data-vis.Rmd

---
title: "Data Visualisation"
author: "Ellie Honan"
date: "2023-03-01"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

# Data visualization with ggplot \<3

## Load Libraries

```{r}
 library(leaflet)
  library(dplyr)
  library(tidyr)
  library(ggplot2)
  library(DT)
  library(scales) # install.packages("scales")
```

## Read Data

```{r}
data_url <- "https://knb.ecoinformatics.org/knb/d1/mn/v2/object/urn%3Auuid%3Af119a05b-bbe7-4aea-93c6-85434dcb1c5e"

esc <- tryCatch(
    read.csv("data/escapement.csv"),
    error=function(cond) {
        message(paste("Escapement file does not seem to exist, so get it from the KNB."))
        esc <- read.csv(url(data_url, method = "libcurl"))
        return(esc)
    }
)

head(esc)
```

Challenge: *Now that we have the data loaded, use your dplyr and tidyr skills to calculate annual escapement by species and region. Hint: try to use separate to extract the year, month, and day from the date column.*

```{r}

#my attempt
esc_df <- esc %>%
  separate(sampleDate, c("year", "month", "day"), "-") 

annual_esc <- esc_df %>% 
  group_by(Species, SASAP.Region) %>% 
  summarise(annual_escape = mean(DailyCount))



# answer
annual_esc <- esc %>% 
  # because I want the year
  separate(sampleDate, c("Year", "Month", "Day"), sep = "-") %>% 
  # make the year column numeric because it was a character 
  mutate(Year = as.numeric(Year)) %>% 
  # because we want annual escapement by species per region
  group_by(Species, SASAP.Region, Year) %>% 
  # calculate the sum of yearly escapements
  summarize(escapement = sum(DailyCount)) %>%
  # this isn't part of the instructions, just pulling out the salmon species for plotting
  # using %in% because filtering for more than one variable
  filter(Species %in% c("Chinook", "Sockeye", "Chum", "Coho", "Pink"))

# double checking what species are present using unique()
unique(annual_esc$Species)

```

## Static figures using ggplot

**Basic** `ggplot` **figure**:

```{r}
ggplot(annual_esc, 
       aes(x = Species, y = escapement)) +
  geom_col()
```

Basic plot with **blue** bars:

```{r}
ggplot(annual_esc,
       aes(x = Species, y = escapement)) + 
       geom_col(fill = "deepskyblue")
```

Plotting escapement for each species by region:

```{r}
ggplot(annual_esc, 
           aes(x = Species, y = escapement, 
           fill = SASAP.Region)) + 
           geom_col()
```

## `ggplot` and the pipe operator

Annual escapement from Kodiak by species

```{r}
annual_esc %>% 
  filter(SASAP.Region == "Kodiak") %>% 
  ggplot(aes(x = Year, 
             y = escapement, 
             color = Species)) +
         geom_line()+
         geom_point()
```

## Customize our plot using `theme_`

```{r}
kodiak_esc <- annual_esc %>% 
  filter(SASAP.Region == "Kodiak")
# note: the "==" is a double operator that looks for true/false. 
```

```{r}
ggplot(kodiak_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) +
   geom_line() + 
   geom_point() +
   ylab("Escapement") +
   ggtitle("Kodiak Salmon Escapement") +
   theme_bw()
    
```

```{r}
ggplot(kodiak_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) +
   geom_line() + 
   geom_point() +
   ylab("Escapement") +
   theme_bw() +
#note: the theme() function needs to go after theme_ as it can get overwritten 
   theme(legend.position = "bottom", 
         legend.title = element_blank())
   
```

## Saving my custom theme

This is really useful - especially for a report where you want all the plots to look similar.

```{r}
#setting the theme
my_theme <- theme_bw() + 
  theme(legend.position = "bottom", 
         legend.title = element_blank())
```

```{r}
#adding the theme to a plot
ggplot(kodiak_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) +
   geom_line() + 
   geom_point() +
   ylab("Escapement") +
   ggtitle("Kodiak Salmon Escapement") +
   my_theme
```

## Fixing the axis numbers using `scale`

```{r}
ggplot(kodiak_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) +
   geom_line() + 
   geom_point() +
  #arrrgh this fixes the annoying 'e' thing!
   scale_y_continuous(labels = comma) +
   ylab("Escapement") +
   ggtitle("Kodiak Salmon Escapement") +
   my_theme
```

## Saving my plot

Saving into a high res .png. Ggsave by default saves the last plot run (can fix this by giving the plot a name)

```{r}
ggsave("kodiak_esc.png", width = 12, height = 3, units = "in")
```

## Creating multiple plots

Plotting escapement throughout years by region for each species

```{r}
ggplot(annual_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) + 
       geom_line() +
       geom_point() + 
       scale_y_continuous(labels = comma) +
       facet_wrap(~SASAP.Region, 
                  #free scale on the y axis
                  scale = "free_y", 
                  ncol = 2) + 
  ylab("Escapement") + 
  my_theme
```

```{r}
ggplot(annual_esc, 
       aes(x = Year, 
           y = escapement, 
           color = Species)) + 
       geom_line() +
       geom_point() + 
       scale_y_continuous(labels = comma) +
       facet_wrap(~SASAP.Region, 
                  #free scale on the y axis
                  scale = "free_y", 
                  ncol = 2) + 
  ylab("Escapement") + 
  theme_minimal() 
```