#If your assignment does not render, you might need to install.packages("htmltools")Read the StudentSurvey into this markdown and answers the following questions
library (tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors#read the StudentSurvey.csv in here
setwd("C:/Users/Admin/Desktop/DATA101")
ssurvey<-read.csv("StudentSurvey.csv")
head(ssurvey)## 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 head of the data set
str(ssurvey)## 'data.frame': 79 obs. of 17 variables:
## $ Year : chr "Senior" "Sophomore" "FirstYear" "Junior" ...
## $ Sex : chr "M" "F" "M" "M" ...
## $ Smoke : chr "No" "Yes" "No" "No" ...
## $ Award : chr "Olympic" "Academy" "Nobel" "Nobel" ...
## $ HigherSAT : chr "Math" "Math" "Math" "Math" ...
## $ Exercise : int 10 4 14 3 3 5 10 13 12 12 ...
## $ TV : int 1 7 5 1 3 4 10 8 1 6 ...
## $ Height : int 71 66 72 63 65 65 66 74 60 65 ...
## $ Weight : int 180 120 208 110 150 114 128 235 115 140 ...
## $ Siblings : int 4 2 2 1 1 2 1 1 7 1 ...
## $ BirthOrder: int 4 2 1 1 1 2 1 1 8 2 ...
## $ VerbalSAT : int 540 520 550 490 720 600 640 660 670 500 ...
## $ MathSAT : int 670 630 560 630 450 550 680 710 700 670 ...
## $ SAT : int 1210 1150 1110 1120 1170 1150 1320 1370 1370 1170 ...
## $ GPA : num 3.13 2.5 2.55 3.1 2.7 3.2 2.77 3.3 3.7 2.09 ...
## $ Pulse : int 54 66 130 78 40 80 94 77 94 63 ...
## $ Piercings : int 0 3 0 0 6 4 8 0 2 2 ...#check the dimensions
dim (ssurvey)## [1] 79 17#create a table of students'sex and "HigherSAT"
table(ssurvey$Sex, ssurvey$HigherSAT)##
## Math Verbal
## F 25 15
## M 24 15# Display summary statistics for VerbalSAT
summary (ssurvey$VerbalSAT)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 420.0 550.0 580.0 583.2 630.0 720.0#Find the average GPA of students
mean (ssurvey$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 <- data.frame(ssurvey$Weight, ssurvey$Exercise)
column_df ## ssurvey.Weight ssurvey.Exercise
## 1 180 10
## 2 120 4
## 3 208 14
## 4 110 3
## 5 150 3
## 6 114 5
## 7 128 10
## 8 235 13
## 9 115 12
## 10 140 12
## 11 135 6
## 12 110 10
## 13 99 3
## 14 165 7
## 15 120 2
## 16 154 14
## 17 110 10
## 18 145 14
## 19 195 20
## 20 200 7
## 21 167 12
## 22 175 10
## 23 155 6
## 24 185 14
## 25 190 12
## 26 165 10
## 27 175 8
## 28 126 0
## 29 187 10
## 30 170 6
## 31 158 5
## 32 119 24
## 33 205 2
## 34 129 10
## 35 145 6
## 36 130 5
## 37 215 5
## 38 135 12
## 39 145 2
## 40 98 7
## 41 150 15
## 42 159 5
## 43 174 7
## 44 160 15
## 45 165 8
## 46 161 14
## 47 130 4
## 48 175 15
## 49 255 4
## 50 160 15
## 51 160 3
## 52 95 3
## 53 115 15
## 54 120 20
## 55 135 3
## 56 180 6
## 57 155 12
## 58 110 4
## 59 215 20
## 60 140 10
## 61 195 10
## 62 185 4
## 63 185 9
## 64 209 12
## 65 145 2
## 66 180 2
## 67 170 5
## 68 135 5
## 69 165 6
## 70 137 10
## 71 147 4
## 72 150 5
## 73 155 17
## 74 160 7
## 75 130 2
## 76 180 8
## 77 150 1
## 78 205 14
## 79 115 12#Access the fourth element in the first column from the StudentSurvey's dataset.
ssurvey[4,1]## [1] "Junior"