#If your assignment does not render, you might need to install.packages("htmltools")
Read the StudentSurvey into this markdown and answers the following questions
#read the StudentSurvey.csv in here
StudentSurvey <- read.csv("StudentSurvey.csv")
# Quick check
names(StudentSurvey)
## [1] "Year" "Sex" "Smoke" "Award" "HigherSAT"
## [6] "Exercise" "TV" "Height" "Weight" "Siblings"
## [11] "BirthOrder" "VerbalSAT" "MathSAT" "SAT" "GPA"
## [16] "Pulse" "Piercings"
#check the head of the data set
head(StudentSurvey)
## Year Sex Smoke Award HigherSAT Exercise TV Height Weight Siblings
## 1 Senior M No Olympic Math 10 1 71 180 4
## 2 Sophomore F Yes Academy Math 4 7 66 120 2
## 3 FirstYear M No Nobel Math 14 5 72 208 2
## 4 Junior M No Nobel Math 3 1 63 110 1
## 5 Sophomore F No Nobel Verbal 3 3 65 150 1
## 6 Sophomore F No Nobel Verbal 5 4 65 114 2
## BirthOrder VerbalSAT MathSAT SAT GPA Pulse Piercings
## 1 4 540 670 1210 3.13 54 0
## 2 2 520 630 1150 2.50 66 3
## 3 1 550 560 1110 2.55 130 0
## 4 1 490 630 1120 3.10 78 0
## 5 1 720 450 1170 2.70 40 6
## 6 2 600 550 1150 3.20 80 4
#check the dimensions
dim(StudentSurvey)
## [1] 79 17
#create a table of students'sex and "HigherSAT"
xtabs(~ Sex + HigherSAT, data=StudentSurvey)
## HigherSAT
## Sex Math Verbal
## F 25 15
## M 24 15
# Display summary statistics for VerbalSAT
summary(StudentSurvey$VerbalSAT)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 420.0 550.0 580.0 583.2 630.0 720.0
#Find the average GPA of students
mean(StudentSurvey$GPA, na.rm = TRUE)
## [1] 3.169114
#Create a new dataframe, call it "column_df". This new dataframe should contain students' weight and number of hours the exercise
column_df <- StudentSurvey[, c("Weight", "Exercise")]
#quick check
head(column_df)
## Weight Exercise
## 1 180 10
## 2 120 4
## 3 208 14
## 4 110 3
## 5 150 3
## 6 114 5
#Access the fourth element in the first column from the StudentSurvey's dataset.
StudentSurvey[4, 1]
## [1] "Junior"