# =========================================================
# CORRELATION HEATMAP — LIME (Pooled Replicates)
# Two styles: corrplot + ggplot
# =========================================================

# -----------------------------
# 1. Install packages (run once)
# -----------------------------
# install.packages(c("tidyverse", "corrplot", "reshape2", "ggplot2"))

# -----------------------------
# 2. Load libraries
# -----------------------------
library(tidyverse)
library(corrplot)
library(reshape2)
library(ggplot2)

# -----------------------------
# 3. Import data
# -----------------------------
data <- read.csv("Lime_Pooled_Data.csv",
                 header = TRUE,
                 stringsAsFactors = FALSE)

# -----------------------------
# 4. Rename columns to full names
# -----------------------------
data <- data %>%
  rename(
    `Number of Fruits` = NoFruits,
    `Fruit Weight (g)` = FruitWt_g,
    `Juice Content (%)` = JuiceContent_pct,
    `Shoot Length (cm)` = ShootLen_cm,
    `Number of Shoots` = NoShoots,
    `Number of Leaves` = NoLeaves,
    `Leaf Area (cm²)` = LeafArea_cm2,
    `Chlorophyll (SPAD)` = SPAD,
    `Days to Flowering` = DaysToFlower,
    `Number of Flowers` = NoFlowers,
    `Total Soluble Solids (°Brix)` = TSS_pct,
    `Acidity (%)` = Acidity_pct
  )

# -----------------------------
# 5. Numeric data for analysis
# (Replication INCLUDED)
# -----------------------------
numeric_all <- data %>%
  select(where(is.numeric))

# -----------------------------
# 6. Compute Pearson correlation
# -----------------------------
cor_matrix <- cor(numeric_all,
                  method = "pearson",
                  use = "complete.obs")

# -----------------------------
# 7. Remove Replication ONLY from display
# -----------------------------
cor_matrix_plot <- cor_matrix[
  !rownames(cor_matrix) %in% "Replication",
  !colnames(cor_matrix) %in% "Replication"
]

print(round(cor_matrix_plot, 3))

# =========================================================
# HEATMAP 1 — CORRPLOT (blue–white–red)
# =========================================================

png("Correlation_Heatmap_corrplot_bluered.png",
    width = 3000,
    height = 2400,
    res = 300)

corrplot(cor_matrix_plot,
         method = "color",
         type = "upper",
         order = "hclust",
         addCoef.col = "black",   # values in black
         tl.col = "black",
         tl.srt = 45,
         number.cex = 0.6,
         col = colorRampPalette(c("#2166AC", "white", "#B2182B"))(200))

dev.off()

# =========================================================
# HEATMAP 2 — GGPLOT (same blue–white–red family)
# =========================================================

# Melt matrix
cor_melt <- melt(cor_matrix_plot)

heatmap_plot <- ggplot(cor_melt,
                       aes(x = Var1, y = Var2, fill = value)) +
  geom_tile(color = "grey85") +
  geom_text(aes(label = sprintf("%.2f", value)),
            color = "black",
            size = 3) +
  scale_fill_gradient2(
    low = "#2166AC",
    mid = "white",
    high = "#B2182B",
    midpoint = 0,
    limit = c(-1, 1),
    name = "Pearson r"
  ) +
  theme_minimal(base_size = 12) +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    panel.grid = element_blank(),
    plot.title = element_text(face = "bold", hjust = 0.5)
  ) +
  coord_fixed() +
  labs(title = "Correlation Heatmap of Lime Traits",
       x = "",
       y = "")

# Display
print(heatmap_plot)

# Save ggplot version
ggsave("Correlation_Heatmap_ggplot_bluered.png",
       plot = heatmap_plot,
       width = 10,
       height = 8,
       dpi = 300)

# =========================================================
# END
# =========================================================