library(tidyverse)
beer <- read_csv(file = 'C:/DATA 101. MC/Data 101/beers.csv')
beer <- beer %>%
rename(alc='Alcohol Content', cal='Calories in 12 oz') %>%
mutate(alc = alc*100)
glimpse(beer)
## Rows: 10
## Columns: 5
## $ Brand <chr> "Big Sky Scape Goat Pale Ale", "Sierra Nevada Harvest Ale", "S…
## $ Brewery <chr> "Big Sky Brewing", "Sierra Nevada", "MillerCoors", "Anheuser B…
## $ Carbs <dbl> 13.9, 19.3, 16.0, 13.3, 5.3, 15.0, 13.7, 13.3, 11.4, 11.8
## $ alc <dbl> 4.70, 6.70, 8.10, 0.40, 4.15, 5.10, 5.00, 5.00, 4.70, 6.20
## $ cal <dbl> 163, 215, 222, 70, 104, 162, 158, 155, 158, 195
names(beer)
## [1] "Brand" "Brewery" "Carbs" "alc" "cal"
knitr:: kable(beer)
| Big Sky Scape Goat Pale Ale |
Big Sky Brewing |
13.9 |
4.70 |
163 |
| Sierra Nevada Harvest Ale |
Sierra Nevada |
19.3 |
6.70 |
215 |
| Steel Reserve |
MillerCoors |
16.0 |
8.10 |
222 |
| O’Doul’s |
Anheuser Busch |
13.3 |
0.40 |
70 |
| Coors Light |
MillerCoors |
5.3 |
4.15 |
104 |
| Genesee Cream Ale |
High Falls Brewing |
15.0 |
5.10 |
162 |
| Sierra Nevada Summerfest Beer |
Sierra Nevada |
13.7 |
5.00 |
158 |
| Michelob Beer |
Anheuser Busch |
13.3 |
5.00 |
155 |
| Flying Dog Doggie Style |
Flying Dog Brewery |
11.4 |
4.70 |
158 |
| Big Sky I.P.A. |
Big Sky Brewing |
11.8 |
6.20 |
195 |
plot(beer$alc,beer$cal,pch=20, col ="red",cex=2, xlb ="% of Alcohol", ylab ="caloris",
main="Beer Calories vs. Alcohol Content")
## Warning in plot.window(...): "xlb" is not a graphical parameter
## Warning in plot.xy(xy, type, ...): "xlb" is not a graphical parameter
## Warning in axis(side = side, at = at, labels = labels, ...): "xlb" is not a
## graphical parameter
## Warning in axis(side = side, at = at, labels = labels, ...): "xlb" is not a
## graphical parameter
## Warning in box(...): "xlb" is not a graphical parameter
## Warning in title(...): "xlb" is not a graphical parameter
abline(lm(beer$cal~beer$alc,data=beer),lwd=2)
par(mfrow=c(1,2)) # creates a side by side box plot
boxplot(beer$cal, col = "yellow", main = "calories")
boxplot(beer$alc, col = "red", main = "Alcohol")
beer <- beer %>% filter(Brand != "O'Doul's")
lin_model <- lm(formula = cal ~ alc, data = beer)
lin_model
##
## Call:
## lm(formula = cal ~ alc, data = beer)
##
## Coefficients:
## (Intercept) alc
## 25.03 26.32
predict(lin_model)
## 1 2 3 4 5 6 7 8
## 148.7287 201.3659 238.2120 134.2535 159.2561 156.6243 156.6243 148.7287
## 9
## 188.2066
res <- residuals(lin_model)
res
## 1 2 3 4 5 6 7
## 14.271307 13.634092 -16.211959 -30.253458 2.743864 1.375725 -1.624275
## 8 9
## 9.271307 6.793396
plot(beer$alc, res, ylab = 'Residual', xlab = 'Alcohol %', pch = 20, cex = 2 ,
main = "Residual")
abline(0, 0, lwd=2)
summary(lin_model)
##
## Call:
## lm(formula = cal ~ alc, data = beer)
##
## Residuals:
## Min 1Q Median 3Q Max
## -30.253 -1.624 2.744 9.271 14.271
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 25.031 24.999 1.001 0.350038
## alc 26.319 4.432 5.938 0.000577 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15.64 on 7 degrees of freedom
## Multiple R-squared: 0.8344, Adjusted R-squared: 0.8107
## F-statistic: 35.26 on 1 and 7 DF, p-value: 0.0005768
correlation_coeff <- cor(beer$alc, beer$cal)
paste0("The coor coef, r", round(correlation_coeff,3))
## [1] "The coor coef, r0.913"
cor.test(beer$cal, beer$alc, conf.level = 0.05)
##
## Pearson's product-moment correlation
##
## data: beer$cal and beer$alc
## t = 5.9384, df = 7, p-value = 0.0005768
## alternative hypothesis: true correlation is not equal to 0
## 5 percent confidence interval:
## 0.9091008 0.9175836
## sample estimates:
## cor
## 0.9134414
predict(lin_model, newdata = list(alc = 7.0), interval = "prediction", level = 0.95)
## fit lwr upr
## 1 209.2615 167.2978 251.2252