Cruise_naming_conventions.Rmd

---
title: "checking_Stations"
author: "Mostafa Soliman"
date: "2024-08-14"
output: html_document
---


```{r}
# Load necessary library
library(dplyr)

# Define the directory path for the combined files
directory_path <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/raw_ctd_data"

# List all CSV files in the directory
csv_files <- list.files(path = directory_path, pattern = "\\.csv$", full.names = TRUE)

# Initialize an empty data frame to store the results
station_counts <- data.frame(Filename = character(), Unique_Stations = numeric(), stringsAsFactors = FALSE)

# Iterate through each file and count unique stations
for (file in csv_files) {
  # Read the CSV file
  data <- read.csv(file, stringsAsFactors = FALSE)
  
  # Check if the 'station' column exists
  if ("station" %in% colnames(data)) {
    unique_stations <- n_distinct(data$station)
  } else {
    unique_stations <- NA
    warning(paste("No 'station' column found in file:", basename(file)))
  }
  
  # Append the result to the data frame
  station_counts <- rbind(station_counts, data.frame(Filename = basename(file), Unique_Stations = unique_stations))
}

# Display the result
print(station_counts)

```


```{r}
# Load necessary library
library(dplyr)

# Define the directory path containing the CSV files
directory_path <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/cleaned"

# List all CSV files in the directory
csv_files <- list.files(path = directory_path, pattern = "\\.csv$", full.names = TRUE)

# Initialize an empty data frame to store the results
station_counts <- data.frame(Filename = character(), Unique_Stations = numeric(), stringsAsFactors = FALSE)

# Iterate through each file and count unique stations
for (file in csv_files) {
  # Read the CSV file
  data <- read.csv(file, stringsAsFactors = FALSE)
  
  # Check if the 'station' column exists
  if ("station" %in% colnames(data)) {
    unique_stations <- n_distinct(data$station)
  } else {
    unique_stations <- NA
    warning(paste("No 'station' column found in file:", basename(file)))
  }
  
  # Append the result to the data frame
  station_counts <- rbind(station_counts, data.frame(Filename = basename(file), Unique_Stations = unique_stations))
}

# Display the result
print(station_counts)

```



```{r}
# Load necessary library
library(dplyr)

# Define the directory path for the cleaned files
directory_path <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/Cruises_with Right_convention_names"

# List all CSV files in the directory
csv_files <- list.files(path = directory_path, pattern = "\\.csv$", full.names = TRUE)

# Initialize an empty data frame to store the results
station_counts <- data.frame(Filename = character(), Unique_Stations = numeric(), stringsAsFactors = FALSE)

# Iterate through each file and count unique stations
for (file in csv_files) {
  # Read the CSV file
  data <- read.csv(file, stringsAsFactors = FALSE)
  
  # Check if the 'station' column exists
  if ("station" %in% colnames(data)) {
    unique_stations <- n_distinct(data$station)
  } else {
    unique_stations <- NA
    warning(paste("No 'station' column found in file:", basename(file)))
  }
  
  # Append the result to the data frame
  station_counts <- rbind(station_counts, data.frame(Filename = basename(file), Unique_Stations = unique_stations))
}

# Display the result
print(station_counts)

```




```{r}
# Load necessary library
library(dplyr)

# Define the path to the specific CSV file
file_path <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/raw_ctd_data/WS1018_ctd_comb.csv"

# Read the CSV file
data <- read.csv(file_path, stringsAsFactors = FALSE)

# Check unique station names
unique_stations_1 <- sort(unique(data$station))
print(unique_stations_1)
 sort(length(unique_stations_1))
```

```{r}
# Load necessary library
library(dplyr)

# Define the path to the specific CSV file
file_path <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/cleaned/WS1018.CSV"

# Read the CSV file
data <- read.csv(file_path, stringsAsFactors = FALSE)

# Check unique station names
unique_stations_2 <- unique(data$station)
print(unique_stations_2)
(length(unique_stations_2))
```




```{r}
# Step 2: Function to standardize station names
standardize_station_name <- function(station_name) {
  # Remove leading periods and zeros, but preserve the decimal structure
  clean_name <- gsub("^0+\\.|^\\.|^0+", "", station_name)
  
  # Remove any remaining leading zeros (while preserving decimals)
  clean_name <- sub("^0+", "", clean_name)
  
  # Replace underscores with periods
  clean_name <- gsub("_", ".", clean_name)
  
  return(clean_name)
}

# Apply the function to the station names
data$station <- sapply(data$station, standardize_station_name)

# Define the output directory
output_dir <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/Cruises_with Right_convention_names"

# Get the original file name and append "_cleaned"
original_file_name <- basename(file_path)
cleaned_file_name <- sub("\\.csv$", "_cleaned.csv", original_file_name)

# Define the output file path with the new name
output_file_path <- file.path(output_dir, cleaned_file_name)

# Create the directory if it doesn't exist
if (!dir.exists(output_dir)) {
  dir.create(output_dir, recursive = TRUE)
}

# Save the cleaned data with the new file name
write.csv(data, output_file_path, row.names = FALSE)

# Confirm the file has been saved
cat("Cleaned data has been saved to:", output_file_path)
```
```{r}
# Load necessary library
library(dplyr)

# Define the path to the directory containing the CSV files
input_dir <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/combined_fl_keys_data"
output_dir <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/Cruises_with Right_convention_names"

# Create the output directory if it doesn't exist
if (!dir.exists(output_dir)) {
  dir.create(output_dir, recursive = TRUE)
}

# Get a list of all CSV files in the input directory
csv_files <- list.files(input_dir, pattern = "\\.csv$", full.names = TRUE)

# Function to standardize station names
standardize_station_name <- function(station_name) {
  # Remove leading periods and zeros, but preserve the decimal structure
  clean_name <- gsub("^0+\\.|^\\.|^0+", "", station_name)
  
  # Remove any remaining leading zeros (while preserving decimals)
  clean_name <- sub("^0+", "", clean_name)
  
  # Replace underscores with periods
  clean_name <- gsub("_", ".", clean_name)
  
  return(clean_name)
}

# Loop through each file, process, and save
for (file_path in csv_files) {
  # Read the CSV file
  data <- read.csv(file_path, stringsAsFactors = FALSE)
  
  # Apply the function to the station names
  data$station <- sapply(data$station, standardize_station_name)
  
  # Get the original file name without changing it
  original_file_name <- basename(file_path)
  
  # Define the output file path with the original name
  output_file_path <- file.path(output_dir, original_file_name)
  
  # Save the cleaned data with the original file name
  write.csv(data, output_file_path, row.names = FALSE)
  
  # Confirm the file has been saved
  cat("Cleaned data has been saved to:", output_file_path, "\n")
}

