Assignment

#Installing needed packages
install.packages("ggplot2")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)

install.packages("dplyr")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)

install.packages("GGally")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)

#Creating a dataframe 
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)

#Loading the needed libraries 
library("ggplot2")
library("dplyr")

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

#Creating 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" = "orange", "UFO Sightings (2010)" = "purple")) +
  labs(x = "Data Point Index", y = "Count", title = "Comparison of Infections and UFO Sightings") +
  theme_minimal() +
  theme(legend.position = "top")

#Creating 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" = "yellow")) +
  labs(x = "Data Point Index", y = "Count", title = "Trends in Infections and Population") +
  theme_minimal() +
  theme(legend.position = "top")

#Creating 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()

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

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

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

#Creating  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()

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

#Conclusion: It is needed the ggplot

Assignment_#4