Students Performance

A dataset of students performance in exams

Load Libraries:

library(tidyverse)

## Warning: package 'tidyverse' was built under R version 3.6.3

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v ggplot2 3.3.2     v purrr   0.3.4
## v tibble  3.0.4     v dplyr   1.0.2
## v tidyr   1.1.2     v stringr 1.4.0
## v readr   1.4.0     v forcats 0.5.0

## Warning: package 'ggplot2' was built under R version 3.6.3

## Warning: package 'tibble' was built under R version 3.6.3

## Warning: package 'tidyr' was built under R version 3.6.3

## Warning: package 'readr' was built under R version 3.6.3

## Warning: package 'purrr' was built under R version 3.6.3

## Warning: package 'dplyr' was built under R version 3.6.3

## Warning: package 'forcats' was built under R version 3.6.3

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(dplyr)
library(ggplot2)
library(plotly)

## Warning: package 'plotly' was built under R version 3.6.3

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

Get Working Directory:

getwd()

## [1] "C:/Users/Maggie/Documents"

Load Dataset:

StudentsPerformance <- read_csv("C:/Users/Maggie/Downloads/StudentsPerformance.csv")

## 
## -- Column specification --------------------------------------------------------
## cols(
##   gender = col_character(),
##   `race/ethnicity` = col_character(),
##   `parental level of education` = col_character(),
##   lunch = col_character(),
##   `test preparation course` = col_character(),
##   `math score` = col_double(),
##   `reading score` = col_double(),
##   `writing score` = col_double()
## )

View Dataset:

view(StudentsPerformance)

Summary of the Dataset:

summary(StudentsPerformance)

##     gender          race/ethnicity     parental level of education
##  Length:1000        Length:1000        Length:1000                
##  Class :character   Class :character   Class :character           
##  Mode  :character   Mode  :character   Mode  :character           
##                                                                   
##                                                                   
##                                                                   
##     lunch           test preparation course   math score     reading score   
##  Length:1000        Length:1000             Min.   :  0.00   Min.   : 17.00  
##  Class :character   Class :character        1st Qu.: 57.00   1st Qu.: 59.00  
##  Mode  :character   Mode  :character        Median : 66.00   Median : 70.00  
##                                             Mean   : 66.09   Mean   : 69.17  
##                                             3rd Qu.: 77.00   3rd Qu.: 79.00  
##                                             Max.   :100.00   Max.   :100.00  
##  writing score   
##  Min.   : 10.00  
##  1st Qu.: 57.75  
##  Median : 69.00  
##  Mean   : 68.05  
##  3rd Qu.: 79.00  
##  Max.   :100.00

Looking at the Head of the Dataset:

head(StudentsPerformance)

## # A tibble: 6 x 8
##   gender `race/ethnicity` `parental level~ lunch `test preparati~ `math score`
##   <chr>  <chr>            <chr>            <chr> <chr>                   <dbl>
## 1 female group B          bachelor's degr~ stan~ none                       72
## 2 female group C          some college     stan~ completed                  69
## 3 female group B          master's degree  stan~ none                       90
## 4 male   group A          associate's deg~ free~ none                       47
## 5 male   group C          some college     stan~ none                       76
## 6 female group B          associate's deg~ stan~ none                       71
## # ... with 2 more variables: `reading score` <dbl>, `writing score` <dbl>

The Dimension of the Dataset: 1000 rows and 8 columns

dim(StudentsPerformance)

## [1] 1000    8

Checking to see if theres any NA’s:

any(is.na(StudentsPerformance))

## [1] FALSE

Creating a table of the test preparation course variable:

Test_Preparation_Course <- table(StudentsPerformance$`test preparation course`)

Creating a simple barplot to see if there are more students who completed the test preparation.

barplot(Test_Preparation_Course, col = "light blue", main = "Barplot of Test Preparation Course")

Parental_Level_of_Education <- table(StudentsPerformance$`parental level of education`)
barplot(Parental_Level_of_Education, main = "Number of Parents in Each Education Level")

Creating a barplot comparing the number students by gender in each race/ethnicity group.

ggplot(StudentsPerformance, aes(StudentsPerformance$`race/ethnicity`, fill = gender)) +
  geom_bar(position = "dodge") +
  xlab("Race/Ethnicity") +
  ggtitle( "Barplot of Students in Each Race/Ethnicity Group by Gender")

Boxplot comparing the score of all three tests:

boxplot(StudentsPerformance[, c("math score", "reading score", "writing score")])

Reshaping my dataset into pivot longer to create a boxplot comparing each test score by gender.

