for_Keo
JLD
October 20, 2016
based on June 27, 2016 document “Database_starting”
Notes on data formatting and directory control etc:
- Make sure that you have a folder (directory) that only contains files specific to this project
- i.e. make a new folder, call it Database for example, and keep all the necessary files in one place so that R knows where to “look” for them.
- NOTE: You can set the working directory (folder) using Session –> set Directory or using the code setw() OR by making an “R Project” which is what I use (I can show you how)
- You will need to save a copy of the database as a .csv in order to import it
- It is good practice to save a new copy of the original database each time you make major edits to the database itself (e.g., if you add data from different papers)
libraries you will need (and therefore, packagse to download if you don’t have them already)
- Most importantly, the packages “dplyr” and “ggplot2” and “knitr” will be extraordinarily useful
- Also, I find “R markdown documents” aka Rmds super helpful
Import data and rename variables
setwd("C:/Users/theco/Desktop/Fish Database Project")
database <- read.csv("database_0806.csv") ## change the name here to whatever you call the database
database <- database %>% rename(d15N = d15N.avg.,
d13C = d13C.avg.,
length = Length..mm..avg.,
baseline_d15N = Baselined15N,
ecology = FeedingHabits,
TL_fishbase = FishBase.Trophic.Level,
lat = Lat,
long = Long,
stationlocationdata = StationLocationData) #.eitherestimatedordirectlyfrompaper
# convert discrete variables to numeric
database$d15N <- as.numeric(as.character(database$d15N)) ## Warning: NAs introduced by coerciondatabase$d13C <- as.numeric(as.character(database$d13C))## Warning: NAs introduced by coerciondatabase$length <- as.numeric(as.character(database$length)) ## Warning: NAs introduced by coerciondatabase$lat <- as.numeric(as.character(database$lat)) ## Warning: NAs introduced by coerciondatabase$lon <- as.numeric(as.character(database$lon)) ## Warning: NAs introduced by coerciondatabase$TL_fishbase <- as.numeric(as.character(database$TL_fishbase)) ## Warning: NAs introduced by coerciondatabase$Authortrophiclevel <- as.numeric(as.character(database$Authortrophiclevel)) ## Warning: NAs introduced by coercionButterfish data?
database %>% filter(CommonName %in% c("Butterfish", "Butter_sh")) %>%
ggplot() +
geom_point(aes(Environment, d15N)) 
btf <- database %>% filter(CommonName %in% c("Butterfish", "Butter_sh"))
#colnames(database)
#sort(unique(database$CommonName))Beginning to plot
gbgom <- database %>%
filter(!is.na(jldCategory), GeneralLocation %in% c("Georges Bank", "Gulf of Maine")) %>%
ggplot(aes(shape = ecology, color = jldCategory, fill = ecology)) +
geom_point(aes(d13C, d15N), size = 8, stroke = 2) +
ggtitle("Georges Bank and Gulf of Maine all species") +
theme_bw() +
theme(axis.text.y = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(3), color = "black")) +
theme(axis.text.x = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(3), color = "black"))
gbgom## Warning: Removed 13 rows containing missing values (geom_point).
#
# ## TO SEE WHAT THE "NOTHINGS" ARE HERE
# df <- gbgom <- database %>%
# filter(!is.na(jldCategory), GeneralLocation %in% c("Georges Bank", "Gulf of Maine"), ecology == "-")
#
# #View(df) Exploratory: gelatinous zooplankton d15N and d13C, colored by latitude…
# sort(unique(database$jldCategory))
zoops <- database %>%
filter(jldCategory == "Gelatinous zooplankton") %>%
ggplot(aes(shape = Environment, color = GeneralLocation, fill = ecology)) +
geom_point(aes(d13C, d15N), size = 8, stroke = 2) +
ggtitle("Gelatinous zooplankton") +
theme_bw() +
theme(axis.text.y = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(3), color = "black")) +
theme(axis.text.x = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(3), color = "black"))
zoops## Warning: Removed 10 rows containing missing values (geom_point).
