library(ggplot2)
ggplot(data = diamonds, aes(x = cut)) + geom_bar()

ggplot(data = diamonds, aes(x = carat, y = price)) + geom_point()

# Create dummy dataset
dummy_data <- data.frame( dummy_metric = cumsum(1:20),
date = seq.Date(as.Date("1980-01-01"), by="1 year", length.out=20)
)

# Plot the data using ggplot2 package
ggplot(data = df.dummy_data, aes(x = date, y = dummy_metric)) + geom_line()


library(dplyr)
library(ggplot2)

diamonds_ideal <- filter(diamonds, cut=="Ideal")
diamonds_ideal <- select(diamonds_ideal, carat, cut, color, price, clarity)
diamonds_ideal <- mutate(diamonds_ideal, price_per_carat = price/carat)

disordered_data <- data.frame(num = c(2,3,5,1,4))
arrange(disordered_data, num)

summarize(diamonds_ideal, avg_price = mean(price, na.rm = TRUE) )



library(ggplot2)
ggplot(data = mtcars, aes(x = wt, y = mpg)) + geom_point()

library(caret)
model.mtcars_lm <- train(mpg ~ wt, data = mtcars, method = "lm")

# coefficients for  slope, intercept

coef.icept <- coef(model.mtcars_lm$finalModel)[1]
coef.slope <- coef(model.mtcars_lm$finalModel)[2]

# Plot scatterplot and regression line

ggplot(data = mtcars, aes(x = wt, y = mpg)) + geom_point() +
geom_abline(slope = coef.slope, intercept = coef.icept, color = "red")

# if use the k-nearest neighbor technique, we could use the method = "knn"