Assignment4

# Load required libraries
library(ggplot2)
library(dplyr)

# Read the data
df <- read.table("infections1.txt", header = TRUE)

# Preview the data
head(df)

NA

# Create a bar plot by binning infection counts
df$infection_bin <- cut(df$infections, breaks = c(0, 100, 500, 1000, 3000, 7000), 
                        labels = c("0-100", "101-500", "501-1000", "1001-3000", "3001-7000"))

ggplot(df, aes(x = infection_bin)) +
  geom_bar(fill = "steelblue") +
  labs(title = "Bar Plot of Infection Count Ranges", x = "Infection Range", y = "Frequency") +
  theme_minimal()

# Observation: Most values fall within the lower range of infections (0-1000),
# but there are some outliers in the 3000-7000 range.

# Sort by population to simulate a time-series-like progression
df_sorted <- df[order(df$pop), ]

ggplot(df_sorted, aes(x = pop, y = infections)) +
  geom_line(color = "darkgreen") +
  labs(title = "Line Chart of Infections Over Increasing Population",
       x = "Population", y = "Infections") +
  theme_minimal()

# Observation: Infections generally increase with population, 
# but the trend is not strictly linear.

ggplot(df, aes(x = pop, y = infections)) +
  geom_point(color = "tomato", alpha = 0.7) +
  labs(title = "Scatter Plot of Infections vs Population",
       x = "Population", y = "Infections") +
  theme_minimal()

# Observation: There appears to be a weak positive relationship between 
# population size and number of infections, with several influential outliers.

# Boxplot of all variables
boxplot(df, main = "Boxplots of Variables", col = c("skyblue", "orange", "green"))

# Observation: The 'infections' and 'pop' variables have significant outliers.
# 'ufo2010' has a smaller range with a few extreme values.

# Histogram of infections
ggplot(df, aes(x = infections)) +
  geom_histogram(fill = "purple", bins = 10, color = "black") +
  labs(title = "Histogram of Infections", x = "Infections", y = "Count") +
  theme_minimal()

# Observation: The distribution is right-skewed, with a majority of cases having lower infection counts.