BOXPLOT <- StudentsPerformance %>%
  select("gender", "math score", "reading score", "writing score") %>%
  pivot_longer(., cols = c("math score", "reading score", "writing score"), names_to = "Tests", values_to = "Score") %>%
 ggplot(aes(x = Tests, y = Score)) +
  geom_boxplot() +
  theme_dark()+
  theme(panel.background = element_rect(fill = "light blue"))+
  ggtitle("Boxplot of Scores by Gender")+
  facet_wrap(~gender)
  

ggplotly(BOXPLOT)

## Warning: `group_by_()` is deprecated as of dplyr 0.7.0.
## Please use `group_by()` instead.
## See vignette('programming') for more help
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_warnings()` to see where this warning was generated.

Using the mutate function to add a overall grade column into the dataset. Add all the test scores together then divide by 3.

StudentsPerformance2 <- mutate(StudentsPerformance, Overall_Grade = (StudentsPerformance$`math score` + StudentsPerformance$`reading score` + StudentsPerformance$`writing score`) / 3) 
StudentsPerformance2

## # A tibble: 1,000 x 9
##    gender `race/ethnicity` `parental level~ lunch `test preparati~ `math score`
##    <chr>  <chr>            <chr>            <chr> <chr>                   <dbl>
##  1 female group B          bachelor's degr~ stan~ none                       72
##  2 female group C          some college     stan~ completed                  69
##  3 female group B          master's degree  stan~ none                       90
##  4 male   group A          associate's deg~ free~ none                       47
##  5 male   group C          some college     stan~ none                       76
##  6 female group B          associate's deg~ stan~ none                       71
##  7 female group B          some college     stan~ completed                  88
##  8 male   group B          some college     free~ none                       40
##  9 male   group D          high school      free~ completed                  64
## 10 female group B          high school      free~ none                       38
## # ... with 990 more rows, and 3 more variables: `reading score` <dbl>, `writing
## #   score` <dbl>, Overall_Grade <dbl>

Using the filter function to see if there’s any student with an overall grade of 100.

filter(StudentsPerformance2, Overall_Grade == 100.00)

## # A tibble: 3 x 9
##   gender `race/ethnicity` `parental level~ lunch `test preparati~ `math score`
##   <chr>  <chr>            <chr>            <chr> <chr>                   <dbl>
## 1 female group E          bachelor's degr~ stan~ none                      100
## 2 male   group E          bachelor's degr~ stan~ completed                 100
## 3 female group E          associate's deg~ stan~ none                      100
## # ... with 3 more variables: `reading score` <dbl>, `writing score` <dbl>,
## #   Overall_Grade <dbl>

Boxplot comparing Student’s overall grade and parental level of education by gender.

ggplot(StudentsPerformance2, aes(x = StudentsPerformance2$`parental level of education`, y = StudentsPerformance2$Overall_Grade )) +
  geom_boxplot() +
  labs(x = "Parental Level of Education", y = "Student's Overall Grade", title = "Boxplot comparing parental level of education to student's overall grade") +
  facet_wrap(~gender)

Barplot of test preparation course by gender.

ggplot(StudentsPerformance2, aes(x = StudentsPerformance2$`test preparation course`, fill = gender)) +
  geom_bar(position = "dodge")+
  labs(x = "Test Preparation Course" , title = "Test Preparation Course by Gender")

Simple boxplot comparing the overall grade by gender.

boxplot(StudentsPerformance2$Overall_Grade ~ StudentsPerformance2$gender, xlab = "Gender", ylab = "Overall Grade", main = "Overall Grade by Gender")

Create a table of gender.

table(StudentsPerformance2$gender)

## 
## female   male 
##    518    482

hist(StudentsPerformance2$Overall_Grade, main = "Histogram of Students' Overall Grade", xlab = "Overall Grade", col = "blue")

Using the mutate function to add Letter Grade column to the dataset.

