Introductiond

Questions

Variation

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 with `binwidth`.

Typical Values

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

    faithful %>%
    
    ggplot(aes(x = eruptions)) +
    geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Unusual Values

diamonds %>%
    
    ggplot(aes (y))+
    geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

diamonds %>%
    ggplot(aes(x = y))+
    geom_histogram()+
    coord_cartesian(ylim = c(0,50))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

## Missing values

diamonds %>%
    # filter(y < 3| y > 20) %>%
     mutate( y = ifelse(y < 3 | y> 20, NA, y)) %>%
    # plot
    ggplot(aes(x = y, y = y)) +
    geom_point()
## Warning: Removed 9 rows containing missing values (`geom_point()`).

## Covariation

### a categorial and continuous varible

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

### Two Categorial Variables

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

### two continuous variables

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

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

## paterns 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()