# Chi-square test is a statistical test used to
# examine the relationship between two
# categorical variables.

# Checks if two categorical variables are related.

#---------------------------------------------
# Chi-square test using Village Weaver data
#---------------------------------------------

library(ggplot2)
library(dplyr)
library(lubridate)
library(tidyr)

# Example: Is bird sex related to sampling month?

weaver<-read.csv('villageweaver.csv')
str(weaver)

# Identify associations between categorical variables (e.g., sex and habitat type).

# If your Chi-square test shows a significant
# result between sex and month, it suggests:
  
# “The proportion of male and female Village
# Weavers captured differs across months
# perhaps due to breeding behaviour or
# migration patterns.”

# If not significant:
  
# “The sex ratio remains consistent across
# months, suggesting no strong seasonal effect.”

#---------------------------------------------
# 1. Sex vs Month
#---------------------------------------------

# Create a contingency table
table_month <- table(weaver$sex, weaver$month)
table_month

# Run Chi-square test
chisq_month <- chisq.test(table_month)
chisq_month

# Interpretation
# The p-value tells us if sex distribution differs across months.
# If p < 0.05, there is a significant relationship between sex and month.

#---------------------------------------------
# 2. Sex vs Year
#---------------------------------------------

# Create contingency table
table_year <- table(weaver$sex, weaver$year)
table_year

# Run Chi-square test
chisq_year <- chisq.test(table_year)
chisq_year

#---------------------------------------------
# 3. Visualizations using ggplot2
#---------------------------------------------
# (a) Bar chart showing sex distribution across months
ggplot(weaver, aes(x = month, fill = sex)) +
  geom_bar(position = "dodge") +
  labs(x = "Month", y = "Number of village weaver ringed") +
  theme_classic()

# To make month in a calender order

# Convert to an ordered factor using lubridate::month()
weaver <- weaver %>%
  mutate(month = month(parse_date_time(month, orders = "b"), label = TRUE, abbr = FALSE))

# Plot the bar chart
ggplot(weaver, aes(x = month, fill = sex)) +
  geom_bar(position = "dodge") +
  labs(x = "Month", y = "Number of village weavers ringed") +
  theme_classic() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

# (b) Bar chart showing sex distribution across years
ggplot(weaver, aes(x = factor(year), fill = sex)) +
  geom_bar(position = "dodge") +
  labs(x = "Year", y = "Number of village weaver ringed") +
  theme_classic()

# To show space for make in year 2004

# Create a summary of counts
weaver_summary <- weaver %>%
  group_by(year, sex) %>%
  summarise(count = n(), .groups = "drop")

# Ensure all year-sex combinations exist
weaver_complete <- weaver_summary %>%
  complete(year, sex, fill = list(count = 0))

# Plot the bar chart
ggplot(weaver_complete, aes(x = factor(year), y = count, fill = sex)) +
  geom_bar(stat = "identity", position = "dodge") +
  labs(x = "Year", y = "Number of village weavers ringed") +
  theme_classic()