Introduction

Question 2

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`.

## `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)

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

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`.

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_rev = ifelse(y < 3 | y > 20, NA, y)) %>%
    
    # Plot
    ggplot(aes(x = x, y = y)) +
    geom_point()

Covariation

A categorical and continuos 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 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)))

Patterns and Models

library(modelr)
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()