HW3

Data Wrangling

Libraries

library(readr)
library(dplyr)

Data Loading & cleaning

student <- read_csv("data.csv")
str(student)

spec_tbl_df [1,000 × 8] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ gender                     : chr [1:1000] "female" "female" "female" "male" ...
 $ race/ethnicity             : chr [1:1000] "group B" "group C" "group B" "group A" ...
 $ parental level of education: chr [1:1000] "bachelor's degree" "some college" "master's degree" "associate's degree" ...
 $ lunch                      : chr [1:1000] "standard" "standard" "standard" "free/reduced" ...
 $ test preparation course    : chr [1:1000] "none" "completed" "none" "none" ...
 $ math score                 : num [1:1000] 72 69 90 47 76 71 88 40 64 38 ...
 $ reading score              : num [1:1000] 72 90 95 57 78 83 95 43 64 60 ...
 $ writing score              : num [1:1000] 74 88 93 44 75 78 92 39 67 50 ...
 - attr(*, "spec")=
  .. 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()
  .. )
 - attr(*, "problems")=<externalptr> 

Check if there are any “NA” values

sapply(student, function(x) sum(is.na(x)))

                     gender              race/ethnicity 
                          0                           0 
parental level of education                       lunch 
                          0                           0 
    test preparation course                  math score 
                          0                           0 
              reading score               writing score 
                          0                           0 

As we can see it is a clean dataset.

Renaming the columns

colnames(student)[2] <- "race_ethnicity_group"
colnames(student)[3] <- "parent_highest_education"
colnames(student)[5] <- "test_preparation_course"
colnames(student)[6] <- "math_marks"
colnames(student)[7] <- "reading_marks"
colnames(student)[8] <- "writing_marks"

Converting few columns from character to factor

student$gender <- as.factor(student$gender)
student$race_ethnicity_group <- as.factor(student$race_ethnicity_group)
student$lunch <- as.factor(student$lunch)
student$test_preparation_course <- as.factor(student$test_preparation_course)

Creating new columns namely total and average score

student$total_marks = student$math_marks  + student$reading_marks + student$writing_marks
student$mean_marks = round((student$total_marks)/3,2)

Alloting grades as per the average score

student <- student %>% 
     mutate(grade = case_when(
         mean_marks >= 90 & mean_marks <= 100 ~ "A",
         mean_marks >= 80 & mean_marks < 90 ~ "B",
         mean_marks >= 70 & mean_marks < 80 ~ "C",
         mean_marks >= 60 & mean_marks < 70  ~ "D",
         mean_marks >= 50 & mean_marks < 60  ~ "E",
         mean_marks < 50 ~ "F"
     )%>% as.factor()
     )

Defining the order of levels in parent’s highest education

student$parent_highest_education <- 
     student$parent_highest_education %>%
     factor(levels = c("some high school","high school", "some college" ,
                       "associate's degree","bachelor's degree", "master's degree")
     )

Lets have a look at our data again :

str(student)

tibble [1,000 × 11] (S3: tbl_df/tbl/data.frame)
 $ gender                  : Factor w/ 2 levels "female","male": 1 1 1 2 2 1 1 2 2 1 ...
 $ race_ethnicity_group    : Factor w/ 5 levels "group A","group B",..: 2 3 2 1 3 2 2 2 4 2 ...
 $ parent_highest_education: Factor w/ 6 levels "some high school",..: 5 3 6 4 3 4 3 3 2 2 ...
 $ 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_marks              : num [1:1000] 72 69 90 47 76 71 88 40 64 38 ...
 $ reading_marks           : num [1:1000] 72 90 95 57 78 83 95 43 64 60 ...
 $ writing_marks           : num [1:1000] 74 88 93 44 75 78 92 39 67 50 ...
 $ total_marks             : num [1:1000] 218 247 278 148 229 232 275 122 195 148 ...
 $ mean_marks              : num [1:1000] 72.7 82.3 92.7 49.3 76.3 ...
 $ grade                   : Factor w/ 6 levels "A","B","C","D",..: 3 2 1 6 3 3 1 6 4 6 ...

summary(student)

    gender    race_ethnicity_group       parent_highest_education
 female:518   group A: 89          some high school  :179        
 male  :482   group B:190          high school       :196        
              group C:319          some college      :226        
              group D:262          associate's degree:222        
              group E:140          bachelor's degree :118        
                                   master's degree   : 59        
          lunch     test_preparation_course   math_marks    
 free/reduced:355   completed:358           Min.   :  0.00  
 standard    :645   none     :642           1st Qu.: 57.00  
                                            Median : 66.00  
                                            Mean   : 66.09  
                                            3rd Qu.: 77.00  
                                            Max.   :100.00  
 reading_marks    writing_marks     total_marks      mean_marks    
 Min.   : 17.00   Min.   : 10.00   Min.   : 27.0   Min.   :  9.00  
 1st Qu.: 59.00   1st Qu.: 57.75   1st Qu.:175.0   1st Qu.: 58.33  
 Median : 70.00   Median : 69.00   Median :205.0   Median : 68.33  
 Mean   : 69.17   Mean   : 68.05   Mean   :203.3   Mean   : 67.77  
 3rd Qu.: 79.00   3rd Qu.: 79.00   3rd Qu.:233.0   3rd Qu.: 77.67  
 Max.   :100.00   Max.   :100.00   Max.   :300.0   Max.   :100.00  
 grade  
 A: 52  
 B:146  
 C:261  
 D:256  
 E:182  
 F:103  

write.csv(student, "./student_final_data.csv")

Potential Research Questions

1. Which gender performs better on an average?

2. How is the performance of students who have completed the preparation course against those who have not?

3. How much does the parental highest education level impact their child’s performance