getwd() # 작업공간 확인 함수
## [1] "C:/2023교통대 대학원"
setwd('c:/data')
df<-read.csv("Data1.csv")
library(dplyr)
##
## 다음의 패키지를 부착합니다: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
glimpse(df)
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU1 <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
str(df)
## 'data.frame': 1925 obs. of 26 variables:
## $ Q1 : int 4 4 4 5 4 4 4 4 4 4 ...
## $ Q2 : int 4 4 4 4 4 4 2 2 4 4 ...
## $ Q3 : int 2 4 4 4 4 4 4 4 4 2 ...
## $ Q4 : int 3 4 4 4 4 4 4 4 4 2 ...
## $ Q5 : int 4 4 2 4 4 4 4 4 2 4 ...
## $ Q6 : int 2 3 4 4 4 4 4 4 1 2 ...
## $ Q7 : int 2 2 4 4 4 4 4 4 3 4 ...
## $ Q8 : int 4 4 4 4 4 4 5 5 2 2 ...
## $ Q9 : int 4 4 4 4 2 4 5 5 3 4 ...
## $ Q10 : int 4 4 2 4 4 4 5 5 2 4 ...
## $ Q11 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q12 : int 4 4 4 4 4 4 5 5 3 4 ...
## $ Q13 : int 4 4 4 4 4 4 5 5 4 4 ...
## $ Q14 : int 4 4 4 4 4 4 5 5 5 4 ...
## $ Q15 : int 4 4 3 4 4 4 4 2 3 4 ...
## $ Q16 : int 4 4 4 4 4 4 5 2 4 4 ...
## $ Q17 : int 4 3 4 4 4 4 2 2 4 4 ...
## $ Q18 : int 4 4 4 4 4 4 4 4 4 4 ...
## $ Q19 : int 4 2 4 4 4 4 4 2 4 2 ...
## $ Q20 : int 4 1 3 4 4 4 4 2 4 2 ...
## $ Gender1 : int 0 0 0 0 0 0 0 0 1 0 ...
## $ EDU1 : int 1 1 2 1 2 1 1 1 4 3 ...
## $ BF : num 3.4 4 3.6 4.2 4 4 3.6 3.6 3.6 3.2 ...
## $ BM : num 3.2 3.4 3.6 4 3.6 4 4.6 4.6 2.2 3.2 ...
## $ Happiness: num 4 4 3.8 4 4 4 4.8 4.4 3.8 4 ...
## $ Peace : num 4 2.8 3.8 4 4 4 3.8 2.4 4 3.2 ...
head(df)
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20
## 1 4 4 2 3 4 2 2 4 4 4 4 4 4 4 4 4 4 4 4 4
## 2 4 4 4 4 4 3 2 4 4 4 4 4 4 4 4 4 3 4 2 1
## 3 4 4 4 4 2 4 4 4 4 2 4 4 4 4 3 4 4 4 4 3
## 4 5 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4
## 5 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4
## 6 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4
## Gender1 EDU1 BF BM Happiness Peace
## 1 0 1 3.4 3.2 4.0 4.0
## 2 0 1 4.0 3.4 4.0 2.8
## 3 0 2 3.6 3.6 3.8 3.8
## 4 0 1 4.2 4.0 4.0 4.0
## 5 0 2 4.0 3.6 4.0 4.0
## 6 0 1 4.0 4.0 4.0 4.0
tail(df)
## Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 Q19 Q20
## 1920 4 4 3 4 4 2 2 3 4 2 2 4 3 4 4 3 4 4 3 4
## 1921 2 2 2 1 2 2 2 2 2 2 1 3 2 1 3 2 2 2 2 2
## 1922 3 2 2 2 3 1 1 1 1 1 3 3 3 4 4 4 4 5 2 2
## 1923 5 4 4 4 4 2 2 2 2 3 3 4 3 4 3 3 3 4 4 4
## 1924 4 4 4 2 2 4 2 4 4 3 3 2 3 4 3 4 4 4 3 4
## 1925 3 3 1 1 2 1 1 1 1 1 4 4 3 2 2 3 4 4 3 2
## Gender1 EDU1 BF BM Happiness Peace
## 1920 1 3 3.8 2.6 3.4 3.6
## 1921 1 2 1.8 2.0 2.0 2.0
## 1922 0 2 2.4 1.0 3.4 3.4
## 1923 0 2 4.2 2.2 3.4 3.6
## 1924 1 2 3.2 3.4 3.0 3.8
## 1925 0 3 2.0 1.0 3.0 3.2
shapiro.test(df$Happiness)
##
## Shapiro-Wilk normality test
##
## data: df$Happiness
## W = 0.96442, p-value < 2.2e-16
# Peace, BM, 정규성 검정 실행해 보세요
options(scipen=100)
shapiro.test(df$Peace)
##
## Shapiro-Wilk normality test
##
## data: df$Peace
## W = 0.97095, p-value < 0.00000000000000022
shapiro.test(df$BM)
##
## Shapiro-Wilk normality test
##
## data: df$BM
## W = 0.98807, p-value = 0.00000000001537
wilcox.test(df$Happiness,mu=3.5)
##
## Wilcoxon signed rank test with continuity correction
##
## data: df$Happiness
## V = 1029154, p-value = 0.000002782
## alternative hypothesis: true location is not equal to 3.5
par(mfrow=c(1,2))
