week 7: code along 6

R for data science: Chapter 6

introduction

questions

Valration

Visualizing distrubutions

diamonds %>%
    ggplot(aes(x = cut)) +
    geom_bar()

diamonds %>%
    ggplot(mapping = aes(x = carat)) +
    geom_histogram(binwidth = 0.5)

diamonds %>%
    
    filter(carat < 3) %>%
    
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = 0.5)

diamonds %>%
    ggplot(aes(x = carat, color = cut)) +
    geom_freqpoly()

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Typical vaules

diamonds %>%
    
    # filter out diamonds > 3 carat
    filter(carat < 3) %>%
    
    # plot
    ggplot(aes(x = carat)) +
    geom_histogram(binwidth = 0.01)

faithful %>%
    ggplot(aes(eruptions)) + 
    geom_histogram(binwidth = 0.25)

unsual values

diamonds %>%
    ggplot(aes(y)) +
    geom_histogram()

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

diamonds %>%
    ggplot(aes(y)) +
    geom_histogram() +
    coord_cartesian(ylim = c(0, 50))

## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.

Missing values

diamonds %>%
    
    #filter(y > 3 | y > 20) %>%
    
    mutate(y_rev = ifelse(y > 3 | y > 20, NA, y)) %>%
    
    # plot
    
    ggplot(aes(x = x, y = y)) +
    geom_point()

covariation

A categorical and continous variable

diamonds %>%
    
    ggplot(aes(x = cut, y = price)) +
    geom_boxplot()

two categorical variables

diamonds %>%
    
    count(color, cut) %>%
    
    ggplot(aes(x = color, y = cut, fill = n)) +
    geom_tile()

two continous variables

library(hexbin)
diamonds %>%
    ggplot(aes(x = carat, y = price)) +
    geom_hex()

diamonds %>%
    filter(carat < 3) %>%
    ggplot(aes(x = carat, y = price)) +
    geom_boxplot(aes(group = cut_width(carat, 0.1 )))

## Warning: Orientation is not uniquely specified when both the x and y aesthetics are
## continuous. Picking default orientation 'x'.

patterns and models

mod <- lm(log(price) ~ log(carat), data = diamonds)

diamonds4 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds4  %>%
    ggplot(aes(carat, resid)) +
    geom_point()

diamonds4 %>%
    ggplot(aes(cut, resid)) +
    geom_boxplot()