.Rhistory

load("~/Documents/Data_Science/R_Analysis/01_Demo/Vehicle analysis.RData")
load("~/Documents/Data_Science/UCSD_BootCamp/Class_Activities/Module15 R/15-1-Student_Resources/01_Ins_RBasics/Solved/01_Ins_RBasics.R")
knitr::opts_chunk$set(echo = TRUE)
summary(cars)
students
# Part I
students <- c("Abraham", "Beatrice", "Cory", "Dinah", "Eric", "Eric")
students
roll_call <- function(class){
print(Sys.Date())
# Create a for loop
for (student in students)
{print (student)}
}
roll_call
roll_call <- function(class){
print(Sys.Date())
# Create a for loop
for (student in students)
{print (student)}
}
# Call the function with the student vector as an argument.
roll_call(students)
locker_combinations <- function(class){
# Create the for loop and print the student name and locker combination.
for (student in students){
print(sample(33,3))
}
}
# Call the function with the student vector as an argument.
locker_combinations(students)
locker_combinations <- function(class){
# Create the for loop and print the student name and locker combination.
for (student in students){
print(sutdent + sample(33,3))
}
}
# Call the function with the student vector as an argument.
locker_combinations(students)
locker_combinations <- function(class){
# Create the for loop and print the student name and locker combination.
for (student in students){
print(student + sample(33,3))
}
}
# Call the function with the student vector as an argument.
locker_combinations(students)
locker_combinations <- function(class){
# Create the for loop and print the student name and locker combination.
for (student in students){
print(student)
print(sample(33,3))
}
}
# Call the function with the student vector as an argument.
locker_combinations(students)
locker_combinations <- function(class){
# Create the for loop and print the student name and locker combination.
for (student in class){
print(student)
print(sample(33,3))
}
}
# Call the function with the student vector as an argument.
locker_combinations(students)
# Part III
for (student in students){
# Create a variable (substring)  that holds the second letter for each student.
second_letter <- substring(student,2,2)
# Create an if statement to find the names of students where the
# second letter that is an "e".
if (second_letter == "e")
{
print(student)
print(sample(33:66,3))
}
}
save.image("~/Documents/Data_Science/UCSD_BootCamp/Class_Activities/Module15 R/15-1-Student_Resources/02_Stu_RBasics/Unsolved/high school students.RData")
knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
data(diamonds, package='ggplot2')
library(tidyverse)
data(diamonds, package='ggplot2')
nrow(diamonds)
head(diamonds, 10)
tail(diamonds, 10)
slice(diamonds, 1:7)
slice(diamonds, 3)
slice(diamonds, c(1,7))
select(diamonds, carat, price)
filter(diamonds, cut=='Ideal')
filter(diamonds, (cut=='Ideal' & price > 500))
total_volume <- mutate(diamonds, x * y * z)
total_volume
?mutate()
# In R, variables can contain periods
total.volume2 <- mutate(diamonds, total.volume=(x*y*z))
total.volume2
summarize(diamonds, mean(price))
cut <- group_by(diamonds, cut)
summarize(cut, mean(price), sum(price))
summarize(cut, avg=mean(price),number=n())
cut2 <- group_by(diamonds, cut, color)
cut2_summary <- summarize(cut2, mean(price))
cut2_summary
students <- read_csv(students.csv)
load("~/Documents/Data_Science/UCSD_BootCamp/Class_Activities/Module15 R/15-1-Student_Resources/06_Evr_Tibble/Resources/students.csv")
students <- read_csv(students.csv)
students <-read_csv(students.csv)
students <-read_csv(students.csv)
students <-read.csv(students.csv)
students <-read.csv(file='students.csv',check.names=F,stringsAsFactors =F)
students <-read.csv(file='students.csv')
students <-read.csv(students.csv)
students <-read.csv(students.csv)
students <-read_csv(students.csv)
?read_csv()
students <-read_csv('students.csv')
library(tidyverse)
mosquito <- read.csv(file="../Resources/mosquito.csv")
setwd("~/Documents/Data_Science/UCSD_BootCamp/Class_Activities/Module15 R/15-2-Student_Resources/Activities/04-Ins_ANOVA")
mosquito <- read.csv(file="../Resources/mosquito.csv")
setwd("~/Documents/Data_Science/UCSD_BootCamp/Class_Activities/Module15 R/15-2-Student_Resources/Activities/04-Ins_ANOVA/Solved")
mosquito <- read.csv(file="../Resources/mosquito.csv")
ggplot(mosquito,aes(x=factor(treatment),y=mosq)) + geom_boxplot()
# aov performs the analysis of variance, but does not provide a p-value
aov(mosq ~ factor(treatment), data=mosquito)
# to obtain a p-value, wrap aov() with a summary() function
summary(aov(mosq ~ factor(treatment), data=mosquito))
ggplot(mosquito,aes(x=factor(treatment),y=mosq)) + geom_boxplot()