hist(df$Happiness)
hist(df$BF)
hist(df$Peace)
boxplot(df$Happiness)
boxplot(df$Peace)
wilcox.test(df$Happiness-df$Peace)
##
## Wilcoxon signed rank test with continuity correction
##
## data: df$Happiness - df$Peace
## V = 596154, p-value = 0.3322
## alternative hypothesis: true location is not equal to 0
par(mfrow=c(2,2))
hist(df$Happiness-df$Peace)
boxplot(df$Happiness-df$Peace)
wilcox.test(df$Happiness~df$Gender1)
##
## Wilcoxon rank sum test with continuity correction
##
## data: df$Happiness by df$Gender1
## W = 463050, p-value = 0.211
## alternative hypothesis: true location shift is not equal to 0
par(mfrow=c(1,1))
boxplot(df$Happiness~df$Gender1)
library(ggplot2)
data(diamonds)
# ctrl+shift+m %>% %>% %>%
df<-read.csv("Data1.csv")
glimpse(df)
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU1 <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
df %>% glimpse()
## Rows: 1,925
## Columns: 26
## $ Q1 <int> 4, 4, 4, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, …
## $ Q2 <int> 4, 4, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 2, 2, …
## $ Q3 <int> 2, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 4, 4, 3, 2, 3, …
## $ Q4 <int> 3, 4, 4, 4, 4, 4, 4, 4, 4, 2, 4, 4, 4, 2, 4, 4, 4, 2, 2, 4, …
## $ Q5 <int> 4, 4, 2, 4, 4, 4, 4, 4, 2, 4, 4, 2, 4, 4, 4, 4, 4, 3, 1, 2, …
## $ Q6 <int> 2, 3, 4, 4, 4, 4, 4, 4, 1, 2, 2, 2, 4, 4, 3, 5, 2, 2, 1, 4, …
## $ Q7 <int> 2, 2, 4, 4, 4, 4, 4, 4, 3, 4, 4, 4, 5, 4, 4, 5, 4, 3, 4, 4, …
## $ Q8 <int> 4, 4, 4, 4, 4, 4, 5, 5, 2, 2, 4, 4, 4, 4, 3, 5, 4, 2, 4, 4, …
## $ Q9 <int> 4, 4, 4, 4, 2, 4, 5, 5, 3, 4, 4, 4, 2, 2, 4, 5, 2, 4, 2, 4, …
## $ Q10 <int> 4, 4, 2, 4, 4, 4, 5, 5, 2, 4, 2, 4, 4, 4, 3, 4, 4, 3, 2, 3, …
## $ Q11 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 3, 4, 4, 4, 4, 5, 4, 3, 3, …
## $ Q12 <int> 4, 4, 4, 4, 4, 4, 5, 5, 3, 4, 4, 3, 4, 3, 3, 4, 5, 4, 4, 2, …
## $ Q13 <int> 4, 4, 4, 4, 4, 4, 5, 5, 4, 4, 4, 4, 2, 4, 4, 4, 5, 4, 4, 4, …
## $ Q14 <int> 4, 4, 4, 4, 4, 4, 5, 5, 5, 4, 4, 4, 3, 4, 5, 4, 5, 4, 4, 4, …
## $ Q15 <int> 4, 4, 3, 4, 4, 4, 4, 2, 3, 4, 4, 3, 1, 4, 4, 4, 5, 4, 4, 4, …
## $ Q16 <int> 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, 4, 4, 4, 5, 4, 5, 4, 4, 4, …
## $ Q17 <int> 4, 3, 4, 4, 4, 4, 2, 2, 4, 4, 4, 4, 3, 2, 4, 5, 4, 4, 3, 4, …
## $ Q18 <int> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 5, 2, 4, 4, 4, …
## $ Q19 <int> 4, 2, 4, 4, 4, 4, 4, 2, 4, 2, 4, 4, 1, 4, 4, 4, 5, 4, 2, 3, …
## $ Q20 <int> 4, 1, 3, 4, 4, 4, 4, 2, 4, 2, 4, 4, 4, 2, 4, 5, 5, 4, 2, 4, …
## $ Gender1 <int> 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, …
## $ EDU1 <int> 1, 1, 2, 1, 2, 1, 1, 1, 4, 3, 2, 1, 1, 3, 3, 2, 1, 1, 1, 4, …
## $ BF <dbl> 3.4, 4.0, 3.6, 4.2, 4.0, 4.0, 3.6, 3.6, 3.6, 3.2, 4.0, 3.2, …
## $ BM <dbl> 3.2, 3.4, 3.6, 4.0, 3.6, 4.0, 4.6, 4.6, 2.2, 3.2, 3.2, 3.6, …
## $ Happiness <dbl> 4.0, 4.0, 3.8, 4.0, 4.0, 4.0, 4.8, 4.4, 3.8, 4.0, 4.0, 3.4, …
## $ Peace <dbl> 4.0, 2.8, 3.8, 4.0, 4.0, 4.0, 3.8, 2.4, 4.0, 3.2, 4.0, 3.9, …
names(diamonds)
