date: “2024-06-20” editor_options: chunk_output_type: console —

Introductions

Questions

Variation

Visualizing Distributions

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 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)

Unusual Values

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

diamonds %>%
    ggplot(aes(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)) %>%
    
    ggplot(aes(x = x, y = y)) +
   
    geom_point()     
## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`geom_point()`).

## Covariation

A Categorical and Continuous Variables

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

Two categorical variables

Two Continuous 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)))

Patterns and Models

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

 diamonds2 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))
 
 diamonds2 %>%
     ggplot(aes(carat, resid)) +
     geom_point()

 diamonds2 %>%
     ggplot(aes(cut, resid)) +
     geom_boxplot()