# aov performs the analysis of variance, but does not provide a p-value
aov(mosq ~ factor(treatment), data=mosquito)
# to obtain a p-value, wrap aov() with a summary() function
summary(aov(mosq ~ factor(treatment), data=mosquito))
qplot(mosquito, geom = 'bar')
View(mosquito)
typeof(mosquito)
typeof(treatment)
treatment_fct <- factor(treatment)
treatment_fct <- factor(mosquito$treatment)
typeof(treatment_fct)
summary(treatment_fct)
qplot(treatment_fct, geom='bar')
setwd("~/Documents/Data_Science/UCSD_BootCamp/Module_Projects/MechaCar_Statistical_Analysis")
library(dplyr)
MechaCar <- read.csv(MechaCar_mpg.csv)
MechaCar <- read.csv("MechaCar_mpg.csv")
View(mosquito)
MechaCar <- read.csv("MechaCar_mpg.csv")
View(MechaCar)
?lm()
lm(mpg ~ vehicle_lenght + vehicle_weight + spoiler_angle + ground_clearance + AWD, data = MechaCar_mpg)
lm(mpg ~ vehicle_lenght + vehicle_weight + spoiler_angle + ground_clearance + AWD, data = MechaCar)
lm(mpg ~ vehicle_length + vehicle_weight + spoiler_angle + ground_clearance + AWD, data = MechaCar)
summary(lm(mpg ~ vehicle_length + vehicle_weight + spoiler_angle + ground_clearance + AWD, data = MechaCar)) #ge
summary(lm(mpg ~ vehicle_length + vehicle_weight + spoiler_angle + ground_clearance + AWD, data = MechaCar))
Suspension_Coil <- read.csv("Suspension_Coil")#import Suspension_Coil dataset
Suspension_Coil <- read.csv("Suspension_Coil.csv")#import Suspension_Coil dataset
summarize(Suspension_Coil)
View(Suspension_Coil)
View(Suspension_Coil)
?summarize
summarise(Suspension_Coil)
summarize(Suspension_Coil$PSI)
total_summary <- summarize(Suspension_Coil$PSI)
total_summary <- summarize(Mean=mean(Suspension_Coil$PSI))
total_summary <- summarize(Suspension_Coil[['PSI']])
class(Suspension_Coil$PSI)='Integer'
total_summary <- summarize(Suspension_Coil$PSI)
total_summary <- Suspension_Coil %>% summarize(Mean=mean('PSI'))
class(Suspension_Coil$PSI)='Numeric'
total_summary <- Suspension_Coil %>% summarize(Mean=mean('PSI'))
class(Suspension_Coil$PSI)='numeric'
total_summary <- Suspension_Coil %>% summarize(Mean=mean('PSI'))
typeof(Suspension_Coil$PSI)
Suspension_Coil <- read.csv("Suspension_Coil.csv")#import Suspension_Coil dataset
typeof(Suspension_Coil$PSI)
mean(Suspension_Coil$PSI)
summary(Suspension_Coil$PSI)
total_summary <- Suspension_Coil %>% summarize(Mean=mean('PSI'))
total_summary <- Suspension_Coil %>% summarize(Mean=mean(PSI))
total_summary <- Suspension_Coil %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=varianc(PSI),SD=sd(PSI))
total_summary <- Suspension_Coil %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=variance(PSI),SD=sd(PSI))
total_summary <- Suspension_Coil %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=var(PSI),SD=sd(PSI))
total_summary
View(total_summary)
lot_summary <- Suspension_Coil %>% group_by(Manfaturing_Lot) %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=var(PSI),SD=sd(PSI), .group = 'keep')#
lot_summary <- Suspension_Coil %>% group_by(Manufaturing_Lot) %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=var(PSI),SD=sd(PSI), .group = 'keep')#create summary table with multiple columns
lot_summary <- Suspension_Coil %>% group_by(Manufacturing_Lot) %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=var(PSI),SD=sd(PSI), .group = 'keep')#create summary table with multiple columns
View(lot_summary)
lot_summary <- Suspension_Coil %>% group_by(Manufacturing_Lot) %>% summarize(Mean=mean(PSI),Median=median(PSI),Variance=var(PSI),SD=sd(PSI), .groups = 'keep')#create summary tabl
?t.test
t.test(Suspension_Coil,mu=1500)#compare all manufacture lots versus population mean.
t.test(Suspension_Coil$PSI,mu=1500)#compare PSI of all manufacture lots versus population mean.
t.test((subset(Suspension_Coil$Manufacturing_Lot=='Lot1'))$PSI,mu=1500)
?subset()
lot1 <- subset(Suspension_Coil$Manufacturing_Lot=='Lot1')
lot1 <- subset(Suspension_Coil, Manufacturing_Lot=='Lot1')
t.test(lot1$PSI,mu=1500)
lot1 <- subset(Suspension_Coil, Manufacturing_Lot=='Lot1')#create subset table of Lot1
t.test(lot1$PSI,mu=1500)#compare PSI of Lot1 versus population mean.
lot2 <- subset(Suspension_Coil, Manufacturing_Lot=='Lot2')#create subset table of Lot2
t.test(lot2$PSI,mu=1500)#compare PSI of Lot2 versus population mean.
lot3 <- subset(Suspension_Coil, Manufacturing_Lot=='Lot3')#create subset table of Lot3
t.test(lot3$PSI,mu=1500)#compare PSI of Lot3 versus population mean.
View(lot1)
save.image("~/Documents/Data_Science/UCSD_BootCamp/Module_Projects/MechaCar_Statistical_Analysis/MechaCar_Challenge.RData")
t.test(Suspension_Coil$PSI,mu=1500)#compare PSI of all manufacture lots versus population mean