Week7: Code along 6

R for Data Sience: Ch6

# Load package
library(tidyverse)
library(tidyquant)

Introduction

Question2

Variation

Visualising distrobution

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()

Trypical 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()

Unusual values

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

diamonds %>%
    
    ggplot(aes(x = y)) +
    geom_histogram() +
    coord_cartesian(ylim = c(0,50))

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()

Covariation

A categorical and continuous varible

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 %>%
    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)

diamonds4 <- diamonds %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

diamonds4 %>%
    ggplot(aes(carat, resid)) +
    geom_point()

diamonds4 %>%
    ggplot(aes(cut, resid)) +
    geom_boxplot()