Week 7: Code along 6

##Introduction

summary(cars)

##      speed           dist       
##  Min.   : 4.0   Min.   :  2.00  
##  1st Qu.:12.0   1st Qu.: 26.00  
##  Median :15.0   Median : 36.00  
##  Mean   :15.4   Mean   : 42.98  
##  3rd Qu.:19.0   3rd Qu.: 56.00  
##  Max.   :25.0   Max.   :120.00

Including Plots

Question2

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 `binwidth`.

Typical values

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

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

Unusual values

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

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

diamonds %>%
    
    ggplot (aes (x = 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 continuous 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

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()

You can also embed plots, for example:

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.