library(ggplot2)
library(datasets)
data(mtcars)
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
data <- mtcars
mtcars$cyl <- factor(mtcars$cyl)
mtcars$vs <- factor(mtcars$vs)
mtcars$disp <- factor(mtcars$disp)
mtcars$hp <- factor(mtcars$hp)
mtcars$grear <- factor(mtcars$gear)
mtcars$carb <- factor(mtcars$carb)
mtcars$am <- factor(mtcars$am, labels=c("Automatic", "Manual"))
data("mtcars")
data <- mtcars
data$am <- as.factor(data$am)
levels(data$am) <- c("A", "M")
data$cyl <- as.factor(data$cyl)
data$gear <- as.factor(data$gear)
data$vs <- as.factor(data$vs)
levels(data$vs) <- c("V", "S")
head(data, n=5)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 V M 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 V M 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 S M 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 S A 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 V A 3 2
str(data)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : Factor w/ 2 levels "V","S": 1 1 2 2 1 2 1 2 2 2 ...
## $ am : Factor w/ 2 levels "A","M": 2 2 2 1 1 1 1 1 1 1 ...
## $ gear: Factor w/ 3 levels "3","4","5": 2 2 2 1 1 1 1 2 2 2 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
levels(data$am) <- c("A", "M")
levels(data$vs) <- c("V", "S")
str(data)
## 'data.frame': 32 obs. of 11 variables:
## $ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
## $ cyl : Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
## $ disp: num 160 160 108 258 360 ...
## $ hp : num 110 110 93 110 175 105 245 62 95 123 ...
## $ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
## $ wt : num 2.62 2.88 2.32 3.21 3.44 ...
## $ qsec: num 16.5 17 18.6 19.4 17 ...
## $ vs : Factor w/ 2 levels "V","S": 1 1 2 2 1 2 1 2 2 2 ...
## $ am : Factor w/ 2 levels "A","M": 2 2 2 1 1 1 1 1 1 1 ...
## $ gear: Factor w/ 3 levels "3","4","5": 2 2 2 1 1 1 1 2 2 2 ...
## $ carb: num 4 4 1 1 2 1 4 2 2 4 ...
head(data, n=5)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 V M 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 V M 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 S M 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 S A 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 V A 3 2
library(ggplot2)
g <- ggplot(data, aes(am, mpg))
g <- g + geom_boxplot(aes(fill = am))
print(g)
correlation <- cor(mtcars$mpg, mtcars)
correlation <- correlation[,order(-abs(correlation[1, ]))]
correlation
## mpg wt cyl disp hp drat vs
## 1.0000000 -0.8676594 -0.8521620 -0.8475514 -0.7761684 0.6811719 0.6640389
## am carb gear qsec
## 0.5998324 -0.5509251 0.4802848 0.4186840
variables <- names(correlation)[1: which(names(correlation) == "am")]
variables
## [1] "mpg" "wt" "cyl" "disp" "hp" "drat" "vs" "am"
first <- lm(mpg ~ am, data)
summary(first)
##
## Call:
## lm(formula = mpg ~ am, data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.3923 -3.0923 -0.2974 3.2439 9.5077
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 17.147 1.125 15.247 1.13e-15 ***
## amM 7.245 1.764 4.106 0.000285 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 4.902 on 30 degrees of freedom
## Multiple R-squared: 0.3598, Adjusted R-squared: 0.3385
## F-statistic: 16.86 on 1 and 30 DF, p-value: 0.000285
last <- lm(mpg ~ ., data)
summary(last)
##
## Call:
## lm(formula = mpg ~ ., data = data)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.2015 -1.2319 0.1033 1.1953 4.3085
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 15.09262 17.13627 0.881 0.3895
## cyl6 -1.19940 2.38736 -0.502 0.6212
## cyl8 3.05492 4.82987 0.633 0.5346
## disp 0.01257 0.01774 0.708 0.4873
## hp -0.05712 0.03175 -1.799 0.0879 .
## drat 0.73577 1.98461 0.371 0.7149
## wt -3.54512 1.90895 -1.857 0.0789 .
## qsec 0.76801 0.75222 1.021 0.3201
## vsS 2.48849 2.54015 0.980 0.3396
## amM 3.34736 2.28948 1.462 0.1601
## gear4 -0.99922 2.94658 -0.339 0.7382
## gear5 1.06455 3.02730 0.352 0.7290
## carb 0.78703 1.03599 0.760 0.4568
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.616 on 19 degrees of freedom
## Multiple R-squared: 0.8845, Adjusted R-squared: 0.8116
## F-statistic: 12.13 on 12 and 19 DF, p-value: 1.764e-06