Project1

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

# Load necessary libraries
library(ggplot2)
library(tibble)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(maps)  # Needed for mapping example

# View dataset structure
str(diamonds)

## tibble [53,940 × 10] (S3: tbl_df/tbl/data.frame)
##  $ carat  : num [1:53940] 0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
##  $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
##  $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
##  $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
##  $ depth  : num [1:53940] 61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
##  $ table  : num [1:53940] 55 61 65 58 58 57 57 55 61 61 ...
##  $ price  : int [1:53940] 326 326 327 334 335 336 336 337 337 338 ...
##  $ x      : num [1:53940] 3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
##  $ y      : num [1:53940] 3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
##  $ z      : num [1:53940] 2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

# Basic bar chart showing the count of cuts
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut))

# Using stat_count() instead of geom_bar()
ggplot(data = diamonds) + 
  stat_count(mapping = aes(x = cut))

# Using "prop" instead of "count"
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, y = ..prop.., group = 1))

## Warning: The dot-dot notation (`..prop..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(prop)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

# Custom dataset for manually specified frequencies
demo <- tribble(
  ~cut, ~freq,
  "Fair", 1610,
  "Good", 4906,
  "Very Good", 12082,
  "Premium", 13791,
  "Ideal", 21551
)

# Bar chart using raw values
ggplot(data = demo) +
  geom_bar(mapping = aes(x = cut, y = freq), stat = "identity")

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

ggplot(data = diamonds) +
stat_count(mapping = aes(x = cut))

demo <- tribble(
~cut, ~freq,
"Fair", 1610,
"Good", 4906,
"Very Good", 12082,
"Premium", 13791,
"Ideal", 21551
)
ggplot(data = demo) +
geom_bar(mapping = aes(x = cut, y = freq), stat = "identity")

ggplot(data = diamonds) + 
  stat_summary(
    mapping = aes(x = cut, y = depth),
    fun.min = min,
    fun.max = max,
    fun = median
  )

# Coloring by cut
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, color = cut))

# Filling by cut
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = cut))

# Filling by clarity (stacked bars)
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity))

# Using position = "identity" (transparent overlap)
ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) + 
  geom_bar(alpha = 1/5, position = "identity")

# Using position = "fill" (normalized height)
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), position = "fill")

# Using position = "dodge" (side-by-side bars)
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")

# Scatter plot without jitter
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy))

# Scatter plot with jitter to prevent overplotting
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy), position = "jitter")

# Standard boxplot
ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + 
  geom_boxplot()

# Flipped boxplot
ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + 
  geom_boxplot() +
  coord_flip()

# Load map data
nz <- map_data("nz")

# Standard map plot
ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black")

# Adjusting aspect ratio using coord_quickmap()
ggplot(nz, aes(long, lat, group = group)) +
  geom_polygon(fill = "white", colour = "black") +
  coord_quickmap()

Project1

Chris Yeu

2025-02-18

R Markdown

Including Plots