```

```{r}
# Load necessary library
library(dplyr)

# Define the paths to the directories
original_dir <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/combined_fl_keys_data"
cleaned_dir <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/Cruises_with Right_convention_names"

# Get a list of all CSV files in both directories
original_files <- list.files(original_dir, pattern = "\\.csv$", full.names = TRUE)
cleaned_files <- list.files(cleaned_dir, pattern = "\\.csv$", full.names = TRUE)

# Function to count unique stations in a file
count_unique_stations <- function(file_path) {
  data <- read.csv(file_path, stringsAsFactors = FALSE)
  return(length(unique(data$station)))
}

# Create a data frame to store the results
results <- data.frame(
  File = character(),
  Original_Station_Count = integer(),
  Cleaned_Station_Count = integer(),
  stringsAsFactors = FALSE
)

# Loop through the files and count stations before and after cleaning
for (original_file in original_files) {
  # Get the corresponding cleaned file name
  cleaned_file_name <- sub("\\.csv$", "_cleaned.csv", basename(original_file))
  cleaned_file_path <- file.path(cleaned_dir, cleaned_file_name)
  
  # Check if the cleaned file exists
  if (cleaned_file_path %in% cleaned_files) {
    # Count stations in the original and cleaned files
    original_station_count <- count_unique_stations(original_file)
    cleaned_station_count <- count_unique_stations(cleaned_file_path)
    
    # Add the results to the data frame
    results <- rbind(results, data.frame(
      File = basename(original_file),
      Original_Station_Count = original_station_count,
      Cleaned_Station_Count = cleaned_station_count
    ))
  }
}

# Display the results
print(results)



```
```{r}
# Load necessary library
library(dplyr)

# Define the paths to the files before and after cleaning
file_before_cleaning <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/01_raw/raw_ctd_data/WS0901_ctd_comb.csv"
file_after_cleaning <- "C:/Users/mostafaawada/Documents/seus-mbon-cruise-ctd-processing/data/cleaned/WS0901.csv"

# Function to get station names and count from a file
get_station_info <- function(file_path) {
  # Read the CSV file
  data <- read.csv(file_path, stringsAsFactors = FALSE)
  
  # Check if the 'station' column exists
  if ("station" %in% colnames(data)) {
    unique_stations <- unique(data$station)
    station_count <- length(unique_stations)
    return(list(station_count = station_count, unique_stations = unique_stations))
  } else {
    warning(paste("No 'station' column found in file:", basename(file_path)))
    return(NULL)
  }
}

# Get station information before cleaning
before_cleaning_info <- get_station_info(file_before_cleaning)

# Get station information after cleaning
after_cleaning_info <- get_station_info(file_after_cleaning)

# Display the results
cat("Before Cleaning:\n")
cat("Number of Unique Stations:", before_cleaning_info$station_count, "\n")
cat("Station Names:\n")
print(before_cleaning_info$unique_stations)

cat("\nAfter Cleaning:\n")
cat("Number of Unique Stations:", after_cleaning_info$station_count, "\n")
cat("Station Names:\n")
print(after_cleaning_info$unique_stations)

