0524.R

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

# Load data
sp <- read.csv(file = "StudentsPerformance.csv", stringsAsFactors = TRUE)

# View the structure of the data
str(sp)

## 'data.frame':    1000 obs. of  8 variables:
##  $ gender                     : Factor w/ 2 levels "female","male": 1 1 1 2 2 1 1 2 2 1 ...
##  $ race.ethnicity             : Factor w/ 5 levels "group A","group B",..: 2 3 2 1 3 2 2 2 4 2 ...
##  $ parental.level.of.education: Factor w/ 6 levels "associate's degree",..: 2 5 4 1 5 1 5 5 3 3 ...
##  $ lunch                      : Factor w/ 2 levels "free/reduced",..: 2 2 2 1 2 2 2 1 1 1 ...
##  $ test.preparation.course    : Factor w/ 2 levels "completed","none": 2 1 2 2 2 2 1 2 1 2 ...
##  $ math.score                 : int  72 69 90 47 76 71 88 40 64 38 ...
##  $ reading.score              : int  72 90 95 57 78 83 95 43 64 60 ...
##  $ writing.score              : int  74 88 93 44 75 78 92 39 67 50 ...

# Plot 1: Math score vs Writing score, colored by lunch type
ggplot(sp, aes(x= math.score, y= writing.score, color = lunch)) + 
  geom_point()

# Calculate the correlation between math and reading scores
math_reading_cor <- cor(sp$math.score, sp$reading.score)
math_reading_cor

## [1] 0.8175797

# Plot 2: Average math score by lunch type
sp %>% 
  group_by(lunch) %>%
  summarise(math = mean(math.score)) %>% 
  ggplot(aes(x= lunch, y= math, fill = lunch)) +
  geom_col()

# Group by parental level of education and calculate average math score
sp1 <- sp %>% 
  group_by(parental.level.of.education) %>%
  summarise(math = round(mean(math.score))) %>% 
  arrange(desc(math))

# Reorder the factor levels for parental education
sp1$parental.level.of.education <- factor(sp1$parental.level.of.education, 
                                          levels = sp1$parental.level.of.education[order(sp1$math,decreasing = TRUE)])

# Plot 3: Average math score by parental level of education
ggplot(sp1, aes(x = parental.level.of.education, y= math, fill = parental.level.of.education)) +
  geom_col() +
  geom_text(aes(label = math, vjust = -0.8, hjust = 0.5, color = parental.level.of.education)) + 
  ylim(min(sp1$math, 0)*1.1, max(sp1$math)*1.1)

# Plot 4: Hide legend for parental education plot
ggplot(sp1, aes(x = parental.level.of.education, y= math, fill = parental.level.of.education)) +
  geom_col(show.legend=F) +
  geom_text(aes(label = math, vjust = -0.8, hjust = 0.5, color = parental.level.of.education), show.legend=F) + 
  ylim(min(sp1$math, 0)*1.1, max(sp1$math)*1.1)

# Plot 5: Gender vs Writing score bar plot
ggplot(sp, aes( x= gender, y = writing.score, fill = gender)) +
  geom_col() +
  labs(x = "Gender", y = "Writing Score") +
  theme_minimal()

# Plot 6: Gender vs Writing score box plot
ggplot(sp, aes( x= gender, y = writing.score, fill = gender)) +
  geom_boxplot() +
  labs(x = "Gender", y = "Writing Score") +
  theme_minimal()