Set the working directory:

  1. Download “StudentSurvey.csv” to your computer.
  2. Set Working directory to the folder you saved your file in.
  3. read the file using read.csv command.
#If your assignment does not render, you might need to install.packages("htmltools")

Instructions:

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 data structure:

#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"