whoah this is quite high:
Pleurobrachia pileus
from Das et al
# create dataframe of just Das et al data
df.Dasetal <- database %>%
filter(References %in% c("Das et al 2003", "Das et al. (2003)", "Das et al., 2003", "Das et al., 2003; Dehn et al., 2007", "Das et al., 2003; Hoekstra et al., 2002", "Das et al., 2003; Loseto et al., 2008", "Das et al., 2003; Loseto et al., 2008; Sara et al., 2009; Lesage et al., 2001; Dehn et al., 2007", "Das et al., 2003; Sara et al., 2009"))
#View(df.Dasetal)
# plot all Das et al data to see how these zooplankton compare to nekton
Dasetal <- database %>%
filter(References %in% c("Das et al 2003", "Das et al. (2003)", "Das et al., 2003", "Das et al., 2003; Dehn et al., 2007", "Das et al., 2003; Hoekstra et al., 2002", "Das et al., 2003; Loseto et al., 2008", "Das et al., 2003; Loseto et al., 2008; Sara et al., 2009; Lesage et al., 2001; Dehn et al., 2007", "Das et al., 2003; Sara et al., 2009")) %>%
ggplot(aes(shape = GeneralLocation, color = jldCategory)) +
geom_point(aes(d13C, d15N), size = 8, stroke = 2, alpha = 0.7) +
ggtitle("Das et al. 2003 -- what's going on with gelatinous zooplankton?") +
theme_bw()
Dasetal
#ggplotly()
# create tally of Das et al data
tally.das <- database %>%
filter(References %in% c("Das et al 2003", "Das et al. (2003)", "Das et al., 2003", "Das et al., 2003; Dehn et al., 2007", "Das et al., 2003; Hoekstra et al., 2002", "Das et al., 2003; Loseto et al., 2008", "Das et al., 2003; Loseto et al., 2008; Sara et al., 2009; Lesage et al., 2001; Dehn et al., 2007", "Das et al., 2003; Sara et al., 2009")) %>%
group_by(GeneralLocation, Environment) %>%
summarise(n = n()) #filter(year >= 1900)
#View(tally.das)
tally.das## Source: local data frame [0 x 3]
## Groups: GeneralLocation [?]
##
## # ... with 3 variables: GeneralLocation <fctr>, Environment <fctr>,
## # n <int>Curious about Gadiformes and their distribution
plot of d15N vs d13C (gadiformes)
### plot of d15N vs d13C (gadiformes)
gads <- database %>%
filter(Category.of.Interest == "Gadiformes") %>%
ggplot(aes(shape = Environment, color = GeneralLocation)) + #fill = ecology
geom_point(aes(d13C, d15N), size = 8, stroke = 2) +
ggtitle("Gadiformes by general location") +
theme_bw() +
theme(axis.text.y = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(3), color = "black")) +
theme(axis.text.x = element_text(size = rel(2.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(3), color = "black"))
gads## Warning: Removed 41 rows containing missing values (geom_point).
# duplicates in the Carscallen or Badalamenti references? (gadiformes)
gadids <- database %>%
filter(Category.of.Interest == "Gadiformes") %>%
select(Category.of.Interest, d15N, d15N.sd., d13C, d13C.sd., CommonName, SpeciesName, GeneralLocation, References, lat, lon)
sort(gadids$d15N)## [1] 9.30 9.40 9.40 9.50 9.50 9.50 9.60 9.96 10.10 10.20 10.30
