getwd()
## [1] "C:/Users/samsung/Desktop"
setwd('c:/data')
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
library(caret)
## 필요한 패키지를 로딩중입니다: ggplot2
## 필요한 패키지를 로딩중입니다: lattice
data(mtcars)
glimpse(mtcars)
## Rows: 32
## Columns: 11
## $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8,…
## $ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8,…
## $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 16…
## $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180…
## $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92,…
## $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.…
## $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18…
## $ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,…
## $ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0,…
## $ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3,…
## $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2,…
library(gapminder)
## Warning: 패키지 'gapminder'는 R 버전 4.3.2에서 작성되었습니다
glimpse(gapminder)
## Rows: 1,704
## Columns: 6
## $ country <fct> "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", …
## $ continent <fct> Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, Asia, …
## $ year <int> 1952, 1957, 1962, 1967, 1972, 1977, 1982, 1987, 1992, 1997, …
## $ lifeExp <dbl> 28.801, 30.332, 31.997, 34.020, 36.088, 38.438, 39.854, 40.8…
## $ pop <int> 8425333, 9240934, 10267083, 11537966, 13079460, 14880372, 12…
## $ gdpPercap <dbl> 779.4453, 820.8530, 853.1007, 836.1971, 739.9811, 786.1134, …
mtcars %>% count(am)
## am n
## 1 0 19
## 2 1 13
gapminder %>% count(continent)
## # A tibble: 5 × 2
## continent n
## <fct> <int>
## 1 Africa 624
## 2 Americas 300
## 3 Asia 396
## 4 Europe 360
## 5 Oceania 24
df<-mtcars %>% filter(am==1) %>% select('am','mpg')
glimpse(df)
## Rows: 13
## Columns: 2
## $ am <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
## $ mpg <dbl> 21.0, 21.0, 22.8, 32.4, 30.4, 33.9, 27.3, 26.0, 30.4, 15.8, 19.7, …
df$am
## [1] 1 1 1 1 1 1 1 1 1 1 1 1 1
shapiro.test(df$mpg)
##
## Shapiro-Wilk normality test
##
## data: df$mpg
## W = 0.9458, p-value = 0.5363
plot(density(df$mpg))
shapiro.test(gapminder$lifeExp)
##
## Shapiro-Wilk normality test
##
## data: gapminder$lifeExp
## W = 0.95248, p-value < 2.2e-16
plot(density(gapminder$lifeExp))
t.test(df$mpg,mu=20,alternative="greater")
##
## One Sample t-test
##
## data: df$mpg
## t = 2.5682, df = 12, p-value = 0.01231
## alternative hypothesis: true mean is greater than 20
## 95 percent confidence interval:
## 21.3441 Inf
## sample estimates:
## mean of x
## 24.39231
t.test(gapminder$lifeExp,mu=58,alternative="greater")
##
## One Sample t-test
##
## data: gapminder$lifeExp
## t = 4.7119, df = 1703, p-value = 1.327e-06
## alternative hypothesis: true mean is greater than 58
## 95 percent confidence interval:
## 58.95946 Inf
## sample estimates:
## mean of x
## 59.47444
t.test(gapminder$lifeExp,mu=59,alternative="greater")
##
## One Sample t-test
##
## data: gapminder$lifeExp
## t = 1.5162, df = 1703, p-value = 0.06483
## alternative hypothesis: true mean is greater than 59
## 95 percent confidence interval:
## 58.95946 Inf
## sample estimates:
## mean of x
## 59.47444
before<-c(59,72,85,69,78,82,55)
after<-c(54,65,84,63,72,83,51)
diff<-before-after
shapiro.test(diff)
##
## Shapiro-Wilk normality test
##
## data: diff
## W = 0.88458, p-value = 0.2476
t.test(before,after,mu=0,alternative='greater',paired=T)
##
## Paired t-test
##
## data: before and after
## t = 3.5949, df = 6, p-value = 0.005718
## alternative hypothesis: true mean difference is greater than 0
## 95 percent confidence interval:
## 1.837829 Inf
## sample estimates:
## mean difference
## 4
tre<-c(10,16,27,15,21,14,16,21,22,23,25,28,27,13,
15,16,21,22,25,28)
con<-c(23,26,27,23,16,18,31,33,28,36,18,21,26,28,29,
33,32,16,18,23)
df<-data.frame(group=c(rep(1,20),rep(2,20)),score=c(tre,con))
glimpse(df)
## Rows: 40
## Columns: 2
## $ group <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2…
## $ score <dbl> 10, 16, 27, 15, 21, 14, 16, 21, 22, 23, 25, 28, 27, 13, 15, 16, …
shapiro.test(tre)
##
## Shapiro-Wilk normality test
##
## data: tre
## W = 0.93475, p-value = 0.1905
var.test(data=df,score~group)
##
## F test to compare two variances
##
## data: score by group
## F = 0.81402, num df = 19, denom df = 19, p-value = 0.6583
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.3221986 2.0565791
## sample estimates:
## ratio of variances
## 0.814019
t.test(data=df,score~group,var.equal=TRUE,mu=0,
alternative="less")
##
## Two Sample t-test
##
## data: score by group
## t = -2.7164, df = 38, p-value = 0.00494
## alternative hypothesis: true difference in means between group 1 and group 2 is less than 0
## 95 percent confidence interval:
## -Inf -1.896672
## sample estimates:
## mean in group 1 mean in group 2
## 20.25 25.25
data(iris)
names(iris)
## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width" "Species"
summary(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
##
fit<-aov(Sepal.Length ~ Species, data = iris)
summary(fit)
## Df Sum Sq Mean Sq F value Pr(>F)
## Species 2 63.21 31.606 119.3 <2e-16 ***
## Residuals 147 38.96 0.265
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
options(scipen=999)
data(iris)
summary(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
##
fit<-aov(Sepal.Length ~ Species, data=iris)
summary(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
##
options(scipen=999)