```
```{r}
# Load necessary libraries
library(ggplot2)
library(sf)
library(akima)
library(raster)
library(dplyr)
library(tidyr)
library(ggspatial)
library(readxl)

# Set the path to your nutrient data file
data_path <- "C:/Users/mostafaawada/Box/mbon_imars_cruises/WSMasterSampleLog.xlsx"

# Load the data from the "All Depths" sheet and ensure it's in a tibble format
data <- as_tibble(read_excel(data_path, sheet = "All Depths"))

# Select relevant columns and filter the data for the nutrients of interest
nutrient_data <- data %>%
  dplyr::select(CruiseID, Latitude, Longitude, Depth, Nitrate, Nitrite, Phosphate, Silicate, Ammonium) %>%
  filter(!is.na(Nitrate) | !is.na(Nitrite) | !is.na(Phosphate) | !is.na(Silicate) | !is.na(Ammonium))

# Create a list of nutrient parameters to be plotted
nutrients <- c("Nitrate", "Nitrite", "Phosphate", "Silicate", "Ammonium")

# Reshape the data to long format for faceting
long_nutrient_data <- nutrient_data %>%
  pivot_longer(cols = all_of(nutrients), names_to = "Nutrient", values_to = "Concentration")

# Create plots for each cruise, faceted by nutrient
plots <- long_nutrient_data %>%
  ggplot(aes(x = Longitude, y = Latitude, fill = Concentration)) +
  geom_tile() +
  facet_wrap(~ Nutrient, scales = "free") +
  coord_fixed() +
  scale_fill_viridis_c(option = "C") +
  theme_minimal() +
  labs(title = "Nutrient Concentrations by Cruise",
       fill = "Concentration (µM)",
       x = "Longitude", y = "Latitude") +
  theme(strip.text = element_text(size = 10))

# Print the plots for each cruise
print(plots)


```

```{r}
# Function to interpolate and plot nutrient data only
plot_interpolated_layer <- function(data, nutrient_column, cruise_id) {
  data_cruise <- data %>% filter(Cruise == cruise_id, !is.na(.data[[nutrient_column]]))

  if (nrow(data_cruise) > 3) {
    interpolated <- akima::interp(x = data_cruise$`Longitude Decimal`, 
                                  y = data_cruise$`Latitude Decimal`, 
                                  z = data_cruise[[nutrient_column]], 
                                  xo = seq(min(data_cruise$`Longitude Decimal`), max(data_cruise$`Longitude Decimal`), length = 100), 
                                  yo = seq(min(data_cruise$`Latitude Decimal`), max(data_cruise$`Latitude Decimal`), length = 100),
                                  duplicate = "mean")

    interp_data <- as.data.frame(interpolated)
    names(interp_data) <- c("Longitude", "Latitude", "Z")

    ggplot() +
      geom_raster(data = interp_data, aes(x = Longitude, y = Latitude, fill = Z), interpolate = TRUE) +
      scale_fill_viridis_c(option = "magma", name = paste(nutrient_column, "(µM)")) +
      geom_polygon(data = florida_map, aes(x = long, y = lat, group = group), fill = "grey90", color = "black") +
      labs(title = paste("Interpolated", nutrient_column, "Layer - Cruise", cruise_id),
           x = "Longitude", y = "Latitude") +
      theme_minimal() +
      coord_sf(xlim = c(-85.5, -79.5), ylim = c(23, 27), expand = FALSE)
  } else {
    ggplot() + labs(title = paste("Not enough data points to interpolate for", nutrient_column))
  }
}

# Test with one nutrient and cruise ID (e.g., "PO4  (uM)", "WS1418")
plot_interpolated_layer(nutrient_data_depth_0, "PO4  (uM)", "WS1418")

```

# creating code to calculate the oxygen saturation 

```{r}
# Load necessary libraries
library(dplyr)
library(readr)

# Define the directory containing the cruise files
directory_path <- "C:/Users/mostafaawada/Desktop/CTD_data_codes/data/cleaned_cruises"

# List all CSV files in the directory
cruise_files <- list.files(path = directory_path, pattern = "\\.csv$", full.names = TRUE)

# Print the list of files to ensure they are correctly listed
print(cruise_files)

```
```{r}
# Loop through each file to read and inspect the data
for (file in cruise_files) {
  # Read the data
  cruise_data <- read_csv(file, show_col_types = FALSE)
  
  # Display the file name to track progress
  cat("Inspecting file:", file, "\n")
  
  # Display the first few rows of the data to get an initial look
  head(cruise_data)
  
  # Check the structure of the data to see the column names and data types
  str(cruise_data)
  
  # Get a summary of the data to understand its distribution
  summary(cruise_data)
  
  # Pause the loop to inspect the output before continuing
  readline(prompt = "Press [Enter] to continue to the next file")
}

```
```{r}
# Loop through each file to calculate and save oxygen saturation percentage
for (file in cruise_files) {
  # Read the data
  cruise_data <- read_csv(file, show_col_types = FALSE)
  
  # Calculate Oxygen Saturation Percentage for each station and depth
  cruise_data <- cruise_data %>%
    group_by(station, depth) %>%
    mutate(Oxygen_saturation_percentage = (dissolved_oxygen / oxygen_saturation) * 100) %>%
    ungroup()
  
  # Save the updated dataset back to the same file
  write_csv(cruise_data, file)
  
  cat("Oxygen saturation percentage calculated and saved for file:", file, "\n")
}

```