สรุปข้อมูลแบบจัดกลุ่มและ group_by()

เหตุใดจึงต้องจัดกลุ่มข้อมูล

library(dplyr)

# Sample sales data
sales <- data.frame(
  region = c('North','North','South','South','East'),
  revenue = c(120, 95, 200, 175, 88),
  units = c(10, 8, 15, 12, 7)
)

print(sales)

พื้นฐานของ group_by()

library(dplyr)

sales <- data.frame(
  region = c('North','North','South','South','East'),
  revenue = c(120, 95, 200, 175, 88),
  units = c(10, 8, 15, 12, 7)
)

# Group by region
grouped <- sales %>% group_by(region)
print(grouped)
print(group_keys(grouped))

summarize() หลัง group_by()

library(dplyr)

sales <- data.frame(
  region = c('North','North','South','South','East'),
  revenue = c(120, 95, 200, 175, 88),
  units = c(10, 8, 15, 12, 7)
)

sales %>%
  group_by(region) %>%
  summarize(
    n = n(),
    mean_revenue = mean(revenue),
    total_units = sum(units)
  )

การนับด้วย n()

library(dplyr)

employees <- data.frame(
  dept = c('HR','HR','Eng','Eng','Eng','Sales'),
  salary = c(55000, 60000, 95000, 105000, 90000, 70000),
  senior = c(FALSE, TRUE, TRUE, TRUE, FALSE, FALSE)
)

employees %>%
  group_by(dept) %>%
  summarize(
    count = n(),
    senior_count = sum(senior),
    avg_salary = mean(salary)
  )

การจัดกลุ่มตามหลายคอลัมน์

library(dplyr)

orders <- data.frame(
  region = c('North','North','South','South','North','South'),
  product = c('A','B','A','B','A','A'),
  sales = c(100, 200, 150, 250, 120, 180)
)

orders %>%
  group_by(region, product) %>%
  summarize(
    total_sales = sum(sales),
    orders = n(),
    .groups = 'drop'
  )

อาร์กิวเมนต์ .groups

library(dplyr)

df <- data.frame(
  year = c(2022,2022,2023,2023),
  quarter = c('Q1','Q2','Q1','Q2'),
  revenue = c(100, 120, 130, 150)
)

# .groups = 'drop' ensures ungrouped result
result <- df %>%
  group_by(year, quarter) %>%
  summarize(total = sum(revenue), .groups = 'drop')

print(result)
print(is.grouped_df(result))  # FALSE

ungroup() อย่างชัดเจน

library(dplyr)

df <- data.frame(
  dept = c('HR','HR','Eng','Eng'),
  salary = c(55000, 60000, 95000, 105000)
)

# Without ungroup: rank is within group
df %>%
  group_by(dept) %>%
  mutate(rank_in_dept = rank(salary)) %>%
  ungroup() %>%
  mutate(rank_overall = rank(salary))

group_keys() และ n_groups()

library(dplyr)

df <- data.frame(
  country = c('US','US','UK','UK','DE'),
  category = c('A','B','A','A','B'),
  value = c(10, 20, 15, 25, 30)
)

grouped <- df %>% group_by(country, category)

cat('Number of groups:', n_groups(grouped), '\n')
print(group_keys(grouped))

การสรุปด้วยสถิติหลายรายการ

library(dplyr)

scores <- data.frame(
  class = c('A','A','A','B','B','B','C','C'),
  score = c(85, 90, 78, 92, 88, 95, 70, 75)
)

scores %>%
  group_by(class) %>%
  summarize(
    n = n(),
    mean_score = round(mean(score), 1),
    median_score = median(score),
    sd_score = round(sd(score), 2),
    min_score = min(score),
    max_score = max(score)
  )

mutate() ที่คำนึงถึงกลุ่ม

library(dplyr)

sales <- data.frame(
  region = c('East','East','West','West','West'),
  rep = c('Alice','Bob','Carol','Dave','Eve'),
  revenue = c(150, 200, 120, 180, 160)
)

sales %>%
  group_by(region) %>%
  mutate(
    region_total = sum(revenue),
    pct_of_region = round(100 * revenue / sum(revenue), 1)
  ) %>%
  ungroup()

การกรองภายในกลุ่ม

library(dplyr)

sales <- data.frame(
  region = c('East','East','West','West','North','North'),
  rep = c('Alice','Bob','Carol','Dave','Eve','Frank'),
  revenue = c(150, 200, 120, 180, 95, 130)
)

# Keep the top rep per region
sales %>%
  group_by(region) %>%
  filter(revenue == max(revenue)) %>%
  ungroup()

ตรวจสอบด่วน

ทบทวน: สรุปข้อมูลแบบจัดกลุ่ม

library(dplyr)

# Full pipeline example
data.frame(
  dept = c('Eng','Eng','HR','HR','Sales'),
  salary = c(95000, 110000, 60000, 65000, 75000)
) %>%
  group_by(dept) %>%
  summarize(
    headcount = n(),
    avg_salary = mean(salary),
    .groups = 'drop'
  ) %>%
  arrange(desc(avg_salary))