Week 7: Code along 6

R for Data Sience Chap 6

Introduction

Questions

Variation

Visualizing Distributions

#bar Chart
ggplot(data = diamonds) +
  geom_bar(mapping = aes(x = cut))

#histogram
smaller <- diamonds %>% 
  filter(carat < 3)
  
ggplot(data = smaller, mapping = aes(x = carat)) +
  geom_histogram(binwidth = 0.1)

#line
ggplot(data = smaller, mapping = aes(x = carat, colour = cut)) +
  geom_freqpoly(binwidth = 0.1)

Typical Values

diamonds %>%
    #filter out diamonds > 3 carats
    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() +
    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 = x, y = y)) +
    geom_point()

## Warning: Removed 9 rows containing missing values or values outside the scale range
## (`geom_point()`).

Covariations

#freqpoly
ggplot(data = diamonds, mapping = aes(x = price)) + 
  geom_freqpoly(mapping = aes(colour = cut), binwidth = 500)

#boxplot
ggplot(data = diamonds, mapping = aes(x = cut, y = price)) +
  geom_boxplot()

#coord_flip
ggplot(data = mpg) +
  geom_boxplot(mapping = aes(x = reorder(class, hwy, FUN = median), y = hwy)) +
  coord_flip()

Two catagorical Variables

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

Two continuous Variables

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

ggplot(data = smaller, mapping = aes(x = carat, y = price)) + 
  geom_boxplot(mapping = 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()

diamonds %>% 
  count(cut, clarity) %>% 
  ggplot(aes(clarity, cut, fill = n)) + 
    geom_tile()