Code Along 6

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Introduction

##Question ## Variations ## Visual distrubutions

diamonds %>%
    ggplot(aes(x + cut)) +
    geom_bar()

## Warning in Ops.ordered(x, cut): '+' is not meaningful for ordered factors

diamonds %>%
    ggplot(mapping = 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`.

### Typical values

diamonds %>%
    #filter out diamonds > 3 carat
    filter(carat > 3) %>%
    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 > 28) %>%
    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()`).

## Covariation

A categorical and continuous variables

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 continouus variables

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()

Code Along 6

pat szkutak

2024-12-02

Introduction

Missing values

A categorical and continuous variables

two categorical variables