#If your assignment does not render, you might need to install.packages("htmltools")
library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
Read the StudentSurvey into this markdown and answers the following questions
#read the StudentSurvey.csv in here
student_survey <- read_csv("StudentSurvey.csv")
## Rows: 79 Columns: 17
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (5): Year, Sex, Smoke, Award, HigherSAT
## dbl (12): Exercise, TV, Height, Weight, Siblings, BirthOrder, VerbalSAT, Mat...
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
student_survey <- student_survey |> mutate(Sex = factor(Sex)) |> mutate(HigherSAT = factor(HigherSAT))
#check the head of the data set
head(student_survey)
## # A tibble: 6 × 17
## Year Sex Smoke Award HigherSAT Exercise TV Height Weight Siblings
## <chr> <fct> <chr> <chr> <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
## 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
## # ℹ 7 more variables: BirthOrder <dbl>, VerbalSAT <dbl>, MathSAT <dbl>,
## # SAT <dbl>, GPA <dbl>, Pulse <dbl>, Piercings <dbl>
#check the dimensions
dim(student_survey)
## [1] 79 17
#create a table of students'sex and "HigherSAT"
xtabs(~ Sex + HigherSAT, data=student_survey)
## HigherSAT
## Sex Math Verbal
## F 25 15
## M 24 15
# Display summary statistics for VerbalSAT
summary(student_survey$VerbalSAT)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 420.0 550.0 580.0 583.2 630.0 720.0
#Find the average GPA of students
mean(student_survey$GPA)
## [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 <- student_survey[, c("Weight", "Exercise")]
#Access the fourth element in the first column from the StudentSurvey's dataset.
student_survey[4,1]
## # A tibble: 1 × 1
## Year
## <chr>
## 1 Junior