---
title: "LE Yellow Island Visualizations"
author: "Chris"
date: "2023-07-31"
output: html_document
output: 
  html_document: 
  theme: readable 
  highlight: zenburn 
    toc: true 
    toc_float: true 
    number_sections: true 
    code_folding: show 
    code_download: true 
editor: 
markdown: 
wrap: 72 
---

###READ ME We will use the following files to explore our data

algae.csv - the algal presence/ absence by top layer and second layer
percentCover.csv - the substrate and second layer information
truncated.csv - this is a simplified version of species data
combinedMarine.csv - this is the post point and manchester data from
MARINe

# Package Install and call

```{r}

# Installation is commented out, remove hashtag if you need to install
#install.packages("kableExtra")
#install.packages('gridExtra')

```

```{r}

#Use library to call your installed packages for use
library(data.table)
library(dplyr)
library('ggplot2')
library("indicspecies")
library(kableExtra)
library(knitr)
library(RColorBrewer)
library(tidyr)
library(tidyverse)
library(vegan)

```

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

# Know where you're working

```{r}

# make sure you know where you are working, remove the #if you need to make this work
#getwd()
#setwd()

```

# Load your data

```{r}

counts<- read.csv("truncated.csv", header= TRUE) #species counts per section
algae<- read.csv("algae.csv", header= TRUE) #algal cover in first and second layer of each quadrat
substrate<- read.csv("substrate.csv", header=TRUE) #substrate percent cover in first and second layer of each quadrat
marine<- read.csv("combinedMarine.csv", header= TRUE)

```

# Inspect your data

```{r}

# remove the hashtag from each operator to use it for each of your data sets
# check out row/ column counts to make sure you've got everything
#dim(counts)

#quick view of data frame structure to see character v factor and such
#str()

#look at the summary of your data to see what categorically exists
#summary()

```

# Big Picture Viz

## Manipulate counts data to make visualizations

```{r}

counts1 <- counts %>%
  gather(key = "Phylum", value = "Count", ANNELIDA:OSTEICHTHYES)

# Sum the counts for each SECTION and Phylum
section_phylum_counts <- counts1 %>%
  group_by(SECTION, Phylum) %>%
  summarize(Total_Count = sum(Count))

# Plot the stacked bar graph for counts by SECTION with phyla as fill
ggplot(section_phylum_counts, aes(x = SECTION, y = Total_Count, fill = Phylum)) +
  geom_bar(stat = "identity") +
  labs(x = "SECTION", y = "Count", title = "Counts for each SECTION by Phylum") +
  theme_minimal()

```

# Same Graph as above but the colors and X-axis have been cleaned up

```{r}

# Get unique Phylum values
unique_phyla <- unique(section_phylum_counts$Phylum)

# Generate a color palette with enough colors to match the number of unique Phylum values
n_colors <- length(unique_phyla)
#custom_colors <- brewer.pal(n_colors, "Spectral")
custom_colors <- c("sienna", "red", "yellow", "royalblue", "purple","seagreen", "black", "orange", "lightgrey")


plot_width <- 10
plot_height <- 6
margin_bottom <- 1.5

# Plot the stacked bar graph for counts by SECTION with phyla as fill and custom colors
ggplot(section_phylum_counts, aes(x = SECTION, y = Total_Count, fill = Phylum)) +
  geom_bar(stat = "identity") +
  scale_fill_manual(values = custom_colors) +  # Set custom colors for the phyla
  labs(x = "SECTION", y = "Count") +
  ggtitle("Phyla Count by Section") +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 90, hjust = 1, vjust = 0.5, face = "bold"),
    plot.margin = unit(c(margin_bottom, 0.5, 0.5, 0.5), "cm"),
    plot.title = element_text(hjust = 0.5),  # Center the plot title
    plot.background = element_rect(fill = "white"),  # Set plot background color
    panel.grid = element_blank(),  # Remove grid lines
    axis.line = element_line(size = 0.5),  # Customize axis line width
    legend.position = "right" ) +
  coord_cartesian(ylim = c(0, max(section_phylum_counts$Total_Count) * 1.1))  # Adjust Y-axis limits# Plot the stacked bar graph for counts by SECTION with phyla as fill and custom colors
all_sections <- 1:8

# Plot the stacked bar graph for counts by SECTION with phyla as fill and custom colors
ggplot(section_phylum_counts, aes(x = factor(SECTION, levels = all_sections), y = Total_Count, fill = Phylum)) +
  geom_bar(stat = "identity") +
  scale_fill_manual(values = custom_colors) +  # Set custom colors for the phyla
  labs(x = "SECTION", y = "Count", title = "Phyla Count by Section") +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(axis.text.x = element_text(angle = 0, hjust = 1, vjust = 0.5, face = "bold")) +
  scale_x_discrete(limits = all_sections)  # Set X-axis labels to include all sections from 1 to 8

