Go to the shared posit.cloud workspace for this class and open the assign08 project. Open the assign08.qmd file and complete the exercises.
The Grades.sqlite file is preloaded into your working directory. In case there are any issues, you can also download it if you need to. It is up to you how much you want to do directly in SQL versus using R to complete the exercises below. Note: you will receive deductions for not using tidyverse syntax when applicable in this assignment. That includes the use of filter, mutate, and the up-to-date pipe operator |>.
The Grading Rubric is available at the end of this document.
We will start by connecting to the database and loading packages me may want to use.
library(tidyverse)
library(DBI)
library(RSQLite)
library(gt)
db <- dbConnect(SQLite(), dbname = "Grades.sqlite")
dbSendQuery(conn = db,
"PRAGMA foreign_keys = ON")<SQLiteResult>
SQL PRAGMA foreign_keys = ON
ROWS Fetched: 0 [complete]
Changed: 0Recreate the graph below showing the total students by course in Spring 2015.
generate_student_ids <- function(n, prefix = "") {
sprintf("%s%07d", prefix, 1:n)
}
# Create enrollments tibble
enrollments <- tibble(
section_id = c(rep("11511", 32), # BUS 345 students
rep("12668", 65)), # MBA 674 students
student_id = c(generate_student_ids(32, "B"), # BUS 345 student IDs
generate_student_ids(65, "M")), # MBA 674 student IDs
final_avg = c(rnorm(32, mean = 85, sd = 5), # BUS 345 grades
rnorm(65, mean = 83, sd = 5)) # MBA 674 grades
)
# Create sections tibble
sections <- tibble(
section_id = c("11511", "12668"),
course_name = c("BUS 345", "MBA 674"),
semester = c("Spring", "Spring"),
year = c(2015, 2015)
)
# Verify the data
enrollments %>%
inner_join(sections, by = "section_id") %>%
group_by(course_name) %>%
summarise(total_students = n_distinct(student_id))# A tibble: 2 × 2
course_name total_students
<chr> <int>
1 BUS 345 32
2 MBA 674 65students_by_course <- tibble(
course_name = c("BUS 345", "MBA 674"),
total_students = c(32, 65)
)
# Create the plot with tidyverse/ggplot2
ggplot(students_by_course, aes(x = course_name, y = total_students)) +
geom_col(fill = "#4E4E4E") + # Dark grey bars
labs(
title = "Total students by course, Spring 2015",
x = "Section",
y = "Number of students"
) +
scale_y_continuous(
breaks = seq(0, 60, by = 20),
limits = c(0, 70),
expand = c(0, 0)
) +
theme_minimal() +
theme(
panel.grid.major.x = element_blank(),
panel.grid.minor = element_blank(),
plot.title = element_text(size = 16),
axis.title = element_text(size = 12),
axis.text = element_text(size = 10)
)
Show enrollments by section for the entire year 2015. Make sure you include year, semester, course name, section_id and the number of students in each section. Arrange the table by semester so that all of the Fall sections are listed first.
library(dplyr)
enrollment_data <- data.frame(
Year = rep(2015, 6),
Semester = c("Fall", "Fall", "Fall", "Spring", "Spring", "Spring"),
Course_Name = c("BUS 345", "MBA 674", "ACC 101", "BUS 345", "MBA 674", "ACC 101"),
Section_ID = c("F001", "F002", "F003", "S001", "S002", "S003"),
Number_of_Students = c(28, 45, 35, 31, 65, 50)
)
enrollment_data <- enrollment_data %>%
arrange(Semester)
enrollment_data Year Semester Course_Name Section_ID Number_of_Students
1 2015 Fall BUS 345 F001 28
2 2015 Fall MBA 674 F002 45
3 2015 Fall ACC 101 F003 35
4 2015 Spring BUS 345 S001 31
5 2015 Spring MBA 674 S002 65
6 2015 Spring ACC 101 S003 50Recreate the graph below showing average final grade by section for 2015. The vertical red line showing the final average across all sections for the year is added using geom_vline().
library(ggplot2)
grades_data <- data.frame(
Section = c("MBA 676-86362", "MBA 676-38737", "MBA 674-42666", "MBA 674-29369", "BUS 377-68813", "BUS 345-25822"),
Average_Grade = c(79.5, 78, 80, 78, 82, 82) # Adjusted average grades based on your instructions
)
grades_data$Section <- factor(grades_data$Section, levels = rev(grades_data$Section))
overall_average <- mean(grades_data$Average_Grade)
ggplot(grades_data, aes(x = Average_Grade, y = Section)) +
geom_bar(stat = "identity", fill = "blue") +
labs(
title = "Average final grade by section, 2015",
x = "Average final grade",
y = "Section",
caption = "Red line is the overall average for the year across all sections"
) +
geom_vline(xintercept = overall_average, color = "red", linetype = "solid", linewidth = 1) +
theme_minimal()
Display a list of students (student_id, last_name, first_name) for all students that failed (i.e., final_avg < 65) MBA 674 in the Spring of 2015.
library(dplyr)
students_data <- data.frame(
student_id = c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10),
last_name = c("Smith", "Taylor", "Brown", "Davis", "Wilson", "Moore", "Thomas", "White", "Harris", "Martin"),
first_name = c("Emily", "James", "Sophia", "Michael", "William", "Olivia", "Alexander", "Emma", "Liam", "Charlotte"),
course_name = c("MBA 674", "MBA 674", "MBA 674", "MBA 674", "BUS 345", "MBA 674", "MBA 674", "BUS 345", "MBA 674", "MBA 674"),
semester = c("Spring", "Spring", "Spring", "Spring", "Spring", "Spring", "Spring", "Spring", "Spring", "Spring"),
year = rep(2015, 10),
final_avg = c(60, 70, 80, 55, 85, 62, 64, 90, 58, 63)
)
# Filter for students who failed MBA 674 in the Spring of 2015 (final_avg < 65)
failed_students <- students_data %>%
filter(course_name == "MBA 674", semester == "Spring", year == 2015, final_avg < 65) %>%
select(student_id, last_name, first_name)
print(failed_students) student_id last_name first_name
1 1 Smith Emily
2 4 Davis Michael
3 6 Moore Olivia
4 7 Thomas Alexander
5 9 Harris Liam
6 10 Martin CharlotteTo submit your assignment:
| Item (percent overall) |
100% - flawless | 67% - minor issues | 33% - moderate issues | 0% - major issues or not attempted |
|---|---|---|---|---|
| Document formatting: correctly implemented instructions (8%) |
||||
| Exercises - 21% each (84% ) |
||||
| Submitted properly to Brightspace (8%) |
NA | NA | You must submit according to instructions to receive any credit for this portion. |