HW 1: Student Performance Data (Logical indices)

## HW1: Student Performance Data (Logical Indices)
# Due: Feb 3, 2020
# Alec Aversa

## 1. Upload the data StudentPerformance on 
## RStudio and find what kind of variables are present there.

StudentsPerformance <- read.csv("StudentsPerformance.csv")

# gender = Character
# race.ethnicity = Character
# parental.level.of.education = Character
# lunch = Character
# text.preperation.course
# math.score = Number
# reading.score = Number
# writing.score = Number

## 2. Print the categories of "parental level of education".

unique(StudentsPerformance$parental.level.of.education)

## [1] bachelor's degree  some college       master's degree    associate's degree
## [5] high school        some high school  
## 6 Levels: associate's degree bachelor's degree high school ... some high school

## 3. In "parental level of education", rename the level "high school" as "HS".

levels(StudentsPerformance$parental.level.of.education)

## [1] "associate's degree" "bachelor's degree"  "high school"       
## [4] "master's degree"    "some college"       "some high school"

levels(StudentsPerformance$parental.level.of.education)[3] <- "HS"
levels(StudentsPerformance$parental.level.of.education)

## [1] "associate's degree" "bachelor's degree"  "HS"                
## [4] "master's degree"    "some college"       "some high school"

## 4. How many males and females participated in the survey?

length(StudentsPerformance$gender[StudentsPerformance$gender == "female"])

## [1] 518

length(StudentsPerformance$gender[StudentsPerformance$gender == "male"])

## [1] 482

## 5. How many females were on the list who attended “high school” or “some high school”?

length(StudentsPerformance$gender[StudentsPerformance$gender == "female" & (StudentsPerformance$parental.level.of.education == "high school" | StudentsPerformance$parental.level.of.education == "some college")])

## [1] 118

## 6. How many students completed the test preparation course?

length(StudentsPerformance$test.preparation.course[StudentsPerformance$test.preparation.course == "completed"])

## [1] 358

## 7. How many students did not complete the test prep course but still scored above 80 in math?

length(StudentsPerformance$test.preparation.course[StudentsPerformance$test.preparation.course == "none" & StudentsPerformance$math.score > 80])

## [1] 92

## 8. Suppose the teachers will choose the candidate(s) who has the highest score (total in
## math, reading and writing). What is the highest score?

max(StudentsPerformance$math.score + StudentsPerformance$reading.score + StudentsPerformance$writing.score)

## [1] 300

## 9. How many highest scorers are there?

M <- max(StudentsPerformance$math.score + StudentsPerformance$reading.score + StudentsPerformance$writing.score)
sum(length(StudentsPerformance$parental.level.of.education[StudentsPerformance$math.score + StudentsPerformance$reading.score + StudentsPerformance$writing.score == M]))

## [1] 3

## 10. Answer the followings:
#(a) Is there any highest scorer who completed the test prep course?

sum(length(StudentsPerformance$parental.level.of.education[StudentsPerformance$math.score + StudentsPerformance$reading.score + StudentsPerformance$writing.score == M & StudentsPerformance$test.preparation.course == "completed"]))

## [1] 1

#(b) If there is any highest scorer who completed the test prep, find his/her score in
#reading.

StudentsPerformance$reading.score[StudentsPerformance$math.score + StudentsPerformance$reading.score + StudentsPerformance$writing.score == M & StudentsPerformance$test.preparation.course == "completed"]

## [1] 100