```

# Next Viz

# fix duplicate M and match the colors to the graph above

```{r}

# Sum the counts for each ZONATION and Phylum
zonation_phylum_counts <- counts1 %>%
  group_by(ZONATION, Phylum) %>%
  summarize(Total_Count = sum(Count))

custom_colors <- c("sienna", "red", "yellow", "royalblue", "purple","seagreen", "black", "orange", "lightgrey")


ggplot(zonation_phylum_counts, aes(x = ZONATION, y = Total_Count, fill = Phylum)) +
  geom_bar(stat = "identity") +
  scale_fill_manual(values = custom_colors) +
  labs(x = "Zonation", y = "Phyla Count", title = "Phyla Count across Zonation") +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5))

```

# MARINe Site Comparison
## Not a bad comparison, but not a true representation

```{r}

# Combine Site and Section to form the X-axis label
marine$Site_Section <- paste(marine$SITE, marine$SECTION, sep = "-")

# Define the custom order of Phylum categories
custom_order <- c("Rhodophyta", "Ochrophyta", "Chlorophyta", "Mollusca", "Cnidaria",  "Arthropoda")

# Match colors to phyla from last graph
custom_colors <- c("indianred4", "salmon2", "mediumseagreen", "green2", "royalblue","red")

# Reorder the Phylum variable based on the custom order
marine$Phylum <- factor(marine$Phylum, levels = custom_order)

# Plot the stacked bar graph
ggplot(marine, aes(x = Site_Section, y = Percent_Cover, fill = Phylum)) +
  geom_bar(stat = "identity", position = "stack") +
  scale_fill_manual(values = custom_colors) +
  labs(title = "Phyla Percent Cover across Site and Section",
       x = "Site - Section",
       y = "Percent Cover") +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
  guides(fill = guide_legend(reverse = TRUE))  # Reverse the order of the legend

```

# Algae Data Visualization

```{r}


# Assuming you already have the 'algae' dataframe, create a new dataframe with the desired format
algae_counts <- algae1 %>%
  pivot_longer(cols = c(BROWN, RED, GREEN, ENCRUSTING, OTHER), names_to = "Algal_Type", values_to = "Presence") %>%
  group_by(SECTION, Algal_Type) %>%
  summarize(Count = sum(ifelse(Presence == "P", 1, 0)))

# Define the custom order for the legend
custom_order <- c("OTHER", "ENCRUSTING","RED", "GREEN", "BROWN")
algae_counts$Algal_Type <- factor(algae_counts$Algal_Type, levels = custom_order)

# Plot the stacked bar chart
ggplot(algae_counts, aes(x = as.factor(SECTION), y = Count, fill = Algal_Type)) +
  geom_bar(stat = "identity") +
  scale_fill_manual(values = c("BROWN" = "brown", "RED" = "red", "GREEN" = "seagreen4", "ENCRUSTING" = "purple", "OTHER" = "gray"),
                    labels = c("BROWN" = "Brown", "RED" = "Red", "GREEN" = "Green", "ENCRUSTING" = "Encrusting", "OTHER" = "Other")) +
  labs(x = "Section", y = "Count", fill = "Algal Type", title = "Algal Cover by Section") +
  theme_minimal() +
  theme(legend.position = "right",
        plot.title = element_text(hjust= 0.5)) +
  guides(fill = guide_legend(reverse = TRUE))  # To customize the order of names in the legend

# Save the plot as an image (optional)
ggsave("stacked_bar_plot.png", width = 10, height = 6)


```

# Stats

```{r}
# Example using vegan package
permanova_result <- adonis(algae ~ "Zonation", algae = "Section", method = "bray")
```

```{r}

#library(vegan)

counts2<- subset(counts, select = -2)

# Calculate dissimilarity matrix
dist_matrix <- vegdist(counts2, method = "bray")

# Perform NMDS analysis
nmds_result <- metaMDS(dist_matrix)

# Create a vector of 8 distinct colors
section_colors <- rainbow(8)

# Plot NMDS results with color-coded sections
plot(nmds_result, type = "n")  # 'n' stands for 'none' to create an empty plot

# Add points to the plot with color-coded sections
points(nmds_result, col = section_colors)

# Add a legend
legend("topright", legend = 1:8, col = section_colors, pch = 1, cex = 1.2, title = "Sections")

```

```{r}
# join summer2023both with taxcorrected to run a second nmds for each site
# load summer & tax data
# change counts2 to match same format

# Assuming your tables are named abbreviation and name
summertax <- merge(summer23both, taxcorrected, by = "species_code", all.x = TRUE)

# View the merged table
print(summertax)


counts3 <- counts2 %>%
  mutate("Site" = ifelse("Yellow" == "1:8", "Yellow", "Section"))
```

```{r}
#correct table format to combine yellow data with marine data



```

```{r}
#block for species richness and diversity

```