Big Data Miderm, Kirill Bas

Report is dedicated to Karina-Katerina Brueva (hustler.spb)

---

Load the Titanic dataset in R and display the first few rows:

# Load necessary libraries
library(ggplot2)

# Load the Titanic dataset from the provided URL
url <- "https://web.stanford.edu/class/archive/cs/cs109/cs109.1166/stuff/titanic.csv"
titanic <- read.csv(url)

# Display the first few rows
head(titanic)

NA

Create a bar chart of the Pclass variable showing the count of passengers by class:

ggplot(titanic, aes(x = factor(Pclass))) +
  geom_bar() +
  labs(title = "Count of Passengers by Class", x = "Passenger Class", y = "Count")

Create a scatter plot of Age vs. Fare, color the points by Survived:

ggplot(titanic, aes(x = Age, y = Fare, color = factor(Survived))) +
  geom_point() +
  labs(title = "Age vs. Fare Colored by Survival", x = "Age", y = "Fare", color = "Survived")

Create a bar chart showing the count of survivors (Survived) grouped by Sex:

ggplot(titanic, aes(x = Sex, fill = factor(Survived))) +
  geom_bar(position = "dodge") +
  labs(title = "Count of Survivors Grouped by Sex", x = "Sex", y = "Count", fill = "Survived")

Create a histogram of the Age variable and facet the plot by Survived:

ggplot(titanic, aes(x = Age)) +
  geom_histogram(binwidth = 5, fill = "blue", color = "black") +
  facet_wrap(~Survived) +
  labs(title = "Histogram of Age Faceted by Survival", x = "Age", y = "Count")

Write R code to create a boxplot for Fare grouped by Pclass:

ggplot(titanic, aes(x = factor(Pclass), y = Fare)) +
  geom_boxplot() +
  labs(title = "Boxplot of Fare Grouped by Pclass", x = "Passenger Class", y = "Fare")

Create a stacked bar chart showing the proportion of Sex within each Pclass:

ggplot(titanic, aes(x = factor(Pclass), fill = Sex)) +
  geom_bar(position = "fill") +
  labs(title = "Proportion of Sex Within Each Pclass", x = "Passenger Class", y = "Proportion", fill = "Sex")

Generate a density plot for the Age variable, filled by the Survived variable:

ggplot(titanic, aes(x = Age, fill = factor(Survived))) +
  geom_density(alpha = 0.5) +
  labs(title = "Density Plot of Age Filled by Survival", x = "Age", y = "Density", fill = "Survived")

Use facet_wrap() to create a faceted scatter plot of Age vs. Fare grouped by Pclass:

ggplot(titanic, aes(x = Age, y = Fare)) +
  geom_point() +
  facet_wrap(~Pclass) +
  labs(title = "Scatter Plot of Age vs. Fare Grouped by Pclass", x = "Age", y = "Fare")

Create a violin plot of Age grouped by Pclass and colored by Survived:

ggplot(titanic, aes(x = factor(Pclass), y = Age, fill = factor(Survived))) +
  geom_violin() +
  labs(title = "Violin Plot of Age Grouped by Pclass and Colored by Survival", x = "Passenger Class", y = "Age", fill = "Survived")