## [1] "carat" "cut" "color" "clarity" "depth" "table" "price"
## [8] "x" "y" "z"
diamonds1<-diamonds %>% rename(ca=clarity,pr=price)
names(diamonds1)
## [1] "carat" "cut" "color" "ca" "depth" "table" "pr" "x" "y"
## [10] "z"
glimpse(diamonds)
## Rows: 53,940
## Columns: 10
## $ carat <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.23, 0.…
## $ cut <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Good, Ver…
## $ color <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J, J, I,…
## $ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1, VS1, …
## $ depth <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59.4, 64…
## $ table <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, 62, 58…
## $ price <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 340, 34…
## $ x <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.00, 4.…
## $ y <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.05, 4.…
## $ z <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.39, 2.…
diamonds %>% select(carat,price)
## # A tibble: 53,940 × 2
## carat price
## <dbl> <int>
## 1 0.23 326
## 2 0.21 326
## 3 0.23 327
## 4 0.29 334
## 5 0.31 335
## 6 0.24 336
## 7 0.24 336
## 8 0.26 337
## 9 0.22 337
## 10 0.23 338
## # … with 53,930 more rows
diamonds %>% select(1:4)
## # A tibble: 53,940 × 4
## carat cut color clarity
## <dbl> <ord> <ord> <ord>
## 1 0.23 Ideal E SI2
## 2 0.21 Premium E SI1
## 3 0.23 Good E VS1
## 4 0.29 Premium I VS2
## 5 0.31 Good J SI2
## 6 0.24 Very Good J VVS2
## 7 0.24 Very Good I VVS1
## 8 0.26 Very Good H SI1
## 9 0.22 Fair E VS2
## 10 0.23 Very Good H VS1
## # … with 53,930 more rows
diamonds %>% slice(1:5)
## # A tibble: 5 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.29 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
diamonds %>% filter(cut=="Good")
## # A tibble: 4,906 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 2 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 3 0.3 Good J SI1 64 55 339 4.25 4.28 2.73
## 4 0.3 Good J SI1 63.4 54 351 4.23 4.29 2.7
## 5 0.3 Good J SI1 63.8 56 351 4.23 4.26 2.71
## 6 0.3 Good I SI2 63.3 56 351 4.26 4.3 2.71
## 7 0.23 Good F VS1 58.2 59 402 4.06 4.08 2.37
## 8 0.23 Good E VS1 64.1 59 402 3.83 3.85 2.46
## 9 0.31 Good H SI1 64 54 402 4.29 4.31 2.75
## 10 0.26 Good D VS2 65.2 56 403 3.99 4.02 2.61
## # … with 4,896 more rows
table(diamonds$cut)
##
## Fair Good Very Good Premium Ideal
## 1610 4906 12082 13791 21551
diamonds %>% filter(price==min(price))
## # A tibble: 2 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
diamonds %>% filter(cut%in%c("ldeal","Good"))
## # A tibble: 4,906 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 2 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 3 0.3 Good J SI1 64 55 339 4.25 4.28 2.73
## 4 0.3 Good J SI1 63.4 54 351 4.23 4.29 2.7
## 5 0.3 Good J SI1 63.8 56 351 4.23 4.26 2.71
## 6 0.3 Good I SI2 63.3 56 351 4.26 4.3 2.71
## 7 0.23 Good F VS1 58.2 59 402 4.06 4.08 2.37
## 8 0.23 Good E VS1 64.1 59 402 3.83 3.85 2.46
## 9 0.31 Good H SI1 64 54 402 4.29 4.31 2.75
## 10 0.26 Good D VS2 65.2 56 403 3.99 4.02 2.61
## # … with 4,896 more rows