---
title: "Celigo_Boxplot-streamlined"
output: html_document
---

```{r boxplot-prep}
# === ------------------------ ===
# === Run Once Before Plotting ===
# === ------------------------ ===

# === LIBRARIES ===
library(ggplot2)
library(tidyr)
library(dplyr)
library(data.table)
library(rstudioapi)

# === DATA IMPORT ===
runs_included = 1

read_multiple_files <- function(n_files = runs_included) {
  data_list <- list()

  for(i in 1:n_files) {
    cat("Selecting file", i, "of", n_files, "\n")
    
    file_path <- file.choose()
    data <- read.csv(file_path, header = TRUE, check.names = TRUE) 
    
    data_list[[i]] <- data
    
  }

  combined_data <- do.call(rbind, data_list)
  return(combined_data)
}

db <- read_multiple_files(runs_included)

setDT(db)

# === DATA PREPARATION ===
prepare_plot_data <- function(raw_data, runs, Location, measures) {
  plot_data <- raw_data %>%
    mutate(Location = factor(Location, levels = Location)) %>%
    pivot_longer(cols = all_of(measures), names_to = "Measure", values_to = "value")
  
  return(plot_data)
}

```

``` {r plot-chunk}
# === MAIN SCRIPT ===

# User settings
locations_to_plot <- c("LJ", "Miramar")
measure_to_plot <- c("Microplastic.Concentration")

# Prepare data
plot_data <- prepare_plot_data(db, locations_to_plot, measure_to_plot)

# Create plot
p <- ggplot(plot_data, aes(x = Location, y = value)) +
  geom_boxplot(width = 0.6, alpha = 0.7, outlier.shape = NA) +
  geom_jitter(width = 0.2, size = 2.5, alpha = 0.8) +
  labs(x = "", y = measure_to_plot, 
       title = paste0(runs_to_plot, " ", measure_to_plot)) +
  theme_classic() +
  theme(
    plot.title = element_text(size = 16, hjust = 0.5),
    axis.text.x = element_text(angle = 45, hjust = 1, size = 10),
    axis.text.y = element_text(size = 14),
    axis.title.y = element_text(size = 16)
  )

# Display and save
print(p)
ggsave("test.png", plot = p, width = 8, height = 6)
cat("\nPlot saved to: boxplot.png\n")
```

```{r}
# === DATA IMPORT ===
runs_included = 1

read_multiple_files <- function(n_files = runs_included) {
  data_list <- list()

  for(i in 1:n_files) {
    cat("Selecting file", i, "of", n_files, "\n")
    
    file_path <- file.choose()
    data <- read.csv(file_path, header = TRUE, check.names = TRUE) 
    
    data_list[[i]] <- data
    
  }

  combined_data <- do.call(rbind, data_list)
  return(combined_data)
}

db <- read_multiple_files(runs_included)

setDT(db)
```


```{r}
# === DATA PREPARATION ===
prepare_plot_data <- function(raw_data, locations, measures) {
  plot_data <- raw_data %>%
    # Filter for the desired locations
    filter(Location %in% locations) %>%
    # Use the unique locations vector for levels
    mutate(Location = factor(Location, levels = locations)) %>%
    pivot_longer(cols = all_of(measures), 
                 names_to = "Measure", 
                 values_to = "value")
  
  return(plot_data)
}
```

```{r}
# === DATA PREPARATION ===
prepare_plot_data <- function(raw_data, locations, measures) {
  plot_data <- raw_data %>%
    # Filter for the desired measures
    filter(Location %in% locations) %>%
    # Use the unique locations vector for levels
    mutate(Location = factor(Location, levels = locations)) %>%
    pivot_longer(cols = all_of(measures), 
                 names_to = "Measure", 
                 values_to = "value")
  
  return(plot_data)
}
```


```{r}
# === MAIN SCRIPT ===
locations_to_plot <- c("Saliva FC Miramar LJ", "Air FC Miramar LJ")
measure_to_plot <- c("Microfiber.Concentration")

# Ensure call matches the revised signature (raw_data, locations, measures)
plot_data <- prepare_plot_data(db, locations_to_plot, measure_to_plot)

fixedtext <- gsub("\\.", " ", measure_to_plot)

# 1. Calculate per-location counts
counts <- plot_data %>%
  group_by(Location) %>%
  summarise(n = n(), .groups = 'drop')

# 2. Construct the multiline string
label_text <- paste(
  c("N", paste(as.character(counts$Location), counts$n, sep = " : ")), 
  collapse = "\n"
)

# 3. Create plot with annotation
p <- ggplot(plot_data, aes(x = Location, y = value)) +
  #geom_boxplot(width = 0.6, alpha = 0.7, outlier.shape = NA) +
  #geom_jitter(width = 0.2, size = 2.5, alpha = 0.8) +
  geom_col(width = 0.6, alpha = 0.7, outlier.shape = NA) +
  # Annotation placed to the right of the plot area
  annotate("text", x = Inf, y = mean(range(plot_data$value)), 
           label = label_text, hjust = 0, lineheight = 1.2, fontface = "bold") +
  labs(x = "", y = paste0(fixedtext),
       title = paste0(fixedtext)) +
  theme_classic() +
  theme(
    axis.title.y = element_text(size = 14),
    plot.title = element_text(size = 18, hjust = 0.5),
    axis.text.x = element_text(angle = 45, hjust = 1, size = 15),
    # Expand right margin to accommodate the text
    plot.margin = margin(5, 80, 5, 5) 
  ) +
  # Prevents the annotation from being cut off
  coord_cartesian(clip = "off"
  )

print(p)
ggsave("MP_Saliva5.png", plot = p, width = 8, height = 6)
```