visualization

data <-airquality
str(data)

## 'data.frame':    153 obs. of  6 variables:
##  $ Ozone  : int  41 36 12 18 NA 28 23 19 8 NA ...
##  $ Solar.R: int  190 118 149 313 NA NA 299 99 19 194 ...
##  $ Wind   : num  7.4 8 12.6 11.5 14.3 14.9 8.6 13.8 20.1 8.6 ...
##  $ Temp   : int  67 72 74 62 56 66 65 59 61 69 ...
##  $ Month  : int  5 5 5 5 5 5 5 5 5 5 ...
##  $ Day    : int  1 2 3 4 5 6 7 8 9 10 ...

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:

The first thing what I did.

library(ggplot2)
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
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ── 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

# 샘플 데이터 생성
data <- airquality %>%
  mutate(Category = factor(Month),  # Make Month a categorical variable
         Value = Wind)   


# 혼란스러운 그래프 생성
ggplot(data, aes(x = Category, y = Value, color = Category)) +
  geom_point(size = 5) +
  geom_jitter(width = 0.2, height = 0) +
  scale_color_manual(values = rainbow(5)) +
  labs(title = "bad graph example",
       x = "category",
       y = "value") +
  theme_minimal() +
  theme(
    legend.position = "bottom",
    plot.title = element_text(size = 20, face = "bold"),
    axis.text.x = element_text(angle = 45, hjust = 1)
  )

Including Plots

library(ggplot2)

# 샘플 데이터 생성
data <- data.frame(
  Category = rep(LETTERS[1:5], each = 20),
  Value = rnorm(100, mean = 50, sd = 10)
)

# 좋은 그래프 생성
ggplot(data, aes(x = Category, y = Value, color = Category)) +
  geom_point(alpha = 0.7, size = 3) +
  geom_jitter(width = 0.2, height = 0, alpha = 0.7) +
  scale_color_brewer(palette = "Set1") +
  labs(title = "good graph example",
       x = "category",
       y = "value") +
  theme_minimal() +
  theme(
    legend.position = "none",
    plot.title = element_text(size = 16, face = "bold"),
    axis.text.x = element_text(angle = 0, hjust = 0.5)
  )

You can also embed plots, for example: Histogram

library(tidyverse)
library(dplyr)
clean_data <- airquality %>%
  filter(!is.na(Wind)) %>%        # Remove missing values in Wind
  group_by(Month) %>%             # Group by month (5 = May, etc.)
  summarize(avg_wind = mean(Wind, na.rm = TRUE))  # Average wind


# 막대 그래프 그리기
ggplot(clean_data, aes(x = factor(Month), y = avg_wind, fill = factor(Month))) +
  geom_bar(stat = "identity") +
  labs(title = "month of average wind",
       x = "month",
       y = "average of wind") +
  theme_minimal() +
  theme(legend.position = "none")

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

#data for the plot

library(ggplot2)

# 히스토그램 생성
ggplot(data = airquality, aes(x = Wind)) +
  geom_histogram(binwidth = 2, fill = "skyblue", color = "black") +
  labs(title = "wind speed distribution",
       x = "wind speed",
       y = "frequency") +
  theme_minimal()

library(ggplot2)

# 상자 그림 생성
ggplot(data = airquality, aes(x = factor(Month), y = Wind, fill = factor(Month))) +
  geom_boxplot() +
  labs(title = "wind speed by month",
       x = "month",
       y = "wind speed") +
  theme_minimal() +
  theme(legend.position = "none")

library(ggplot2)

# economics 데이터셋을 사용한 선 그래프 생성
ggplot(data = airquality, aes(x = factor(Month), y = Wind)) +
  geom_line(color = "blue") +
  labs(title = "wind speed by month",
       x = "month",
       y = "wind") +
  theme_minimal()

library(ggplot2)

library(dplyr)
library(dplyr)
library(ggplot2)

# Summarize counts and proportions by Month
data <- airquality %>%
  count(Month) %>%
  mutate(prop = n / sum(n) * 100,
         ypos = cumsum(prop) - 0.5 * prop)

# Pie chart with ggplot2
ggplot(data, aes(x = "", y = prop, fill = factor(Month))) +
  geom_bar(width = 1, stat = "identity") +
  coord_polar("y", start = 0) +
  labs(title = "observation of each month",
       fill = "month") +
  theme_void() +
  theme(legend.position = "right") +
  geom_text(aes(y = ypos, label = paste0(round(prop, 1), "%")), color = "white")

library(ggplot2)

library(ggplot2)

ggplot(data = airquality, aes(x = Wind, y = Ozone)) +
  geom_point() +
  facet_wrap(~ factor(Month)) +
  labs(title = "Every month of wind speed and Ozonoe relationship",
       x = "wind speed",
       y = "Ozone") +
  theme_minimal()

## Warning: Removed 37 rows containing missing values or values outside the scale range
## (`geom_point()`).