = 0.2 )+
stat_summary(fun=mean, geom="line") +
stat_summary(fun=mean, geom="point", shape=21, size=3) +
scale_x_continuous(limits = c(0.8, 9.2),
breaks = seq(1, 9, 1),
expand = c(0, 0))+
scale_y_continuous(#limits = c(0, 20),
# breaks = seq(0, 35, 2),
# expand = c(0, 0),
name=expression(NH[4]~"["~mu~"M]"))+
#geom_vline(xintercept=5.5, linetype="dashed")+
geom_vline(xintercept=7.8, linetype="dashed", colour="#990033") +
col_4_fill
NH4Plot
#ggsave(file="Outputs/NH4_plot.svg", NH4Plot, width=5.5, height=4.0)PO4
PH4_plot<- ggplot(filter(Nutrients, Treatment!="Source"),
aes (Week, PO4.uM., fill=Treatment)) +
stat_summary(fun.data = "mean_cl_boot",geom = "errorbar", width = 0.2 )+
stat_summary(fun=mean, geom="line") +
stat_summary(fun=mean, geom="point", shape=21, size=3) +
scale_x_continuous(limits = c(0.8, 9.2),
breaks = seq(1, 9, 1),
expand = c(0, 0))+
scale_y_continuous(name=expression(PO[4]~"["~mu~"M]"))+
geom_vline(xintercept=7.8, linetype="dashed", colour="#990033") +
col_4_fill
PH4_plot
#ggsave(file="Outputs/PO4_plot.svg", PH4_plot, width=5.5, height=4.0)Nutrients summary
NH4.Summary<- as.data.frame(Nutrients %>%
group_by(Week, Treatment) %>%
summarize(Temp_mean = mean (NH4, na.rm = T),
Temp_sd = sd (NH4, na.rm = T)))
NH4.Summary<-reshape(NH4.Summary, idvar = "Treatment", timevar = "Week", direction = "wide")
NH4.Summary#write.csv(NH4.Summary, "Outputs/NH4_Summary.csv", row.names = F)
PO4.Summary<- as.data.frame(Nutrients %>%
group_by(Week, Treatment) %>%
summarize(Sal_mean = min (PO4.uM., na.rm = T),
Sal_sd = sd (PO4.uM., na.rm = T)))
PO4.Summary<-reshape(PO4.Summary, idvar = "Treatment", timevar = "Week", direction = "wide")
PO4.Summary#write.csv(PO4.Summary, "Outputs/PO4_Summary.csv", row.names = F)Tank conditions plot
TanksPlot<-grid.arrange(meanTemp + theme(legend.position = "none",
axis.text.x=element_blank(),
axis.title.x = element_blank()),
NH4Plot + theme(legend.position = "none",
axis.text.x=element_blank(),
axis.title.x = element_blank()),
PH4_plot, nrow=3)
#ggsave(file="Outputs/Tanks.svg", TanksPlot, width=7.5, height=7.5)Packages used
# Creates bibliography
#knitr::write_bib(c(.packages()), "packages.bib")Auguie, Baptiste. 2017. GridExtra: Miscellaneous Functions for "Grid" Graphics. https://CRAN.R-project.org/package=gridExtra.
Grolemund, Garrett, and Hadley Wickham. 2011. “Dates and Times Made Easy with lubridate.” Journal of Statistical Software 40 (3): 1–25. https://www.jstatsoft.org/v40/i03/.
Henry, Lionel, and Hadley Wickham. 2020. Purrr: Functional Programming Tools. https://CRAN.R-project.org/package=purrr.
Müller, Kirill, and Hadley Wickham. 2021. Tibble: Simple Data Frames. https://CRAN.R-project.org/package=tibble.
R Core Team. 2020. R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing. https://www.R-project.org/.
Spinu, Vitalie, Garrett Grolemund, and Hadley Wickham. 2021. Lubridate: Make Dealing with Dates a Little Easier. https://CRAN.R-project.org/package=lubridate.
Wickham, Hadley. 2007. “Reshaping Data with the reshape Package.” Journal of Statistical Software 21 (12): 1–20. http://www.jstatsoft.org/v21/i12/.
———. 2016. Ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. https://ggplot2.tidyverse.org.
———. 2019. Stringr: Simple, Consistent Wrappers for Common String Operations. https://CRAN.R-project.org/package=stringr.
———. 2020. Reshape2: Flexibly Reshape Data: A Reboot of the Reshape Package. https://github.com/hadley/reshape.
———. 2021a. Forcats: Tools for Working with Categorical Variables (Factors). https://CRAN.R-project.org/package=forcats.
———. 2021b. Tidyr: Tidy Messy Data. https://CRAN.R-project.org/package=tidyr.
———. 2021c. Tidyverse: Easily Install and Load the Tidyverse. https://CRAN.R-project.org/package=tidyverse.
Wickham, Hadley, Mara Averick, Jennifer Bryan, Winston Chang, Lucy D’Agostino McGowan, Romain François, Garrett Grolemund, et al. 2019. “Welcome to the tidyverse.” Journal of Open Source Software 4 (43): 1686. https://doi.org/10.21105/joss.01686.
Wickham, Hadley, Winston Chang, Lionel Henry, Thomas Lin Pedersen, Kohske Takahashi, Claus Wilke, Kara Woo, Hiroaki Yutani, and Dewey Dunnington. 2021. Ggplot2: Create Elegant Data Visualisations Using the Grammar of Graphics. https://CRAN.R-project.org/package=ggplot2.
Wickham, Hadley, Romain François, Lionel Henry, and Kirill Müller. 2021. Dplyr: A Grammar of Data Manipulation. https://CRAN.R-project.org/package=dplyr.
Wickham, Hadley, and Jim Hester. 2020. Readr: Read Rectangular Text Data. https://CRAN.R-project.org/package=readr.