StudentsPerformance3 <- mutate(StudentsPerformance2, Letter_Grade = cut(StudentsPerformance2$Overall_Grade, breaks = c(0,59.99,69.99,79.99,89.99,100), labels = c( "F", "D", "C", "B", "A"), right = FALSE, include.lowest = TRUE))
view(StudentsPerformance3)

Facet wrap barplot comparing student’s letter grade by gender and race/ethnicity.

ggplot(StudentsPerformance3, aes(x = StudentsPerformance3$Letter_Grade, fill = gender)) +
  geom_bar(position = "dodge") +
  facet_wrap(~ StudentsPerformance3$`race/ethnicity`)+
  xlab("Letter Grade")

A mosaicplot comparing the letter grade and whether they have taken test preparation course.

mosaicplot(StudentsPerformance3$Letter_Grade ~ StudentsPerformance3$`test preparation course`, main = "Mosaicplot of Letter Grade and Test Preparation Course", xlab = "Letter Grade", ylab ="Test Preparation Course")

Mosaic plot comparing the categorical variables of Race/Ethnicity, Gender and whether students took a test preparation course.

Select <- StudentsPerformance3 %>%
  select(1:2, 5, 10)

Table <- table(Select$gender, Select$`race/ethnicity`,Select$`test preparation course`, Select$Letter_Grade)
MP <- mosaicplot(Table)

An interactive plot comparing student letter grade by Race/Ethniciy, gender and whether they had taken a test preparation course.

GGPLOT <- ggplot(StudentsPerformance3, aes(x = StudentsPerformance3$`race/ethnicity`, fill = StudentsPerformance3$Letter_Grade))+
  geom_bar(position = "dodge") +
  facet_wrap(StudentsPerformance3$`test preparation course` ~StudentsPerformance3$gender)+
   theme_dark()+
  theme(panel.background = element_rect(fill = "#2D2D2D"), legend.background = element_rect(fill = "#2D2D2D"), legend.title = element_text(size = 8))+
  scale_fill_viridis_d()+
  labs(title = "Comparing Student Letter Grade by Race/Ethnicity, Gender and Whether They Had Taken a Test Preparation Course", y = "Count", x = "Race/Ethnicity", fill = "Letter Grade", face = "bold")

Using config(displayModeBar = FALSE) to remove the display mode bar.

ggplotly(GGPLOT) %>%
  config(displayModeBar = FALSE)

Essay: My dataset is Students Performance on Exams from Kaggle. It is a fictional dataset, meaning the data in this dataset is inaccurate. The dataset documented student’s math, reading, and writing scores. Besides the quantitative variables(math, reading, and writing scores), the dataset also includes five categorical variables such as gender(gender of the student), race/ethnicity(five different groups), parental level of education(parent’s educational level of the student), lunch(whether the student has standard or free/reduced lunch), and test preparation course(whether or not the student has taken a test preparation course). I was able to find out that there are 1000 rows and 8 columns of data in this dataset by using the dim function. I started exploring the dataset by using the summary, head, and any(is.na) function to look at the summary, the variables, and the first 6 rows, and if there are any missing values in the dataset. Also, I was able to use the filter, mutate, and select function from the dplyr library. I used the filter function to see if there were any students with an overall grade of 100 and found out that there were 3 students. I also use the mutate function to add columns such as student’s overall grade and their grades in Letter form. Then I used the select function to select different categorical variables to create a mosaic plot. I chose this topic because I’m also a student, so it will be easier to relate to. I chose this dataset because I like the fact that they have different test scores so I thought it would be interesting to see each gender do on different kinds of tests.
According to a blog post I read called, “Gender differences on the ACT test: Boys score higher on math and science; girl score higher on English and Reading,” written by Mark J. Perry stated that high school girls tend to do slightly better in the areas of language and reading on average, while high school boys exhibit slightly greater cognitive abilities in math and science on average. In this dataset, in one of my data visualization, a boxplot shows that girls did do better in reading and writing test, while boys did better in math. In my data visualizations, I was able to see that the higher the number of students who completed the test preparation course, the higher the number of students with the letter grade A. The group of students who did complete the test preparation course receives a much lower number of the letter grade F compared to the group who did not. It’s also interesting that slightly more girls completed the test preparation course than boys. Overall, I think test preparation courses are helpful for testing taking. One thing that I wanted to show but could not get to work on was creating a mosaic plot for all my categorical variables. Since my dataset is categorical variables heavy, I thought a complex mosaic plot would work well in comparing gender, race/ethnicity, parental level of education, lunch, and test preparation.