## [12] 10.32 10.40 10.40 10.50 10.60 10.60 10.70 10.80 10.80 10.87 10.90
## [23] 10.90 10.99 11.00 11.00 11.06 11.10 11.10 11.10 11.10 11.14 11.20
## [34] 11.20 11.20 11.30 11.30 11.30 11.30 11.30 11.30 11.39 11.40 11.40
## [45] 11.50 11.60 11.60 11.80 11.80 11.80 11.86 11.90 11.90 12.00 12.00
## [56] 12.04 12.06 12.10 12.19 12.20 12.20 12.20 12.20 12.30 12.30 12.30
## [67] 12.30 12.30 12.30 12.30 12.36 12.40 12.40 12.45 12.60 12.60 12.69
## [78] 12.70 12.70 12.74 12.80 12.80 12.80 12.80 12.82 12.90 12.90 12.90
## [89] 12.97 12.99 13.00 13.00 13.00 13.00 13.10 13.10 13.10 13.10 13.15
## [100] 13.20 13.23 13.30 13.30 13.30 13.30 13.36 13.40 13.40 13.40 13.40
## [111] 13.46 13.49 13.50 13.50 13.50 13.50 13.50 13.60 13.60 13.60 13.60
## [122] 13.60 13.60 13.60 13.64 13.70 13.70 13.70 13.70 13.70 13.70 13.70
## [133] 13.70 13.78 13.80 13.80 13.86 13.92 13.97 14.00 14.00 14.00 14.06
## [144] 14.10 14.15 14.18 14.20 14.20 14.20 14.20 14.21 14.21 14.21 14.27
## [155] 14.27 14.30 14.30 14.30 14.30 14.30 14.30 14.30 14.31 14.31 14.36
## [166] 14.39 14.40 14.40 14.40 14.41 14.50 14.59 14.60 14.60 14.60 14.62
## [177] 14.70 14.70 14.70 14.70 14.70 14.70 14.75 14.80 14.80 14.80 14.80
## [188] 14.80 14.80 14.80 14.80 14.81 14.87 14.90 14.92 15.00 15.00 15.00
## [199] 15.04 15.07 15.10 15.11 15.12 15.19 15.20 15.20 15.20 15.20 15.20
## [210] 15.20 15.20 15.25 15.30 15.43 15.50 15.50 15.50 15.60 15.60 15.60
## [221] 15.70 15.70 15.70 15.70 15.73 15.80 15.80 15.86 15.87 16.00 16.08
## [232] 16.10 16.20 16.40 16.40 16.50 16.70 16.80 16.90 17.03 17.10 17.20
## [243] 17.30 17.30 17.90 19.10 19.10 19.20 19.20#View(gadids)plot of length (mm) vs. d15N (gadiformes)
# in black to see accidental replicates
# sort(colnames(database))
database %>%
filter(length %in% c(115:900), Category.of.Interest == "Gadiformes") %>%
ggplot(aes(x = length, y = d15N)) +
geom_point(aes(color = factor(lat), shape = GeneralLocation, fill = factor(lat)), stroke = 2, size = 4, alpha = 0.7) +
scale_shape_manual(values=1:nlevels(database$GeneralLocation)) +
theme_bw() +
theme(legend.background = element_rect(fill = 'pink', size = 3)) +
ggtitle("Gadiformes: shape = location, fill = latitude, size = spp")
database %>%
filter(length %in% c(115:900), Category.of.Interest == "Gadiformes") %>%
ggplot(aes(x = length, y = d15N)) +
geom_point(aes(fill = factor(lat)), stroke = 2, size = 4, alpha = 0.7) +
scale_shape_manual(values=1:nlevels(database$GeneralLocation)) +
theme_bw() +
theme(legend.background = element_rect(fill = 'pink', size = 3)) +
ggtitle("Gadiformes - replicates appear dark black")
# in color, with species identified (gadiformes)
database %>%
filter(length %in% c(115:900),
Category.of.Interest == "Gadiformes") %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(lat)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N of Gadiformes colored by latitude") +
xlab("Length (mm)") +
ylab("d15N (â°)")
# in color, with species identified (gadiformes)
database %>%
filter(length %in% c(115:900),
Category.of.Interest == "Gadiformes") %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by Gadiform species") +
xlab("Length (mm)") +
ylab("d15N (â°)")
