Week 7: Apply it to your data 6

Import data

data <- read_excel("Apply_1.xlsx")

Introduction

Questions

Variation

ggplot(data = data) +
    geom_bar(mapping = aes(x = release_year))

Visualizing distributions

data %>%
    ggplot(aes(x = release_year)) +
    geom_bar()

data %>%
    ggplot(mapping = aes(x = release_year)) +
    geom_histogram(binwidth = 0.5)

Typical values

data %>% 

    # Filter out release_year > 2005
    filter(release_year > 2005) %>%
    
    # Plot
    ggplot(aes(x = release_year)) +
    geom_histogram(binwidth = 0.5)

Unusual values

data %>%
    ggplot(aes(age_difference)) +
    geom_histogram() 

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

data %>% 
    ggplot(aes(age_difference)) +
    geom_histogram() +
    coord_cartesian(ylim = c(0,50))

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

Missing Values

data %>%
    
    # filter(age_difference < 35 | age_difference > 55) %>%
    
    mutate(age_difference = ifelse(age_difference < 35 | age_difference > 55, NA, age_difference)) %>%
    
    # Plot
    ggplot(aes(x = release_year, y = age_difference)) +
    geom_point()

## Warning: Removed 1141 rows containing missing values or values outside the scale range
## (`geom_point()`).

Covariation

A categorical and continuous variable

data %>% 
    
    ggplot(aes(x = release_year, y = age_difference)) +
    geom_boxplot()

## Warning: Continuous x aesthetic
## ℹ did you forget `aes(group = ...)`?

Two categorical variables

data %>% 
    count(character_1_gender, character_2_gender) %>%
    
    ggplot(aes(x = character_1_gender, y = character_2_gender, fill = n)) + 
    geom_tile()

Two continous variables

library(hexbin)
data %>%
    ggplot(aes(x = release_year, y = age_difference)) +
    geom_hex()

Patterns and models

library(modelr)
mod <- lm(log(actor_1_age) ~ log(actor_2_age), data = data)

data4 <- data %>%
    modelr::add_residuals(mod) %>%
    mutate(resid = exp(resid))

data4 %>%
    ggplot(aes(actor_2_age, resid)) +
    geom_point()