R Notebook

install.packages("ggplot2")

trying URL 'http://rspm/default/__linux__/noble/latest/src/contrib/ggplot2_4.0.2.tar.gz'
Content type 'application/x-gzip' length 8482095 bytes (8.1 MB)
==================================================
downloaded 8.1 MB


The downloaded source packages are in
    ‘/tmp/RtmpVfDS4d/downloaded_packages’

install.packages("dplyr")

trying URL 'http://rspm/default/__linux__/noble/latest/src/contrib/dplyr_1.2.1.tar.gz'
Content type 'application/x-gzip' length 1521233 bytes (1.5 MB)
==================================================
downloaded 1.5 MB


The downloaded source packages are in
    ‘/tmp/RtmpVfDS4d/downloaded_packages’

install.packages("GGally")

trying URL 'http://rspm/default/__linux__/noble/latest/src/contrib/GGally_2.4.0.tar.gz'
Content type 'application/x-gzip' length 2003384 bytes (1.9 MB)
==================================================
downloaded 1.9 MB


The downloaded source packages are in
    ‘/tmp/RtmpVfDS4d/downloaded_packages’

# Infection Data Visualizations in R

# Create the data frame
infections <- c(245, 215, 2076, 5023, 189, 195, 123, 116, 3298, 430, 502, 126, 112, 67, 52, 39, 54, 2356, 6781, 120, 2389, 279, 257, 290, 234, 5689, 261, 672, 205)
ufo2010 <- c(2, 6, 2, 59, 0, 1, 1, 0, 115, 0, 0, 0, 0, 0, 0, 0, 6, 4, 2, 7, 2, 9, 2, 29, 10, 169, 1, 40, 16)
pop <- c(25101, 61912, 33341, 409061, 7481, 18675, 25581, 22286, 459598, 3915, 67197, 34365, 3911, 32122, 31459, 2311, 28350, 101482, 19005, 20679, 36745, 162812, 15927, 251417, 153920, 1554720, 16148, 305455, 37276)

df <- data.frame(infections, ufo2010, pop)

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

# --- 1. Bar Graph: Comparing Infections and UFO Sightings ---
ggplot(df, aes(x = 1:nrow(df))) +
  geom_bar(aes(y = infections, fill = "Infections"), stat = "identity", position = "dodge") +
  geom_bar(aes(y = ufo2010, fill = "UFO Sightings (2010)"), stat = "identity", position = "dodge", alpha = 0.7) +
  scale_fill_manual("Variables", values = c("Infections" = "skyblue", "UFO Sightings (2010)" = "salmon")) +
  labs(x = "Data Point Index", y = "Count", title = "Comparison of Infections and UFO Sightings") +
  theme_minimal() +
  theme(legend.position = "top")

#There is a moderate positive correlation between infections and UFO sightings (~0.60) #Population has a strong correlation with UFO sightings (~0.94), suggesting population drives sightings #Distributions are highly skewed with several extreme outliers affecting relationships

# --- 2. Line Chart: Trends in Infections and Population ---
ggplot(df, aes(x = 1:nrow(df))) +
  geom_line(aes(y = infections, color = "Infections"), linewidth = 1) +
  geom_line(aes(y = pop, color = "Population"), linewidth = 1, linetype = "dashed") +
  scale_color_manual("Variables", values = c("Infections" = "green", "Population" = "purple")) +
  labs(x = "Data Point Index", y = "Count", title = "Trends in Infections and Population") +
  theme_minimal() +
  theme(legend.position = "top")

#There is a positive relationship where more UFO sightings tend to align with higher infections #Larger population points (bigger bubbles) are associated with higher values in both variables #A few large-population outliers heavily influence the trend

# --- 3. Scatter Plot: Relationship between Population and Infections ---
ggplot(df, aes(x = pop, y = infections)) +
  geom_point(color = "blue", alpha = 0.6) +
  labs(x = "Population", y = "Number of Infections", title = "Relationship between Population and Number of Infections") +
  theme_minimal()

#There is a clear positive correlation between population and UFO sightings #Most observations are clustered at low population and low sightings #A few high-population outliers drive the upward trend

# --- 4. Box Plot: Distribution of Infections ---
ggplot(df, aes(y = infections)) +
  geom_boxplot(fill = "lightcoral") +
  labs(y = "Number of Infections", title = "Distribution of Number of Infections") +
  theme_minimal()

#The distribution is strongly right-skewed with most values near zero #A small number of extreme values create a long tail #UFO sightings are generally rare across the dataset

# --- 5. Histogram: Frequency Distribution of UFO Sightings ---
ggplot(df, aes(x = ufo2010)) +
  geom_histogram(binwidth = 5, fill = "orange", color = "black", alpha = 0.7) +
  labs(x = "Number of UFO Sightings (2010)", y = "Frequency", title = "Frequency Distribution of UFO Sightings (2010)") +
  theme_minimal()

#The data is right-skewed with several high-value outliers #Most infection counts are relatively low compared to a few extreme cases #The variability suggests uneven spread across observations

# --- 6. Scatter Plot: Relationship between Population and UFO Sightings ---
ggplot(df, aes(x = pop, y = ufo2010)) +
  geom_point(color = "purple", alpha = 0.6) +
  labs(x = "Population", y = "Number of UFO Sightings (2010)", title = "Relationship between Population and UFO Sightings (2010)") +
  theme_minimal()

#There is a weak to moderate positive relationship between population and infections #Higher population tends to correspond to higher infections, but inconsistently #Outliers significantly impact the overall pattern

# --- 7. Scatter Plot: Infections vs. UFOs with Population Size ---
ggplot(df, aes(x = ufo2010, y = infections, size = pop)) +
  geom_point(alpha = 0.6, color = "maroon") +
  scale_size_continuous(name = "Population Size") +
  labs(x = "Number of UFO Sightings (2010)", y = "Number of Infections", title = "Infections vs. UFO Sightings, Size by Population") +
  theme_minimal()

#Population fluctuates dramatically compared to infections #Infections remain relatively stable with small variations #There is no clear synchronized trend between the two variables

# --- 8. Pair Plot: Overview of Relationships ---
library(GGally)
ggpairs(df) +
  ggtitle("Pair Plot of Infections, UFO Sightings, and Population") +
  theme_minimal()

#Infections are consistently much higher than UFO sightings #UFO sightings remain low with minimal variation #There is no clear pattern linking both variables across observations