### STILL TO DO/modify:
### plot of d15N vs. latitude (gadiformes)
# colored by length?
# Atlantic Ocean
database %>%
filter(length %in% c(115:900),
Category.of.Interest == "Gadiformes",
lon <= 30,
lon >= -90) %>%
ggplot() +
geom_point(aes(x = lat, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by Gadiform species in the Atlantic Ocean") +
xlab("Latitude") +
ylab("d15N (â°)")
# All oceans
database %>%
filter(length %in% c(115:900),
Category.of.Interest == "Gadiformes") %>%
ggplot() +
# geom_point(aes(x = lon, y = lat, colour = factor(lon)),
# size = 5,
# alpha = 0.7) +
geom_jitter(aes(x = lon, y = lat, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7,
position = position_jitter(width = 7, height = 7)) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Lat vs. lon colored by Gadiform species in the all oceans") +
ylab("Latitude") +
xlab("Longitude")
ggplotly()###Length vs d15N across all oceans
unique(database$GeneralLocation)## [1] Hawaii
## [2] Labrador Shelf
## [3] North Norway
## [4] Antarctic
## [5] Georges Bank
## [6] Canadian Arctic
## [7] Horn Island
## [8] Narragansett Bay
## [9] Mediterranean Sea
## [10] Mad Island Marsh
## [11] Northeast Pacific Ocean
## [12] Baffin Bay
## [13] Boston Harbor
## [14] Acquatina Lagoon
## [15] Sea of Japan
## [16] Norway
## [17] Mediterannean Sea
## [18] Gulf of St. Lawrence
## [19] Arctic
## [20] Lancaster Sound
## [21] Cananéia Lagoon Estuarine System
## [22] Hudson Bay
## [23] Saglek Bay
## [24] Caribbean Sea
## [25] St. Kitts
## [26] Isle of May
## [27] Chesapeake Bay
## [28] Cumberland Sound
## [29] Stellwagen Bay
## [30] West Greenland
## [31] Barrow Strait
## [32] North Sea
## [33] Denmark
## [34] Massachusetts Bay
## [35] North Sea
## [36] Gulf of Alaska
## [37] Greenland
## [38] Southwest Greenland
## [39] Spitsbergen
## [40] Iceland
## [41] Barents Sea
## [42] Prince William Sound
## [43] Benguela
## [44] California Current
## [45] Pacific Ocean
## [46] Newfoundland/Georges Band
## [47] Washington-Oregon
## [48] East Japan
## [49] Kuroshio-Oyashio
## [50] Taiwan
## [51] Atlantic Ocean
## [52] Bering Sea
## [53] Gulf of Maine
## [54] Mururoa Atoll, French Polynesia
## [55] Strangford Lough
## [56] Massachusetts, U.S.A. (shelf)
## [57] Dipper Harbor
## [58] Cutler
## [59] Scheldt Estuary
## [60] Everywhere
## [61] Baltic Sea
## [62] Salish Sea
## [63] Funk Island
## [64] St. Kilda
## [65] North Atlantic Ocean
## [66] Svalbard
## [67] East Greenland
## [68] Caribbean
## [69] St. Lawrence
## [70] Australia
## [71] Celtic Sea
## [72] Northeast Greenland
## [73] Gulf of Mexico
## [74] Tasma Sea Abyssal basin
## [75] Mid-Atlantic Ridge
## [76] Eastern Baltic Sea
## [77] Western Baltic Sea
## [78] Arabian Sea
## [79] Rhode Island and Block Island Sound
## [80] North Alaska
## [81] Hutt River, New Zealand
## [82] St. Marks
## [83] Shelikof Strait
## [84] Northern Norway
## [85] Southwest Alaska
## [86] South Alaska
## [87] Rio Santa Cruz
## [88] Northwest Miramichi River
## [89] European Lakes
## [90] Quebec
## [91] Bering Strait
## [92] Conception Bay
## [93] Georgia, USA and KZN shelf, South Africa
## [94] Cape Cod
## [95] Davis Strait
## [96] Joux (ch)
## [97] Little River
## [98] Snoqualmie River, Wash.
## [99] Headwater lake of the Pointe Wolfe River
## [100] Chip River
## [101] Meade River
## [102] Martha's Vineyard
## [103] Kvichak River, Alaska
## [104] Northwest Atlantic
## [105] Bay of Biscay
## [106] Mid-Atlantic Bight
## [107] Grenada
## [108] North Carolina Gulf Stream
## [109] Jan Mayen
## [110] Vestjorden/Lofoten
## [111] North Carolina
## 111 Levels: Acquatina Lagoon Antarctic Arabian Sea ... Western Baltic Sea## number of individuals per species in each environment
tally_species_env <- database %>%
group_by(Environment, SpeciesName) %>%
summarise(n = n())
## number of species per environment
tally_species_env_tally <- tally_species_env %>%
group_by(Environment) %>%
summarise(NumberOfSp = n())
## plot
tally_species_env_tally %>% filter(Environment != "-", Environment != "") %>%
ggplot(aes(Environment, NumberOfSp)) +
geom_point(size = 5)+
labs(x = "", y = "Count of species", title = "# of species per environment")
## number of individuals per species in each part of the world
tally_species_loc <- database %>%
group_by(GeneralLocation, SpeciesName) %>%
summarise(n = n())
## number of species per environment
tally_species_loc_tally <- tally_species_loc %>%
group_by(GeneralLocation) %>%
summarise(NumberOfLoc = n())
## plot
tally_species_loc_tally %>% filter(GeneralLocation != "-", GeneralLocation != "") %>%
ggplot(aes(GeneralLocation, NumberOfLoc)) +
geom_point(size = 5) +
geom_text(aes(label=NumberOfLoc), hjust=-0.5, vjust=-0.5) +
labs(x = "", y = "Count of species", title = "# of species per location") +
theme(axis.text.x = element_text(angle=90, vjust=0.5, size=12))
# Atlantic
database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lon <= 30,
lon >= -90) %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
#stat_smooth(method="lm", x=length, y=d15N) + # Needs x and y aesthetics in the ggplot() thing
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by species in the Atlantic Ocean") +
xlab("Length") +
ylab("d15N (â°)")
databasestat <- database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lon <= 30,
lon >= -90)
x <- databasestat$length
y <- databasestat$d15N
cor.test(y,x)##
## Pearson's product-moment correlation
##
## data: y and x
## t = 4.5801, df = 159, p-value = 9.333e-06
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.1971389 0.4711961
## sample estimates:
## cor
## 0.3414035lm <- lm(y~x)
lm##
## Call:
## lm(formula = y ~ x)
##
## Coefficients:
## (Intercept) x
## 11.908962 0.003755summary(lm)##
## Call:
## lm(formula = y ~ x)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.1835 -1.6497 -0.0614 1.1802 6.2640
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.191e+01 2.906e-01 40.99 < 2e-16 ***
## x 3.755e-03 8.199e-04 4.58 9.33e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.893 on 159 degrees of freedom
## Multiple R-squared: 0.1166, Adjusted R-squared: 0.111
## F-statistic: 20.98 on 1 and 159 DF, p-value: 9.333e-06# Pacific
database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lon <= -75 || lon >= 120) %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by species in the Pacific Ocean") +
xlab("Length") +
ylab("d15N (â°)")
# Southern
database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lat <= -50) %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by species in the Southern Ocean") +
xlab("Length") +
ylab("d15N (â°)") 
# Europe
database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lat >= 30,
lon <= 45,
lon >= -25) %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by species in Europe") +
xlab("Length") +
ylab("d15N (â°)") 
# Indian
database %>%
filter(length %in% c(115:900),
#Category.of.Interest == "Gadiformes",
lat <= 30,
lat >= -45,
lon <= 120,
lon >= 30) %>%
ggplot() +
geom_point(aes(x = length, y = d15N, colour = factor(SpeciesName)),
size = 5,
alpha = 0.7) +
theme_bw() +
scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
ggtitle("Length vs. d15N colored by species in the Indian Ocean") +
xlab("Length") +
ylab("d15N (â°)") 
## Not working
# # Data per region
# database %>%
# filter(length %in% c(115:900),
# !is.na(SpeciesName)
# #Category.of.Interest == "Gadiformes",
# ) %>%
# ggplot(aes(y=SpeciesName)) +
# facet_wrap(~Environment)
# theme_bw() +
# scale_fill_continuous(guide = guide_legend(title = "Species Name")) +
# # scale_x_continuous(breaks = seq(100, 2000, by = 100)) +
# theme(axis.text.y = element_text(size = rel(1.5), color = "black")) +
# theme(axis.title.y = element_text(size = rel(1.75), color = "black")) +
# theme(axis.text.x = element_text(size = rel(1.5), color = "black")) +
# theme(axis.title.x = element_text(size = rel(1.75), color = "black")) +
# ggtitle("Length vs. d15N colored by species in the Indian Ocean") +
# xlab("Length") +
# ylab("d15N (â°)")
#summarise_by, group_by#View(database)
d <- database %>%
filter(jldCategory %in% c(1),
!is.na(d15N)) %>%,
inner_join(Station %>%
filter(gear.id %in% c(77,78),
month %in% c(9:11),
year %in% c(2013:2014),
lat >= 65.5,
lon <= -20,
lon >= -26) %>%
select(synis.id, year, month, square, gear.id,
sample.class, lon, lat, depth, botnhiti)) %>%
rename(temperature = botnhiti) %>%
mutate(sel.length = ifelse(length %in% 65:74,TRUE, FALSE))